Compare commits
48 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| d8da529be0 | |||
| 0258a40b0d | |||
| f6a8752d00 | |||
| 5b7480ddaf | |||
| 8aa790cc48 | |||
| 0ade0ec734 | |||
| d960e211d3 | |||
| 6fba4d6931 | |||
| 12c18dcf65 | |||
| a286865fe5 | |||
| 28c0ff73bd | |||
| 761cf9f3e0 | |||
| 6a9d8a4dd5 | |||
| 4c95b200e4 | |||
| 6ae1312ff1 | |||
| 765ed36340 | |||
| feca776077 | |||
| d79b30a1a6 | |||
| 7db139b83e | |||
| 0987dabfc4 | |||
| 947506c7b8 | |||
| 6c67e61962 | |||
| 0990f32808 | |||
| d41878c2b1 | |||
| e023638135 | |||
| 0d52344d27 | |||
| 5bd303788b | |||
| afac8fb670 | |||
| 1c8a32c3fd | |||
| 96b474223d | |||
| 42d7a39c49 | |||
| bad3fa4035 | |||
| d819fc09f0 | |||
| c35979d9f9 | |||
| f3c0540b42 | |||
| 5b4192acb5 | |||
| 16d94894b7 | |||
| ae8d38fc31 | |||
| b2521988e1 | |||
| dae123adac | |||
| 1c9ddbbea2 | |||
| 3f2782f5b7 | |||
| 865623ef3e | |||
| 4fdce3ca2c | |||
| c47881106e | |||
| 9a70f7378b | |||
| b18f608594 | |||
| d1f8a734c5 |
@@ -198,6 +198,32 @@ All phrasing paths emit `{"response":"...","mood":"..."}` (parsed in `replier_ll
|
||||
note, query, act, chat, system`). `llm/check_prompt_parity.py` in the training
|
||||
workspace enforces that the Go and relabelling prompts remain identical.
|
||||
|
||||
## Russian patterns — three mechanisms, no fourth
|
||||
|
||||
Hand-written Russian stem patterns were swept out on 2026-08-04 (owner's call: not a
|
||||
pattern, and the resident model cannot be asked per turn either). A regex whose output is a
|
||||
fact or a route is the defect; a regex over structured input — HTML, MIME, JSON, a URL, an
|
||||
argv list — is not. Before writing a Russian word list, pick one of these:
|
||||
|
||||
- **`internal/lexicon`** — closed classes, in `lexicon_ru_v1.json`. Interrogatives,
|
||||
capture verbs, cardinals, day offsets, weekdays, months, spoken hours. Editing a word is
|
||||
a data change, and there is exactly one copy: months used to live in three files.
|
||||
- **`internal/morph`** — grammar, from the vendored golem Russian dictionary. `IsVerbForm`
|
||||
and `SameWord`. Note that lemma matching is BROADER than stem-plus-one-ending, so a verb
|
||||
slot that means the imperative must be matched exactly — `говори` and `говорил` are one
|
||||
lemma and only one of them is a command (`cmd/mavend/quiet_toggle.go`).
|
||||
- **`cmd/mavend/topics.go` and the embedder** — open sets, where the question is what a
|
||||
turn is ABOUT. Frozen seeds per subject plus a real `other` class, scored against the
|
||||
turn's own query vector. Same shape as the personal boundary in `personalboundary.go`,
|
||||
with one difference: a topic must clear the runner-up by `topicMargin`, because a false
|
||||
claim here spends a network scan rather than one honest "не знаю". The old keyword tests
|
||||
stay as the offline floor and may remain narrow, since they are no longer the only answer.
|
||||
- **The ecosystem trio** — when the answer is not in the utterance at all. Identity is
|
||||
Nexus's, never a local pattern.
|
||||
|
||||
Seeds are scoring data. Editing one moves a recogniser and must be re-measured against the
|
||||
`TestONNX*` tests, not eyeballed.
|
||||
|
||||
## Non-goals (hard constraints)
|
||||
|
||||
Not a nag, not autonomous. Maven's persona is **feminine** — Russian
|
||||
|
||||
+3
-2
@@ -16,6 +16,7 @@ import (
|
||||
"log"
|
||||
|
||||
"github.com/kami/maven/internal/loop"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
@@ -35,10 +36,10 @@ func (h *reactiveHandler) resolveAck(ctx context.Context, text string, src turnS
|
||||
}
|
||||
if err := h.api.ResolveNudge(ctx, target.ID, store.NudgeActed, now); err != nil {
|
||||
log.Printf("voice: ack nudge %d (%s, %s): %v", target.ID, target.Rule, src, err)
|
||||
return "не получилось отметить.", true
|
||||
return phraser.Ack(phraser.FailAck, nil), true
|
||||
}
|
||||
log.Printf("voice: acked nudge %d (rule %s) from %s", target.ID, target.Rule, src)
|
||||
return "отлично, отметила.", true
|
||||
return phraser.Ack(phraser.AckNudge, nil), true
|
||||
}
|
||||
|
||||
// ackFromFact — post-action hook, called once the turn's decision has been
|
||||
|
||||
@@ -40,6 +40,7 @@ import (
|
||||
"context"
|
||||
"log"
|
||||
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
@@ -58,10 +59,14 @@ func (h *reactiveHandler) actionChat(ctx context.Context, dec router.Decision) s
|
||||
// Conversational: build history from dialogue session (prior user turns)
|
||||
// and let the LLM respond from general knowledge + context.
|
||||
history := h.chatHistory()
|
||||
// The phraser hands back its own fallback text alongside the error, so the
|
||||
// turn survives a dead server and the failure still reaches the log.
|
||||
reply, err := h.phraser.PhraseChat(ctx, dec.Utterance, history)
|
||||
if err != nil {
|
||||
log.Printf("voice: chat: %v", err)
|
||||
return "поговорили."
|
||||
}
|
||||
if reply == "" {
|
||||
return phraser.ChatFallback()
|
||||
}
|
||||
return reply
|
||||
}
|
||||
|
||||
@@ -6,6 +6,7 @@ import (
|
||||
"log"
|
||||
|
||||
"github.com/kami/maven/internal/mcp"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/tool"
|
||||
)
|
||||
@@ -50,31 +51,37 @@ func (h *reactiveHandler) actionAct(ctx context.Context, dec router.Decision) st
|
||||
// destructive: park it and ask. The next utterance answers.
|
||||
phrase := actPhrase(dec.Slots.Fn, dec.Slots.Args)
|
||||
h.park(dec.Slots.Fn, dec.Slots.Args, phrase)
|
||||
return "выполнить «" + phrase + "»? скажи «да» или «нет»."
|
||||
return phraser.A(phraser.ActConfirm, map[string]string{"name": phrase})
|
||||
case errors.Is(err, tool.ErrNeedsAuthedSurface):
|
||||
// Irreversible (internal/tool/risk.go). A confirm turn would not
|
||||
// help: everything that proposed this act — the STT, the router,
|
||||
// the fuzzy allowlist match — is a guess, and a spoken "да" checks
|
||||
// none of it. She names the gap instead.
|
||||
return phraser.A(phraser.ActNeedsAuthedSurface, nil)
|
||||
case errors.Is(err, tool.ErrNotEnabled):
|
||||
return h.proposeGap(ctx, dec)
|
||||
case errors.Is(err, tool.ErrNotConnected), errors.Is(err, mcp.ErrNotConnected), errors.Is(err, mcp.ErrNoServer):
|
||||
// The row is enabled and the backend is gone. Drafting a proposal
|
||||
// for it (the ErrNotEnabled path) would be answering the wrong
|
||||
// question.
|
||||
return "этот инструмент включён, но сервер, который его выполняет, сейчас не подключён."
|
||||
return phraser.A(phraser.ActServerDown, nil)
|
||||
case errors.Is(err, mcp.ErrToolGone):
|
||||
return "сервер больше не предлагает этот инструмент — я сняла его с разрешённых, посмотри на /tools."
|
||||
return phraser.A(phraser.ActWithdrawn, nil)
|
||||
case errors.Is(err, mcp.ErrNeedsArgs):
|
||||
// An MCP tool that wants named arguments a spoken verb cannot
|
||||
// supply. Guessing them would be a wrong act, so she says so
|
||||
// instead — the tool is still runnable from the authed surface,
|
||||
// where a human types them.
|
||||
return "этому инструменту нужны аргументы, которые я из голоса не соберу — я не буду угадывать."
|
||||
return phraser.A(phraser.ActNeedsArgs, nil)
|
||||
}
|
||||
log.Printf("voice: tool %s: %v", dec.Slots.Fn, err)
|
||||
if out != "" {
|
||||
return "не получилось выполнить команду: " + firstLine(out)
|
||||
return phraser.A(phraser.ActFailOut, map[string]string{"out": firstLine(out)})
|
||||
}
|
||||
return "не получилось выполнить команду."
|
||||
return phraser.A(phraser.ActFail, nil)
|
||||
}
|
||||
if out != "" {
|
||||
return "готово: " + firstLine(out)
|
||||
return phraser.A(phraser.ActDoneOut, map[string]string{"out": firstLine(out)})
|
||||
}
|
||||
return "готово."
|
||||
return phraser.A(phraser.ActDone, nil)
|
||||
}
|
||||
|
||||
@@ -0,0 +1,75 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// The act path speaks each tier (Vikunja #449): a safe row runs, a destructive
|
||||
// one costs a confirm turn, an irreversible one is refused with the reason.
|
||||
func TestActPathSpeaksTheTiers(t *testing.T) {
|
||||
h, st, _ := newClarifyHandler(t)
|
||||
ctx := context.Background()
|
||||
now := h.now()
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
cmd []string
|
||||
destructive bool
|
||||
}{
|
||||
{"status", []string{"true"}, false},
|
||||
{"restart", []string{"true"}, true},
|
||||
{"wipe", []string{"rm", "-rf"}, true},
|
||||
} {
|
||||
if _, err := st.ProposeTool(ctx, tc.name, "test", "homelab", now); err != nil {
|
||||
t.Fatalf("propose %s: %v", tc.name, err)
|
||||
}
|
||||
if err := st.EnableTool(ctx, tc.name, tc.cmd, tc.destructive, "homelab", now); err != nil {
|
||||
t.Fatalf("enable %s: %v", tc.name, err)
|
||||
}
|
||||
}
|
||||
|
||||
act := func(fn string) string {
|
||||
return h.actionAct(ctx, router.Decision{
|
||||
Intent: router.IntentAct,
|
||||
Utterance: fn,
|
||||
Slots: router.Slots{Fn: fn, HasFn: true},
|
||||
})
|
||||
}
|
||||
|
||||
if reply := act("status"); !strings.HasPrefix(reply, "готово") {
|
||||
t.Errorf("safe act replied %q; want it to have run", reply)
|
||||
}
|
||||
// PR 112's review cut «скажи «да» или «нет».» — he knows how to answer a
|
||||
// yes/no question — so the confirm turn is recognised by the question.
|
||||
if reply := act("restart"); !strings.Contains(reply, "да или нет") {
|
||||
t.Errorf("destructive act replied %q; want a confirm turn", reply)
|
||||
}
|
||||
// Clear the confirm the destructive act parked, so what is pending after
|
||||
// the irreversible one is only what the irreversible one parked.
|
||||
h.mu.Lock()
|
||||
h.pending = nil
|
||||
h.mu.Unlock()
|
||||
|
||||
reply := act("wipe")
|
||||
if strings.Contains(reply, "да или нет") {
|
||||
t.Fatalf("irreversible act asked for a confirm: %q", reply)
|
||||
}
|
||||
if !strings.Contains(reply, "не вернуть") {
|
||||
t.Errorf("irreversible act replied %q; want it to name the reason", reply)
|
||||
}
|
||||
// Nothing was parked, so a later "да" cannot pick it up.
|
||||
h.mu.Lock()
|
||||
pending := h.pending
|
||||
h.mu.Unlock()
|
||||
if pending != nil {
|
||||
t.Errorf("an irreversible act parked %+v", pending)
|
||||
}
|
||||
// And it is still an enabled row — refusing to run it from voice is not
|
||||
// the same as taking it off the allowlist.
|
||||
if got, err := st.LookupTool(ctx, "wipe"); err != nil || got.Status != "enabled" {
|
||||
t.Errorf("wipe is %+v, %v; want it still enabled", got, err)
|
||||
}
|
||||
}
|
||||
@@ -6,6 +6,7 @@ import (
|
||||
"strconv"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
@@ -14,7 +15,7 @@ import (
|
||||
// it for recall, and let pattern detection propose a routine.
|
||||
func (h *reactiveHandler) actionFact(ctx context.Context, dec router.Decision) string {
|
||||
if !dec.Slots.HasKey {
|
||||
return "не разобрала, что записать — попробуй иначе."
|
||||
return phraser.Ack(phraser.FailFactUnparsed, nil)
|
||||
}
|
||||
// A question is never a fact about him (#470). "какая последняя версия
|
||||
// языка Go?" used to land here, and the value stored was whatever the
|
||||
@@ -62,7 +63,7 @@ func (h *reactiveHandler) actionFact(ctx context.Context, dec router.Decision) s
|
||||
factID, err := h.api.WriteFact(ctx, req)
|
||||
if err != nil {
|
||||
log.Printf("voice: write fact: %v", err)
|
||||
return "не получилось сохранить факт."
|
||||
return phraser.Ack(phraser.FailFact, nil)
|
||||
}
|
||||
// Index the fact in long-term memory (best-effort, must not fail the fact
|
||||
// write). Facts aren't in the notes table, so this is the only recall path
|
||||
|
||||
@@ -0,0 +1,143 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"log"
|
||||
"strings"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
// Standing lists on the voice path (Vikunja #453).
|
||||
//
|
||||
// Three halves, mirroring what task capture already does: an add that runs at
|
||||
// the top of actionNote, a read-back query source, and a crossing-off that runs
|
||||
// on the same note path because "всё купил" is note-shaped.
|
||||
//
|
||||
// These read h.dataStore rather than the CoreAPI. A list is local to the core
|
||||
// and nothing outside it writes one: the web UI has no list page, no reach
|
||||
// files groceries, and the digestion worker does not read the table. When
|
||||
// something outside mavend needs to add to a list, the ipc seam is what it
|
||||
// grows through — the intake rules that CaptureTaskReq documents are about
|
||||
// shared intake, and there is none here yet.
|
||||
//
|
||||
// Nothing here speaks unprompted. A list is answered when asked about.
|
||||
|
||||
// captureListFromNote claims the turn when the utterance adds to, clears, or
|
||||
// crosses one item off a list. ("", false) hands the turn back to the note path.
|
||||
func (h *reactiveHandler) captureListFromNote(ctx context.Context, dec router.Decision) (string, bool) {
|
||||
if h.dataStore == nil {
|
||||
return "", false
|
||||
}
|
||||
// Clearing is read before removing on purpose: "всё купил" and "купил
|
||||
// молоко" start with the same word, and only the second one names an item.
|
||||
if list, ok := router.ParseListClear(dec.Utterance); ok {
|
||||
n, err := h.dataStore.ClearList(ctx, list, h.now())
|
||||
if err != nil {
|
||||
log.Printf("voice: clear list: %v", err)
|
||||
return "не получилось обновить список.", true
|
||||
}
|
||||
if n == 0 {
|
||||
return "в списке и так ничего не было.", true
|
||||
}
|
||||
return "вычеркнула всё, список пустой.", true
|
||||
}
|
||||
if cap, ok := router.ParseListRemove(dec.Utterance); ok {
|
||||
if reply, ok := h.removeListItem(ctx, cap); ok {
|
||||
return reply, true
|
||||
}
|
||||
// Nothing on the list by that name. "купил новый ноутбук" is a note and
|
||||
// must stay one, so the turn goes back rather than claiming a removal
|
||||
// that removed nothing.
|
||||
return "", false
|
||||
}
|
||||
cap, ok := router.ParseListCapture(dec.Utterance)
|
||||
if !ok {
|
||||
return "", false
|
||||
}
|
||||
res, err := h.dataStore.AddListItem(ctx, store.ListItem{
|
||||
List: cap.List,
|
||||
Item: cap.Item,
|
||||
Source: "tap:voice",
|
||||
CreatedTs: h.now(),
|
||||
})
|
||||
if err != nil {
|
||||
log.Printf("voice: add list item: %v", err)
|
||||
return "не получилось добавить в список.", true
|
||||
}
|
||||
if !res.Created {
|
||||
return cap.Item + " уже в списке.", true
|
||||
}
|
||||
return "добавила в список: " + cap.Item + ".", true
|
||||
}
|
||||
|
||||
// removeListItem crosses one named item off. It reports false when the list
|
||||
// holds nothing by that name, which is what keeps the marker words from
|
||||
// swallowing ordinary notes.
|
||||
func (h *reactiveHandler) removeListItem(ctx context.Context, cap router.ListCapture) (string, bool) {
|
||||
items, err := h.dataStore.ListItems(ctx, cap.List, "")
|
||||
if err != nil {
|
||||
log.Printf("voice: list items: %v", err)
|
||||
return "", false
|
||||
}
|
||||
want := store.NormalizeTaskText(cap.Item)
|
||||
for _, li := range items {
|
||||
if store.NormalizeTaskText(li.Item) != want {
|
||||
continue
|
||||
}
|
||||
if err := h.dataStore.SetListItemStatus(ctx, li.ID, store.ListItemDone, h.now()); err != nil {
|
||||
log.Printf("voice: cross off list item: %v", err)
|
||||
return "не получилось обновить список.", true
|
||||
}
|
||||
return "вычеркнула: " + li.Item + ".", true
|
||||
}
|
||||
return "", false
|
||||
}
|
||||
|
||||
// queryList — "что в списке покупок?", "что мне купить?".
|
||||
//
|
||||
// A query source, so it sits in querySources and either claims the turn or
|
||||
// passes it on. It is before the recall sources for the reason every specific
|
||||
// source is: the notes pass would otherwise answer a list question with
|
||||
// whatever note is nearest.
|
||||
func (h *reactiveHandler) queryList(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
list, ok := router.ParseListQuery(t.dec.Utterance)
|
||||
if !ok || h.dataStore == nil {
|
||||
return "", false
|
||||
}
|
||||
items, err := h.dataStore.ListItems(ctx, list, "")
|
||||
if err != nil {
|
||||
log.Printf("voice: list items: %v", err)
|
||||
return "не получилось посмотреть список.", true
|
||||
}
|
||||
return formatListRU(list, items), true
|
||||
}
|
||||
|
||||
// formatListRU reads a list aloud. One sentence, comma-separated, because a
|
||||
// shopping list is heard in a shop and a numbered recital is unusable there.
|
||||
func formatListRU(list string, items []store.ListItem) string {
|
||||
name := "списке " + listGenitive(list)
|
||||
if len(items) == 0 {
|
||||
return "в " + name + " пусто."
|
||||
}
|
||||
names := make([]string, 0, len(items))
|
||||
for _, li := range items {
|
||||
names = append(names, li.Item)
|
||||
}
|
||||
return "в " + name + ": " + strings.Join(names, ", ") + "."
|
||||
}
|
||||
|
||||
// listGenitive puts a list tag into the case "список <…>" needs. Russian
|
||||
// declines the noun and she must not say "в списке покупки".
|
||||
func listGenitive(list string) string {
|
||||
switch list {
|
||||
case "покупки":
|
||||
return "покупок"
|
||||
case "аптека":
|
||||
return "аптеки"
|
||||
case "хозяйство":
|
||||
return "хозяйства"
|
||||
}
|
||||
return list
|
||||
}
|
||||
@@ -0,0 +1,184 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
func listNow() time.Time { return time.Date(2026, 8, 4, 9, 0, 0, 0, time.UTC) }
|
||||
|
||||
func listHandler(t *testing.T) *reactiveHandler {
|
||||
t.Helper()
|
||||
return &reactiveHandler{dataStore: newTestStore(t), now: listNow}
|
||||
}
|
||||
|
||||
func askList(t *testing.T, h *reactiveHandler, utterance string) (string, bool) {
|
||||
t.Helper()
|
||||
return h.captureListFromNote(context.Background(), router.Decision{
|
||||
Intent: router.IntentNote, Utterance: utterance,
|
||||
})
|
||||
}
|
||||
|
||||
func TestListCaptureAddsAndReadsBack(t *testing.T) {
|
||||
h := listHandler(t)
|
||||
for _, u := range []string{"добавь в список покупок молоко", "добавь в список хлеб"} {
|
||||
if reply, ok := askList(t, h, u); !ok {
|
||||
t.Fatalf("%q was not claimed (reply %q)", u, reply)
|
||||
}
|
||||
}
|
||||
if reply, ok := askList(t, h, "добавь в список покупок молоко"); !ok || !strings.Contains(reply, "уже") {
|
||||
t.Errorf("second молоко replied %q, %v; want an already-there answer", reply, ok)
|
||||
}
|
||||
answer, ok := h.queryList(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: "что в списке покупок?"},
|
||||
})
|
||||
if !ok {
|
||||
t.Fatal("the list question was not claimed")
|
||||
}
|
||||
if !strings.Contains(answer, "молоко") || !strings.Contains(answer, "хлеб") {
|
||||
t.Errorf("answer %q; want both items", answer)
|
||||
}
|
||||
if strings.Contains(answer, "списке покупки") {
|
||||
t.Errorf("answer %q declines the list name wrong", answer)
|
||||
}
|
||||
}
|
||||
|
||||
// An utterance with no list marker is a note and must stay one, whichever half
|
||||
// of the parser it brushes against.
|
||||
func TestListCapturePassesOrdinaryNotes(t *testing.T) {
|
||||
h := listHandler(t)
|
||||
for _, u := range []string{
|
||||
"молоко закончилось",
|
||||
"надо бы съездить в магазин",
|
||||
"купил новый ноутбук",
|
||||
"добавь в список покупок",
|
||||
} {
|
||||
if reply, ok := askList(t, h, u); ok {
|
||||
t.Errorf("%q was claimed as a list turn: %q", u, reply)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestListCrossOffOneItemAndThenAll(t *testing.T) {
|
||||
h := listHandler(t)
|
||||
for _, u := range []string{
|
||||
"добавь в список покупок молоко",
|
||||
"добавь в список покупок хлеб",
|
||||
"добавь в список аптеки бинт",
|
||||
} {
|
||||
if _, ok := askList(t, h, u); !ok {
|
||||
t.Fatalf("%q was not claimed", u)
|
||||
}
|
||||
}
|
||||
reply, ok := askList(t, h, "вычеркни молоко")
|
||||
if !ok || !strings.Contains(reply, "молоко") {
|
||||
t.Fatalf("cross off replied %q, %v", reply, ok)
|
||||
}
|
||||
open, err := h.dataStore.ListItems(context.Background(), "покупки", "")
|
||||
if err != nil {
|
||||
t.Fatalf("list: %v", err)
|
||||
}
|
||||
if len(open) != 1 || open[0].Item != "хлеб" {
|
||||
t.Fatalf("open list %+v; want only хлеб", open)
|
||||
}
|
||||
if reply, ok := askList(t, h, "всё купил"); !ok || !strings.Contains(reply, "пустой") {
|
||||
t.Errorf("clear replied %q, %v", reply, ok)
|
||||
}
|
||||
open, err = h.dataStore.ListItems(context.Background(), "покупки", "")
|
||||
if err != nil {
|
||||
t.Fatalf("list: %v", err)
|
||||
}
|
||||
if len(open) != 0 {
|
||||
t.Errorf("%d items still open after всё купил", len(open))
|
||||
}
|
||||
// The other list is untouched, and it is read back on its own.
|
||||
answer, ok := h.queryList(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: "покажи список аптеки"},
|
||||
})
|
||||
if !ok || !strings.Contains(answer, "бинт") {
|
||||
t.Errorf("аптека answer %q, %v; want бинт", answer, ok)
|
||||
}
|
||||
}
|
||||
|
||||
func TestQueryListSaysWhenItIsEmpty(t *testing.T) {
|
||||
h := listHandler(t)
|
||||
answer, ok := h.queryList(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: "что мне купить?"},
|
||||
})
|
||||
if !ok {
|
||||
t.Fatal("the list question was not claimed")
|
||||
}
|
||||
if !strings.Contains(answer, "пусто") {
|
||||
t.Errorf("empty answer %q; want it to say so", answer)
|
||||
}
|
||||
if _, ok := h.queryList(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Intent: router.IntentQuery, Utterance: "какие у меня задачи?"},
|
||||
}); ok {
|
||||
t.Error("the list source claimed a task question")
|
||||
}
|
||||
}
|
||||
|
||||
// Stage 0 answers a list turn without the model: the grammars route it, and the
|
||||
// action handlers re-parse what the grammar matched.
|
||||
func TestListGrammarsRouteWithoutTheModel(t *testing.T) {
|
||||
cases := []struct {
|
||||
utterance string
|
||||
want router.Intent
|
||||
}{
|
||||
{"добавь в список покупок молоко", router.IntentNote},
|
||||
{"что в списке покупок?", router.IntentQuery},
|
||||
{"всё купил", router.IntentNote},
|
||||
}
|
||||
for _, c := range cases {
|
||||
var got router.Intent
|
||||
claimed := false
|
||||
for _, g := range router.ListGrammars() {
|
||||
m := g.Pattern.FindStringSubmatch(c.utterance)
|
||||
if m == nil {
|
||||
continue
|
||||
}
|
||||
if dec, ok := g.Build(m); ok {
|
||||
got, claimed = dec.Intent, true
|
||||
break
|
||||
}
|
||||
}
|
||||
if !claimed {
|
||||
t.Errorf("no list grammar claimed %q", c.utterance)
|
||||
continue
|
||||
}
|
||||
if got != c.want {
|
||||
t.Errorf("%q routed to %v; want %v", c.utterance, got, c.want)
|
||||
}
|
||||
}
|
||||
for _, g := range router.ListGrammars() {
|
||||
m := g.Pattern.FindStringSubmatch("напомни купить молоко завтра")
|
||||
if m == nil {
|
||||
continue
|
||||
}
|
||||
if _, ok := g.Build(m); ok {
|
||||
t.Errorf("grammar %s claimed a reminder", g.Name)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestListStoreSourceIsVoice(t *testing.T) {
|
||||
h := listHandler(t)
|
||||
if _, ok := askList(t, h, "добавь в список покупок молоко"); !ok {
|
||||
t.Fatal("not claimed")
|
||||
}
|
||||
items, err := h.dataStore.ListItems(context.Background(), "покупки", "")
|
||||
if err != nil {
|
||||
t.Fatalf("list: %v", err)
|
||||
}
|
||||
if len(items) != 1 || items[0].Source != "tap:voice" {
|
||||
t.Errorf("stored %+v; want one row from tap:voice", items)
|
||||
}
|
||||
if items[0].Status != store.ListItemOpen {
|
||||
t.Errorf("status %q; want open", items[0].Status)
|
||||
}
|
||||
}
|
||||
@@ -5,6 +5,7 @@ import (
|
||||
"log"
|
||||
"strconv"
|
||||
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
@@ -17,19 +18,25 @@ func (h *reactiveHandler) actionNote(ctx context.Context, dec router.Decision) s
|
||||
if reply, ok := h.captureTaskFromNote(ctx, dec); ok {
|
||||
return reply
|
||||
}
|
||||
// A standing list is neither work nor recall (Vikunja #453). Checked here
|
||||
// for the same reason and at the same cost: before the embedding is paid
|
||||
// for, and it passes the turn straight back when no marker matches.
|
||||
if reply, ok := h.captureListFromNote(ctx, dec); ok {
|
||||
return reply
|
||||
}
|
||||
// embed the note text with the same model the classifier uses, persist
|
||||
// via CoreAPI (source=tap:voice). Semantic recall lives in `notes`, not
|
||||
// facts — no predicate reads it (spec's two-memory split).
|
||||
vec, err := router.EmbedPassage(ctx, h.embedder, dec.Utterance)
|
||||
if err != nil {
|
||||
log.Printf("voice: embed note: %v", err)
|
||||
return "не получилось сохранить заметку."
|
||||
return phraser.Ack(phraser.FailNote, nil)
|
||||
}
|
||||
noteTs := h.now()
|
||||
noteID, err := h.api.WriteNote(ctx, noteTs, dec.Utterance, vec, "tap:voice")
|
||||
if err != nil {
|
||||
log.Printf("voice: write note: %v", err)
|
||||
return "не получилось сохранить заметку."
|
||||
return phraser.Ack(phraser.FailNote, nil)
|
||||
}
|
||||
// Insert into long-term memory (best-effort, must not fail the note write).
|
||||
// text/ts in the meta make a Search hit self-describing (see bestRecall).
|
||||
|
||||
+60
-42
@@ -85,6 +85,11 @@ var querySources = []querySource{
|
||||
// the money facts the poller wrote, and the notes pass would otherwise
|
||||
// answer it from whatever he once said about spending. Its matcher needs a
|
||||
// money noun plus an actual ask, so "я потратил весь день" is untouched.
|
||||
// Next to "tasks" and for the same reason: "что мне купить?" is a question
|
||||
// about the shopping list, and the recall pass would otherwise answer it
|
||||
// from an old note about the shop. Its matcher needs an explicit list
|
||||
// marker, so "надо бы съездить в магазин" is untouched.
|
||||
{name: "list", answer: (*reactiveHandler).queryList},
|
||||
{name: "money", answer: (*reactiveHandler).queryMoney},
|
||||
// Before the recall sources and before general knowledge: "что нового?" is
|
||||
// a question about the feeds she reads, and general knowledge would answer
|
||||
@@ -147,9 +152,9 @@ func (h *reactiveHandler) actionQuery(ctx context.Context, dec router.Decision)
|
||||
// The previous question cannot be re-asked for another day. Saying so
|
||||
// beats "не знаю", which reads as "no data for tomorrow" when the
|
||||
// truth is that she never looked.
|
||||
return "про другой день так не отвечу — спроси целиком."
|
||||
return phraser.Q(phraser.QueryOtherDay, nil)
|
||||
}
|
||||
return "не знаю."
|
||||
return phraser.Q(phraser.QueryUnknown, nil)
|
||||
}
|
||||
|
||||
// queryFactByKey — when the dialogue layer resolved an anaphoric reference to
|
||||
@@ -167,11 +172,11 @@ func (h *reactiveHandler) queryFactByKey(ctx context.Context, t *queryTurn) (str
|
||||
if dec.Slots.HasTime {
|
||||
// The query asks about timing — the fact's own timestamp is the
|
||||
// answer it's looking for. Format as a natural reply.
|
||||
return fmt.Sprintf("я записала это %s", formatTime(f.Ts)), true
|
||||
return phraser.Q(phraser.QueryFactWhen, map[string]string{"when": formatTime(f.Ts)}), true
|
||||
}
|
||||
// General fact reference: describe what we know.
|
||||
if dec.Utterance == "" {
|
||||
return fmt.Sprintf("вот что я знаю: %s — %s", dec.Slots.Key, f.Value), true
|
||||
return phraser.Q(phraser.QueryFactValue, map[string]string{"key": dec.Slots.Key, "value": f.Value}), true
|
||||
}
|
||||
// The utterance still carries the question; fall through to normal RAG
|
||||
// with the resolved key in context.
|
||||
@@ -197,7 +202,7 @@ func (h *reactiveHandler) queryDayPlan(ctx context.Context, t *queryTurn) (strin
|
||||
plan, err := h.api.DayPlan(ctx)
|
||||
if err != nil {
|
||||
log.Printf("voice: day plan: %v", err)
|
||||
return "не получилось собрать план.", true
|
||||
return phraser.Q(phraser.QueryFailPlan, nil), true
|
||||
}
|
||||
if !router.IsRestOfDayQuery(t.dec.Utterance) {
|
||||
return plan.Spoken, true
|
||||
@@ -242,7 +247,7 @@ func (h *reactiveHandler) queryHabits(ctx context.Context, t *queryTurn) (string
|
||||
facts, err := h.api.RecentActiveFactsByKind(ctx, string(store.KindSelf), habitFactWindow)
|
||||
if err != nil {
|
||||
log.Printf("voice: habits: recent facts: %v", err)
|
||||
return "не получилось посмотреть записи.", true
|
||||
return phraser.Q(phraser.QueryFailNotes, nil), true
|
||||
}
|
||||
obs := make([]memory.Observation, 0, len(facts))
|
||||
for _, f := range facts {
|
||||
@@ -281,7 +286,7 @@ func (h *reactiveHandler) queryFeeds(ctx context.Context, t *queryTurn) (string,
|
||||
// Claim the turn rather than fall through: "не читаю ленты" is true, and
|
||||
// letting general knowledge answer "что нового?" would be an invented
|
||||
// news bulletin.
|
||||
return "я пока не читаю ленты — они не настроены.", true
|
||||
return phraser.Q(phraser.QueryFeedsOff, nil), true
|
||||
}
|
||||
// By source, not the last 200 notes of any kind: a busy day of voice notes
|
||||
// used to push the newest headline out of the window, and she answered "в
|
||||
@@ -289,7 +294,7 @@ func (h *reactiveHandler) queryFeeds(ctx context.Context, t *queryTurn) (string,
|
||||
notes, err := h.api.RecentNotesFromSource(ctx, rss.SourcePrefix, feedNoteWindow)
|
||||
if err != nil {
|
||||
log.Printf("voice: feeds: recent notes: %v", err)
|
||||
return "не получилось посмотреть ленты.", true
|
||||
return phraser.Q(phraser.QueryFailFeeds, nil), true
|
||||
}
|
||||
var picked []string
|
||||
for _, n := range notes {
|
||||
@@ -306,11 +311,11 @@ func (h *reactiveHandler) queryFeeds(ctx context.Context, t *queryTurn) (string,
|
||||
}
|
||||
if len(picked) == 0 {
|
||||
if q.Category != "" {
|
||||
return "по этой теме в лентах пока ничего.", true
|
||||
return phraser.Q(phraser.QueryFeedsTopic, nil), true
|
||||
}
|
||||
return "в лентах пока ничего нового.", true
|
||||
return phraser.Q(phraser.QueryFeedsEmpty, nil), true
|
||||
}
|
||||
return "вот что нового: " + strings.Join(picked, "; "), true
|
||||
return phraser.Q(phraser.QueryFeedsNew, map[string]string{"items": strings.Join(picked, "; ")}), true
|
||||
}
|
||||
|
||||
// queryCalendar — "что у меня сегодня?", "планы на завтра?"
|
||||
@@ -324,7 +329,7 @@ func (h *reactiveHandler) queryCalendar(ctx context.Context, t *queryTurn) (stri
|
||||
events, err := h.api.CalendarEvents(ctx, date, date.Add(24*time.Hour))
|
||||
if err != nil {
|
||||
log.Printf("voice: calendar events: %v", err)
|
||||
return "не получилось проверить календарь.", true
|
||||
return phraser.Q(phraser.QueryFailCalendar, nil), true
|
||||
}
|
||||
// Provenance travels with each event. A work meeting relayed off a phone
|
||||
// notification (source ambient:notif, #126) is stored below full confidence
|
||||
@@ -341,7 +346,7 @@ func (h *reactiveHandler) queryCalendar(ctx context.Context, t *queryTurn) (stri
|
||||
// calls States and nothing else, so there is no confirm turn here — the only
|
||||
// way to CHANGE something is an enabled allowlist row through tool.Executor.
|
||||
func (h *reactiveHandler) queryHome(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
if !isHomeQuery(t.dec.Utterance) {
|
||||
if !h.turnIsAbout(ctx, t, topicHome, isHomeQuery) {
|
||||
return "", false
|
||||
}
|
||||
if h.home == nil {
|
||||
@@ -363,32 +368,35 @@ func (h *reactiveHandler) queryHome(ctx context.Context, t *queryTurn) (string,
|
||||
// because Scan takes no target — the utterance selects the question, never the
|
||||
// subnet.
|
||||
func (h *reactiveHandler) queryNetwork(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
if !isNetworkQuery(t.dec.Utterance) {
|
||||
if !h.turnIsAbout(ctx, t, topicNetwork, isNetworkQuery) {
|
||||
return "", false
|
||||
}
|
||||
if h.netscan == nil {
|
||||
// Fall through, same as queryHome: an unconfigured scanner must not
|
||||
// swallow "сколько устройств в сети?" before recall has looked.
|
||||
return "", false
|
||||
// The recogniser already matched, so this is a question about HIS LAN
|
||||
// and there is no scanner to answer it. Falling through sent it to the
|
||||
// search leg, which answered with a paragraph about routers in general
|
||||
// and put his network question on an upstream engine (Vikunja #479).
|
||||
// A missing capability names itself.
|
||||
return phraser.Q(phraser.QueryNetOff, nil), true
|
||||
}
|
||||
return h.netscan.scanSummary(ctx)
|
||||
}
|
||||
|
||||
func (h *reactiveHandler) queryWeather(ctx context.Context, t *queryTurn) (string, bool) {
|
||||
if !isWeatherQuery(t.dec.Utterance) {
|
||||
if !h.turnIsAbout(ctx, t, topicWeather, isWeatherQuery) {
|
||||
return "", false
|
||||
}
|
||||
loc := extractWeatherLocation(t.dec.Utterance, h.weatherLocation)
|
||||
if loc == "" {
|
||||
// He named no city and voice.weather.default_location is unset. Saying
|
||||
// so is the only honest answer; picking a city would be inventing one.
|
||||
return "не знаю, для какого города — задай voice.weather.default_location или назови город.", true
|
||||
return phraser.Q(phraser.QueryWeatherWhere, nil), true
|
||||
}
|
||||
ctxWT, cancel := context.WithTimeout(ctx, 5*time.Second)
|
||||
defer cancel()
|
||||
w, err := h.weatherProvider.CurrentWeather(ctxWT, loc)
|
||||
if errors.Is(err, weather.ErrNotConfigured) {
|
||||
return "погода не настроена.", true
|
||||
return phraser.Q(phraser.QueryWeatherOff, nil), true
|
||||
}
|
||||
if errors.Is(err, weather.ErrLocationUnknown) {
|
||||
// He named a place and the geocoder does not have it. Saying so beats
|
||||
@@ -397,9 +405,14 @@ func (h *reactiveHandler) queryWeather(ctx context.Context, t *queryTurn) (strin
|
||||
}
|
||||
if err != nil {
|
||||
log.Printf("voice: weather: %v", err)
|
||||
return "не получилось узнать погоду.", true
|
||||
return phraser.Q(phraser.QueryFailWeather, nil), true
|
||||
}
|
||||
return fmt.Sprintf("в %s сейчас %.0f градусов, %s.", w.Location, w.Temperature, w.Condition), true
|
||||
return phraser.Q(phraser.QueryWeatherNow, map[string]string{
|
||||
"location": w.Location,
|
||||
"temp": fmt.Sprintf("%.0f", w.Temperature),
|
||||
"word": phraser.Degrees(w.Temperature),
|
||||
"condition": w.Condition,
|
||||
}), true
|
||||
}
|
||||
|
||||
// queryEmbed isn't an answer source — it's the shared cost the two recall
|
||||
@@ -409,7 +422,7 @@ func (h *reactiveHandler) queryEmbed(ctx context.Context, t *queryTurn) (string,
|
||||
vec, err := router.EmbedQuery(ctx, h.embedder, t.dec.Utterance)
|
||||
if err != nil {
|
||||
log.Printf("voice: embed query: %v", err)
|
||||
return "не получилось найти ответ.", true
|
||||
return phraser.Q(phraser.QueryFailAnswer, nil), true
|
||||
}
|
||||
t.vec = vec
|
||||
return "", false
|
||||
@@ -450,7 +463,13 @@ func (h *reactiveHandler) queryMemory(ctx context.Context, t *queryTurn) (string
|
||||
// A note is phrased in Maven's voice; a fact is read back as it was
|
||||
// stored.
|
||||
if hit.Meta["type"] == "note" {
|
||||
if reply, perr := h.phraser.PhraseQuery(ctx, t.dec.Utterance, []string{text}); perr == nil && reply != "" {
|
||||
reply, perr := h.phraser.PhraseQuery(ctx, t.dec.Utterance, []string{text})
|
||||
switch {
|
||||
case perr != nil:
|
||||
// Reading the note back verbatim beats the phraser's own fallback,
|
||||
// which only wraps the same text in "вот что я нашла:".
|
||||
log.Printf("voice: recall phrase: %v", perr)
|
||||
case reply != "":
|
||||
return reply, true
|
||||
}
|
||||
}
|
||||
@@ -472,7 +491,7 @@ func (h *reactiveHandler) queryNotes(ctx context.Context, t *queryTurn) (string,
|
||||
notes, err := h.api.QueryNotes(ctx, t.vec, 5)
|
||||
if err != nil {
|
||||
log.Printf("voice: query notes: %v", err)
|
||||
return "не получилось найти ответ.", true
|
||||
return phraser.Q(phraser.QueryFailAnswer, nil), true
|
||||
}
|
||||
t.notes = notes
|
||||
noteScores := make([]float64, len(notes))
|
||||
@@ -497,7 +516,7 @@ func (h *reactiveHandler) queryNotes(ctx context.Context, t *queryTurn) (string,
|
||||
log.Printf("voice: phrase query: %v", err)
|
||||
}
|
||||
if reply == "" {
|
||||
reply = "вот что я нашла: " + texts[0]
|
||||
reply = phraser.Q(phraser.QueryFound, map[string]string{"text": texts[0]})
|
||||
}
|
||||
return reply, true
|
||||
}
|
||||
@@ -519,25 +538,24 @@ func (h *reactiveHandler) queryWeb(ctx context.Context, t *queryTurn) (string, b
|
||||
return "", false
|
||||
}
|
||||
if h.crawler == nil {
|
||||
// Fall through. Reading pages is off unless configured, and on a daemon
|
||||
// where it was never turned on the older behaviour is right: the model
|
||||
// answers the question as if the URL had not been said. Announcing a
|
||||
// configuration status is for a capability that exists and failed, not
|
||||
// for one he never asked for.
|
||||
return "", false
|
||||
// He named a URL, so the question is about that page and nothing else
|
||||
// can answer it. The older comment here argued for falling through and
|
||||
// letting the model answer as if the URL had not been said; that is a
|
||||
// guess dressed as an answer (Vikunja #479).
|
||||
return phraser.Q(phraser.QueryPageOff, nil), true
|
||||
}
|
||||
ctxFetch, cancel := context.WithTimeout(ctx, 30*time.Second)
|
||||
defer cancel()
|
||||
page, err := h.crawler.Page(ctxFetch, link)
|
||||
if err != nil {
|
||||
if errors.Is(err, crawl.ErrRobots) {
|
||||
return "эта страница закрыта для чтения — robots.txt не разрешает.", true
|
||||
return phraser.Q(phraser.QueryPageBlocked, nil), true
|
||||
}
|
||||
log.Printf("voice: web: %v", err)
|
||||
return "не получилось прочитать страницу.", true
|
||||
return phraser.Q(phraser.QueryFailPage, nil), true
|
||||
}
|
||||
if page.Text == "" {
|
||||
return "страница открылась, но читать там нечего.", true
|
||||
return phraser.Q(phraser.QueryPageEmpty, nil), true
|
||||
}
|
||||
// The page is handed to the phraser the same way a note is: as context for
|
||||
// the question he actually asked. She answers the question, she does not
|
||||
@@ -547,7 +565,7 @@ func (h *reactiveHandler) queryWeb(ctx context.Context, t *queryTurn) (string, b
|
||||
if reply == "" {
|
||||
// No phraser (or it failed): read back the top of the page rather than
|
||||
// pretend the fetch did not happen.
|
||||
return "вот что на странице: " + crawl.TrimRunes(page.Text, 300), true
|
||||
return phraser.Q(phraser.QueryPageText, map[string]string{"text": crawl.TrimRunes(page.Text, 300)}), true
|
||||
}
|
||||
return reply, true
|
||||
}
|
||||
@@ -613,7 +631,7 @@ func (h *reactiveHandler) querySearch(ctx context.Context, t *queryTurn) (string
|
||||
if reply == "" {
|
||||
// No phraser, or it failed. Read back the best evidence rather than
|
||||
// pretend the search did not happen.
|
||||
return "вот что я нашла: " + crawl.TrimRunes(resp.Snippets()[0], 300), true
|
||||
return phraser.Q(phraser.QueryFound, map[string]string{"text": crawl.TrimRunes(resp.Snippets()[0], 300)}), true
|
||||
}
|
||||
return reply, true
|
||||
}
|
||||
@@ -694,7 +712,7 @@ func (h *reactiveHandler) queryKiwix(ctx context.Context, t *queryTurn) (string,
|
||||
if reply == "" {
|
||||
// No phraser, or it failed. Read back the best hit rather than pretend
|
||||
// the search did not happen.
|
||||
return "вот что я нашла: " + crawl.TrimRunes(top.Title+" — "+page.Text, 300), true
|
||||
return phraser.Q(phraser.QueryFound, map[string]string{"text": crawl.TrimRunes(top.Title+" — "+page.Text, 300)}), true
|
||||
}
|
||||
return reply, true
|
||||
}
|
||||
@@ -724,7 +742,7 @@ func (h *reactiveHandler) queryPersonal(ctx context.Context, t *queryTurn) (stri
|
||||
return "", false
|
||||
}
|
||||
log.Printf("voice: %q is about him and his own data did not answer it; not asking the world", t.dec.Utterance)
|
||||
return "не знаю — не нашла у тебя такой записи.", true
|
||||
return phraser.Q(phraser.QueryPersonalNone, nil), true
|
||||
}
|
||||
|
||||
// personalMarkers — first-person POSSESSION, not first person generally.
|
||||
@@ -792,15 +810,15 @@ func (h *reactiveHandler) queryGeneral(ctx context.Context, t *queryTurn) (strin
|
||||
if h.phraser == nil {
|
||||
// No model of any size. That is not the workstation being asleep, so it
|
||||
// is not that gap: it is simply not knowing.
|
||||
return "не знаю.", true
|
||||
return phraser.Q(phraser.QueryUnknown, nil), true
|
||||
}
|
||||
reply, err := h.phraseWorld(ctx, t.dec.Utterance, nil)
|
||||
if errors.Is(err, phraser.ErrNoWorldModel) {
|
||||
log.Printf("voice: %q needs the world model and it is not available", t.dec.Utterance)
|
||||
return worldGap, true
|
||||
return worldGap(), true
|
||||
}
|
||||
if err != nil || reply == "" {
|
||||
return "не знаю.", true
|
||||
return phraser.Q(phraser.QueryUnknown, nil), true
|
||||
}
|
||||
return reply, true
|
||||
}
|
||||
|
||||
@@ -4,6 +4,7 @@ import (
|
||||
"context"
|
||||
"log"
|
||||
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
@@ -21,13 +22,13 @@ func (h *reactiveHandler) actionReminder(ctx context.Context, dec router.Decisio
|
||||
}
|
||||
}
|
||||
if !dec.Slots.HasTime {
|
||||
return "не получилось разобрать время напоминания."
|
||||
return phraser.Ack(phraser.FailReminderTime, nil)
|
||||
}
|
||||
}
|
||||
payload := `{"text":` + jsonString(dec.Utterance) + `}`
|
||||
if _, err := h.api.CreateReminder(ctx, dec.Slots.Time, payload, ""); err != nil {
|
||||
log.Printf("voice: create reminder: %v", err)
|
||||
return "не получилось поставить напоминание."
|
||||
return phraser.Ack(phraser.FailReminder, nil)
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
@@ -5,6 +5,7 @@ import (
|
||||
"log"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
"github.com/kami/maven/internal/tasks"
|
||||
@@ -40,18 +41,18 @@ func (h *reactiveHandler) captureTaskFromNote(ctx context.Context, dec router.De
|
||||
})
|
||||
if err != nil {
|
||||
log.Printf("voice: capture task: %v", err)
|
||||
return "не получилось записать задачу.", true
|
||||
return phraser.Ack(phraser.FailTask, nil), true
|
||||
}
|
||||
if resp.Promoted {
|
||||
// It was a candidate Maven derived from something she read, and he has
|
||||
// now said it himself. Saying "уже в списке" here would be answering a
|
||||
// confirmation with a shrug.
|
||||
return "поняла, беру в работу: " + cap.Text, true
|
||||
return phraser.Ack(phraser.AckTaskUrgent, map[string]string{"text": cap.Text}), true
|
||||
}
|
||||
if !resp.Created {
|
||||
return "это уже в списке.", true
|
||||
return phraser.Ack(phraser.AckTaskDuplicate, nil), true
|
||||
}
|
||||
return "записала: " + cap.Text, true
|
||||
return phraser.Ack(phraser.AckTask, map[string]string{"text": cap.Text}), true
|
||||
}
|
||||
|
||||
// queryTasks — "какие у меня задачи?", "что мне нужно сделать?".
|
||||
|
||||
@@ -8,6 +8,7 @@ import (
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
@@ -108,7 +109,7 @@ func TestCaptureTaskFromNoteReportsStoreFailure(t *testing.T) {
|
||||
if !ok {
|
||||
t.Fatal("a failed capture still claims the turn — the note path must not double-write")
|
||||
}
|
||||
if !strings.Contains(reply, "не получилось") {
|
||||
if !phraser.IsAck(phraser.FailTask, nil, reply) {
|
||||
t.Errorf("reply = %q, want an honest failure", reply)
|
||||
}
|
||||
}
|
||||
@@ -137,7 +138,7 @@ func TestQueryTasksRecitesTheLiveList(t *testing.T) {
|
||||
if !(openIdx < candIdx) {
|
||||
t.Errorf("reply = %q, want confirmed work before candidates", reply)
|
||||
}
|
||||
if !strings.Contains(reply, "не подтвердил") {
|
||||
if !strings.Contains(reply, "не подтверждал") {
|
||||
t.Errorf("reply = %q, want the candidate flagged as unconfirmed", reply)
|
||||
}
|
||||
}
|
||||
|
||||
+16
-11
@@ -125,13 +125,17 @@ func TestQueryWebPassesWithoutAURL(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// A daemon where page reading was never turned on — the default — answers the
|
||||
// question the way it did before the capability existed. Claiming the turn to
|
||||
// report a configuration status is for something that exists and failed.
|
||||
func TestQueryWebPassesWhenNotConfigured(t *testing.T) {
|
||||
// A daemon where page reading was never turned on names the gap. He asked
|
||||
// about one page, nothing else on the box can read it, and the old behaviour
|
||||
// here was to answer as though the URL had not been said (Vikunja #479).
|
||||
func TestQueryWebNamesTheGapWhenNotConfigured(t *testing.T) {
|
||||
h := buildWebHandler(nil)
|
||||
if reply, ok := askWeb(h, "посмотри https://example.org/page"); ok {
|
||||
t.Fatalf("an unconfigured crawler claimed the turn with %q", reply)
|
||||
reply, ok := askWeb(h, "посмотри https://example.org/page")
|
||||
if !ok {
|
||||
t.Fatal("an unconfigured crawler let the page question fall through")
|
||||
}
|
||||
if !phraser.IsQ(phraser.QueryPageOff, nil, reply) {
|
||||
t.Errorf("got %q, want the gap named", reply)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -156,21 +160,22 @@ func TestQueryWebRefusesNonHTML(t *testing.T) {
|
||||
if !ok {
|
||||
t.Fatal("the web source did not claim a question with a URL")
|
||||
}
|
||||
if !strings.Contains(reply, "не получилось") {
|
||||
if !phraser.IsQ(phraser.QueryFailPage, nil, reply) {
|
||||
t.Errorf("reply = %q, want the read-failed answer", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// robots.txt is honoured on the answer path too, and she says so instead of
|
||||
// reporting a generic failure.
|
||||
// robots.txt is honoured on the answer path too, and she says the page is
|
||||
// closed instead of reporting a generic failure.
|
||||
func TestQueryWebObeysRobots(t *testing.T) {
|
||||
h := buildWebHandler(crawl.New(&robotsDenyFetcher{}, crawl.Config{}))
|
||||
reply, ok := askWeb(h, "посмотри https://example.org/private")
|
||||
if !ok {
|
||||
t.Fatal("the web source did not claim a question with a URL")
|
||||
}
|
||||
if !strings.Contains(reply, "robots.txt") {
|
||||
t.Errorf("reply = %q, want the robots answer", reply)
|
||||
// She names the cause without reading a filename out loud.
|
||||
if !strings.Contains(reply, "закрыта для чтения") || strings.Contains(reply, "robots") {
|
||||
t.Errorf("reply = %q, want the closed-page answer with no filename", reply)
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -10,6 +10,7 @@ import (
|
||||
|
||||
"github.com/kami/maven/internal/calendar"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
@@ -147,8 +148,8 @@ func TestQueryDayPlanCoreFailure(t *testing.T) {
|
||||
if !ok {
|
||||
t.Fatal("a failed plan read must still answer, not fall through to RAG")
|
||||
}
|
||||
if reply != "не получилось собрать план." {
|
||||
t.Errorf("reply = %q", reply)
|
||||
if !phraser.IsQ(phraser.QueryFailPlan, nil, reply) {
|
||||
t.Errorf("reply = %q, want the honest failure", reply)
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
+142
-31
@@ -9,10 +9,25 @@ import (
|
||||
"time"
|
||||
|
||||
hexisclient "github.com/kami/hexis/pkg/client"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
"github.com/kami/maven/internal/tool"
|
||||
)
|
||||
|
||||
// The three services, spelled the way she says them out loud. A service that is
|
||||
// down or refusing has to be named: they degrade independently, so "не
|
||||
// отвечает" on its own tells him nothing he can act on, and each call site
|
||||
// already knows which one it was talking to — it records the same name in the
|
||||
// trace (Vikunja #521).
|
||||
const (
|
||||
serviceNexus = "Nexus"
|
||||
serviceHexis = "Hexis"
|
||||
)
|
||||
|
||||
// serviceVars — the one-key map the eco_down and eco_denied lines take.
|
||||
func serviceVars(name string) map[string]string { return map[string]string{"name": name} }
|
||||
|
||||
// praxisCapability is one arm of the Praxis act dispatch. This is an interface
|
||||
// rather than a map[string]func because each arm carries its own state: the
|
||||
// verb aliases it answers to, the trace name it records, and its own reply
|
||||
@@ -144,10 +159,10 @@ func (listAttentionCapability) handle(ctx context.Context, h *reactiveHandler, p
|
||||
log.Printf("ecosystem: praxis attention: %v", err)
|
||||
h.recordEcosystemTrace(ctx, "praxis", "list_attention", traceStatusForError(err),
|
||||
started, traceErrorFields(err))
|
||||
return "не могу сейчас узнать, что требует внимания."
|
||||
return phraser.A(phraser.AttentionFail, nil)
|
||||
}
|
||||
if len(items) == 0 {
|
||||
return "ничего не требует внимания."
|
||||
return phraser.A(phraser.AttentionNone, nil)
|
||||
}
|
||||
h.recordPraxisTrace(ctx, "list_attention", started, map[string]any{"count": len(items)})
|
||||
var parts []string
|
||||
@@ -157,6 +172,11 @@ func (listAttentionCapability) handle(ctx context.Context, h *reactiveHandler, p
|
||||
importance, _ := item["importance"].(float64)
|
||||
rule, _ := item["rule"].(string)
|
||||
s := title
|
||||
if s == "" {
|
||||
// An item Praxis returned without a title is not an item she can
|
||||
// read out. Counting it would put an empty slot in the list.
|
||||
continue
|
||||
}
|
||||
if importance > 0 {
|
||||
s += fmt.Sprintf(" (важность %d", int(importance))
|
||||
if rule != "" {
|
||||
@@ -175,7 +195,13 @@ func (listAttentionCapability) handle(ctx context.Context, h *reactiveHandler, p
|
||||
}
|
||||
}
|
||||
}
|
||||
return "требует внимания: " + strings.Join(parts, "; ")
|
||||
if len(parts) == 0 {
|
||||
// Praxis returned items and not one of them could be said. "ничего не
|
||||
// требует внимания" is the honest answer; the list line would render as
|
||||
// its own label and a colon (Vikunja #521).
|
||||
return phraser.A(phraser.AttentionNone, nil)
|
||||
}
|
||||
return phraser.A(phraser.AttentionList, map[string]string{"items": strings.Join(parts, "; ")})
|
||||
}
|
||||
|
||||
// listChangesCapability reads the recent-changes feed.
|
||||
@@ -192,19 +218,29 @@ func (listChangesCapability) handle(ctx context.Context, h *reactiveHandler, px
|
||||
log.Printf("ecosystem: praxis changes: %v", err)
|
||||
h.recordEcosystemTrace(ctx, "praxis", "list_changes", traceStatusForError(err),
|
||||
started, traceErrorFields(err))
|
||||
return "не могу сейчас узнать об изменениях."
|
||||
return phraser.A(phraser.ChangesFail, nil)
|
||||
}
|
||||
if len(changes) == 0 {
|
||||
return "нет изменений."
|
||||
return phraser.A(phraser.ChangesNone, nil)
|
||||
}
|
||||
h.recordPraxisTrace(ctx, "list_changes", started, map[string]any{"count": len(changes)})
|
||||
var parts []string
|
||||
for _, c := range changes {
|
||||
title, _ := c["title"].(string)
|
||||
if title == "" {
|
||||
continue
|
||||
}
|
||||
typ, _ := c["change_type"].(string)
|
||||
if typ == "" {
|
||||
parts = append(parts, title)
|
||||
continue
|
||||
}
|
||||
parts = append(parts, fmt.Sprintf("%s (%s)", title, typ))
|
||||
}
|
||||
return "изменения: " + strings.Join(parts, "; ")
|
||||
if len(parts) == 0 {
|
||||
return phraser.A(phraser.ChangesNone, nil)
|
||||
}
|
||||
return phraser.A(phraser.ChangesList, map[string]string{"items": strings.Join(parts, "; ")})
|
||||
}
|
||||
|
||||
// entityAttentionCapability answers "what's going on with X" by resolving X to
|
||||
@@ -230,12 +266,12 @@ func (entityAttentionCapability) handle(ctx context.Context, h *reactiveHandler,
|
||||
subject = dec.Slots.Text
|
||||
}
|
||||
if subject == "" {
|
||||
return "про что именно спросить?"
|
||||
return phraser.A(phraser.EcoAboutWhat, nil)
|
||||
}
|
||||
if h.ecosystem == nil || h.ecosystem.nexus == nil {
|
||||
// Without Nexus there is no canonical ref to scope by. Say so rather
|
||||
// than quietly answering about something else.
|
||||
return "не могу связать это с сущностью — Nexus не настроен."
|
||||
return phraser.A(phraser.EcoNoNexus, nil)
|
||||
}
|
||||
|
||||
started := h.now()
|
||||
@@ -248,15 +284,15 @@ func (entityAttentionCapability) handle(ctx context.Context, h *reactiveHandler,
|
||||
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceStatusForError(err), started,
|
||||
mergeFields(traceErrorFields(err), map[string]any{"subject": redactSubject(subject)}))
|
||||
if unauthorizedEcosystemError(err) {
|
||||
return "экосистема отклоняет доступ, проверь токен."
|
||||
return phraser.A(phraser.EcoDenied, serviceVars(serviceNexus))
|
||||
}
|
||||
return "экосистема недоступна, попробуй ещё раз."
|
||||
return phraser.A(phraser.EcoDown, serviceVars(serviceNexus))
|
||||
}
|
||||
if len(ambiguous) > 0 {
|
||||
return "уточни, что именно: " + strings.Join(ambiguous, ", ") + "?"
|
||||
return phraser.A(phraser.EcoAmbiguous, map[string]string{"items": strings.Join(ambiguous, ", ")})
|
||||
}
|
||||
if entityID == "" {
|
||||
return "не знаю такой сущности."
|
||||
return phraser.A(phraser.EcoUnknownEntity, nil)
|
||||
}
|
||||
if displayName == "" {
|
||||
displayName = subject
|
||||
@@ -268,7 +304,7 @@ func (entityAttentionCapability) handle(ctx context.Context, h *reactiveHandler,
|
||||
log.Printf("ecosystem: praxis attention for %s: %v", entityID, err)
|
||||
h.recordEcosystemTrace(ctx, "praxis", "entity_attention", traceStatusForError(err),
|
||||
queried, mergeFields(traceErrorFields(err), map[string]any{"entity_id": entityID}))
|
||||
return "не могу сейчас узнать, что требует внимания по «" + displayName + "»."
|
||||
return phraser.A(phraser.AttentionFailEntity, map[string]string{"name": displayName})
|
||||
}
|
||||
items, scoped := scopedToEntity(items, entityID)
|
||||
if !scoped {
|
||||
@@ -279,7 +315,7 @@ func (entityAttentionCapability) handle(ctx context.Context, h *reactiveHandler,
|
||||
log.Printf("ecosystem: praxis returned unscoped items for %s, refusing to answer", entityID)
|
||||
h.recordEcosystemTrace(ctx, "praxis", "entity_attention", traceFailed, queried,
|
||||
map[string]any{"entity_id": entityID, "class": "unscoped_response"})
|
||||
return "не могу сейчас узнать, что требует внимания по «" + displayName + "»."
|
||||
return phraser.A(phraser.AttentionFailEntity, map[string]string{"name": displayName})
|
||||
}
|
||||
h.recordPraxisTrace(ctx, "entity_attention", queried, map[string]any{
|
||||
"entity_id": entityID, "count": len(items),
|
||||
@@ -303,9 +339,9 @@ func (entityAttentionCapability) handle(ctx context.Context, h *reactiveHandler,
|
||||
parts = append(parts, known)
|
||||
}
|
||||
if len(parts) == 0 {
|
||||
return "по «" + displayName + "» ничего нет."
|
||||
return phraser.A(phraser.AttentionNoneEntity, map[string]string{"name": displayName})
|
||||
}
|
||||
return "по «" + displayName + "»: " + strings.Join(parts, "; ")
|
||||
return phraser.A(phraser.AttentionListEntity, map[string]string{"name": displayName, "items": strings.Join(parts, "; ")})
|
||||
}
|
||||
|
||||
// scopedToEntity drops items that carry an entity_id other than the one asked
|
||||
@@ -370,7 +406,7 @@ func (h *reactiveHandler) localFactsForEntity(ctx context.Context, entityID stri
|
||||
if len(parts) == 0 {
|
||||
return ""
|
||||
}
|
||||
out := "я помню: " + strings.Join(parts, ", ")
|
||||
out := phraser.A(phraser.EcoRecall, map[string]string{"items": strings.Join(parts, ", ")})
|
||||
if more {
|
||||
out += ", и это не всё"
|
||||
}
|
||||
@@ -497,6 +533,64 @@ func traceErrorFields(err error) map[string]any {
|
||||
return fields
|
||||
}
|
||||
|
||||
// entityResolution — what asking Nexus about a turn's candidate names came to.
|
||||
// One shape rather than five return values, because the caller needs the
|
||||
// reference that answered as well as the answer: it goes in the trace.
|
||||
type entityResolution struct {
|
||||
subject string // the reference Nexus answered about
|
||||
entityID string // set when exactly one name resolved
|
||||
displayName string // that entity's name as Nexus spells it
|
||||
ambiguous []string // candidate display names to ask between
|
||||
err error // a dependency failure, not a miss
|
||||
}
|
||||
|
||||
// resolveEntityCandidates asks Nexus about each name the turn offered and
|
||||
// reports what it knows, stopping early where the answer is already decided.
|
||||
//
|
||||
// The rules, in the order they apply:
|
||||
//
|
||||
// - A dependency failure ends it. Nexus being down is not "no such entity",
|
||||
// and asking about the next name would report the outage as a miss.
|
||||
// - Nexus calling one name ambiguous ends it. It has the candidates and it is
|
||||
// telling us to ask.
|
||||
// - Two names resolving to different entities is a clarify too, this time ours:
|
||||
// "перезапусти nginx на muzick-indexer" names both a service and its host,
|
||||
// and picking either would be inventing an intent he did not state.
|
||||
// - Nothing resolving returns the first name as the subject, so the trace says
|
||||
// what was actually looked for.
|
||||
func (h *reactiveHandler) resolveEntityCandidates(ctx context.Context, refs []string) entityResolution {
|
||||
var out entityResolution
|
||||
for _, ref := range refs {
|
||||
entityID, displayName, ambiguous, err := h.ecosystem.resolveEntityReference(ctx, ref, nil)
|
||||
if err != nil {
|
||||
return entityResolution{subject: ref, err: err}
|
||||
}
|
||||
if len(ambiguous) > 0 {
|
||||
return entityResolution{subject: ref, ambiguous: ambiguous}
|
||||
}
|
||||
if entityID == "" {
|
||||
continue
|
||||
}
|
||||
if out.entityID == "" {
|
||||
out = entityResolution{subject: ref, entityID: entityID, displayName: displayName}
|
||||
continue
|
||||
}
|
||||
if entityID == out.entityID {
|
||||
continue
|
||||
}
|
||||
// Both are real and they are not the same thing. Hand back the names
|
||||
// Nexus spells, not the words he happened to say.
|
||||
return entityResolution{
|
||||
subject: out.subject,
|
||||
ambiguous: []string{out.displayName, displayName},
|
||||
}
|
||||
}
|
||||
if out.entityID == "" && len(refs) > 0 {
|
||||
out.subject = refs[0]
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// handleHexisAct — resolves entity references through Nexus and executes
|
||||
// matching capabilities through Hexis. Returns a reply string when handled,
|
||||
// or "" to fall through to the system command executor.
|
||||
@@ -514,27 +608,27 @@ func (h *reactiveHandler) handleHexisAct(ctx context.Context, dec router.Decisio
|
||||
|
||||
// Resolve the utterance text as an entity reference through Nexus. An
|
||||
// ambiguous match must stop and clarify — never guess a mutation target.
|
||||
// The name comes from entityReferenceText, not straight from the Text slot:
|
||||
// the model transliterates Latin names as it routes (Vikunja #476).
|
||||
subject := entityReferenceText(dec)
|
||||
// The names come from entityReferences, not straight from the Text slot: the
|
||||
// model transliterates Latin names as it routes (Vikunja #476, #524).
|
||||
started := h.now()
|
||||
entityID, displayName, ambiguous, err := h.ecosystem.resolveEntityReference(ctx, subject, nil)
|
||||
res := h.resolveEntityCandidates(ctx, entityReferences(dec))
|
||||
subject, entityID, displayName, ambiguous, err := res.subject, res.entityID, res.displayName, res.ambiguous, res.err
|
||||
if err != nil {
|
||||
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceStatusForError(err), started,
|
||||
mergeFields(traceErrorFields(err), map[string]any{"subject": redactSubject(subject)}))
|
||||
if unauthorizedEcosystemError(err) {
|
||||
return "экосистема отклоняет доступ, проверь токен."
|
||||
return phraser.A(phraser.EcoDenied, serviceVars(serviceNexus))
|
||||
}
|
||||
// A genuine Nexus dependency failure, not "no such entity" — stop here
|
||||
// and report degradation rather than silently falling through to the
|
||||
// local command executor (ECOSYSTEM-SPEC.md: services degrade
|
||||
// independently, never a silent all-clear).
|
||||
return "экосистема недоступна, попробуй ещё раз."
|
||||
return phraser.A(phraser.EcoDown, serviceVars(serviceNexus))
|
||||
}
|
||||
if len(ambiguous) > 0 {
|
||||
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceAmbig, started,
|
||||
map[string]any{"candidates": len(ambiguous)})
|
||||
return "уточни, что именно: " + strings.Join(ambiguous, ", ") + "?"
|
||||
return phraser.A(phraser.EcoAmbiguous, map[string]string{"items": strings.Join(ambiguous, ", ")})
|
||||
}
|
||||
if entityID == "" {
|
||||
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceNotFound, started,
|
||||
@@ -553,9 +647,9 @@ func (h *reactiveHandler) handleHexisAct(ctx context.Context, dec router.Decisio
|
||||
h.recordEcosystemTrace(ctx, "hexis", "capabilities", traceStatusForError(err), discovered,
|
||||
mergeFields(traceErrorFields(err), map[string]any{"entity_id": entityID}))
|
||||
if unauthorizedEcosystemError(err) {
|
||||
return "экосистема отклоняет доступ, проверь токен."
|
||||
return phraser.A(phraser.EcoDenied, serviceVars(serviceHexis))
|
||||
}
|
||||
return "экосистема недоступна, попробуй ещё раз."
|
||||
return phraser.A(phraser.EcoDown, serviceVars(serviceHexis))
|
||||
}
|
||||
h.recordEcosystemTrace(ctx, "hexis", "capabilities", traceOK, discovered,
|
||||
map[string]any{"entity_id": entityID, "count": len(caps)})
|
||||
@@ -598,13 +692,30 @@ func (h *reactiveHandler) handleHexisAct(ctx context.Context, dec router.Decisio
|
||||
for _, m := range matches {
|
||||
names = append(names, m.Name)
|
||||
}
|
||||
return "какую команду для " + displayName + ": " + strings.Join(names, ", ") + "?"
|
||||
return phraser.A(phraser.ActWhich, map[string]string{"name": displayName, "items": strings.Join(names, ", ")})
|
||||
}
|
||||
matched := matches[0]
|
||||
|
||||
// Read-only capabilities run immediately; mutating ones are parked for an
|
||||
// explicit spoken confirm bound to this capability + target.
|
||||
if !matched.ReadOnly {
|
||||
// The tier decides, and Hexis owns the tier (Vikunja #523). read_only alone
|
||||
// used to decide it here, which flattened three answers into two: a
|
||||
// capability that wipes the thing it names got the same single spoken "да"
|
||||
// as one that restarts a service, and requires_confirmation — which the
|
||||
// Hexis contract calls server-derived and not settable by a caller — was
|
||||
// read by nobody. docs/ecosystem.md §17.3 says confirmation follows risk.
|
||||
tier := tool.RiskOfCapability(matched.Risk, matched.ReadOnly, matched.RequiresConfirmation)
|
||||
policy := tool.PolicyFor(tier)
|
||||
if !policy.VoiceMayRun {
|
||||
// Irreversible. A confirm turn would not help, for the same reason it
|
||||
// does not help a local row: the STT heard it, the model routed it and
|
||||
// a substring matched the capability, and a spoken "да" checks none of
|
||||
// those. She names the gap and he runs it himself.
|
||||
h.recordEcosystemTrace(ctx, "hexis", "confirmation", traceRefused, started,
|
||||
map[string]any{"entity_id": entityID, "capability": matched.Name, "risk": string(tier)})
|
||||
return phraser.A(phraser.ActNeedsAuthedSurface, nil)
|
||||
}
|
||||
if policy.Confirm {
|
||||
h.mu.Lock()
|
||||
h.pendingHexis = &pendingHexisExec{
|
||||
capabilityID: matched.ID,
|
||||
@@ -616,7 +727,7 @@ func (h *reactiveHandler) handleHexisAct(ctx context.Context, dec router.Decisio
|
||||
h.mu.Unlock()
|
||||
h.recordEcosystemTrace(ctx, "hexis", "confirmation", tracePending, started,
|
||||
map[string]any{"entity_id": entityID, "capability": matched.Name})
|
||||
return "выполнить «" + matched.Name + "» для " + displayName + "? скажи «да» или «нет»."
|
||||
return phraser.A(phraser.ActConfirmEntity, map[string]string{"name": matched.Name, "name_entity": displayName})
|
||||
}
|
||||
|
||||
return h.execHexis(ctx, matched.ID, matched.Name, entityID, displayName)
|
||||
@@ -636,7 +747,7 @@ func (h *reactiveHandler) execHexis(ctx context.Context, capID, capName, entityI
|
||||
mergeFields(traceErrorFields(err), map[string]any{
|
||||
"entity_id": entityID, "capability": capName, "causation_id": causationID,
|
||||
}))
|
||||
return "не получилось выполнить команду для " + displayName + "."
|
||||
return phraser.A(phraser.ActFailEntity, map[string]string{"name": displayName})
|
||||
}
|
||||
// One record per hop: the second write this used to make said the same
|
||||
// thing under a different key, in a different shape.
|
||||
@@ -644,7 +755,7 @@ func (h *reactiveHandler) execHexis(ctx context.Context, capID, capName, entityI
|
||||
"entity_id": entityID, "entity_name": displayName,
|
||||
"capability": capName, "causation_id": causationID,
|
||||
})
|
||||
return "команда выполнена для " + displayName + "."
|
||||
return phraser.A(phraser.ActDoneEntity, map[string]string{"name": displayName})
|
||||
}
|
||||
|
||||
// hexisBeforeClarify gives an entity-shaped act one chance at Hexis before she
|
||||
|
||||
@@ -96,7 +96,7 @@ func TestEcosystem_OutagesLeaveNoSharedFailureState(t *testing.T) {
|
||||
// A Nexus outage during a Hexis act writes a failure trace, and a shared
|
||||
// store is the one thing the Praxis path could inherit it through.
|
||||
nexus.SetFault(503)
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); strings.Contains(reply, "выполнена") {
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); actRan(reply) {
|
||||
t.Fatalf("nexus outage must not report success, got %q", reply)
|
||||
}
|
||||
if len(tracesFor(t, h, "nexus", "resolve")) == 0 {
|
||||
@@ -117,7 +117,7 @@ func TestEcosystem_OutagesLeaveNoSharedFailureState(t *testing.T) {
|
||||
if reply := h.handlePraxisAct(ctx, praxisActDec("list_attention")); strings.Contains(reply, "disk") {
|
||||
t.Fatalf("praxis outage must not serve content, got %q", reply)
|
||||
}
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !strings.Contains(reply, "выполнена") {
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !actRan(reply) {
|
||||
t.Fatalf("a praxis outage must not block the hexis path, got %q", reply)
|
||||
}
|
||||
}
|
||||
@@ -154,7 +154,7 @@ func TestEcosystem_ResolvedWithoutEntityFailsClosed(t *testing.T) {
|
||||
if reply == "" {
|
||||
t.Fatal("a resolve with no entity must degrade, not fall through to local execution")
|
||||
}
|
||||
if strings.Contains(reply, "выполнена") {
|
||||
if actRan(reply) {
|
||||
t.Fatalf("a resolve with no entity must not report success, got %q", reply)
|
||||
}
|
||||
if hexis.Count("", "/api/v1") != 0 {
|
||||
@@ -212,7 +212,7 @@ func TestEcosystem_MalformedNexusResponseFailsClosed(t *testing.T) {
|
||||
|
||||
nexus.SetBody(`{"status":"resolved","entity":`)
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if reply == "" || strings.Contains(reply, "выполнена") {
|
||||
if reply == "" || actRan(reply) {
|
||||
t.Fatalf("malformed nexus body must degrade, got %q", reply)
|
||||
}
|
||||
if hexis.Count("", "/api/v1") != 0 {
|
||||
@@ -232,7 +232,7 @@ func TestEcosystem_UnknownContractFieldsTolerated(t *testing.T) {
|
||||
nexus := newFakeNexus(t, body)
|
||||
hexis := newFakeHexis(t, restartCaps(), fixtureHexisExecuted("exec_1", "succeeded"))
|
||||
h := ecoHandler(t, nexus, nil, hexis)
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !strings.Contains(reply, "выполнена") {
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !actRan(reply) {
|
||||
t.Fatalf("%s contract shape must still resolve and execute, got %q", name, reply)
|
||||
}
|
||||
})
|
||||
@@ -250,7 +250,7 @@ func TestEcosystem_CancelledContextDegrades(t *testing.T) {
|
||||
ctx, cancel := context.WithTimeout(context.Background(), 30*time.Millisecond)
|
||||
defer cancel()
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if reply == "" || strings.Contains(reply, "выполнена") {
|
||||
if reply == "" || actRan(reply) {
|
||||
t.Fatalf("cancelled resolve must degrade, got %q", reply)
|
||||
}
|
||||
if hexis.Count("", "/api/v1") != 0 {
|
||||
@@ -268,7 +268,7 @@ func TestEcosystem_ExecutionFailureIsNotSuccess(t *testing.T) {
|
||||
h := ecoHandler(t, nexus, nil, hexis)
|
||||
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if strings.Contains(reply, "выполнена") {
|
||||
if actRan(reply) {
|
||||
t.Fatalf("failed execution must not read as success, got %q", reply)
|
||||
}
|
||||
if reply == "" {
|
||||
@@ -291,7 +291,7 @@ func TestEcosystem_SuccessfulActionWritesATrace(t *testing.T) {
|
||||
hexis := newFakeHexis(t, restartCaps(), fixtureHexisExecuted("exec_1", "succeeded"))
|
||||
h := ecoHandler(t, nexus, nil, hexis)
|
||||
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !strings.Contains(reply, "выполнена") {
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !actRan(reply) {
|
||||
t.Fatalf("setup: expected success, got %q", reply)
|
||||
}
|
||||
exec := tracesFor(t, h, "hexis", "execute")
|
||||
@@ -313,7 +313,7 @@ func TestEcosystem_TracesStayOutOfFacts(t *testing.T) {
|
||||
hexis := newFakeHexis(t, restartCaps(), fixtureHexisExecuted("exec_1", "succeeded"))
|
||||
h := ecoHandler(t, nexus, nil, hexis)
|
||||
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !strings.Contains(reply, "выполнена") {
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !actRan(reply) {
|
||||
t.Fatalf("setup: expected success, got %q", reply)
|
||||
}
|
||||
if len(traces(t, h)) == 0 {
|
||||
@@ -434,7 +434,7 @@ func TestEcosystem_TotalOutageSaysSoForEveryPath(t *testing.T) {
|
||||
if reply == "" {
|
||||
t.Errorf("%s: total outage must not answer with silence", name)
|
||||
}
|
||||
if strings.Contains(reply, "выполнена") {
|
||||
if actRan(reply) {
|
||||
t.Errorf("%s: total outage must not claim success: %q", name, reply)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -105,13 +105,13 @@ func TestFakeNexus_FaultInjectionThenRecovery(t *testing.T) {
|
||||
|
||||
nexus.SetFault(503)
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if strings.Contains(reply, "выполнена") {
|
||||
if actRan(reply) {
|
||||
t.Fatalf("nexus outage must not report success, got %q", reply)
|
||||
}
|
||||
|
||||
nexus.SetFault(0)
|
||||
reply = h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if !strings.Contains(reply, "выполнена") {
|
||||
if !actRan(reply) {
|
||||
t.Fatalf("expected success once nexus recovers, got %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -11,6 +11,7 @@ import (
|
||||
hexisclient "github.com/kami/hexis/pkg/client"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
@@ -85,7 +86,7 @@ func TestHexisMutatingRequiresConfirm(t *testing.T) {
|
||||
|
||||
// The follow-up "да" turn executes exactly the parked capability.
|
||||
confirmReply, handled := h.resolveConfirm(ctx, "да")
|
||||
if !handled || !strings.Contains(confirmReply, "выполнена") {
|
||||
if !handled || !actRan(confirmReply) {
|
||||
t.Fatalf("confirm should execute, got handled=%v reply=%q", handled, confirmReply)
|
||||
}
|
||||
if !*executed {
|
||||
@@ -125,7 +126,7 @@ func TestHexisReadOnlyExecutesImmediately(t *testing.T) {
|
||||
if h.pendingHexis != nil {
|
||||
t.Fatal("read-only cap should not park a confirmation")
|
||||
}
|
||||
if !strings.Contains(reply, "выполнена") {
|
||||
if !actRan(reply) {
|
||||
t.Fatalf("unexpected reply %q", reply)
|
||||
}
|
||||
}
|
||||
@@ -186,7 +187,7 @@ func TestHexisNexusErrorFailsClosed(t *testing.T) {
|
||||
if reply == "" {
|
||||
t.Fatal("nexus dependency failure must not fall through with an empty reply")
|
||||
}
|
||||
if strings.Contains(reply, "выполнена") {
|
||||
if actRan(reply) {
|
||||
t.Fatalf("nexus dependency failure must not report success, got %q", reply)
|
||||
}
|
||||
}
|
||||
@@ -219,7 +220,7 @@ func TestHexisUnavailableFailsClosed(t *testing.T) {
|
||||
if reply == "" {
|
||||
t.Fatal("hexis dependency failure must not fall through with an empty reply")
|
||||
}
|
||||
if strings.Contains(reply, "выполнена") {
|
||||
if actRan(reply) {
|
||||
t.Fatalf("hexis dependency failure must not report success, got %q", reply)
|
||||
}
|
||||
}
|
||||
@@ -241,3 +242,73 @@ func TestHexisNotFoundStillFallsThrough(t *testing.T) {
|
||||
t.Fatal("not_found resolution must never execute a hexis capability")
|
||||
}
|
||||
}
|
||||
|
||||
// actRan — the reply is the line she says when a capability ran against an
|
||||
// entity. The tests used to look for the substring "выполнена", which was a
|
||||
// literal out of the act file: the review reworded that line to "готово: {name}"
|
||||
// and seventeen assertions went with it (Vikunja #521).
|
||||
func actRan(reply string) bool {
|
||||
return phraser.IsA(phraser.ActDoneEntity, map[string]string{"name": muzickIndexer}, reply)
|
||||
}
|
||||
|
||||
// muzickIndexer — the display name every ecosystem fixture resolves to.
|
||||
const muzickIndexer = "Muzick indexer"
|
||||
|
||||
// read_only used to be the whole decision on this path, which meant a
|
||||
// capability that destroys what it names got the same single spoken "да" as one
|
||||
// that restarts a service. Hexis declares the tier and the voice path is not an
|
||||
// authorised surface for the top one (Vikunja #523).
|
||||
func TestHexisIrreversibleCapabilityIsNotRunFromVoice(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
resolved := `{"status":"resolved","entity":{"id":"ent_muzick","display_name":"Muzick indexer","type":"service"}}`
|
||||
caps := `[{"id":"cap_wipe","name":"restart","read_only":false,"risk":"irreversible","requires_confirmation":true}]`
|
||||
h, executed := newHexisTestHandler(t, resolved, caps)
|
||||
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if *executed {
|
||||
t.Fatal("an irreversible capability ran from the voice path")
|
||||
}
|
||||
if h.pendingHexis != nil {
|
||||
t.Fatal("an irreversible capability parked a confirm; a spoken да is not enough authority")
|
||||
}
|
||||
if !strings.Contains(reply, "не вернуть") {
|
||||
t.Errorf("reply = %q; want it to name why she will not run it", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// The other half: Hexis calling a capability safe is enough to run it, even
|
||||
// though read_only is the field that used to decide. Nothing here re-derives.
|
||||
func TestHexisSafeCapabilityRunsOnItsDeclaredTier(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
resolved := `{"status":"resolved","entity":{"id":"ent_muzick","display_name":"Muzick indexer","type":"service"}}`
|
||||
caps := `[{"id":"cap_status","name":"restart","read_only":true,"risk":"safe"}]`
|
||||
h, executed := newHexisTestHandler(t, resolved, caps)
|
||||
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if !*executed {
|
||||
t.Fatal("a capability Hexis calls safe should run")
|
||||
}
|
||||
if !actRan(reply) {
|
||||
t.Fatalf("unexpected reply %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
// A mutating capability with no declared tier keeps the confirm turn it has
|
||||
// always had, so the split does not quietly loosen an existing box.
|
||||
func TestHexisUndeclaredTierStillConfirms(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
resolved := `{"status":"resolved","entity":{"id":"ent_muzick","display_name":"Muzick indexer","type":"service"}}`
|
||||
caps := `[{"id":"cap_restart","name":"restart","read_only":false}]`
|
||||
h, executed := newHexisTestHandler(t, resolved, caps)
|
||||
|
||||
reply := h.handleHexisAct(ctx, actDec("muzick indexer"))
|
||||
if *executed {
|
||||
t.Fatal("a mutating capability ran without a confirm")
|
||||
}
|
||||
if h.pendingHexis == nil {
|
||||
t.Fatal("a mutating capability did not park a confirm")
|
||||
}
|
||||
if !strings.Contains(reply, "да или нет") {
|
||||
t.Errorf("reply = %q; want the confirm question", reply)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -142,7 +142,7 @@ func TestEcosystemTrace_SuccessfulActionTracesEveryHop(t *testing.T) {
|
||||
hexis := newFakeHexis(t, restartCaps(), fixtureHexisExecuted("exec_1", "succeeded"))
|
||||
h := ecoHandler(t, nexus, nil, hexis)
|
||||
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !strings.Contains(reply, "выполнена") {
|
||||
if reply := h.handleHexisAct(ctx, actDec("muzick indexer")); !actRan(reply) {
|
||||
t.Fatalf("setup: expected success, got %q", reply)
|
||||
}
|
||||
|
||||
|
||||
+43
-21
@@ -13,6 +13,11 @@ import (
|
||||
// ride along because "muzick-indexer" and "nginx.conf" are one name, not two.
|
||||
var latinRun = regexp.MustCompile(`[A-Za-z][A-Za-z0-9._-]*(?:\s+[A-Za-z][A-Za-z0-9._-]*)*`)
|
||||
|
||||
// maxEntityReferences caps how many names one utterance may send to Nexus. The
|
||||
// cap is not about correctness, it is about one turn not fanning out into a
|
||||
// dozen HTTP calls when the utterance is a paragraph of English.
|
||||
const maxEntityReferences = 4
|
||||
|
||||
// hasLatin reports whether s carries a Latin letter.
|
||||
func hasLatin(s string) bool {
|
||||
for _, r := range s {
|
||||
@@ -23,37 +28,54 @@ func hasLatin(s string) bool {
|
||||
return false
|
||||
}
|
||||
|
||||
// entityReferenceText is the name Nexus is asked to resolve.
|
||||
// entityReferences returns the names Nexus is asked to resolve, in the order
|
||||
// they were said.
|
||||
//
|
||||
// Normally that is the router's Text slot, which is the verb phrase the model
|
||||
// wrote. But the resident model rewrites a Russian utterance as it routes, and
|
||||
// on the way it transliterates: "перезапусти muzick indexer" came back as
|
||||
// Normally there is one, and it is the router's Text slot — the verb phrase the
|
||||
// model wrote. But the resident model rewrites a Russian utterance as it routes,
|
||||
// and on the way it transliterates: "перезапусти muzick indexer" came back as
|
||||
// "перезагрузить музик индексер" (Vikunja #476). Nexus is then asked for a
|
||||
// service nobody has ever named, so the act cannot resolve its target even
|
||||
// with every gate open.
|
||||
// service nobody has ever named, so the act cannot resolve its target even with
|
||||
// every gate open.
|
||||
//
|
||||
// The recovery is deliberately narrow. Only when the utterance holds a Latin
|
||||
// run and the model's Text holds none has a name certainly been rewritten —
|
||||
// then the longest Latin run in his own words is the reference. Anything else
|
||||
// keeps the Text slot, so an English utterance and a Russian entity name are
|
||||
// both untouched. Un-transliterating the Cyrillic back is not attempted: the
|
||||
// The recovery is deliberately narrow. Only when the utterance holds a Latin run
|
||||
// and the model's Text holds none has a name certainly been rewritten. Anything
|
||||
// else keeps the Text slot, so an English utterance and a Russian entity name
|
||||
// are both untouched. Un-transliterating the Cyrillic back is not attempted: the
|
||||
// surface form he said is right there, and guessing at a reverse mapping would
|
||||
// invent a second name to be wrong about.
|
||||
func entityReferenceText(dec router.Decision) string {
|
||||
//
|
||||
// What this does NOT do is pick. It used to return the longest run, and length
|
||||
// is a guess: "перезапусти nginx на muzick-indexer" has two names in it and the
|
||||
// longer one is not reliably the target. Nexus owns which names it knows
|
||||
// (docs/ecosystem.md — ambiguous resolution asks the owner, it does not pick),
|
||||
// so every run goes over and Nexus answers. Two runs that both resolve are a
|
||||
// clarify, not a coin toss.
|
||||
func entityReferences(dec router.Decision) []string {
|
||||
text := dec.Slots.Text
|
||||
if hasLatin(text) || !hasLatin(dec.Utterance) {
|
||||
return text
|
||||
return []string{text}
|
||||
}
|
||||
longest := ""
|
||||
var refs []string
|
||||
seen := map[string]bool{}
|
||||
for _, m := range latinRun.FindAllString(dec.Utterance, -1) {
|
||||
if len(m) > len(longest) {
|
||||
longest = m
|
||||
m = strings.TrimSpace(m)
|
||||
// A single stray letter is not a name.
|
||||
if len(m) < 2 {
|
||||
continue
|
||||
}
|
||||
key := strings.ToLower(m)
|
||||
if seen[key] {
|
||||
continue
|
||||
}
|
||||
seen[key] = true
|
||||
refs = append(refs, m)
|
||||
if len(refs) == maxEntityReferences {
|
||||
break
|
||||
}
|
||||
}
|
||||
longest = strings.TrimSpace(longest)
|
||||
// A single stray letter is not a name.
|
||||
if len(longest) < 2 {
|
||||
return text
|
||||
if len(refs) == 0 {
|
||||
return []string{text}
|
||||
}
|
||||
return longest
|
||||
return refs
|
||||
}
|
||||
|
||||
+101
-12
@@ -2,61 +2,76 @@ package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/http"
|
||||
"strings"
|
||||
"sync"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// TestEntityReferenceText pins when his own words win over the model's.
|
||||
func TestEntityReferenceText(t *testing.T) {
|
||||
// TestEntityReferences pins when his own words win over the model's, and that
|
||||
// every name he said goes over rather than one of them being picked.
|
||||
func TestEntityReferences(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
utterance string
|
||||
text string
|
||||
want string
|
||||
want []string
|
||||
}{
|
||||
{
|
||||
name: "the model transliterated the name",
|
||||
utterance: "перезапусти muzick indexer",
|
||||
text: "перезагрузить музик индексер",
|
||||
want: "muzick indexer",
|
||||
want: []string{"muzick indexer"},
|
||||
},
|
||||
{
|
||||
name: "it kept the name, so nothing to repair",
|
||||
utterance: "перезапусти muzick indexer",
|
||||
text: "перезагрузить muzick indexer",
|
||||
want: "перезагрузить muzick indexer",
|
||||
want: []string{"перезагрузить muzick indexer"},
|
||||
},
|
||||
{
|
||||
name: "an all-Russian entity name is not a rewrite",
|
||||
utterance: "перезапусти домашний сервер",
|
||||
text: "перезагрузить домашний сервер",
|
||||
want: "перезагрузить домашний сервер",
|
||||
want: []string{"перезагрузить домашний сервер"},
|
||||
},
|
||||
{
|
||||
name: "an English turn never enters the recovery",
|
||||
utterance: "restart muzick indexer",
|
||||
text: "restart muzick indexer",
|
||||
want: "restart muzick indexer",
|
||||
want: []string{"restart muzick indexer"},
|
||||
},
|
||||
{
|
||||
name: "the longest Latin run is the name",
|
||||
name: "both names go over, in the order he said them",
|
||||
utterance: "а перезапусти-ка nginx на muzick-indexer, пожалуйста",
|
||||
text: "перезагрузить нгинкс",
|
||||
want: "muzick-indexer",
|
||||
want: []string{"nginx", "muzick-indexer"},
|
||||
},
|
||||
{
|
||||
name: "one stray letter is not a name",
|
||||
utterance: "перезапусти сервер a",
|
||||
text: "перезагрузить сервер",
|
||||
want: "перезагрузить сервер",
|
||||
want: []string{"перезагрузить сервер"},
|
||||
},
|
||||
{
|
||||
name: "the same name twice is one question",
|
||||
utterance: "перезапусти nginx, ну правда, nginx",
|
||||
text: "перезагрузить нгинкс",
|
||||
want: []string{"nginx"},
|
||||
},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
dec := router.Decision{Utterance: tc.utterance, Slots: router.Slots{Text: tc.text}}
|
||||
if got := entityReferenceText(dec); got != tc.want {
|
||||
t.Fatalf("entityReferenceText = %q, want %q", got, tc.want)
|
||||
got := entityReferences(dec)
|
||||
if len(got) != len(tc.want) {
|
||||
t.Fatalf("entityReferences = %q, want %q", got, tc.want)
|
||||
}
|
||||
for i := range got {
|
||||
if got[i] != tc.want[i] {
|
||||
t.Fatalf("entityReferences = %q, want %q", got, tc.want)
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
@@ -131,3 +146,77 @@ func TestClarifyStillAsksWithoutHexis(t *testing.T) {
|
||||
t.Fatal("she must still ask what to do")
|
||||
}
|
||||
}
|
||||
|
||||
// nexusInOrder serves one resolve answer per call, in order, so a test can say
|
||||
// what Nexus knows about the first name and what it knows about the second. The
|
||||
// last body repeats once the list runs out.
|
||||
func nexusInOrder(t *testing.T, bodies ...string) *fakeServer {
|
||||
t.Helper()
|
||||
var mu sync.Mutex
|
||||
n := 0
|
||||
return newFakeServer(t, map[string]http.HandlerFunc{
|
||||
"POST /api/v1/resolve": func(w http.ResponseWriter, r *http.Request) {
|
||||
mu.Lock()
|
||||
body := bodies[min(n, len(bodies)-1)]
|
||||
n++
|
||||
mu.Unlock()
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
_, _ = w.Write([]byte(body))
|
||||
},
|
||||
})
|
||||
}
|
||||
|
||||
// TestTwoResolvedNamesAsk — «перезапусти nginx на muzick-indexer» names a
|
||||
// service and the host it runs on. Both are real, and which one he meant is not
|
||||
// in the utterance, so she asks. Picking one by length was the old behaviour and
|
||||
// length is not evidence (Vikunja #524).
|
||||
func TestTwoResolvedNamesAsk(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
nexus := nexusInOrder(t,
|
||||
fixtureNexusResolved("ent_nginx", "nginx", "service"),
|
||||
fixtureNexusResolved("ent_host", "Muzick indexer", "device"),
|
||||
)
|
||||
hexis := newFakeHexis(t, restartCaps(), fixtureHexisExecuted("exec_1", "succeeded"))
|
||||
h := ecoHandler(t, nexus, nil, hexis)
|
||||
|
||||
dec := router.Decision{
|
||||
Utterance: "перезапусти nginx на muzick-indexer",
|
||||
Intent: router.IntentAct,
|
||||
Slots: router.Slots{Text: "перезагрузить нгинкс", Fn: "restart", HasFn: true},
|
||||
}
|
||||
reply := h.handleHexisAct(ctx, dec)
|
||||
if !strings.Contains(reply, "nginx") || !strings.Contains(reply, "Muzick indexer") {
|
||||
t.Fatalf("reply = %q, want both names she found", reply)
|
||||
}
|
||||
if hexis.Count("POST", "/api/v1/execute") != 0 {
|
||||
t.Fatal("she must not execute against a target she is still asking about")
|
||||
}
|
||||
}
|
||||
|
||||
// TestTheNameNexusKnowsWins — the other half. Two names go over and only one is
|
||||
// an entity, so there is nothing to ask about and the act runs.
|
||||
func TestTheNameNexusKnowsWins(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
nexus := nexusInOrder(t,
|
||||
fixtureNexusNotFound(),
|
||||
fixtureNexusResolved("ent_muzick", "Muzick indexer", "service"),
|
||||
)
|
||||
hexis := newFakeHexis(t, restartCaps(), fixtureHexisExecuted("exec_1", "succeeded"))
|
||||
h := ecoHandler(t, nexus, nil, hexis)
|
||||
|
||||
dec := router.Decision{
|
||||
Utterance: "перезапусти nginx на muzick-indexer",
|
||||
Intent: router.IntentAct,
|
||||
Slots: router.Slots{Text: "перезагрузить нгинкс", Fn: "restart", HasFn: true},
|
||||
}
|
||||
reply := h.handleHexisAct(ctx, dec)
|
||||
if reply == "" {
|
||||
t.Fatal("the resolvable name must carry the act")
|
||||
}
|
||||
if len(nexus.Requests()) != 2 {
|
||||
t.Fatalf("nexus asked %d times, want both names", len(nexus.Requests()))
|
||||
}
|
||||
if hexis.Count("POST", "/api/v1/execute") == 0 {
|
||||
t.Fatal("hexis was never asked to run it")
|
||||
}
|
||||
}
|
||||
|
||||
@@ -79,7 +79,7 @@ func TestQueryFeedsByCategory(t *testing.T) {
|
||||
t.Fatalf("reply = %q, want only the технологии item", reply)
|
||||
}
|
||||
reply, _ = askFeeds(t, h, "что нового по спорту?")
|
||||
if !strings.Contains(reply, "ничего") {
|
||||
if !phraser.IsQ(phraser.QueryFeedsTopic, nil, reply) {
|
||||
t.Fatalf("reply = %q, want an honest empty answer for an unread category", reply)
|
||||
}
|
||||
}
|
||||
@@ -87,16 +87,22 @@ func TestQueryFeedsByCategory(t *testing.T) {
|
||||
// "не настроены" and "ничего нового" are different truths, and neither may be
|
||||
// answered by the model inventing a bulletin.
|
||||
func TestQueryFeedsOffAndEmptyDiffer(t *testing.T) {
|
||||
// Against the entries, not against a substring: both of these have several
|
||||
// wordings, so "ничего нового" passed only on the turns the picker happened
|
||||
// to choose the first one.
|
||||
off := buildFeedHandler(t, false)
|
||||
reply, ok := askFeeds(t, off, "что нового в лентах?")
|
||||
if !ok || !strings.Contains(reply, "не настроены") {
|
||||
if !ok || !phraser.IsQ(phraser.QueryFeedsOff, nil, reply) {
|
||||
t.Fatalf("feeds off: reply = %q, ok = %v", reply, ok)
|
||||
}
|
||||
on := buildFeedHandler(t, true)
|
||||
reply, ok = askFeeds(t, on, "что нового в лентах?")
|
||||
if !ok || !strings.Contains(reply, "ничего нового") {
|
||||
if !ok || !phraser.IsQ(phraser.QueryFeedsEmpty, nil, reply) {
|
||||
t.Fatalf("feeds on but empty: reply = %q, ok = %v", reply, ok)
|
||||
}
|
||||
if phraser.IsQ(phraser.QueryFeedsOff, nil, reply) {
|
||||
t.Fatalf("an empty feed answered as an unconfigured one: %q", reply)
|
||||
}
|
||||
}
|
||||
|
||||
func TestQueryFeedsPassesOnANonFeedQuestion(t *testing.T) {
|
||||
|
||||
+5
-20
@@ -11,6 +11,7 @@ import (
|
||||
"github.com/kami/maven/internal/config"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/netscan"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
)
|
||||
|
||||
// scanBudget — the whole spoken scan, end to end. A voice turn that takes
|
||||
@@ -106,7 +107,7 @@ func (w *netWiring) scanSummary(ctx context.Context) (string, bool) {
|
||||
res, err := w.scan(ctx)
|
||||
if err != nil {
|
||||
log.Printf("netscan: scan: %v", err)
|
||||
return "не получилось просканировать сеть.", true
|
||||
return phraser.Q(phraser.QueryFailNetscan, nil), true
|
||||
}
|
||||
// A truncated run is not a statement about the LAN. Saying "нашла 6
|
||||
// устройств" after stopping two thirds of the way through the range is a
|
||||
@@ -116,9 +117,9 @@ func (w *netWiring) scanSummary(ctx context.Context) (string, bool) {
|
||||
tail = ", но успела посмотреть не всю сеть"
|
||||
}
|
||||
if len(res.Hosts) == 0 {
|
||||
return "в сети никого не нашла" + tail + ".", true
|
||||
return phraser.Q(phraser.QueryNetEmpty, map[string]string{"tail": tail}), true
|
||||
}
|
||||
out := fmt.Sprintf("нашла %d %s", len(res.Hosts), hostWord(len(res.Hosts)))
|
||||
out := fmt.Sprintf("нашла %d %s", len(res.Hosts), phraser.Devices(len(res.Hosts)))
|
||||
if shape := scanShape(res.Hosts); shape != "" {
|
||||
out += ", " + shape
|
||||
}
|
||||
@@ -179,7 +180,7 @@ func (w *netWiring) writeScanRecord(ctx context.Context, res netscan.Result) {
|
||||
if w.api == nil {
|
||||
return
|
||||
}
|
||||
head := fmt.Sprintf("сканирование сети: %d %s", len(res.Hosts), hostWord(len(res.Hosts)))
|
||||
head := fmt.Sprintf("сканирование сети: %d %s", len(res.Hosts), phraser.Devices(len(res.Hosts)))
|
||||
if res.Truncated {
|
||||
head += " (не вся сеть)"
|
||||
}
|
||||
@@ -210,22 +211,6 @@ func (w *netWiring) writeScanRecord(ctx context.Context, res netscan.Result) {
|
||||
}
|
||||
}
|
||||
|
||||
// hostWord — Russian counts inflect the noun: 1 устройство, 2-4 устройства,
|
||||
// 5+ устройств, and the teens are all the last form.
|
||||
func hostWord(n int) string {
|
||||
if n%100 >= 11 && n%100 <= 14 {
|
||||
return "устройств"
|
||||
}
|
||||
switch n % 10 {
|
||||
case 1:
|
||||
return "устройство"
|
||||
case 2, 3, 4:
|
||||
return "устройства"
|
||||
default:
|
||||
return "устройств"
|
||||
}
|
||||
}
|
||||
|
||||
// isNetworkQuery recognises a question about the LAN, narrowly. It needs a
|
||||
// network word AND an ask: "интернет не работает" is a complaint, not a request
|
||||
// to scan, and a scan she runs unasked is exactly the noisy behaviour the
|
||||
|
||||
+21
-12
@@ -10,6 +10,8 @@ import (
|
||||
|
||||
"github.com/kami/maven/internal/config"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
func TestWireNetScanOffUnlessEnabled(t *testing.T) {
|
||||
@@ -74,18 +76,6 @@ func TestScanSummaryOnAnEmptyRange(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestHostWordAgreesWithTheCount(t *testing.T) {
|
||||
for n, want := range map[int]string{
|
||||
1: "устройство", 2: "устройства", 4: "устройства", 5: "устройств",
|
||||
11: "устройств", 12: "устройств", 21: "устройство", 22: "устройства",
|
||||
25: "устройств", 111: "устройств", 101: "устройство", 0: "устройств",
|
||||
} {
|
||||
if got := hostWord(n); got != want {
|
||||
t.Errorf("hostWord(%d) = %q, want %q", n, got, want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestIsNetworkQuery(t *testing.T) {
|
||||
yes := []string{
|
||||
"какие устройства в сети?",
|
||||
@@ -169,3 +159,22 @@ func TestScanSummarySpeaksACountAndWritesTheAddresses(t *testing.T) {
|
||||
t.Errorf("a repeat question rescanned and rewrote the record (%d notes)", api.n)
|
||||
}
|
||||
}
|
||||
|
||||
// An unconfigured scanner names the gap instead of declining the turn.
|
||||
//
|
||||
// Falling through sent "какие устройства в сети?" to the search leg, which
|
||||
// answered with a paragraph about routers in general — and put a question about
|
||||
// his own LAN on an upstream engine, which the personal boundary exists to
|
||||
// prevent (Vikunja #479).
|
||||
func TestQueryNetworkNamesTheGapWhenNotConfigured(t *testing.T) {
|
||||
h := &reactiveHandler{}
|
||||
reply, ok := h.queryNetwork(context.Background(), &queryTurn{
|
||||
dec: router.Decision{Utterance: "какие устройства в сети?"},
|
||||
})
|
||||
if !ok {
|
||||
t.Fatal("an unconfigured scanner let the question fall through to search")
|
||||
}
|
||||
if !phraser.IsQ(phraser.QueryNetOff, nil, reply) {
|
||||
t.Errorf("got %q, want the gap named", reply)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,134 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"log"
|
||||
"regexp"
|
||||
"strings"
|
||||
"sync"
|
||||
|
||||
"github.com/kami/maven/internal/delivery"
|
||||
"github.com/kami/maven/internal/loop"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/phraser/eval"
|
||||
)
|
||||
|
||||
// The persona checks, run before she speaks (Vikunja #399).
|
||||
//
|
||||
// RunChecks and RunTalkChecks only ever ran from the eval package, so
|
||||
// everything the fixtures measured was offline knowledge: we could say "about
|
||||
// one reply in three is broken" and still ship every one of them. This runs the
|
||||
// cheap half of that on the live path, and replaces a failing message with the
|
||||
// deterministic floor.
|
||||
//
|
||||
// Which checks: the unambiguous string tests only — feminine self-reference,
|
||||
// how she addresses him, and a leaked-reasoning test. Not length, which is
|
||||
// path-specific, and not ontopic, which compares against fragments the fixture
|
||||
// supplies and runtime does not have. Not hisgender either — see guardSpoken.
|
||||
//
|
||||
// No retry. A retry doubles the latency on the exact turn that is already going
|
||||
// badly, and on the nudge path the moment has passed.
|
||||
//
|
||||
// The known cost, written down because it is real: a wrongly flagged good reply
|
||||
// is replaced by a flatter stub one. That is the right trade — a stub sentence
|
||||
// is dull, a leaked reasoning trace is broken — but it means these checks can
|
||||
// no longer be tuned for sensitivity alone.
|
||||
|
||||
// checkLeak — the name reported when the model's scaffolding reaches the text.
|
||||
const checkLeak = "leak"
|
||||
|
||||
// leakPatterns — reasoning and protocol that belongs to the model, not to him.
|
||||
// The resident model is a Thinking variant, so an unclosed reasoning block is
|
||||
// the failure mode, not a hypothetical (Vikunja #398).
|
||||
var leakPatterns = []*regexp.Regexp{
|
||||
regexp.MustCompile(`(?i)<\s*/?\s*think`),
|
||||
regexp.MustCompile(`(?i)thinking\s*(process|:)`),
|
||||
regexp.MustCompile(`(?i)^\s*(assistant|user|system)\s*:`),
|
||||
// Raw contract JSON: the parser already unwraps a good one, so a body that
|
||||
// still carries the keys is one it could not read.
|
||||
regexp.MustCompile(`"(response|mood|body|summary)"\s*:`),
|
||||
// The persona block quoted back at him.
|
||||
regexp.MustCompile(`(?i)(ты\s+—?\s*мэйвен|системный промпт|system prompt)`),
|
||||
}
|
||||
|
||||
// checkPersonaLeak reports whether the model's own scaffolding is in the text.
|
||||
func checkPersonaLeak(body string) (string, bool) {
|
||||
for _, re := range leakPatterns {
|
||||
if m := re.FindString(body); m != "" {
|
||||
return "leaked " + strings.TrimSpace(m), false
|
||||
}
|
||||
}
|
||||
return "", true
|
||||
}
|
||||
|
||||
// personaRejects counts what the guard caught, by check name, so the real
|
||||
// production rate is knowable rather than inferred from the fixture.
|
||||
var personaRejects = struct {
|
||||
mu sync.Mutex
|
||||
by map[string]int
|
||||
}{by: map[string]int{}}
|
||||
|
||||
func personaRejectCounts() map[string]int {
|
||||
personaRejects.mu.Lock()
|
||||
defer personaRejects.mu.Unlock()
|
||||
out := make(map[string]int, len(personaRejects.by))
|
||||
for k, v := range personaRejects.by {
|
||||
out[k] = v
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// guardSpoken checks a phrased message. It returns the failed check and false
|
||||
// when the message must not be said; path names the caller, for the log.
|
||||
//
|
||||
// An empty message passes: the caller already treats that as a failure and
|
||||
// falls back on its own, and reporting it as a persona breach would put a
|
||||
// misleading line in the count.
|
||||
func guardSpoken(path, body string) (string, bool) {
|
||||
if strings.TrimSpace(body) == "" {
|
||||
return "", true
|
||||
}
|
||||
if detail, ok := checkPersonaLeak(body); !ok {
|
||||
return rejectSpoken(path, checkLeak, detail, body), false
|
||||
}
|
||||
// Feminine and address only. HisGender is not run here: it reads a
|
||||
// sentence-initial feminine verb with no pronoun — "записала, что ты выпил
|
||||
// воды" — as a woman being addressed, when it is her own correct
|
||||
// self-reference. Offline that is a point of score; on this path it would
|
||||
// replace a good reply with a stub one on every fact she confirms.
|
||||
for _, r := range []eval.Result{eval.Feminine(body), eval.Address(body)} {
|
||||
if !r.Pass {
|
||||
return rejectSpoken(path, r.Name, r.Detail, body), false
|
||||
}
|
||||
}
|
||||
return "", true
|
||||
}
|
||||
|
||||
// rejectSpoken logs what she nearly said and counts it. The whole text, not a
|
||||
// prefix: the point of the log line is that the failure can be read back later
|
||||
// and argued with.
|
||||
func rejectSpoken(path, check, detail, body string) string {
|
||||
personaRejects.mu.Lock()
|
||||
personaRejects.by[check]++
|
||||
personaRejects.mu.Unlock()
|
||||
log.Printf("persona: %s rejected on %s (%s): %q", path, check, detail, body)
|
||||
return check
|
||||
}
|
||||
|
||||
// guardNudge checks a phrased nudge and falls back to the deterministic floor
|
||||
// when it fails. The nudge path, unlike the reply path, cannot ask again: the
|
||||
// tick has already decided she speaks, so the choice is the floor's wording or
|
||||
// a broken sentence.
|
||||
func guardNudge(pn delivery.PhrasedNudge, cand loop.Candidate) delivery.PhrasedNudge {
|
||||
if _, ok := guardSpoken("nudge", pn.Body); ok {
|
||||
return pn
|
||||
}
|
||||
stub, err := phraser.NewStub().PhraseNudge(context.Background(), cand)
|
||||
if err != nil {
|
||||
// The Stub is templates over the candidate and does not fail. If it
|
||||
// somehow does, the model's text is still what the rule decided to
|
||||
// say, and saying nothing is the worse outcome.
|
||||
return pn
|
||||
}
|
||||
return stub
|
||||
}
|
||||
@@ -0,0 +1,75 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/delivery"
|
||||
"github.com/kami/maven/internal/loop"
|
||||
)
|
||||
|
||||
func TestGuardPassesWhatSheShouldSay(t *testing.T) {
|
||||
good := []string{
|
||||
"записала: купить хлеб.",
|
||||
"поняла, напомню в 11:00.",
|
||||
"ты не пил воду с утра.",
|
||||
"я рада, что получилось.",
|
||||
"",
|
||||
}
|
||||
for _, body := range good {
|
||||
if check, ok := guardSpoken("test", body); !ok {
|
||||
t.Errorf("guardSpoken(%q) rejected on %s", body, check)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestGuardStopsWhatSheShouldNot(t *testing.T) {
|
||||
bad := []struct {
|
||||
body string
|
||||
want string
|
||||
}{
|
||||
{"<think>он просил воду</think> попей воды.", checkLeak},
|
||||
{"Thinking Process: он давно не пил.", checkLeak},
|
||||
{`{"response": "попей воды", "mood": "neutral"}`, checkLeak},
|
||||
{"я напомнил тебе про воду.", "feminine"},
|
||||
{"вы давно не пили воду.", "address"},
|
||||
}
|
||||
for _, c := range bad {
|
||||
check, ok := guardSpoken("test", c.body)
|
||||
if ok {
|
||||
t.Errorf("guardSpoken(%q) let it through", c.body)
|
||||
continue
|
||||
}
|
||||
if check != c.want {
|
||||
t.Errorf("guardSpoken(%q) failed on %s; want %s", c.body, check, c.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestGuardCountsWhatItCaught(t *testing.T) {
|
||||
before := personaRejectCounts()[checkLeak]
|
||||
if _, ok := guardSpoken("test", "<think>…"); ok {
|
||||
t.Fatal("a leaked reasoning block was let through")
|
||||
}
|
||||
if after := personaRejectCounts()[checkLeak]; after != before+1 {
|
||||
t.Errorf("leak count %d; want %d", after, before+1)
|
||||
}
|
||||
}
|
||||
|
||||
// TestGuardNudgeFallsBackToTheFloor — a broken nudge is replaced by the
|
||||
// deterministic wording, not dropped and not retried.
|
||||
func TestGuardNudgeFallsBackToTheFloor(t *testing.T) {
|
||||
cand := loop.Candidate{Rule: loop.Rule{Name: "water"}}
|
||||
bad := delivery.PhrasedNudge{Candidate: cand, Body: "Thinking Process: он не пил.", Mood: "neutral"}
|
||||
got := guardNudge(bad, cand)
|
||||
if got.Body == bad.Body {
|
||||
t.Fatal("the broken nudge was delivered unchanged")
|
||||
}
|
||||
if strings.TrimSpace(got.Body) == "" {
|
||||
t.Fatal("the nudge was dropped rather than re-worded")
|
||||
}
|
||||
good := delivery.PhrasedNudge{Candidate: cand, Body: "попей воды.", Mood: "neutral"}
|
||||
if guardNudge(good, cand).Body != good.Body {
|
||||
t.Error("a good nudge was replaced")
|
||||
}
|
||||
}
|
||||
@@ -121,8 +121,8 @@ func TestQueryRecallNoteCanWin(t *testing.T) {
|
||||
{text: "выучил пару аккордов", score: 0.50, kind: "note"},
|
||||
})
|
||||
reply := askQuery(t, h, q)
|
||||
if want := "вот что я нашла: молоко стоит в холодильнике"; reply != want {
|
||||
t.Errorf("reply %q, want %q", reply, want)
|
||||
if !phraser.IsSourcesFallback(reply, "молоко стоит в холодильнике") {
|
||||
t.Errorf("reply %q, want the note read back", reply)
|
||||
}
|
||||
// One text, the winning memory's — the answer came from the memory
|
||||
// pass, not from handing the phraser every note in the table.
|
||||
@@ -151,7 +151,7 @@ func TestQueryRecallNoteCanWin(t *testing.T) {
|
||||
{text: "молоко стоит в холодильнике", score: 0.860, kind: "note"},
|
||||
{text: "молоко закончилось", score: 0.858, kind: "note"},
|
||||
})
|
||||
if reply := askQuery(t, h, q); reply != "не знаю." {
|
||||
if reply := askQuery(t, h, q); !phraser.IsUnknownFallback(reply) {
|
||||
t.Errorf("reply %q, want silence", reply)
|
||||
}
|
||||
})
|
||||
|
||||
+60
-39
@@ -11,6 +11,8 @@ import (
|
||||
"unicode"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/morph"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
)
|
||||
|
||||
// resolveQuietToggle — pre-route keyword check. Returns (reply, true) when
|
||||
@@ -32,10 +34,10 @@ func (h *reactiveHandler) resolveQuietToggle(ctx context.Context, text string, s
|
||||
return "", false
|
||||
}
|
||||
val := "false"
|
||||
reply := "тихий режим выключен."
|
||||
reply := phraser.Ack(phraser.AckQuietOff, nil)
|
||||
if on {
|
||||
val = "true"
|
||||
reply = "тихий режим включён. буду реже напоминать."
|
||||
reply = phraser.Ack(phraser.AckQuietOn, nil)
|
||||
}
|
||||
if _, err := h.api.WriteFact(ctx, ipc.WriteFactReq{
|
||||
Ts: h.now(),
|
||||
@@ -46,34 +48,44 @@ func (h *reactiveHandler) resolveQuietToggle(ctx context.Context, text string, s
|
||||
Confidence: 1.0,
|
||||
}); err != nil {
|
||||
log.Printf("voice: write quiet_hours: %v", err)
|
||||
return "не получилось переключить тихий режим.", true
|
||||
return phraser.Ack(phraser.FailQuiet, nil), true
|
||||
}
|
||||
return reply, true
|
||||
}
|
||||
|
||||
// quietInflections — the inflectional endings a stem may carry and still be
|
||||
// the same word. Adjective/adverb/noun/verb endings, all ≤3 letters. This is
|
||||
// what separates "тихий"/"тихом"/"тихо" (stem "тих" + a real ending) from
|
||||
// "тихонько"/"потихоньку", which are different words: "онько" is not an
|
||||
// ending, and "потихоньку" doesn't start with the stem at all.
|
||||
var quietInflections = []string{
|
||||
"", "а", "е", "и", "й", "о", "у", "ы", "ю", "я",
|
||||
"ая", "ее", "ей", "ем", "ие", "ий", "им", "их", "ия", "ию", "ое", "ой", "ом", "ую", "ые", "ый", "ым", "ых", "ья",
|
||||
"ами", "ого", "ому", "ыми", "ать", "ить", "ять",
|
||||
}
|
||||
|
||||
// quietStem reports whether tok is the given stem carrying at most one
|
||||
// inflectional ending. Word boundaries come from tokenisation (see
|
||||
// quietTokens), not from a regexp — Go's \b is ASCII-oriented and treats every
|
||||
// Cyrillic letter as a non-word character, so `\bтих\b` would happily match
|
||||
// inside "тихонько". Comparing whole tokens sidesteps that entirely.
|
||||
func quietStem(tok, stem string) bool {
|
||||
if !strings.HasPrefix(tok, stem) {
|
||||
return false
|
||||
}
|
||||
suffix := tok[len(stem):]
|
||||
for _, e := range quietInflections {
|
||||
if suffix == e {
|
||||
// quietStem reports whether tok is one of the words a vocabulary slot accepts.
|
||||
// A slot is written as alternatives joined by "|", and an alternative comes in
|
||||
// two flavours:
|
||||
//
|
||||
// - a dictionary form, matched through the dictionary, so every case and
|
||||
// gender of it counts. This is what the nouns and adjectives want: "тихий",
|
||||
// "тихом", "тихо" and "тише" are one word.
|
||||
// - a form prefixed with "=", matched as the exact token. This is what the
|
||||
// VERBS want, and it is not a shortcut. A command is an imperative, and the
|
||||
// dictionary quite correctly files "говори" and "говорил" under one lemma —
|
||||
// so lemma-matching a verb slot read "он говорил тихим голосом весь вечер",
|
||||
// a remark about his evening, as an order to go quiet. Aspect pairs are two
|
||||
// separate verbs, which is why several imperatives are listed by hand.
|
||||
//
|
||||
// Word boundaries come from tokenisation (see quietTokens), not from a regexp —
|
||||
// Go's \b is ASCII-oriented and treats every Cyrillic letter as a non-word
|
||||
// character, so `\bтих\b` would happily match inside "тихонько". Comparing whole
|
||||
// tokens sidesteps that entirely.
|
||||
//
|
||||
// The comparison is a dictionary lookup, not a stem plus a list of 36 endings
|
||||
// (Vikunja #526). The distinction the old comment described is exactly the one a
|
||||
// dictionary makes: "тихий", "тихом", "тихо" and "тише" are one word inflected,
|
||||
// while "тихонько" and "потихоньку" are different words — and the dictionary
|
||||
// knows that without anybody deciding that "онько" is not an ending.
|
||||
func quietStem(tok, slot string) bool {
|
||||
for _, form := range strings.Split(slot, "|") {
|
||||
if exact, ok := strings.CutPrefix(form, "="); ok {
|
||||
if tok == exact {
|
||||
return true
|
||||
}
|
||||
continue
|
||||
}
|
||||
if morph.SameWord(tok, form) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
@@ -116,7 +128,10 @@ func quietPhrase(tokens, pattern []string) bool {
|
||||
return false
|
||||
}
|
||||
|
||||
// quietOffPhrases / quietOnPhrases — the toggle vocabulary, as stem sequences.
|
||||
// quietOffPhrases / quietOnPhrases — the toggle vocabulary, as sequences of
|
||||
// dictionary forms. They used to be truncated stems ("тих", "выключ"), which is
|
||||
// what the ending list existed to complete; a dictionary form needs no
|
||||
// completing (Vikunja #526).
|
||||
//
|
||||
// Note what is NOT here any more: the OFF list used to carry {"не", "тих"} and
|
||||
// the ON list {"не", "шум"} / {"не", "беспоко"}. Both were adjacency patterns,
|
||||
@@ -127,36 +142,42 @@ func quietPhrase(tokens, pattern []string) bool {
|
||||
var (
|
||||
quietOffPhrases = [][]string{
|
||||
{"quiet", "off"}, {"quiet", "end"},
|
||||
{"громк", "режим"}, {"шумн", "режим"},
|
||||
{"отмен", "тих"}, {"выключ", "тих"},
|
||||
{"громкий", "режим"}, {"шумный", "режим"},
|
||||
{"=отмени|=отменяй|=отменить", "тихий"},
|
||||
{"=выключи|=выключай|=выключить", "тихий"},
|
||||
}
|
||||
quietOnPhrases = [][]string{
|
||||
{"quiet", "on"}, {"quiet", "mode"},
|
||||
{"тих", "режим"}, {"не", "шум"}, {"не", "беспоко"},
|
||||
{"тихий", "режим"}, {"не", "=шуми|=шумите"}, {"не", "=беспокой|=беспокоить"},
|
||||
// The noun form and the comparative. "режим тишины" is how the
|
||||
// setting is named half the time, and "сделай потише" is how it is
|
||||
// actually asked for out loud. Both used to fall through to the
|
||||
// router, which has no quiet intent, so the command did nothing.
|
||||
{"режим", "тишин"}, {"сделай", "тише"}, {"сделай", "потише"},
|
||||
{"говори", "тише"}, {"будь", "потише"},
|
||||
{"тих"}, {"потише"},
|
||||
{"режим", "тишина"}, {"=сделай", "тихий"}, {"=сделай", "потише"},
|
||||
{"=говори", "тихий"}, {"=будь", "потише"},
|
||||
{"тихий"}, {"потише"},
|
||||
}
|
||||
)
|
||||
|
||||
// quietWordStems — every stem that names the setting. Used by the
|
||||
// quietWordStems — every word that names the setting. Used by the
|
||||
// negated-but-unmatched fallback in classifyQuietToggle, which has to
|
||||
// recognise "хватит тишины" without an ON phrase having matched.
|
||||
var quietWordStems = []string{"тих", "тишин", "потише"}
|
||||
var quietWordStems = []string{"тихий", "тишина", "потише"}
|
||||
|
||||
// quietNegatorWords — negators that are whole words with no useful stem.
|
||||
var quietNegatorWords = map[string]bool{
|
||||
"не": true, "нет": true, "хватит": true, "no": true, "not": true, "off": true,
|
||||
}
|
||||
|
||||
// quietNegatorStems — negators that inflect. Matched through quietStem, the
|
||||
// same one-ending rule the toggle vocabulary uses, so "выключи", "выключить"
|
||||
// and "выключай" all count and "выключатель" does not.
|
||||
var quietNegatorStems = []string{"выключ", "отмен", "прекрат", "убер", "stop", "cancel", "disable"}
|
||||
// quietNegatorStems — negators that inflect. Imperatives, matched exactly for
|
||||
// the reason quietStem gives: "выключи" is a command and "выключил" is a report
|
||||
// about earlier, and one lemma covers both. "выключатель" was never a negator
|
||||
// and is not one now.
|
||||
var quietNegatorStems = []string{
|
||||
"=выключи|=выключай|=выключить", "=отмени|=отменяй|=отменить",
|
||||
"=прекрати|=прекращай|=прекратить", "=убери|=убирай|=убрать",
|
||||
"stop", "cancel", "disable",
|
||||
}
|
||||
|
||||
// quietNegated reports whether the utterance carries a negator. Two ON phrases
|
||||
// are themselves built on "не" — "не шуми", "не беспокой" — and those are
|
||||
|
||||
@@ -30,5 +30,10 @@ func (r *llmReplier) Reply(d router.Decision) string {
|
||||
if err != nil || out == "" {
|
||||
return r.stub.Reply(d)
|
||||
}
|
||||
// The persona checks, on the live path (personaguard.go). A reply that
|
||||
// leaks reasoning or calls him "вы" is worse than a flat one.
|
||||
if _, ok := guardSpoken("reply", out); !ok {
|
||||
return r.stub.Reply(d)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
@@ -5,6 +5,7 @@ import (
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/llm"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/voice"
|
||||
)
|
||||
@@ -29,12 +30,12 @@ func TestLLMReplierPassesTheModelReplyThrough(t *testing.T) {
|
||||
|
||||
func TestLLMReplierFallsBackToStubOnError(t *testing.T) {
|
||||
r := newLLMReplier(stubCompleter{err: errReplierTest}, nil)
|
||||
assertStub(t, r, router.Decision{Intent: router.IntentNote}, "llm error")
|
||||
assertAck(t, r, router.Decision{Intent: router.IntentNote}, phraser.AckNote, "llm error")
|
||||
}
|
||||
|
||||
func TestLLMReplierFallsBackToStubOnEmpty(t *testing.T) {
|
||||
r := newLLMReplier(stubCompleter{out: ""}, nil)
|
||||
assertStub(t, r, router.Decision{Intent: router.IntentNote}, "empty llm")
|
||||
assertAck(t, r, router.Decision{Intent: router.IntentNote}, phraser.AckNote, "empty llm")
|
||||
}
|
||||
|
||||
func TestLLMReplierClarifyUsesStub(t *testing.T) {
|
||||
@@ -42,6 +43,16 @@ func TestLLMReplierClarifyUsesStub(t *testing.T) {
|
||||
assertStub(t, r, router.Decision{Clarify: true}, "clarify")
|
||||
}
|
||||
|
||||
// assertAck — the stub picks between variants now, so two calls to it are not
|
||||
// expected to match. What must hold is that the reply is a line that entry can
|
||||
// produce, which is the same claim without pinning one wording.
|
||||
func assertAck(t *testing.T, r *llmReplier, d router.Decision, key, what string) {
|
||||
t.Helper()
|
||||
if got := r.Reply(d); !phraser.IsAck(key, nil, got) {
|
||||
t.Errorf("on %s: got %q, want a %q line", what, got, key)
|
||||
}
|
||||
}
|
||||
|
||||
func assertStub(t *testing.T, r *llmReplier, d router.Decision, what string) {
|
||||
t.Helper()
|
||||
got, want := r.Reply(d), voice.NewStubReplier().Reply(d)
|
||||
|
||||
+26
-36
@@ -4,6 +4,10 @@
|
||||
// plural agreement, clock/date rendering, and the "do I actually know this
|
||||
// place/day" guards that pick an honest reply over a confidently wrong one.
|
||||
// Extend this file rather than voice.go for anything in that shape.
|
||||
//
|
||||
// Count agreement is not here. It is say.CountWord, because there were four
|
||||
// copies of the same three-way rule and two of the sites that needed it were
|
||||
// spelling one form out (Vikunja #521).
|
||||
package main
|
||||
|
||||
import (
|
||||
@@ -11,17 +15,15 @@ import (
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
"github.com/kami/maven/internal/say"
|
||||
)
|
||||
|
||||
var ruWeekdays = []string{
|
||||
"воскресенье", "понедельник", "вторник", "среда",
|
||||
"четверг", "пятница", "суббота",
|
||||
}
|
||||
|
||||
var ruMonths = []string{
|
||||
"января", "февраля", "марта", "апреля", "мая", "июня",
|
||||
"июля", "августа", "сентября", "октября", "ноября", "декабря",
|
||||
}
|
||||
// Weekday and month names are a closed class — the language has seven and
|
||||
// twelve — so they live complete in internal/lexicon, where internal/ttsnorm
|
||||
// reads the same twelve month names instead of keeping a second copy
|
||||
// (Vikunja #525).
|
||||
|
||||
// onlyLocalTimeReply — the honest answer when the user asks the time somewhere
|
||||
// other than here. She only keeps one clock, and saying so is better than
|
||||
@@ -33,13 +35,15 @@ var ruMonths = []string{
|
||||
const onlyLocalTimeReply = "я знаю только местное время, про другие города пока не скажу."
|
||||
|
||||
// notPlaceAfterV — words that follow "в" without naming a place, so
|
||||
// mentionsUnknownPlace does not mistake them for a city.
|
||||
var notPlaceAfterV = map[string]bool{
|
||||
"данный": true, "данную": true, "этот": true, "эту": true,
|
||||
"котором": true, "какое": true, "какой": true, "который": true,
|
||||
"общем": true, "точности": true, "курсе": true, "сутках": true,
|
||||
"часах": true, "минутах": true, "секундах": true, "неделе": true,
|
||||
}
|
||||
// mentionsUnknownPlace does not mistake them for a city. Closed set, kept
|
||||
// complete in internal/lexicon.
|
||||
var notPlaceAfterV = func() map[string]bool {
|
||||
m := map[string]bool{}
|
||||
for _, w := range lexicon.NotPlaceAfterV() {
|
||||
m[w] = true
|
||||
}
|
||||
return m
|
||||
}()
|
||||
|
||||
// mentionsUnknownPlace reports whether the question has a "в <слово>" phrase
|
||||
// that looks like a place we do not know ("который час в киеве"). Used only to
|
||||
@@ -94,11 +98,11 @@ func mentionsUnknownDay(u string) bool {
|
||||
// ruClock renders the clock part of the time reply: "15 часов 4 минуты".
|
||||
func ruClock(t time.Time) string {
|
||||
h, m := t.Hour(), t.Minute()
|
||||
hourWord := ruPlural(h, "час", "часа", "часов")
|
||||
hourWord := say.CountWord(h, "час", "часа", "часов")
|
||||
if m == 0 {
|
||||
return fmt.Sprintf("%d %s ровно", h, hourWord)
|
||||
}
|
||||
return fmt.Sprintf("%d %s %d %s", h, hourWord, m, ruPlural(m, "минута", "минуты", "минут"))
|
||||
return fmt.Sprintf("%d %s %d %s", h, hourWord, m, say.CountWord(m, "минута", "минуты", "минут"))
|
||||
}
|
||||
|
||||
// dayPrefix names the day relative to now ("завтра", "вчера", …) so the date
|
||||
@@ -118,22 +122,6 @@ func dayPrefix(now, day time.Time) string {
|
||||
return "это"
|
||||
}
|
||||
|
||||
func ruPlural(n int, one, two, many string) string {
|
||||
n = n % 100
|
||||
if n > 10 && n < 20 {
|
||||
return many
|
||||
}
|
||||
n = n % 10
|
||||
switch n {
|
||||
case 1:
|
||||
return one
|
||||
case 2, 3, 4:
|
||||
return two
|
||||
default:
|
||||
return many
|
||||
}
|
||||
}
|
||||
|
||||
// hasDurationWords checks whether u is asking about elapsed/remaining time
|
||||
// rather than the current clock — guards replySystem from replying "сейчас
|
||||
// X часов" to "сколько времени прошло". Mirrors the stage0.go build filter.
|
||||
@@ -169,11 +157,13 @@ func formatTime(t time.Time) string {
|
||||
case diff < 10*time.Minute:
|
||||
return "несколько минут назад"
|
||||
case diff < 60*time.Minute:
|
||||
return fmt.Sprintf("%d минут назад", int(diff.Minutes()))
|
||||
n := int(diff.Minutes())
|
||||
return fmt.Sprintf("%d %s назад", n, say.CountWord(n, "минуту", "минуты", "минут"))
|
||||
case diff < 2*time.Hour:
|
||||
return "час назад"
|
||||
case diff < 24*time.Hour:
|
||||
return fmt.Sprintf("%d часа назад", int(diff.Hours()))
|
||||
n := int(diff.Hours())
|
||||
return fmt.Sprintf("%d %s назад", n, say.CountWord(n, "час", "часа", "часов"))
|
||||
default:
|
||||
return t.Format("2 января 15:04")
|
||||
}
|
||||
|
||||
+10
-5
@@ -4,10 +4,12 @@ import (
|
||||
"context"
|
||||
"fmt"
|
||||
"log"
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/config"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/smarthome"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
@@ -140,10 +142,10 @@ func (w *homeWiring) homeSummary(ctx context.Context) (string, bool) {
|
||||
ents, err := w.client.States(ctx)
|
||||
if err != nil {
|
||||
log.Printf("smarthome: summary: %v", err)
|
||||
return "не смогла достучаться до дома.", true
|
||||
return phraser.A(phraser.HomeUnreachable, nil), true
|
||||
}
|
||||
if len(ents) == 0 {
|
||||
return "дом ничего не отдаёт.", true
|
||||
return phraser.A(phraser.HomeEmpty, nil), true
|
||||
}
|
||||
var on []string
|
||||
var sensors []string
|
||||
@@ -177,7 +179,7 @@ func (w *homeWiring) homeSummary(ctx context.Context) (string, bool) {
|
||||
}
|
||||
// Silent truncation on a status read is the same failure as the cap
|
||||
// one layer up: she has to say the list is not the whole list.
|
||||
line := "включено: " + strings.Join(shown, ", ")
|
||||
line := phraser.A(phraser.HomeOn, map[string]string{"items": strings.Join(shown, ", ")})
|
||||
if rest > 0 {
|
||||
line += fmt.Sprintf(" и ещё %d", rest)
|
||||
}
|
||||
@@ -185,7 +187,10 @@ func (w *homeWiring) homeSummary(ctx context.Context) (string, bool) {
|
||||
case dark > 0 && len(sensors) == 0:
|
||||
// Nothing is on and everything she can see is unreachable. "всё
|
||||
// выключено" would be a claim about the house she cannot make.
|
||||
return fmt.Sprintf("дом молчит: %d %s не отвечают.", dark, hostWord(dark)), true
|
||||
return phraser.A(phraser.HomeDark, map[string]string{
|
||||
"count": strconv.Itoa(dark),
|
||||
"word": phraser.Devices(dark),
|
||||
}), true
|
||||
default:
|
||||
parts = append(parts, "всё выключено")
|
||||
}
|
||||
@@ -193,7 +198,7 @@ func (w *homeWiring) homeSummary(ctx context.Context) (string, bool) {
|
||||
parts = append(parts, strings.Join(sensors, ", "))
|
||||
}
|
||||
if dark > 0 {
|
||||
parts = append(parts, fmt.Sprintf("%d %s не отвечают", dark, hostWord(dark)))
|
||||
parts = append(parts, fmt.Sprintf("%d %s не отвечают", dark, phraser.Devices(dark)))
|
||||
}
|
||||
return strings.Join(parts, "; ") + ".", true
|
||||
}
|
||||
|
||||
+15
-6
@@ -11,6 +11,7 @@ import (
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
@@ -51,10 +52,10 @@ func (h *reactiveHandler) resolveSnooze(ctx context.Context, text string, src tu
|
||||
}
|
||||
if err := h.api.ResolveNudge(ctx, target.ID, store.NudgeSnoozed, now); err != nil {
|
||||
log.Printf("voice: snooze nudge %d (%s, %s): %v", target.ID, target.Rule, src, err)
|
||||
return "не получилось отложить.", true
|
||||
return phraser.Ack(phraser.FailSnooze, nil), true
|
||||
}
|
||||
log.Printf("voice: snoozed nudge %d (rule %s) from %s", target.ID, target.Rule, src)
|
||||
return "хорошо, вернусь к этому позже.", true
|
||||
return phraser.Ack(phraser.AckSnooze, nil), true
|
||||
}
|
||||
|
||||
// pendingNudge — the newest still-pending nudge sent inside snoozeWindow.
|
||||
@@ -81,15 +82,23 @@ func (h *reactiveHandler) pendingNudge(ctx context.Context, now time.Time) (ipc.
|
||||
return ipc.Nudge{}, false
|
||||
}
|
||||
|
||||
// snoozePhrases — the deferral vocabulary, as stem sequences. Matched by
|
||||
// quietPhrase (quiet_toggle.go), which carries the rule that matters here:
|
||||
// snoozePhrases — the deferral vocabulary. Matched by quietPhrase and quietStem
|
||||
// (quiet_toggle.go), so an adverb is matched through the dictionary and a verb
|
||||
// exactly, prefixed with "=": "напомни" is a request and "напомнил" is a report
|
||||
// about earlier, and the dictionary files both under напомнить (Vikunja #526).
|
||||
// The verbs used to be truncated stems — "напомн", "отлож" — which is what the
|
||||
// deleted ending list existed to complete.
|
||||
//
|
||||
// quietPhrase carries the rule that matters here:
|
||||
// a single-word pattern matches only a single-word utterance. Bare "потом" is
|
||||
// an answer; "потом схожу за водой" is a plan, and reporting a plan must not
|
||||
// silence the rule that prompted it.
|
||||
var snoozePhrases = [][]string{
|
||||
{"не", "сейчас"}, {"не", "могу", "сейчас"}, {"не", "до", "этого"},
|
||||
{"напомн", "позже"}, {"напомн", "потом"}, {"спрос", "позже"},
|
||||
{"отлож"}, {"позже"}, {"потом"}, {"попозже"}, {"погоди"},
|
||||
{"=напомни|=напоминай", "позже"}, {"=напомни|=напоминай", "потом"},
|
||||
{"=спроси|=спрашивай", "позже"},
|
||||
{"=отложи|=отложим|=откладывай"}, {"позже"}, {"потом"}, {"попозже"},
|
||||
{"=погоди|=погодите"},
|
||||
{"not", "now"}, {"later"}, {"snooze"}, {"remind", "me", "later"},
|
||||
}
|
||||
|
||||
|
||||
+9
-1
@@ -28,6 +28,7 @@ import (
|
||||
"github.com/kami/maven/internal/pattern"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/routine"
|
||||
"github.com/kami/maven/internal/say"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
@@ -176,6 +177,9 @@ func (t *tickLoop) tick(ctx context.Context, now time.Time) {
|
||||
t.queueNudge(ctx, cand, state, now)
|
||||
} else {
|
||||
pn, err := t.phraser.PhraseNudge(ctx, *cand)
|
||||
if err == nil {
|
||||
pn = guardNudge(pn, *cand)
|
||||
}
|
||||
if err != nil {
|
||||
log.Printf("tick: phrase nudge %s: %v", cand.Rule.Name, err)
|
||||
} else {
|
||||
@@ -627,7 +631,11 @@ func (t *tickLoop) maybeDrainDigest(ctx context.Context, state loop.State, now t
|
||||
fmt.Fprintf(&b, " · и ещё %d", extra)
|
||||
}
|
||||
body := b.String()
|
||||
summary := fmt.Sprintf("%d отложенных уведомлений", len(entries))
|
||||
// The adjective declines with the noun, so the count picks the whole
|
||||
// phrase: 1 отложенное уведомление, 2 отложенных уведомления, 5
|
||||
// отложенных уведомлений.
|
||||
summary := fmt.Sprintf("%d %s", len(entries), say.CountWord(len(entries),
|
||||
"отложенное уведомление", "отложенных уведомления", "отложенных уведомлений"))
|
||||
|
||||
cand := loop.Candidate{
|
||||
Rule: loop.Rule{Name: "digest", Severity: loop.Severity(maxSev)},
|
||||
|
||||
@@ -0,0 +1,203 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"log"
|
||||
"sync"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// Which subject is this question about — the weather, the house, the LAN, or
|
||||
// none of them. Third of the three mechanisms replacing hand-written Russian
|
||||
// patterns (Vikunja #522, owner's call 2026-08-04). internal/lexicon holds the
|
||||
// sets that can be finished and internal/morph answers the grammar questions;
|
||||
// this is for the sets that can never be finished, because "is this about the
|
||||
// house" is a question about meaning and no word list closes it.
|
||||
//
|
||||
// The three recognisers this replaces were each built the same way: a stem list,
|
||||
// an ask test, a device-noun list, and a bail-out list for the neighbouring
|
||||
// topic. Every one of their own comments admits the shape. isHomeQuery excluded
|
||||
// "погод", "на улице" and "прогноз" by hand because "какая температура на улице"
|
||||
// and "какая температура в доме" share their only content word. isNetworkQuery
|
||||
// matched "сети" as a whole token because the substring lives inside "посетил",
|
||||
// so "сколько машин я посетил" read as a request to scan the LAN. Those are not
|
||||
// bugs in the lists, they are the lists being asked to do semantics.
|
||||
//
|
||||
// So the seeds decide, the same way the personal boundary does
|
||||
// (personalboundary.go), against the same embedder and the same query vector the
|
||||
// turn already carries. One difference in the gate, and it is deliberate. The
|
||||
// boundary claims on the sign of the difference, because there a false claim
|
||||
// costs one honest "не знаю". Here a false claim runs a network scan, or names a
|
||||
// capability as off on a box where it is simply not the subject — so a topic has
|
||||
// to win by a margin, and the losing side of a thin call falls through to the
|
||||
// next query source, which is what the narrow regexes were achieving.
|
||||
//
|
||||
// The regexes stay as the offline floor, unchanged, for a handler with no
|
||||
// embedder or a turn whose vector never got computed. They are allowed to remain
|
||||
// narrow now precisely because they are no longer the only answer.
|
||||
|
||||
// topicLabel — the subjects worth telling apart, plus the one that means none of
|
||||
// them. topicOther is a real class and not a threshold: a question needs
|
||||
// somewhere to lose TO, and "интернет не работает" losing to a set that contains
|
||||
// complaints is a better statement than it failing a number.
|
||||
type topicLabel string
|
||||
|
||||
const (
|
||||
topicWeather topicLabel = "weather"
|
||||
topicHome topicLabel = "home"
|
||||
topicNetwork topicLabel = "network"
|
||||
topicOther topicLabel = "other"
|
||||
)
|
||||
|
||||
// topicMargin — how far a topic must clear the runner-up. Small, because the
|
||||
// margins between neighbouring topics are small: measured on held-out
|
||||
// utterances, a true weather question clears the home set by roughly 0.02 to
|
||||
// 0.09 and the nearest wrong call sits under 0.01. It exists at all for the
|
||||
// asymmetry named above — this gate spends a scan, so a coin-flip falls
|
||||
// through rather than acts.
|
||||
const topicMargin = 0.01
|
||||
|
||||
// topicSeedSets — frozen scoring data, like personalSeeds. Editing one moves a
|
||||
// recogniser and has to be re-measured against TestONNXTopics, not eyeballed.
|
||||
//
|
||||
// Each set covers the phrasings its old regex covered, INCLUDING the ones it
|
||||
// needed a bail-out list for: the weather set carries "какая температура на
|
||||
// улице" and the home set "какая температура в доме", so the pair that forced
|
||||
// isHomeQuery to exclude weather words by hand is now just two seeds sitting on
|
||||
// their own sides.
|
||||
var topicSeedSets = map[topicLabel][]string{
|
||||
topicWeather: {
|
||||
"какая сегодня погода",
|
||||
"какая температура на улице",
|
||||
"будет дождь сегодня",
|
||||
"на улице холодно",
|
||||
"прогноз погоды на завтра",
|
||||
"сколько градусов сейчас",
|
||||
"what is the weather like",
|
||||
"is it going to rain today",
|
||||
},
|
||||
topicHome: {
|
||||
"что включено в доме",
|
||||
"какая температура в доме",
|
||||
"свет в квартире горит",
|
||||
"сколько лампочек включено дома",
|
||||
"что у меня дома с датчиками",
|
||||
"умный дом что сейчас работает",
|
||||
"розетки в доме включены",
|
||||
"what is on in the house",
|
||||
},
|
||||
topicNetwork: {
|
||||
"какие устройства в сети",
|
||||
"кто в сети сейчас",
|
||||
"просканируй локальную сеть",
|
||||
"сколько машин в сетке",
|
||||
"покажи хосты в сети",
|
||||
"какие адреса заняты в локальной сети",
|
||||
"кто подключён к вайфаю",
|
||||
"what devices are on the network",
|
||||
},
|
||||
topicOther: {
|
||||
// Complaints, which are not requests to scan or to read the house.
|
||||
// isNetworkQuery's comment names this one: a scan she runs unasked is
|
||||
// the noisy behaviour the bounds exist to prevent.
|
||||
"интернет не работает",
|
||||
"вайфай тормозит",
|
||||
"свет погас",
|
||||
// Statements. "я дома" was the reason isHomeQuery needed an ask test.
|
||||
"я дома",
|
||||
"я уже дома",
|
||||
// The collision that made "сети" a whole-token match.
|
||||
"сколько машин я посетил",
|
||||
"сколько домов мы посмотрели",
|
||||
// Ordinary questions, his and the world's, so a topic has something
|
||||
// real to lose to rather than an arbitrary floor.
|
||||
"почему небо синее",
|
||||
"какая столица франции",
|
||||
"что я говорил про бэкапы",
|
||||
"что у меня сегодня по календарю",
|
||||
"напомни мне позвонить маме",
|
||||
"what did i say about backups",
|
||||
},
|
||||
}
|
||||
|
||||
// topicIndex holds the embedded seeds. Zero value is usable and means "not
|
||||
// loaded yet"; a handler built without an embedder never loads and every caller
|
||||
// uses its own floor instead.
|
||||
type topicIndex struct {
|
||||
once sync.Once
|
||||
vecs map[topicLabel][][]float32
|
||||
loaded bool
|
||||
}
|
||||
|
||||
// load embeds every set once per process, on the QUERY side — a question
|
||||
// compared with a question, for the reason personalBoundary.load gives.
|
||||
func (x *topicIndex) load(ctx context.Context, emb router.Embedder) {
|
||||
x.once.Do(func() {
|
||||
if emb == nil {
|
||||
return
|
||||
}
|
||||
vecs := make(map[topicLabel][][]float32, len(topicSeedSets))
|
||||
for label, seeds := range topicSeedSets {
|
||||
out := make([][]float32, 0, len(seeds))
|
||||
for _, s := range seeds {
|
||||
v, err := router.EmbedQuery(ctx, emb, s)
|
||||
if err != nil {
|
||||
log.Printf("voice: topic seeds unavailable (%v); falling back to keyword matching", err)
|
||||
return
|
||||
}
|
||||
out = append(out, v)
|
||||
}
|
||||
vecs[label] = out
|
||||
}
|
||||
x.vecs, x.loaded = vecs, true
|
||||
})
|
||||
}
|
||||
|
||||
// best returns the nearest label, how far it cleared the runner-up, and whether
|
||||
// the seeds answered at all. ok is false when they are not loaded, which is the
|
||||
// caller's signal to use its floor.
|
||||
func (x *topicIndex) best(vec []float32) (label topicLabel, margin float64, ok bool) {
|
||||
if !x.loaded || len(vec) == 0 {
|
||||
return "", 0, false
|
||||
}
|
||||
first, second := -1.0, -1.0
|
||||
for l, seeds := range x.vecs {
|
||||
top := -1.0
|
||||
for _, s := range seeds {
|
||||
if c := cosine(vec, s); c > top {
|
||||
top = c
|
||||
}
|
||||
}
|
||||
switch {
|
||||
case top > first:
|
||||
label, first, second = l, top, first
|
||||
case top > second:
|
||||
second = top
|
||||
}
|
||||
}
|
||||
return label, first - second, true
|
||||
}
|
||||
|
||||
// turnIsAbout — the recogniser every topic source calls. The seeds decide when
|
||||
// the embedder is there, which is every deployed box; floor is the source's own
|
||||
// keyword test, which answers when they are not.
|
||||
//
|
||||
// A topic that wins without the margin is reported as a pass, and logged: it is
|
||||
// the one outcome where the seeds and the old regexes are most likely to
|
||||
// disagree, and a silent near-miss is how a recogniser drifts.
|
||||
func (h *reactiveHandler) turnIsAbout(ctx context.Context, t *queryTurn, want topicLabel, floor func(string) bool) bool {
|
||||
h.topics.load(ctx, h.embedder)
|
||||
label, margin, ok := h.topics.best(t.vec)
|
||||
if !ok {
|
||||
return floor(t.dec.Utterance)
|
||||
}
|
||||
if label != want {
|
||||
return false
|
||||
}
|
||||
if margin < topicMargin {
|
||||
log.Printf("voice: %q reads as %s by only %.4f; passing it on", t.dec.Utterance, want, margin)
|
||||
return false
|
||||
}
|
||||
return true
|
||||
}
|
||||
@@ -0,0 +1,117 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// TestTopicFloorAnswersWithoutSeeds — a handler with no embedder never loads the
|
||||
// seeds, and every topic source has to keep working. This is the case that used
|
||||
// to be the only one, so a regression here is the three recognisers going
|
||||
// silent on a box with no embedder at all.
|
||||
func TestTopicFloorAnswersWithoutSeeds(t *testing.T) {
|
||||
h := &reactiveHandler{}
|
||||
for _, tc := range []struct {
|
||||
utterance string
|
||||
label topicLabel
|
||||
floor func(string) bool
|
||||
want bool
|
||||
}{
|
||||
{"какая сегодня погода", topicWeather, isWeatherQuery, true},
|
||||
{"что включено в доме?", topicHome, isHomeQuery, true},
|
||||
{"какие устройства в сети?", topicNetwork, isNetworkQuery, true},
|
||||
{"почему небо синее", topicWeather, isWeatherQuery, false},
|
||||
{"я дома", topicHome, isHomeQuery, false},
|
||||
{"интернет не работает", topicNetwork, isNetworkQuery, false},
|
||||
} {
|
||||
turn := &queryTurn{dec: router.Decision{Utterance: tc.utterance}}
|
||||
if got := h.turnIsAbout(context.Background(), turn, tc.label, tc.floor); got != tc.want {
|
||||
t.Errorf("turnIsAbout(%q, %s) = %v, want %v", tc.utterance, tc.label, got, tc.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestONNXTopics — the number that matters, scored against the embedder homesrv
|
||||
// actually runs. Opt-in via MAVEN_ONNX_LIB, like TestONNXPersonalBoundary.
|
||||
//
|
||||
// Every case is held out: none of these strings is a seed. It asserts what the
|
||||
// gate does, not what the raw scorer says — a label under topicMargin is not a
|
||||
// claim, and one held-out case turns on exactly that.
|
||||
//
|
||||
// The first three rows are the collisions the old regexes needed hand-written
|
||||
// bail-outs for: the temperature pair that made isHomeQuery exclude weather
|
||||
// words, and the
|
||||
// "посетил" substring that made isNetworkQuery match "сети" as a whole token.
|
||||
func TestONNXTopics(t *testing.T) {
|
||||
lib := os.Getenv("MAVEN_ONNX_LIB")
|
||||
if lib == "" {
|
||||
t.Skip("MAVEN_ONNX_LIB unset — see AGENTS.md § Embedder model for intent routing")
|
||||
}
|
||||
dir := filepath.Join("../..", "models/embedder/multilingual-e5-small")
|
||||
emb, err := router.NewONNXEmbedder(filepath.Join(dir, "model_quantized.onnx"), filepath.Join(dir, "tokenizer.json"), lib)
|
||||
if err != nil {
|
||||
t.Skipf("onnx embedder unavailable: %v", err)
|
||||
}
|
||||
defer emb.Close()
|
||||
|
||||
cases := []struct {
|
||||
utterance string
|
||||
want topicLabel
|
||||
}{
|
||||
{"какая температура на улице?", topicWeather},
|
||||
{"какая температура в доме?", topicHome},
|
||||
{"сколько машин я посетил?", topicOther},
|
||||
{"сколько сейчас градусов", topicWeather},
|
||||
{"дождь будет вечером?", topicWeather},
|
||||
{"тепло сегодня на улице?", topicWeather},
|
||||
{"свет на кухне включен?", topicHome},
|
||||
{"что сейчас включено дома", topicHome},
|
||||
{"датчики в квартире что показывают", topicHome},
|
||||
{"просканируй сеть", topicNetwork},
|
||||
{"сколько устройств в локальной сети", topicNetwork},
|
||||
{"кто сейчас в сетке", topicNetwork},
|
||||
// The case the margin exists for. It reads as network by 0.0055, under
|
||||
// topicMargin, so the gate passes it on — which is right: it is a
|
||||
// complaint, and a scan she runs unasked is the behaviour the bounds
|
||||
// prevent.
|
||||
{"вайфай опять отвалился", topicOther},
|
||||
{"я уже приехал домой", topicOther},
|
||||
{"что я говорил про погоду в москве", topicOther},
|
||||
{"напомни полить цветы", topicOther},
|
||||
}
|
||||
|
||||
h := &reactiveHandler{embedder: emb}
|
||||
ctx := context.Background()
|
||||
h.topics.load(ctx, emb)
|
||||
if !h.topics.loaded {
|
||||
t.Fatal("topic seeds did not load")
|
||||
}
|
||||
right := 0
|
||||
for _, tc := range cases {
|
||||
vec, err := router.EmbedQuery(ctx, emb, tc.utterance)
|
||||
if err != nil {
|
||||
t.Fatalf("embed %q: %v", tc.utterance, err)
|
||||
}
|
||||
label, margin, ok := h.topics.best(vec)
|
||||
if !ok {
|
||||
t.Fatalf("best(%q) not ok", tc.utterance)
|
||||
}
|
||||
// What the gate would do, which is the thing under test: a label that
|
||||
// does not clear the margin is not a claim.
|
||||
got := label
|
||||
if margin < topicMargin {
|
||||
got = topicOther
|
||||
}
|
||||
if got == tc.want {
|
||||
right++
|
||||
} else {
|
||||
t.Errorf("%q: %s by %.4f, want %s", tc.utterance, label, margin, tc.want)
|
||||
}
|
||||
t.Logf(" %-40s -> %-8s margin %.4f", tc.utterance, label, margin)
|
||||
}
|
||||
t.Logf("topics: %d/%d", right, len(cases))
|
||||
}
|
||||
+8
-2
@@ -55,6 +55,7 @@ import (
|
||||
"github.com/kami/maven/internal/crawl"
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
"github.com/kami/maven/internal/memory"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
@@ -76,6 +77,11 @@ type reactiveHandler struct {
|
||||
tts tts.Synthesizer
|
||||
router *router.Router
|
||||
embedder router.Embedder // reused for note write/query (same model as the classifier)
|
||||
// topics — the embedded seed sets behind the weather, house and LAN
|
||||
// recognisers (topics.go). Same lifecycle as boundary below: zero value is
|
||||
// usable, loads on first query, and with no embedder it never loads and
|
||||
// each source falls back to its own keyword test.
|
||||
topics topicIndex
|
||||
// boundary — the embedded seed sets behind the personal boundary
|
||||
// (personalboundary.go). Zero value is usable and loads on first query;
|
||||
// with no embedder it never loads and the boundary uses personalMarkers.
|
||||
@@ -452,8 +458,8 @@ func (h *reactiveHandler) replySystem(ctx context.Context, dec router.Decision)
|
||||
// this arm was fixed for, so say what she can do instead.
|
||||
return onlyNearDaysReply
|
||||
}
|
||||
dow := ruWeekdays[day.Weekday()]
|
||||
month := ruMonths[day.Month()-1]
|
||||
dow := lexicon.Weekday(int(day.Weekday()))
|
||||
month := lexicon.MonthGenitive(int(day.Month()))
|
||||
return fmt.Sprintf("%s %s, %d %s %d года", prefix, dow, day.Day(), month, day.Year())
|
||||
case strings.Contains(u, "кто дома") || strings.Contains(u, "человек дома"):
|
||||
return "присутствие пока не подключено к голосовому запросу."
|
||||
|
||||
@@ -382,6 +382,10 @@ func buildRouter(emb router.Embedder, acts router.ActMatcher, threshold float64,
|
||||
// question and must keep reaching replySystem, while "что у меня сегодня"
|
||||
// is an agenda question and must not.
|
||||
grammars = append(grammars, router.AgendaQueryGrammars()...)
|
||||
// After the agenda rules: "расскажи, что у меня сегодня" is an agenda
|
||||
// question first and a narrative request second (Vikunja #498).
|
||||
grammars = append(grammars, router.NarrativeQueryGrammars()...)
|
||||
grammars = append(grammars, router.ListGrammars()...)
|
||||
grammars = append(grammars, router.ReminderGrammar())
|
||||
// Last, and it matches any utterance shape — its Build is the filter. An
|
||||
// explicit capture marker beats the model, which called it an act and
|
||||
|
||||
@@ -23,7 +23,11 @@ type worldPhraser interface {
|
||||
// question about his meeting came back as a swimming competition in Nottingham.
|
||||
// Naming the gap is the rule CLAUDE.md already applies to a sibling service
|
||||
// being down.
|
||||
const worldGap = "сейчас не могу ответить — большая модель недоступна, а придумывать не хочу."
|
||||
//
|
||||
// The wording lives in fallbacks_ru_v1.json and is fixed there, not picked from
|
||||
// variants: this sentence names one specific gap and must not drift into a
|
||||
// general "I don't know".
|
||||
func worldGap() string { return phraser.WorldGap() }
|
||||
|
||||
// phraseWorld asks the world model, or reports the gap.
|
||||
//
|
||||
@@ -54,7 +58,11 @@ func (h *reactiveHandler) phraseSource(ctx context.Context, name, utterance stri
|
||||
log.Printf("voice: %s: no world model, reading the source back instead", name)
|
||||
return ""
|
||||
case err != nil:
|
||||
// The resident phraser answers this call with its fallback text and the
|
||||
// error together. Drop the text: these callers hold the passage itself
|
||||
// and read it back better than "вот что я нашла: <passage>" does.
|
||||
log.Printf("voice: %s: phrase: %v", name, err)
|
||||
return ""
|
||||
}
|
||||
return reply
|
||||
}
|
||||
|
||||
@@ -35,7 +35,7 @@ func TestQueryGeneralNamesTheGap(t *testing.T) {
|
||||
if !ok {
|
||||
t.Fatal("queryGeneral passed on the last source in the chain")
|
||||
}
|
||||
if reply != worldGap {
|
||||
if reply != worldGap() {
|
||||
t.Fatalf("reply = %q, want the named gap", reply)
|
||||
}
|
||||
if g.worldCalls != 1 {
|
||||
@@ -51,7 +51,7 @@ func TestQueryGeneralWithoutAWorldModelIsUnchanged(t *testing.T) {
|
||||
if !ok {
|
||||
t.Fatal("queryGeneral passed on the last source in the chain")
|
||||
}
|
||||
if reply != "не знаю." {
|
||||
if !phraser.IsUnknownFallback(reply) {
|
||||
t.Fatalf("reply = %q, want the Stub's answer", reply)
|
||||
}
|
||||
}
|
||||
@@ -61,12 +61,12 @@ func TestQueryGeneralWithoutAWorldModelIsUnchanged(t *testing.T) {
|
||||
// English in it.
|
||||
func TestWorldGapIsInPersona(t *testing.T) {
|
||||
for _, bad := range []string{"вы", "ваш", "рад ", "дорогой", "милый"} {
|
||||
if strings.Contains(worldGap, bad) {
|
||||
t.Errorf("the gap phrase contains %q: %s", bad, worldGap)
|
||||
if strings.Contains(worldGap(), bad) {
|
||||
t.Errorf("the gap phrase contains %q: %s", bad, worldGap())
|
||||
}
|
||||
}
|
||||
if strings.ContainsAny(worldGap, "abcdefghijklmnopqrstuvwxyz") {
|
||||
t.Errorf("the gap phrase has Latin letters in it: %s", worldGap)
|
||||
if strings.ContainsAny(worldGap(), "abcdefghijklmnopqrstuvwxyz") {
|
||||
t.Errorf("the gap phrase has Latin letters in it: %s", worldGap())
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -317,6 +317,40 @@ don't improvise.** Destructive ones still gate behind confirm.
|
||||
Misroute correction is append-only and grows the router's examples with use —
|
||||
same shape as `nudges.outcome` tuning cooldowns, no retrain.
|
||||
|
||||
#### Risk tiers, not one boolean
|
||||
|
||||
`Destructive` on a tool row is one bit set by whoever ticked the checkbox on
|
||||
`/tools`. It is a mechanism, and it never said which acts are destructive,
|
||||
whether a confirmed act stays confirmed, or what a new tool domain inherits.
|
||||
`internal/tool/risk.go` is the policy (Vikunja #449). The tier is DERIVED from
|
||||
the row, not stored, so it can be argued with in one place instead of being
|
||||
whatever the last person to enable the tool believed.
|
||||
|
||||
| Tier | What it is | What it costs |
|
||||
|---|---|---|
|
||||
| `safe` | a read, or a change he can undo by saying the opposite | runs on first hearing |
|
||||
| `destructive` | it changes something real and undoing it takes work | one confirm turn, every time |
|
||||
| `irreversible` | the thing does not come back: a wipe, a format, a delete with no bin | voice may not authorise it at all |
|
||||
|
||||
Three rules fall out, and they are the part that was missing:
|
||||
|
||||
- **Which acts are destructive is not only the checkbox.** A house row always
|
||||
is, because there is no read-only way to turn the heating off. A row whose
|
||||
argv names one of the irreversible verbs always is, whatever the row says.
|
||||
- **A confirmed act never stays confirmed.** At any tier. A confirmation binds
|
||||
one capability, one target and one argument list, and it dies with the parked
|
||||
turn (90s). "The same act again" is a new act. A sticky confirm is a standing
|
||||
grant and nothing on the voice path may hold one.
|
||||
- **A new domain inherits `destructive`, not `safe`.** A dispatch shape the
|
||||
policy does not recognise gets the confirm turn. A domain argues its way down
|
||||
to running freely; it never has to argue its way up to being gated.
|
||||
|
||||
The irreversible tier is refused rather than asked about, because a confirm
|
||||
turn would be theatre: everything that proposed the act — an STT guess, a
|
||||
router guess, a fuzzy allowlist match — is a guess, and a spoken "да" checks
|
||||
none of it. She names the gap and he runs it himself. The row stays enabled;
|
||||
refusing to run it from voice is not the same as taking it off the allowlist.
|
||||
|
||||
---
|
||||
|
||||
## Voice pipeline (STT / TTS)
|
||||
@@ -654,6 +688,31 @@ add a new principle; it applied the existing one at smaller and smaller scope.
|
||||
|
||||
---
|
||||
|
||||
## A list is the fourth shape
|
||||
|
||||
Facts, notes and tasks were the three append-only shapes. `list_items` is the
|
||||
fourth (Vikunja #453): an item, a status, and a list tag.
|
||||
|
||||
It is not a task. Milk is not work, nothing prioritises it, and the ranker must
|
||||
not start counting groceries as outstanding errands. It is not a fact either,
|
||||
because it claims nothing about the world. What it is, is a set that grows and
|
||||
shrinks.
|
||||
|
||||
The property that makes the separate table worth it: no predicate reads a list.
|
||||
Nothing ranks it, nothing nudges about it, the digestion worker ignores it. So
|
||||
two people adding to the same list at once cost nothing — there is no order to
|
||||
disagree about and no lifecycle past crossed-off.
|
||||
|
||||
The unique index is the tasks one, per list, and live rows only. Saying "молоко"
|
||||
twice before the shop is one line; saying it again next week, after the last one
|
||||
was crossed off, is a new line.
|
||||
|
||||
Spoken, it is four turns: add, read back, cross one item off, cross the lot off.
|
||||
All four are matched deterministically in `internal/router/list.go` and all four
|
||||
run at stage 0, because an add and a read-back are cheap and should not depend on
|
||||
the resident model having a good turn. Crossing one item off claims the turn only
|
||||
when the list holds that item, which is what keeps "купил новый ноутбук" a note.
|
||||
|
||||
## Calendar
|
||||
|
||||
Integration with **Radicale** (self-hosted CalDAV), not Nextcloud. Scope is
|
||||
|
||||
@@ -10,12 +10,15 @@ require (
|
||||
modernc.org/sqlite v1.54.0
|
||||
)
|
||||
|
||||
require github.com/kami/hexis v0.0.0
|
||||
require (
|
||||
github.com/aaaton/golem/v4 v4.0.2
|
||||
github.com/aaaton/golem/v4/dicts/ru v0.0.0-20250408131944-3488790fc110
|
||||
github.com/kami/hexis v0.0.0
|
||||
)
|
||||
|
||||
require (
|
||||
github.com/dustin/go-humanize v1.0.1 // indirect
|
||||
github.com/google/uuid v1.6.0 // indirect
|
||||
github.com/kami/praxis v0.0.0
|
||||
github.com/mattn/go-isatty v0.0.20 // indirect
|
||||
github.com/ncruces/go-strftime v1.0.0 // indirect
|
||||
github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
|
||||
|
||||
@@ -1,3 +1,8 @@
|
||||
github.com/aaaton/golem/v4 v4.0.0/go.mod h1:OfK/S5v9Exsx1yO21WorREuIVV+Y5K2hygP0A9oJCCI=
|
||||
github.com/aaaton/golem/v4 v4.0.2 h1:m4FvpSL8Zcv7XjmrKiBP7dp5FzhPCji9FcQRcH6T23k=
|
||||
github.com/aaaton/golem/v4 v4.0.2/go.mod h1:OfK/S5v9Exsx1yO21WorREuIVV+Y5K2hygP0A9oJCCI=
|
||||
github.com/aaaton/golem/v4/dicts/ru v0.0.0-20250408131944-3488790fc110 h1:aRLhKltXUyZg/7DoZE5PcNhETfTjMBXBEzD/JVRVVN4=
|
||||
github.com/aaaton/golem/v4/dicts/ru v0.0.0-20250408131944-3488790fc110/go.mod h1:n14MqOgbLBidXRIvLw9H3/vFyE4+PcjVxYOu05f55R4=
|
||||
github.com/coder/websocket v1.8.12 h1:5bUXkEPPIbewrnkU8LTCLVaxi4N4J8ahufH2vlo4NAo=
|
||||
github.com/coder/websocket v1.8.12/go.mod h1:LNVeNrXQZfe5qhS9ALED3uA+l5pPqvwXg3CKoDBB2gs=
|
||||
github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=
|
||||
|
||||
@@ -4,6 +4,8 @@ import (
|
||||
"strings"
|
||||
"time"
|
||||
"unicode"
|
||||
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
)
|
||||
|
||||
// Ambient events — the work calendar read (Vikunja #126).
|
||||
@@ -48,18 +50,6 @@ type Notification struct {
|
||||
// reposting a notification for a meeting already under way.
|
||||
const ambientPastGrace = 2 * time.Hour
|
||||
|
||||
// dayWords maps the words that move a notification off Posted's day. Only
|
||||
// explicit ones: an offset is a claim about which day, and guessing which day
|
||||
// is exactly the guess this parse refuses to make.
|
||||
var dayWords = map[string]int{
|
||||
"завтра": 1,
|
||||
"tomorrow": 1,
|
||||
"сегодня": 0,
|
||||
"today": 0,
|
||||
"tonight": 0,
|
||||
"послезавтра": 2,
|
||||
}
|
||||
|
||||
// EventFromNotification turns a notification into the event it describes, or
|
||||
// reports false when it does not clearly describe one.
|
||||
//
|
||||
@@ -104,11 +94,16 @@ func EventFromNotification(n Notification) (Event, bool) {
|
||||
}
|
||||
|
||||
// dayOffset reports how many days off Posted's day the notification puts the
|
||||
// event. Words are matched whole, so "послезавтра" is not read as "завтра".
|
||||
// event. Only explicit words move it: an offset is a claim about which day, and
|
||||
// guessing which day is exactly the guess this parse refuses to make.
|
||||
//
|
||||
// The words are a closed class and live complete in internal/lexicon (Vikunja
|
||||
// #525), which is how "позавчера" resolves here now — it never did while the map
|
||||
// was inline. Matched whole, so "послезавтра" is not read as "завтра".
|
||||
func dayOffset(line string) int {
|
||||
for _, f := range strings.Fields(strings.ToLower(line)) {
|
||||
f = strings.Trim(f, ".,;:!?—–-()\"'«»")
|
||||
if off, ok := dayWords[f]; ok {
|
||||
if off, ok := lexicon.DayOffset(f); ok {
|
||||
return off
|
||||
}
|
||||
}
|
||||
@@ -121,7 +116,7 @@ func dayOffset(line string) int {
|
||||
func stripDayWords(s string) string {
|
||||
out := make([]string, 0, 8)
|
||||
for _, f := range strings.Fields(s) {
|
||||
if _, ok := dayWords[strings.Trim(strings.ToLower(f), ".,;:!?—–-()\"'«»")]; ok {
|
||||
if _, ok := lexicon.DayOffset(strings.Trim(f, ".,;:!?—–-()\"'«»")); ok {
|
||||
continue
|
||||
}
|
||||
out = append(out, f)
|
||||
|
||||
@@ -0,0 +1,219 @@
|
||||
// Package lexicon holds the Russian word sets that can be finished.
|
||||
//
|
||||
// A closed class has a fixed number of members: the language has as many
|
||||
// interrogative pronouns as it has, and no utterance will ever contain a
|
||||
// thirteenth month. Those sets belong in a data file, complete, and that is what
|
||||
// this package is (Vikunja #522, owner's call 2026-08-04 — "not pattern, 100%").
|
||||
//
|
||||
// It is the first of three mechanisms that replaced hand-written Russian
|
||||
// patterns, and the only one that answers with certainty. The other two are the
|
||||
// embedder, for recognising an open set of phrasings, and a morphological
|
||||
// dictionary, for questions about grammar. A list that can never be finished is
|
||||
// a guess dressed as a rule and does not go here.
|
||||
//
|
||||
// What this package does NOT do is match. It hands out sets and lookups; the
|
||||
// caller decides what to do with a hit, because "this token is an interrogative"
|
||||
// and "this utterance is a question" are different claims.
|
||||
package lexicon
|
||||
|
||||
import (
|
||||
"embed"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"sort"
|
||||
"strings"
|
||||
"unicode"
|
||||
"unicode/utf8"
|
||||
)
|
||||
|
||||
//go:embed lexicon_ru_v1.json
|
||||
var files embed.FS
|
||||
|
||||
// ruFile is the versioned file this package reads. A new version is a new file,
|
||||
// not an edit to this one, so a caller pinned to v1 keeps the words it was
|
||||
// measured against.
|
||||
const ruFile = "lexicon_ru_v1.json"
|
||||
|
||||
type lexiconFile struct {
|
||||
SchemaVersion int `json:"schema_version"`
|
||||
Name string `json:"name"`
|
||||
Sets map[string]lexiSet `json:"sets"`
|
||||
}
|
||||
|
||||
type lexiSet struct {
|
||||
Note string `json:"note"`
|
||||
Words []string `json:"words"`
|
||||
Values map[string]int `json:"values"`
|
||||
}
|
||||
|
||||
// ru is parsed once at init. A malformed embedded file is a build-time mistake
|
||||
// that survived to runtime, and there is no sane degraded behaviour for "the
|
||||
// months are missing", so it panics rather than answering with an empty set.
|
||||
var ru = mustLoad()
|
||||
|
||||
func mustLoad() lexiconFile {
|
||||
data, err := files.ReadFile(ruFile)
|
||||
if err != nil {
|
||||
panic(fmt.Sprintf("lexicon: read %s: %v", ruFile, err))
|
||||
}
|
||||
var f lexiconFile
|
||||
if err := json.Unmarshal(data, &f); err != nil {
|
||||
panic(fmt.Sprintf("lexicon: parse %s: %v", ruFile, err))
|
||||
}
|
||||
for _, name := range []string{
|
||||
"interrogatives", "capture_verbs", "narrative_requests", "cardinals",
|
||||
"day_offsets", "weekdays", "months_genitive", "hours_spoken",
|
||||
"not_place_after_v",
|
||||
} {
|
||||
s, ok := f.Sets[name]
|
||||
if !ok || (len(s.Words) == 0 && len(s.Values) == 0) {
|
||||
panic(fmt.Sprintf("lexicon: %s has no set %q", ruFile, name))
|
||||
}
|
||||
}
|
||||
return f
|
||||
}
|
||||
|
||||
// words returns a copy of a word set, so a caller cannot edit the lexicon by
|
||||
// holding onto what it was given.
|
||||
func words(set string) []string {
|
||||
src := ru.Sets[set].Words
|
||||
out := make([]string, len(src))
|
||||
copy(out, src)
|
||||
return out
|
||||
}
|
||||
|
||||
// Interrogatives returns the question words, Russian and English.
|
||||
func Interrogatives() []string { return words("interrogatives") }
|
||||
|
||||
// CaptureVerbs returns the imperatives that mean "record this".
|
||||
func CaptureVerbs() []string { return words("capture_verbs") }
|
||||
|
||||
// NarrativeRequests returns the imperatives that mean "tell me about".
|
||||
func NarrativeRequests() []string { return words("narrative_requests") }
|
||||
|
||||
// NotPlaceAfterV returns the words that follow "в" without naming a place.
|
||||
func NotPlaceAfterV() []string { return words("not_place_after_v") }
|
||||
|
||||
// Cardinal reports the value of a spoken number word. The word is compared
|
||||
// lowercased and trimmed, because it arrives from a tokenizer that may not have
|
||||
// done either.
|
||||
func Cardinal(word string) (int, bool) {
|
||||
n, ok := ru.Sets["cardinals"].Values[norm(word)]
|
||||
return n, ok
|
||||
}
|
||||
|
||||
// DayOffset reports how many days a relative day word moves from today.
|
||||
//
|
||||
// The zero value is a real answer here — "сегодня" is offset 0 — so the second
|
||||
// return is the only way to tell a hit from a miss. Callers that used to switch
|
||||
// on strings.Contains had to order "послезавтра" before "завтра" by hand,
|
||||
// because one contains the other; a lookup has no such trap.
|
||||
func DayOffset(word string) (int, bool) {
|
||||
n, ok := ru.Sets["day_offsets"].Values[norm(word)]
|
||||
return n, ok
|
||||
}
|
||||
|
||||
// DayOffsetWords lists the relative day words themselves, sorted so the order is
|
||||
// stable across builds — a caller that folds them into a regexp alternation would
|
||||
// otherwise produce a different pattern every run. Map iteration order is why
|
||||
// this sorts rather than the caller.
|
||||
func DayOffsetWords() []string {
|
||||
vals := ru.Sets["day_offsets"].Values
|
||||
out := make([]string, 0, len(vals))
|
||||
for w := range vals {
|
||||
out = append(out, w)
|
||||
}
|
||||
sort.Strings(out)
|
||||
return out
|
||||
}
|
||||
|
||||
// DayOffsetIn finds a relative day word anywhere in a phrase and reports its
|
||||
// offset. Where two words appear, the one that moves furthest from today wins in
|
||||
// absolute terms: "не сегодня, а послезавтра" is about the day after tomorrow,
|
||||
// and the longest-match rule that picking the first word would need is exactly
|
||||
// what the old Contains switch got wrong.
|
||||
func DayOffsetIn(text string) (int, bool) {
|
||||
lower := norm(text)
|
||||
best, found := 0, false
|
||||
for word, n := range ru.Sets["day_offsets"].Values {
|
||||
if !containsWord(lower, word) {
|
||||
continue
|
||||
}
|
||||
if !found || abs(n) > abs(best) {
|
||||
best, found = n, true
|
||||
}
|
||||
}
|
||||
return best, found
|
||||
}
|
||||
|
||||
// Weekday returns the Russian name of a weekday index, Sunday first, matching
|
||||
// Go's time.Weekday. An index off the end returns "".
|
||||
func Weekday(i int) string { return at("weekdays", i) }
|
||||
|
||||
// MonthGenitive returns the month name a date takes — "10 июля", not "июль".
|
||||
// The set is 1-indexed, so MonthGenitive(int(t.Month())) is the whole call.
|
||||
func MonthGenitive(m int) string { return at("months_genitive", m) }
|
||||
|
||||
// HourSpoken returns an hour spelled out for the voice. 0 to 23.
|
||||
func HourSpoken(h int) string { return at("hours_spoken", h) }
|
||||
|
||||
func at(set string, i int) string {
|
||||
w := ru.Sets[set].Words
|
||||
if i < 0 || i >= len(w) {
|
||||
return ""
|
||||
}
|
||||
return w[i]
|
||||
}
|
||||
|
||||
func norm(s string) string { return strings.ToLower(strings.TrimSpace(s)) }
|
||||
|
||||
func abs(n int) int {
|
||||
if n < 0 {
|
||||
return -n
|
||||
}
|
||||
return n
|
||||
}
|
||||
|
||||
// containsWord reports whether haystack holds needle on word boundaries. Go's
|
||||
// \b is ASCII-only and never fires after a Cyrillic letter, so the boundary is
|
||||
// checked here instead: a rune on either side must not be a letter or a digit.
|
||||
func containsWord(haystack, needle string) bool {
|
||||
if needle == "" {
|
||||
return false
|
||||
}
|
||||
from := 0
|
||||
for {
|
||||
i := strings.Index(haystack[from:], needle)
|
||||
if i < 0 {
|
||||
return false
|
||||
}
|
||||
i += from
|
||||
if boundaryBefore(haystack, i) && boundaryAfter(haystack, i+len(needle)) {
|
||||
return true
|
||||
}
|
||||
from = i + len(needle)
|
||||
if from >= len(haystack) {
|
||||
return false
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func boundaryBefore(s string, i int) bool {
|
||||
if i == 0 {
|
||||
return true
|
||||
}
|
||||
r, _ := utf8.DecodeLastRuneInString(s[:i])
|
||||
return !wordRune(r)
|
||||
}
|
||||
|
||||
func boundaryAfter(s string, i int) bool {
|
||||
if i >= len(s) {
|
||||
return true
|
||||
}
|
||||
r, _ := utf8.DecodeRuneInString(s[i:])
|
||||
return !wordRune(r)
|
||||
}
|
||||
|
||||
func wordRune(r rune) bool {
|
||||
return unicode.IsLetter(r) || unicode.IsDigit(r) || r == '_'
|
||||
}
|
||||
@@ -0,0 +1,123 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"name": "russian closed-class lexicons v1",
|
||||
"notes": [
|
||||
"Every set here is a CLOSED CLASS: the language has a fixed number of members and the list can be finished. That is why it is a list at all. A word list that can never be finished is a guess dressed as a rule, and it belongs with the embedder, not here (Vikunja #522).",
|
||||
"Editing a word is a data change. No Go change, no rebuild of a pattern, no second copy to keep in step — month names used to live in two files and day offsets in three.",
|
||||
"Interrogatives and capture verbs carry their English members too. He speaks both languages in one sentence and the router sees one utterance.",
|
||||
"The sets are matched over tokens, never as substrings: \"что\" inside \"чтобы\" and \"как\" inside \"какао\" are not questions.",
|
||||
"Order matters in weekdays, months and hours, and nowhere else. weekdays starts at Sunday because Go's time.Weekday does. months is 1-indexed with an empty slot at 0 for the same reason. hours is indexed by the hour itself.",
|
||||
"A form missing from a closed set is a bug report, not a judgement call. Add it."
|
||||
],
|
||||
"sets": {
|
||||
"interrogatives": {
|
||||
"note": "The Russian interrogative pronouns and adverbs, declined, plus the English ones. Closed class: this is the whole list, and a question word outside it does not exist.",
|
||||
"words": [
|
||||
"что", "чего", "чему", "чем", "чём",
|
||||
"кто", "кого", "кому", "кем", "ком",
|
||||
"какой", "какая", "какое", "какие", "какого", "какому", "каким", "каких", "какими", "каком",
|
||||
"который", "которая", "которое", "которые", "которого", "котором",
|
||||
"чей", "чья", "чьё", "чьи",
|
||||
"где", "куда", "откуда", "когда", "докуда",
|
||||
"почему", "зачем", "отчего", "как", "сколько", "насколько", "каково",
|
||||
"what", "who", "whom", "whose", "why", "when", "where", "which", "how"
|
||||
]
|
||||
},
|
||||
"capture_verbs": {
|
||||
"note": "An explicit instruction to record something, in the imperative he actually speaks. Not a closed class in the grammatical sense, but a closed set of the commands Maven answers to — it is her vocabulary, and its members are decided here rather than discovered.",
|
||||
"words": [
|
||||
"запиши", "запомни", "отметь", "заметь", "добавь", "сохрани", "занеси", "внеси",
|
||||
"note", "remember", "log", "save", "add"
|
||||
]
|
||||
},
|
||||
"narrative_requests": {
|
||||
"note": "\"Tell me about X\" asks for knowledge Maven does not hold about him. It carries no question mark and no interrogative, which is how \"расскажи про битву при Ватерлоо\" reached the fact store (#470).",
|
||||
"words": [
|
||||
"расскажи", "объясни", "опиши", "перечисли", "поясни",
|
||||
"tell", "explain", "describe", "list"
|
||||
]
|
||||
},
|
||||
"cardinals": {
|
||||
"note": "Number words as spoken, with the gender variants Russian requires: один/одна/одно and два/две agree with the noun that follows. Values are the number itself. Twenties and up are compounds and are read as their parts, so only the round members are listed.",
|
||||
"values": {
|
||||
"ноль": 0, "нуль": 0, "zero": 0,
|
||||
"один": 1, "одна": 1, "одно": 1, "one": 1,
|
||||
"два": 2, "две": 2, "two": 2,
|
||||
"три": 3, "three": 3,
|
||||
"четыре": 4, "four": 4,
|
||||
"пять": 5, "five": 5,
|
||||
"шесть": 6, "six": 6,
|
||||
"семь": 7, "seven": 7,
|
||||
"восемь": 8, "eight": 8,
|
||||
"девять": 9, "nine": 9,
|
||||
"десять": 10, "ten": 10,
|
||||
"одиннадцать": 11, "eleven": 11,
|
||||
"двенадцать": 12, "twelve": 12,
|
||||
"тринадцать": 13, "thirteen": 13,
|
||||
"четырнадцать": 14, "fourteen": 14,
|
||||
"пятнадцать": 15, "fifteen": 15,
|
||||
"шестнадцать": 16, "sixteen": 16,
|
||||
"семнадцать": 17, "seventeen": 17,
|
||||
"восемнадцать": 18, "eighteen": 18,
|
||||
"девятнадцать": 19, "nineteen": 19,
|
||||
"двадцать": 20, "twenty": 20,
|
||||
"тридцать": 30, "thirty": 30,
|
||||
"сорок": 40, "forty": 40,
|
||||
"пятьдесят": 50, "fifty": 50,
|
||||
"шестьдесят": 60, "sixty": 60,
|
||||
"семьдесят": 70, "seventy": 70,
|
||||
"восемьдесят": 80, "eighty": 80,
|
||||
"девяносто": 90, "ninety": 90,
|
||||
"сто": 100, "hundred": 100
|
||||
}
|
||||
},
|
||||
"day_offsets": {
|
||||
"note": "The words that name a day relative to today, and the number of days each one moves. Only explicit ones: an offset is a claim about which day, and guessing which day is the guess these callers refuse to make. Multi-word members are matched as a phrase.",
|
||||
"values": {
|
||||
"позавчера": -2,
|
||||
"вчера": -1,
|
||||
"yesterday": -1,
|
||||
"сегодня": 0,
|
||||
"today": 0,
|
||||
"tonight": 0,
|
||||
"завтра": 1,
|
||||
"tomorrow": 1,
|
||||
"послезавтра": 2,
|
||||
"day after tomorrow": 2
|
||||
}
|
||||
},
|
||||
"weekdays": {
|
||||
"note": "Nominative, starting at Sunday so the index is Go's time.Weekday.",
|
||||
"words": [
|
||||
"воскресенье", "понедельник", "вторник", "среда",
|
||||
"четверг", "пятница", "суббота"
|
||||
]
|
||||
},
|
||||
"months_genitive": {
|
||||
"note": "The form a date takes: \"10 июля\", not \"июль\". 1-indexed, so slot 0 is empty and month numbers need no arithmetic.",
|
||||
"words": [
|
||||
"", "января", "февраля", "марта", "апреля", "мая", "июня",
|
||||
"июля", "августа", "сентября", "октября", "ноября", "декабря"
|
||||
]
|
||||
},
|
||||
"hours_spoken": {
|
||||
"note": "Hours spelled out for the voice: \"3 ч\" is fine on a screen and wrong out loud. Indexed by the hour, 0 to 23.",
|
||||
"words": [
|
||||
"ноль", "один", "два", "три", "четыре", "пять", "шесть", "семь", "восемь",
|
||||
"девять", "десять", "одиннадцать", "двенадцать", "тринадцать",
|
||||
"четырнадцать", "пятнадцать", "шестнадцать", "семнадцать", "восемнадцать",
|
||||
"девятнадцать", "двадцать", "двадцать один", "двадцать два", "двадцать три"
|
||||
]
|
||||
},
|
||||
"not_place_after_v": {
|
||||
"note": "Words that follow the preposition \"в\" without naming a place, so \"в общем\" and \"в котором часу\" are not read as a city we do not know.",
|
||||
"words": [
|
||||
"данный", "данную", "данное", "этот", "эту", "это", "том", "той",
|
||||
"котором", "которой", "какое", "какой", "который", "каком",
|
||||
"общем", "точности", "курсе", "принципе", "итоге", "целом",
|
||||
"сутках", "часах", "минутах", "секундах", "неделе", "месяце", "году",
|
||||
"начале", "конце", "середине", "течение", "течении"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,114 @@
|
||||
package lexicon
|
||||
|
||||
import "testing"
|
||||
|
||||
// TestClosedSetsAreComplete — the point of the package. A closed class can be
|
||||
// finished, so the test names the members that were MISSING from the inline Go
|
||||
// lists this package replaced (Vikunja #525) and every one of them has to be
|
||||
// there. Add to this list when a form turns up unhandled.
|
||||
func TestClosedSetsAreComplete(t *testing.T) {
|
||||
inter := map[string]bool{}
|
||||
for _, w := range Interrogatives() {
|
||||
inter[w] = true
|
||||
}
|
||||
// Instrumental and prepositional cases of что and кто, and the declined
|
||||
// какой. The old list had что/чего and nothing else, so "чем ты занята" and
|
||||
// "в каком часу" carried no interrogative at all.
|
||||
for _, w := range []string{"чем", "чём", "чему", "кем", "ком", "каком", "какими", "насколько"} {
|
||||
if !inter[w] {
|
||||
t.Errorf("interrogatives is missing %q", w)
|
||||
}
|
||||
}
|
||||
|
||||
for _, tc := range []struct {
|
||||
word string
|
||||
want int
|
||||
}{
|
||||
{"ноль", 0}, {"одна", 1}, {"две", 2}, {"одиннадцать", 11},
|
||||
{"пятнадцать", 15}, {"двадцать", 20}, {"сорок", 40}, {"девяносто", 90},
|
||||
{"сто", 100}, {"twelve", 12},
|
||||
} {
|
||||
got, ok := Cardinal(tc.word)
|
||||
if !ok || got != tc.want {
|
||||
t.Errorf("Cardinal(%q) = %d, %v; want %d, true", tc.word, got, ok, tc.want)
|
||||
}
|
||||
}
|
||||
if _, ok := Cardinal("бэкап"); ok {
|
||||
t.Error("Cardinal must not answer for a word that is not a number")
|
||||
}
|
||||
}
|
||||
|
||||
// TestDayOffsetHasNoOrderingTrap — the defect a lookup removes. The callers this
|
||||
// replaced used strings.Contains in a switch, so "послезавтра" had to be tested
|
||||
// before "завтра" by hand or the day after tomorrow read as tomorrow.
|
||||
func TestDayOffsetHasNoOrderingTrap(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
text string
|
||||
want int
|
||||
ok bool
|
||||
}{
|
||||
{"послезавтра", 2, true},
|
||||
{"завтра", 1, true},
|
||||
{"сегодня", 0, true},
|
||||
{"вчера", -1, true},
|
||||
{"позавчера", -2, true},
|
||||
{"встреча послезавтра в 14:30", 2, true},
|
||||
{"Tomorrow at 09:00", 1, true},
|
||||
{"не сегодня, а послезавтра", 2, true},
|
||||
{"в четверг", 0, false},
|
||||
{"завтраком", 0, false},
|
||||
} {
|
||||
got, ok := DayOffsetIn(tc.text)
|
||||
if ok != tc.ok || (ok && got != tc.want) {
|
||||
t.Errorf("DayOffsetIn(%q) = %d, %v; want %d, %v", tc.text, got, ok, tc.want, tc.ok)
|
||||
}
|
||||
}
|
||||
// "сегодня" is offset 0, which is also the zero value, so the second return
|
||||
// is the only thing that separates a hit from a miss.
|
||||
if n, ok := DayOffset("сегодня"); n != 0 || !ok {
|
||||
t.Errorf("DayOffset(сегодня) = %d, %v; want 0, true", n, ok)
|
||||
}
|
||||
}
|
||||
|
||||
// TestIndexedSetsLineUpWithTheirCallers — weekdays start at Sunday because Go's
|
||||
// time.Weekday does, and months are 1-indexed so a month number needs no
|
||||
// arithmetic. Off-by-one here is a wrong date spoken out loud.
|
||||
func TestIndexedSetsLineUpWithTheirCallers(t *testing.T) {
|
||||
if got := Weekday(0); got != "воскресенье" {
|
||||
t.Errorf("Weekday(0) = %q, want воскресенье", got)
|
||||
}
|
||||
if got := Weekday(1); got != "понедельник" {
|
||||
t.Errorf("Weekday(1) = %q, want понедельник", got)
|
||||
}
|
||||
if got := MonthGenitive(1); got != "января" {
|
||||
t.Errorf("MonthGenitive(1) = %q, want января", got)
|
||||
}
|
||||
if got := MonthGenitive(12); got != "декабря" {
|
||||
t.Errorf("MonthGenitive(12) = %q, want декабря", got)
|
||||
}
|
||||
if got := MonthGenitive(0); got != "" {
|
||||
t.Errorf("MonthGenitive(0) = %q, want the empty slot", got)
|
||||
}
|
||||
if got := HourSpoken(23); got != "двадцать три" {
|
||||
t.Errorf("HourSpoken(23) = %q, want двадцать три", got)
|
||||
}
|
||||
for _, i := range []int{-1, 7, 13, 24} {
|
||||
if got := Weekday(i); i >= 7 && got != "" {
|
||||
t.Errorf("Weekday(%d) = %q, want empty", i, got)
|
||||
}
|
||||
}
|
||||
if got := HourSpoken(24); got != "" {
|
||||
t.Errorf("HourSpoken(24) = %q, want empty", got)
|
||||
}
|
||||
}
|
||||
|
||||
// TestCallerCannotEditTheLexicon — the sets are handed out as copies. A caller
|
||||
// that sorted the slice it was given would otherwise reorder weekdays for
|
||||
// everybody.
|
||||
func TestCallerCannotEditTheLexicon(t *testing.T) {
|
||||
first := Interrogatives()
|
||||
first[0] = "мутировало"
|
||||
if again := Interrogatives(); again[0] == "мутировало" {
|
||||
t.Fatal("the lexicon handed out its own backing array")
|
||||
}
|
||||
}
|
||||
+30
-34
@@ -3,8 +3,11 @@ package memory
|
||||
import (
|
||||
"fmt"
|
||||
"sort"
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/say"
|
||||
)
|
||||
|
||||
// Behavioural memory — "what do I usually do?" (Vikunja #254).
|
||||
@@ -337,13 +340,14 @@ func (p Profile) FormatWeekdayRU(wd time.Weekday) string {
|
||||
day := weekdayRU[int(wd)%7]
|
||||
acts := p.Weekly[wd]
|
||||
if len(acts) > 0 {
|
||||
return fmt.Sprintf("по %s ты обычно %s.", day, joinActivities(acts))
|
||||
return say.S(say.HabitWeekday, map[string]string{"day": day, "items": joinActivities(acts)})
|
||||
}
|
||||
if len(p.Everyday) > 0 {
|
||||
return fmt.Sprintf("по %s у тебя нет ничего особенного — то же, что и в остальные дни: %s.",
|
||||
day, joinActivities(p.Everyday))
|
||||
return say.S(say.HabitWeekdaySame, map[string]string{
|
||||
"day": day, "items": joinActivities(p.Everyday),
|
||||
})
|
||||
}
|
||||
return fmt.Sprintf("по %s я пока не вижу у тебя ничего постоянного.", day)
|
||||
return say.S(say.HabitWeekdayNone, map[string]string{"day": day})
|
||||
}
|
||||
|
||||
// FormatWeekendRU reads back what distinguishes Saturday and Sunday.
|
||||
@@ -355,19 +359,17 @@ func (p Profile) FormatWeekendRU() string {
|
||||
sat, sun := p.Weekly[time.Saturday], p.Weekly[time.Sunday]
|
||||
switch {
|
||||
case len(sat) > 0 && len(sun) > 0:
|
||||
return fmt.Sprintf("по субботам ты обычно %s, по воскресеньям — %s.",
|
||||
joinActivities(sat), joinActivities(sun))
|
||||
return say.S(say.HabitWeekendBoth, map[string]string{
|
||||
"items_sat": joinActivities(sat), "items_sun": joinActivities(sun),
|
||||
})
|
||||
case len(sat) > 0:
|
||||
return fmt.Sprintf("по субботам ты обычно %s, а по воскресеньям ничего постоянного.",
|
||||
joinActivities(sat))
|
||||
return say.S(say.HabitWeekendSat, map[string]string{"items": joinActivities(sat)})
|
||||
case len(sun) > 0:
|
||||
return fmt.Sprintf("по воскресеньям ты обычно %s, а по субботам ничего постоянного.",
|
||||
joinActivities(sun))
|
||||
return say.S(say.HabitWeekendSun, map[string]string{"items": joinActivities(sun)})
|
||||
case len(p.Everyday) > 0:
|
||||
return fmt.Sprintf("по выходным у тебя нет ничего особенного — то же, что и в остальные дни: %s.",
|
||||
joinActivities(p.Everyday))
|
||||
return say.S(say.HabitWeekendSame, map[string]string{"items": joinActivities(p.Everyday)})
|
||||
}
|
||||
return "по выходным я пока не вижу у тебя ничего постоянного."
|
||||
return say.S(say.HabitWeekendNone, nil)
|
||||
}
|
||||
|
||||
// FormatOverallRU reads back the habits that hold across the whole week, and
|
||||
@@ -378,33 +380,23 @@ func (p Profile) FormatWeekendRU() string {
|
||||
// a year of them, and only one of those is worth believing.
|
||||
func (p Profile) FormatOverallRU() string {
|
||||
if len(p.All) == 0 {
|
||||
return "я ещё не набрала достаточно записей, чтобы говорить о привычках."
|
||||
return say.S(say.HabitOverallNone, nil)
|
||||
}
|
||||
return fmt.Sprintf("обычно ты %s — %s.", joinActivities(p.All), p.spanRU())
|
||||
return say.S(say.HabitOverall, map[string]string{
|
||||
"items": joinActivities(p.All), "span": p.spanRU(),
|
||||
})
|
||||
}
|
||||
|
||||
// spanRU — "по записям за последние N дней", or a vaguer phrase when the window
|
||||
// is too short to name in days.
|
||||
func (p Profile) spanRU() string {
|
||||
if p.Since.IsZero() || !p.Until.After(p.Since) {
|
||||
return "по записям за сегодня"
|
||||
return say.S(say.HabitSpanToday, nil)
|
||||
}
|
||||
days := int(p.Until.Sub(p.Since).Hours()/24) + 1
|
||||
return fmt.Sprintf("по записям за последние %d %s", days, pluralDaysRU(days))
|
||||
}
|
||||
|
||||
// pluralDaysRU — the Russian count form of "день" for n.
|
||||
func pluralDaysRU(n int) string {
|
||||
switch {
|
||||
case n%100 >= 11 && n%100 <= 14:
|
||||
return "дней"
|
||||
case n%10 == 1:
|
||||
return "день"
|
||||
case n%10 >= 2 && n%10 <= 4:
|
||||
return "дня"
|
||||
default:
|
||||
return "дней"
|
||||
}
|
||||
return say.S(say.HabitSpanDays, map[string]string{
|
||||
"n": strconv.Itoa(days), "word": say.Days(days),
|
||||
})
|
||||
}
|
||||
|
||||
// maxRecited bounds a spoken profile. A list of fifteen habits read aloud is
|
||||
@@ -423,14 +415,18 @@ func joinActivities(acts []Activity) string {
|
||||
// come from the model, so an unglossed one is as likely to be
|
||||
// "выпил_воды" as a noun, and "обычно ты выпил_воды около 09:00" is
|
||||
// not a sentence.
|
||||
gloss = fmt.Sprintf("отмечаешь «%s»", strings.ReplaceAll(a.Key, "_", " "))
|
||||
gloss = say.S(say.HabitUnglossed, map[string]string{
|
||||
"key": strings.ReplaceAll(a.Key, "_", " "),
|
||||
})
|
||||
}
|
||||
if !a.HasTypical {
|
||||
parts[i] = gloss
|
||||
continue
|
||||
}
|
||||
parts[i] = fmt.Sprintf("%s около %02d:%02d", gloss,
|
||||
int(a.TypicalAt.Hours()), int(a.TypicalAt.Minutes())%60)
|
||||
parts[i] = say.S(say.HabitAt, map[string]string{
|
||||
"gloss": gloss,
|
||||
"time": fmt.Sprintf("%02d:%02d", int(a.TypicalAt.Hours()), int(a.TypicalAt.Minutes())%60),
|
||||
})
|
||||
}
|
||||
if len(parts) == 1 {
|
||||
return parts[0]
|
||||
|
||||
@@ -5,6 +5,8 @@ import (
|
||||
"testing"
|
||||
"time"
|
||||
"unicode"
|
||||
|
||||
"github.com/kami/maven/internal/say"
|
||||
)
|
||||
|
||||
// habitHistory — n weeks of the same weekday, at the given local time.
|
||||
@@ -70,7 +72,7 @@ func TestBuildProfileNeedsMoreThanOneDay(t *testing.T) {
|
||||
if len(p.All) != 0 || len(p.Weekly) != 0 {
|
||||
t.Fatalf("one day of rows must produce no habit: %+v / %+v", p.All, p.Weekly)
|
||||
}
|
||||
if got := p.FormatOverallRU(); !strings.Contains(got, "не набрала достаточно") {
|
||||
if got := p.FormatOverallRU(); !say.IsS(say.HabitOverallNone, nil, got) {
|
||||
t.Errorf("empty profile reads %q", got)
|
||||
}
|
||||
}
|
||||
@@ -124,7 +126,7 @@ func TestProfileFormatRUPersona(t *testing.T) {
|
||||
if got != want {
|
||||
t.Errorf("got %q\nwant %q", got, want)
|
||||
}
|
||||
if empty := p.FormatWeekdayRU(time.Thursday); !strings.Contains(empty, "ничего постоянного") {
|
||||
if empty := p.FormatWeekdayRU(time.Thursday); !strings.Contains(empty, "постоянного") {
|
||||
t.Errorf("an unknown weekday reads %q", empty)
|
||||
}
|
||||
// Persona: she addresses him informally, never in the masculine about
|
||||
@@ -203,7 +205,9 @@ func TestWeekdayProfileExcludesEverydayHabits(t *testing.T) {
|
||||
// A day with nothing of its own says so rather than reciting water as if
|
||||
// Wednesday were the reason for it.
|
||||
wed := p.FormatWeekdayRU(time.Wednesday)
|
||||
if !strings.Contains(wed, "ничего особенного") || !strings.Contains(wed, "воду") {
|
||||
if !say.IsS(say.HabitWeekdaySame, map[string]string{
|
||||
"day": "средам", "items": "пьёшь воду около 13:30",
|
||||
}, wed) {
|
||||
t.Fatalf("plain weekday readout should say the day is unremarkable and name the daily habits: %q", wed)
|
||||
}
|
||||
}
|
||||
@@ -313,16 +317,19 @@ func TestOverallNamesThePeriod(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// The no-data weekday answer is about him, not about her. "у меня пока нет
|
||||
// ничего постоянного" answers a question nobody asked.
|
||||
func TestEmptyWeekdayAnswerIsAboutHim(t *testing.T) {
|
||||
// The no-data weekday answer is about his week, not about her. "у меня пока нет
|
||||
// ничего постоянного" answers a question nobody asked. It does say "я не вижу",
|
||||
// because what she is reporting is the state of her records — and it names the
|
||||
// day, which is what makes it an answer to what he asked (Vikunja #521: "у тебя"
|
||||
// came out as filler, the day carries it).
|
||||
func TestEmptyWeekdayAnswerIsAboutHisWeek(t *testing.T) {
|
||||
p := BuildProfile(nil, behaviorNow())
|
||||
got := p.FormatWeekdayRU(time.Wednesday)
|
||||
if strings.Contains(got, "у меня") {
|
||||
t.Errorf("got %q", got)
|
||||
}
|
||||
if !strings.Contains(got, "у тебя") {
|
||||
t.Errorf("got %q, want an answer about him", got)
|
||||
if !strings.Contains(got, "средам") {
|
||||
t.Errorf("got %q, want the day he asked about", got)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -340,17 +347,6 @@ func TestQuietPrefixDoesNotSwallowRealKeys(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestPluralDaysRU(t *testing.T) {
|
||||
for _, c := range []struct {
|
||||
n int
|
||||
want string
|
||||
}{{1, "день"}, {2, "дня"}, {5, "дней"}, {11, "дней"}, {21, "день"}, {22, "дня"}, {114, "дней"}} {
|
||||
if got := pluralDaysRU(c.n); got != c.want {
|
||||
t.Errorf("pluralDaysRU(%d) = %q, want %q", c.n, got, c.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// "по выходным" is a question about two days, answered as two days.
|
||||
func TestFormatWeekendRU(t *testing.T) {
|
||||
now := behaviorNow()
|
||||
|
||||
@@ -6,6 +6,7 @@ import (
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/say"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
@@ -164,17 +165,20 @@ func (p Plan) FormatRU() string {
|
||||
// it is over, and saying it was empty is a false statement about a day
|
||||
// he just lived.
|
||||
if p.Rest {
|
||||
return "на сегодня больше ничего не запланировано."
|
||||
return say.S(say.PlanRestEmpty, nil)
|
||||
}
|
||||
return fmt.Sprintf("на %s ничего не запланировано.", p.Date.Format("02.01.2006"))
|
||||
return say.S(say.PlanDayEmpty, map[string]string{"date": p.Date.Format("02.01.2006")})
|
||||
}
|
||||
parts := make([]string, len(p.Items))
|
||||
for i, it := range p.Items {
|
||||
line := fmt.Sprintf("%s — %s", it.At.Format("15:04"), it.Text)
|
||||
if it.Uncertain {
|
||||
line = "похоже, " + line
|
||||
line = say.S(say.PlanUncertain, map[string]string{"line": line})
|
||||
}
|
||||
parts[i] = line
|
||||
}
|
||||
return fmt.Sprintf("план на %s: %s.", p.Date.Format("02.01.2006"), strings.Join(parts, "; "))
|
||||
return say.S(say.PlanDay, map[string]string{
|
||||
"date": p.Date.Format("02.01.2006"),
|
||||
"items": strings.Join(parts, "; "),
|
||||
})
|
||||
}
|
||||
|
||||
@@ -4,6 +4,7 @@ import (
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
"unicode"
|
||||
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
@@ -137,7 +138,7 @@ func TestPlanFormatRU(t *testing.T) {
|
||||
want := "план на 03.08.2026: 10:00 — Standup @ 10:00-10:30; " +
|
||||
"10:30 — утро — осталось: витамины; " +
|
||||
"похоже, 14:00 — Планёрка @ 14:00-14:30; " +
|
||||
"18:30 — позвонить маме."
|
||||
"18:30 — позвонить маме"
|
||||
if got != want {
|
||||
t.Errorf("got %q\nwant %q", got, want)
|
||||
}
|
||||
@@ -215,3 +216,26 @@ func TestBuildPlanIgnoresAnUnopenedWindow(t *testing.T) {
|
||||
t.Fatalf("got %+v", p.Items)
|
||||
}
|
||||
}
|
||||
|
||||
// plan_uncertain nests one rendered line inside another sentence: «похоже, » in
|
||||
// front of what this loop already built. That reads as one sentence only while
|
||||
// what arrives starts lowercase, and it does here because every line starts with
|
||||
// the clock time. A capital after the hedge would be «похоже, Планёрка».
|
||||
func TestTheUncertainHedgeRunsIntoLowercase(t *testing.T) {
|
||||
now := time.Date(2026, 8, 3, 9, 0, 0, 0, time.UTC)
|
||||
p := Plan{Date: now, Items: []PlanEntry{
|
||||
{At: planAt(now, 14, 0), Text: "Планёрка", Kind: PlanEvent, Uncertain: true},
|
||||
}}
|
||||
got := p.FormatRU()
|
||||
const hedge = "похоже, "
|
||||
i := strings.Index(got, hedge)
|
||||
if i < 0 {
|
||||
t.Fatalf("%q does not hedge an uncertain item", got)
|
||||
}
|
||||
for _, r := range got[i+len(hedge):] {
|
||||
if unicode.IsUpper(r) {
|
||||
t.Fatalf("the hedge runs into a capital: %q", got)
|
||||
}
|
||||
break
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,127 @@
|
||||
// Package morph answers questions about Russian grammar from a dictionary.
|
||||
//
|
||||
// The second of the three mechanisms replacing hand-written Russian patterns
|
||||
// (Vikunja #522, owner's call 2026-08-04). internal/lexicon holds the sets that
|
||||
// can be finished; the embedder recognises an open set of phrasings; and this
|
||||
// package answers the questions that are about grammar rather than meaning:
|
||||
//
|
||||
// - is this word a form of a verb, so it carries its own subject?
|
||||
// - are these two tokens the same word in different cases?
|
||||
//
|
||||
// Three places used to answer those from a list of letter endings, and each list
|
||||
// was wrong in a way its own comment admitted. "канал" read as a past-tense verb
|
||||
// because it ends in -ал. A list of nineteen nouns ending in л existed only to
|
||||
// suppress the false positives of "ends in л means masculine past tense", which
|
||||
// is a pattern conceding it is wrong. Grammar is what a dictionary is for.
|
||||
//
|
||||
// Not the resident model. This has to be right every time, offline, in
|
||||
// microseconds, and a 1.7B is neither reliable enough nor fast enough to ask.
|
||||
//
|
||||
// The dictionary is github.com/aaaton/golem's Russian data, vendored. It is
|
||||
// embedded in the module, so a load failure is not a network problem and not a
|
||||
// config problem — it is corrupt data that got past the build. Every function
|
||||
// answers conservatively in that case rather than failing the turn, and says so
|
||||
// in its own doc comment.
|
||||
package morph
|
||||
|
||||
import (
|
||||
"log"
|
||||
"strings"
|
||||
"sync"
|
||||
|
||||
"github.com/aaaton/golem/v4"
|
||||
"github.com/aaaton/golem/v4/dicts/ru"
|
||||
)
|
||||
|
||||
var (
|
||||
once sync.Once
|
||||
lemma *golem.Lemmatizer
|
||||
loadErr error
|
||||
)
|
||||
|
||||
// dict loads the lemmatizer on first use. Loading costs a few megabytes of maps,
|
||||
// which is why it is not done at init: a daemon that never sees Russian never
|
||||
// pays for it.
|
||||
func dict() *golem.Lemmatizer {
|
||||
once.Do(func() {
|
||||
lemma, loadErr = golem.New(ru.New())
|
||||
if loadErr != nil {
|
||||
// Once, not per call: this is a permanent condition and a voice loop
|
||||
// would otherwise fill the log with it at speech rate.
|
||||
log.Printf("morph: russian dictionary unavailable, answering conservatively: %v", loadErr)
|
||||
}
|
||||
})
|
||||
return lemma
|
||||
}
|
||||
|
||||
// Available reports whether the dictionary loaded. Callers do not need it to be
|
||||
// correct — every function below has a defined answer without it — but a test
|
||||
// that means to measure the dictionary should skip rather than pass vacuously.
|
||||
func Available() bool {
|
||||
dict()
|
||||
return loadErr == nil
|
||||
}
|
||||
|
||||
// Lemma returns the dictionary form of a word, or the word itself when the
|
||||
// dictionary does not know it or could not load. An unknown word is its own
|
||||
// lemma: "бэкап" is not in the dictionary and there is nothing better to say
|
||||
// about it than what he said.
|
||||
func Lemma(word string) string {
|
||||
w := strings.ToLower(strings.TrimSpace(word))
|
||||
if w == "" {
|
||||
return ""
|
||||
}
|
||||
l := dict()
|
||||
if l == nil {
|
||||
return w
|
||||
}
|
||||
if got := l.Lemma(w); got != "" {
|
||||
return got
|
||||
}
|
||||
return w
|
||||
}
|
||||
|
||||
// infinitiveEndings — how a Russian infinitive ends. This is not a stem pattern:
|
||||
// it is applied to a LEMMA the dictionary returned, where the infinitive is the
|
||||
// dictionary form of every verb by definition, so the test is about the
|
||||
// dictionary's own output and not about the word he said.
|
||||
//
|
||||
// The reflexive forms are listed because a reflexive lemma keeps its particle:
|
||||
// "тренировался" lemmatises to "тренироваться", which ends in "ся" rather than
|
||||
// "ть".
|
||||
var infinitiveEndings = []string{"ться", "тись", "чься", "ть", "ти", "чь"}
|
||||
|
||||
// IsVerbForm reports whether a word is some form of a verb — past tense, present,
|
||||
// imperative, reflexive, participle. A verb carries its own subject and tense, so
|
||||
// in Russian one verb is a whole sentence, which is what the callers care about.
|
||||
//
|
||||
// Without the dictionary this answers false: not knowing is not evidence that a
|
||||
// word IS a verb, and the callers all treat false as the cautious direction.
|
||||
func IsVerbForm(word string) bool {
|
||||
if dict() == nil {
|
||||
return false
|
||||
}
|
||||
l := Lemma(word)
|
||||
for _, e := range infinitiveEndings {
|
||||
if strings.HasSuffix(l, e) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// SameWord reports whether two tokens are the same word in different cases —
|
||||
// "режим" and "режиме", "тихий" and "тихо". It is the test a stem-plus-endings
|
||||
// comparison was approximating, and it draws the line the ending list could not:
|
||||
// "тихонько" and "потихоньку" are different words, and the dictionary says so
|
||||
// because it has never heard of either.
|
||||
//
|
||||
// Without the dictionary this falls back to exact equality, which is the
|
||||
// narrowest honest answer.
|
||||
func SameWord(a, b string) bool {
|
||||
la, lb := Lemma(a), Lemma(b)
|
||||
if la == "" || lb == "" {
|
||||
return false
|
||||
}
|
||||
return la == lb
|
||||
}
|
||||
@@ -0,0 +1,96 @@
|
||||
package morph
|
||||
|
||||
import "testing"
|
||||
|
||||
// TestVerbFormsAreVerbs — the question internal/router/singletoken.go asks. Every
|
||||
// one of these is a whole sentence in Russian, because the verb carries its own
|
||||
// subject, tense and gender.
|
||||
func TestVerbFormsAreVerbs(t *testing.T) {
|
||||
if !Available() {
|
||||
t.Skip("russian dictionary unavailable")
|
||||
}
|
||||
for _, w := range []string{
|
||||
"поужинал", "сходил", "выпил", "напомнил", "поняла", "сделала",
|
||||
"пришёл", "начал", "работаешь", "занимаюсь",
|
||||
// Reflexive: the lemma keeps its particle, so "тренироваться" ends in
|
||||
// "ся" and not "ть". That is why the ending list carries both.
|
||||
"тренировался", "проснулся",
|
||||
} {
|
||||
if !IsVerbForm(w) {
|
||||
t.Errorf("IsVerbForm(%q) = false, want true (lemma %q)", w, Lemma(w))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestNounsEndingInLAreNotVerbs — the list this package deleted. Nineteen nouns
|
||||
// lived in internal/phraser/eval/checks.go as exceptions to "ends in л means
|
||||
// masculine past tense", plus the ones internal/router/singletoken.go named as
|
||||
// its own known errors. A list of exceptions to a pattern is the pattern
|
||||
// conceding it is wrong, so all of them are here and none may be a verb.
|
||||
func TestNounsEndingInLAreNotVerbs(t *testing.T) {
|
||||
if !Available() {
|
||||
t.Skip("russian dictionary unavailable")
|
||||
}
|
||||
for _, w := range []string{
|
||||
"стол", "стул", "пол", "зал", "гол", "узел", "отдел", "файл", "канал",
|
||||
"угол", "футбол", "вокзал", "металл", "интервал", "уровень", "мускул",
|
||||
"апрель", "июль", "рубль",
|
||||
// singletoken.go named these: "канал" read as past tense, and short
|
||||
// nouns needed a length exemption to survive a two-letter suffix test.
|
||||
"нос", "лес", "газ", "вода", "бэкап",
|
||||
} {
|
||||
if IsVerbForm(w) {
|
||||
t.Errorf("IsVerbForm(%q) = true, want false (lemma %q)", w, Lemma(w))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestSameWordDrawsTheLineTheEndingListCouldNot — the question
|
||||
// cmd/mavend/quiet_toggle.go asks. Its comment describes exactly this: "тихий",
|
||||
// "тихом" and "тихо" are one word inflected, while "тихонько" and "потихоньку"
|
||||
// are different words. The dictionary says so; a list of 36 endings approximated
|
||||
// it.
|
||||
func TestSameWordDrawsTheLineTheEndingListCouldNot(t *testing.T) {
|
||||
if !Available() {
|
||||
t.Skip("russian dictionary unavailable")
|
||||
}
|
||||
for _, w := range []string{"тихий", "тихом", "тихо", "тише"} {
|
||||
if !SameWord(w, "тихий") {
|
||||
t.Errorf("SameWord(%q, тихий) = false, want true (lemma %q)", w, Lemma(w))
|
||||
}
|
||||
}
|
||||
for _, w := range []string{"тихонько", "потихоньку"} {
|
||||
if SameWord(w, "тихий") {
|
||||
t.Errorf("SameWord(%q, тихий) = true, want false", w)
|
||||
}
|
||||
}
|
||||
for _, w := range []string{"режим", "режима", "режиме", "режимы"} {
|
||||
if !SameWord(w, "режим") {
|
||||
t.Errorf("SameWord(%q, режим) = false, want true (lemma %q)", w, Lemma(w))
|
||||
}
|
||||
}
|
||||
if SameWord("режим", "тихий") {
|
||||
t.Error("SameWord matched two unrelated words")
|
||||
}
|
||||
}
|
||||
|
||||
// TestUnknownWordIsItsOwnLemma — "бэкап" is not in the dictionary, and there is
|
||||
// nothing better to say about it than what he said. Two spellings of an unknown
|
||||
// word still compare equal, which is what the exact-equality fallback rests on.
|
||||
func TestUnknownWordIsItsOwnLemma(t *testing.T) {
|
||||
if got := Lemma("бэкап"); got != "бэкап" {
|
||||
t.Errorf("Lemma(бэкап) = %q, want бэкап", got)
|
||||
}
|
||||
if got := Lemma(" БЭКАП "); got != "бэкап" {
|
||||
t.Errorf("Lemma trims and lowercases: got %q", got)
|
||||
}
|
||||
if !SameWord("бэкап", "БЭКАП") {
|
||||
t.Error("SameWord must still compare an unknown word with itself")
|
||||
}
|
||||
if got := Lemma(""); got != "" {
|
||||
t.Errorf("Lemma(empty) = %q, want empty", got)
|
||||
}
|
||||
if SameWord("", "") {
|
||||
t.Error("two empty tokens are not a word")
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,84 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"name": "russian capture acknowledgements v1",
|
||||
"notes": [
|
||||
"What she says after storing something he said, and what she says when storing it failed. Edit the wording here, no Go changes needed.",
|
||||
"Rules: she is feminine about herself, he is a man addressed as ты. Never вы/вас/ваш, never он/его about him. No pet names.",
|
||||
"He hears these many times a day, so most entries carry variants: identical wording is what makes a confirmation stop registering as one.",
|
||||
"Placeholders: {key} {value} the fact he stated, {fn} the action, {text} the task title. His data is interpolated Go-side — the file holds the frame, never his words.",
|
||||
"An acknowledgement confirms and stops. It does not ask a follow-up question and it does not editorialise about what he stored."
|
||||
],
|
||||
"entries": {
|
||||
"ack_fact": {
|
||||
"variants": ["записала факт.", "записала.", "запомнила."]
|
||||
},
|
||||
"ack_fact_key": {
|
||||
"variants": ["отметила: {key}", "записала: {key}", "запомнила: {key}"]
|
||||
},
|
||||
"ack_fact_kv": {
|
||||
"variants": ["отметила: {key} = {value}", "записала: {key} — {value}", "запомнила: {key} — {value}"]
|
||||
},
|
||||
"ack_note": {
|
||||
"variants": ["сохранила заметку.", "заметка сохранена.", "записала в заметки."]
|
||||
},
|
||||
"ack_reminder": {
|
||||
"variants": ["напомню.", "напомню, не забуду.", "хорошо, напомню."]
|
||||
},
|
||||
"ack_act": {
|
||||
"variants": ["ок, записала действие: {fn}", "приняла действие: {fn}"]
|
||||
},
|
||||
"ack_task": {
|
||||
"variants": ["записала: {text}", "добавила в задачи: {text}", "внесла в список: {text}"]
|
||||
},
|
||||
"ack_task_urgent": {
|
||||
"variants": ["поняла, беру в работу: {text}", "поняла, это срочно: {text}"]
|
||||
},
|
||||
"ack_task_duplicate": {
|
||||
"variants": ["это уже в списке.", "такое уже есть в задачах."]
|
||||
},
|
||||
"ack_nudge": {
|
||||
"variants": ["отлично, отметила.", "отметила.", "хорошо, отметила."]
|
||||
},
|
||||
"ack_snooze": {
|
||||
"variants": ["хорошо, вернусь к этому позже.", "ладно, напомню попозже.", "хорошо, отложила."]
|
||||
},
|
||||
"ack_generic": {
|
||||
"variants": ["приняла.", "поняла."]
|
||||
},
|
||||
"quiet_on": {
|
||||
"fixed": true,
|
||||
"variants": ["тихий режим включён. буду реже напоминать."]
|
||||
},
|
||||
"quiet_off": {
|
||||
"fixed": true,
|
||||
"variants": ["тихий режим выключен."]
|
||||
},
|
||||
"fail_fact": {
|
||||
"variants": ["не получилось сохранить факт.", "факт не сохранился."]
|
||||
},
|
||||
"fail_note": {
|
||||
"variants": ["не получилось сохранить заметку.", "заметка не сохранилась."]
|
||||
},
|
||||
"fail_reminder": {
|
||||
"variants": ["не получилось поставить напоминание.", "напоминание не поставилось."]
|
||||
},
|
||||
"fail_reminder_time": {
|
||||
"variants": ["не получилось разобрать время напоминания.", "не поняла, на когда напомнить."]
|
||||
},
|
||||
"fail_task": {
|
||||
"variants": ["не получилось записать задачу.", "задача не записалась."]
|
||||
},
|
||||
"fail_ack": {
|
||||
"variants": ["не получилось отметить.", "не смогла отметить."]
|
||||
},
|
||||
"fail_snooze": {
|
||||
"variants": ["не получилось отложить.", "не смогла отложить."]
|
||||
},
|
||||
"fail_quiet": {
|
||||
"variants": ["не получилось переключить тихий режим.", "тихий режим не переключился."]
|
||||
},
|
||||
"fail_fact_unparsed": {
|
||||
"variants": ["не разобрала, что записать — попробуй иначе.", "не поняла, что записать. скажи иначе?"]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,164 @@
|
||||
package phraser
|
||||
|
||||
// The capture acknowledgements — what she says after storing something he said,
|
||||
// and what she says when storing it failed.
|
||||
//
|
||||
// They were string literals in eight files under cmd/mavend plus the stub
|
||||
// replier in internal/voice. He hears them many times a day, which is exactly
|
||||
// why they need variants and exactly why rewording one must not be a rebuild.
|
||||
// Same shape as fallbacks_ru_v1.json, on the shared deck (deck.go).
|
||||
//
|
||||
// His data stays Go-side. The file holds "отметила: {key} = {value}"; the key
|
||||
// and the value are interpolated here, so nothing he said lives in the copy.
|
||||
|
||||
import (
|
||||
_ "embed"
|
||||
"log"
|
||||
"math/rand"
|
||||
"sync"
|
||||
|
||||
"github.com/kami/maven/internal/say"
|
||||
)
|
||||
|
||||
//go:embed ack_ru_v1.json
|
||||
var ackJSON []byte
|
||||
|
||||
// AckSchemaVersion — this family's own version. A file that changes on a
|
||||
// different day than the fallbacks cannot share their number (Vikunja #397).
|
||||
const AckSchemaVersion = 1
|
||||
|
||||
// The entry keys. Namespaced by family, because the floor map behind a nil deck
|
||||
// is process-wide.
|
||||
const (
|
||||
AckFact = "ack_fact"
|
||||
AckFactKey = "ack_fact_key"
|
||||
AckFactValue = "ack_fact_kv"
|
||||
AckNote = "ack_note"
|
||||
AckReminder = "ack_reminder"
|
||||
AckAct = "ack_act"
|
||||
AckTask = "ack_task"
|
||||
AckTaskUrgent = "ack_task_urgent"
|
||||
AckTaskDuplicate = "ack_task_duplicate"
|
||||
AckNudge = "ack_nudge"
|
||||
AckSnooze = "ack_snooze"
|
||||
AckGeneric = "ack_generic"
|
||||
AckQuietOn = "quiet_on"
|
||||
AckQuietOff = "quiet_off"
|
||||
|
||||
FailFact = "fail_fact"
|
||||
FailFactUnparsed = "fail_fact_unparsed"
|
||||
FailNote = "fail_note"
|
||||
FailReminder = "fail_reminder"
|
||||
FailReminderTime = "fail_reminder_time"
|
||||
FailTask = "fail_task"
|
||||
FailAck = "fail_ack"
|
||||
FailSnooze = "fail_snooze"
|
||||
FailQuiet = "fail_quiet"
|
||||
)
|
||||
|
||||
// ackKeys — every key the code requires the file to define.
|
||||
var ackKeys = []string{
|
||||
AckFact, AckFactKey, AckFactValue, AckNote, AckReminder, AckAct,
|
||||
AckTask, AckTaskUrgent, AckTaskDuplicate, AckNudge, AckSnooze, AckGeneric,
|
||||
AckQuietOn, AckQuietOff,
|
||||
FailFact, FailFactUnparsed, FailNote, FailReminder, FailReminderTime,
|
||||
FailTask, FailAck, FailSnooze, FailQuiet,
|
||||
}
|
||||
|
||||
// ackFloor — the literal each key falls back to when the file is unusable.
|
||||
// These are the exact strings that lived in Go before this file existed.
|
||||
var ackFloor = map[string]string{
|
||||
AckFact: "записала факт.",
|
||||
AckFactKey: "отметила: {key}",
|
||||
AckFactValue: "отметила: {key} = {value}",
|
||||
AckNote: "сохранила заметку.",
|
||||
AckReminder: "напомню.",
|
||||
AckAct: "ок, записала действие: {fn}",
|
||||
AckTask: "записала: {text}",
|
||||
AckTaskUrgent: "поняла, беру в работу: {text}",
|
||||
AckTaskDuplicate: "это уже в списке.",
|
||||
AckNudge: "отлично, отметила.",
|
||||
AckSnooze: "хорошо, вернусь к этому позже.",
|
||||
AckGeneric: "приняла.",
|
||||
AckQuietOn: "тихий режим включён. буду реже напоминать.",
|
||||
AckQuietOff: "тихий режим выключен.",
|
||||
|
||||
FailFact: "не получилось сохранить факт.",
|
||||
FailFactUnparsed: "не разобрала, что записать — попробуй иначе.",
|
||||
FailNote: "не получилось сохранить заметку.",
|
||||
FailReminder: "не получилось поставить напоминание.",
|
||||
FailReminderTime: "не получилось разобрать время напоминания.",
|
||||
FailTask: "не получилось записать задачу.",
|
||||
FailAck: "не получилось отметить.",
|
||||
FailSnooze: "не получилось отложить.",
|
||||
FailQuiet: "не получилось переключить тихий режим.",
|
||||
}
|
||||
|
||||
// Acks picks a hand-written Russian acknowledgement. Safe for concurrent use.
|
||||
type Acks struct{ d *say.Deck }
|
||||
|
||||
// LoadAcks reads the embedded file. Pass a source to make the picking
|
||||
// reproducible in tests; nil seeds from the clock.
|
||||
func LoadAcks(src rand.Source) (*Acks, error) {
|
||||
d, err := say.Load(ackJSON, AckSchemaVersion, ackKeys, ackFloor, src)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
// The three entries that exist to read his own words back. A variant
|
||||
// without the placeholder would confirm the capture and drop what was
|
||||
// captured, which reads as a successful save of nothing.
|
||||
for _, req := range []struct{ key, ph string }{
|
||||
{AckFactKey, "{key}"}, {AckFactValue, "{key}"}, {AckFactValue, "{value}"},
|
||||
{AckAct, "{fn}"}, {AckTask, "{text}"}, {AckTaskUrgent, "{text}"},
|
||||
} {
|
||||
if err := d.RequirePlaceholder(req.key, req.ph); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
return &Acks{d: d}, nil
|
||||
}
|
||||
|
||||
// deck reads through a nil *Acks, which is the unloadable-file case.
|
||||
func (a *Acks) deck() *say.Deck {
|
||||
if a == nil {
|
||||
return say.FloorDeck(ackFloor)
|
||||
}
|
||||
return a.d
|
||||
}
|
||||
|
||||
// Say returns one line for key, with his data filled into the frame. Pass nil
|
||||
// when the entry takes none.
|
||||
func (a *Acks) Say(key string, vars map[string]string) string {
|
||||
return a.deck().Text(key, vars)
|
||||
}
|
||||
|
||||
// Variants returns every line the file can produce, for the persona scorer.
|
||||
func (a *Acks) Variants() []string { return a.deck().Variants() }
|
||||
|
||||
var (
|
||||
ackOnce sync.Once
|
||||
acks *Acks
|
||||
)
|
||||
|
||||
// DefaultAcks returns the shared instance, loading it on first use. A broken
|
||||
// file logs once and leaves a nil *Acks, which still answers from ackFloor.
|
||||
func DefaultAcks() *Acks {
|
||||
ackOnce.Do(func() {
|
||||
a, err := LoadAcks(nil)
|
||||
if err != nil {
|
||||
log.Printf("phraser: acknowledgements unavailable, using the built-in lines: %v", err)
|
||||
return
|
||||
}
|
||||
acks = a
|
||||
})
|
||||
return acks
|
||||
}
|
||||
|
||||
// Ack — one acknowledgement line, the way every caller says it.
|
||||
func Ack(key string, vars map[string]string) string { return DefaultAcks().Say(key, vars) }
|
||||
|
||||
// IsAck reports whether text is a line key could have produced. For the daemon
|
||||
// tests, which can no longer compare against one literal.
|
||||
func IsAck(key string, vars map[string]string, text string) bool {
|
||||
return DefaultAcks().deck().Matches(key, vars, text)
|
||||
}
|
||||
@@ -0,0 +1,85 @@
|
||||
package phraser
|
||||
|
||||
import (
|
||||
"math/rand"
|
||||
"strconv"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func loadTestActs(t *testing.T) *Acts {
|
||||
t.Helper()
|
||||
a, err := LoadActs(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadActs: %v", err)
|
||||
}
|
||||
return a
|
||||
}
|
||||
|
||||
// She talks about a lamp or a server, never about a row in a schema. «сущность»
|
||||
// and «экосистема» are the same defect as saying a capability id out loud.
|
||||
func TestNoActLineSaysASchemaWord(t *testing.T) {
|
||||
a := loadTestActs(t)
|
||||
for _, v := range a.Variants() {
|
||||
for _, word := range []string{"сущност", "экосистем"} {
|
||||
if strings.Contains(v, word) {
|
||||
t.Errorf("variant %q says %q out loud", v, word)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Nexus, Praxis and Hexis fail independently, so "не отвечает" with no subject
|
||||
// is not an answer he can act on.
|
||||
func TestAServiceFailureNamesTheService(t *testing.T) {
|
||||
a := loadTestActs(t)
|
||||
for _, key := range []string{EcoDown, EcoDenied} {
|
||||
got := a.Say(key, map[string]string{"name": "Praxis"})
|
||||
if !strings.HasPrefix(got, "Praxis ") {
|
||||
t.Errorf("%s = %q, want it to name the service", key, got)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// A confirmation prompt for a destructive act is the worst place for an unfilled
|
||||
// placeholder, so the two names it interpolates are distinct keys and both are
|
||||
// declared.
|
||||
func TestConfirmEntityFillsBothNames(t *testing.T) {
|
||||
a := loadTestActs(t)
|
||||
got := a.Say(ActConfirmEntity, map[string]string{
|
||||
"name": "restart", "name_entity": "Muzick indexer",
|
||||
})
|
||||
if strings.ContainsAny(got, "{}") {
|
||||
t.Fatalf("act_confirm_entity = %q, want no placeholder left", got)
|
||||
}
|
||||
if !strings.Contains(got, "restart") || !strings.Contains(got, "Muzick indexer") {
|
||||
t.Fatalf("act_confirm_entity = %q, want both names", got)
|
||||
}
|
||||
}
|
||||
|
||||
// home_dark counts unreachable devices, and Russian inflects the noun after the
|
||||
// number: the count goes in {count} and the noun comes from the helper.
|
||||
func TestHomeDarkCountsWithTheHelper(t *testing.T) {
|
||||
a := loadTestActs(t)
|
||||
for n, want := range map[int]string{1: "1 устройство", 2: "2 устройства", 5: "5 устройств"} {
|
||||
got := a.Say(HomeDark, map[string]string{"count": strconv.Itoa(n), "word": Devices(n)})
|
||||
if !strings.Contains(got, want) {
|
||||
t.Errorf("home_dark for %d = %q, want %q in it", n, got, want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Four truths, four entries: a failure must not be able to report itself as a
|
||||
// success, and an empty result must not read as a failure.
|
||||
func TestActOutcomesStayDistinct(t *testing.T) {
|
||||
a := loadTestActs(t)
|
||||
seen := map[string]string{}
|
||||
for _, key := range actKeys {
|
||||
for _, v := range a.d.VariantsOf(key) {
|
||||
if prev, dup := seen[v]; dup {
|
||||
t.Errorf("%s and %s both say %q", prev, key, v)
|
||||
}
|
||||
seen[v] = key
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,197 @@
|
||||
package phraser
|
||||
|
||||
// The act and smart-home replies — what she says when a capability ran, refused,
|
||||
// or could not be reached.
|
||||
//
|
||||
// Fourth family on the shared deck (deck.go). They were literals in
|
||||
// ecosystem_acts.go, actions_act.go and smarthome.go, where a reworded line was
|
||||
// a rebuild of the daemon that executes his house.
|
||||
//
|
||||
// The four outcomes stay four entries. Reporting a refusal with the wording of
|
||||
// a success is the one failure mode this family can have, and a shared variant
|
||||
// set is how it would happen.
|
||||
|
||||
import (
|
||||
_ "embed"
|
||||
"log"
|
||||
"math/rand"
|
||||
"sync"
|
||||
|
||||
"github.com/kami/maven/internal/say"
|
||||
)
|
||||
|
||||
//go:embed acts_ru_v1.json
|
||||
var actJSON []byte
|
||||
|
||||
// ActSchemaVersion — this family's own version.
|
||||
const ActSchemaVersion = 1
|
||||
|
||||
// The entry keys.
|
||||
const (
|
||||
ActDone = "act_done"
|
||||
ActDoneOut = "act_done_out"
|
||||
ActDoneEntity = "act_done_entity"
|
||||
ActConfirm = "act_confirm"
|
||||
ActConfirmEntity = "act_confirm_entity"
|
||||
ActWhich = "act_which"
|
||||
ActFail = "act_fail"
|
||||
ActFailOut = "act_fail_out"
|
||||
ActFailEntity = "act_fail_entity"
|
||||
ActServerDown = "act_server_down"
|
||||
ActWithdrawn = "act_withdrawn"
|
||||
ActNeedsArgs = "act_needs_args"
|
||||
// ActNeedsAuthedSurface — the irreversible tier, local row or Hexis
|
||||
// capability alike. Not a failure and not a refusal to help: a spoken "да"
|
||||
// is the only authority the voice path can offer, and this is the one act
|
||||
// it is not enough for (Vikunja #449, #523).
|
||||
ActNeedsAuthedSurface = "act_needs_authed_surface"
|
||||
|
||||
EcoDenied = "eco_denied"
|
||||
EcoDown = "eco_down"
|
||||
EcoAmbiguous = "eco_ambiguous"
|
||||
EcoUnknownEntity = "eco_unknown_entity"
|
||||
EcoNoNexus = "eco_no_nexus"
|
||||
EcoAboutWhat = "eco_about_what"
|
||||
EcoRecall = "eco_recall"
|
||||
|
||||
AttentionNone = "attention_none"
|
||||
AttentionList = "attention_list"
|
||||
AttentionFail = "attention_fail"
|
||||
AttentionNoneEntity = "attention_none_entity"
|
||||
AttentionListEntity = "attention_list_entity"
|
||||
AttentionFailEntity = "attention_fail_entity"
|
||||
ChangesNone = "changes_none"
|
||||
ChangesList = "changes_list"
|
||||
ChangesFail = "changes_fail"
|
||||
HomeUnreachable = "home_unreachable"
|
||||
HomeEmpty = "home_empty"
|
||||
HomeOn = "home_on"
|
||||
HomeDark = "home_dark"
|
||||
)
|
||||
|
||||
var actKeys = []string{
|
||||
ActDone, ActDoneOut, ActDoneEntity, ActConfirm, ActConfirmEntity, ActWhich,
|
||||
ActFail, ActFailOut, ActFailEntity, ActServerDown, ActWithdrawn, ActNeedsArgs,
|
||||
ActNeedsAuthedSurface,
|
||||
EcoDenied, EcoDown, EcoAmbiguous, EcoUnknownEntity, EcoNoNexus, EcoAboutWhat, EcoRecall,
|
||||
AttentionNone, AttentionList, AttentionFail,
|
||||
AttentionNoneEntity, AttentionListEntity, AttentionFailEntity,
|
||||
ChangesNone, ChangesList, ChangesFail,
|
||||
HomeUnreachable, HomeEmpty, HomeOn, HomeDark,
|
||||
}
|
||||
|
||||
// actFloor — the literal each key falls back to when the file is unusable. It
|
||||
// started as the exact strings that lived in Go before this file existed and now
|
||||
// tracks the file's first variant instead, because a floor that keeps the
|
||||
// wording review threw out would say it back on the one turn nobody is watching.
|
||||
var actFloor = map[string]string{
|
||||
ActDone: "готово.",
|
||||
ActDoneOut: "готово: {out}",
|
||||
ActDoneEntity: "готово: {name}.",
|
||||
ActConfirm: "выполнить «{name}»? да или нет.",
|
||||
ActConfirmEntity: "выполнить «{name}» для {name_entity}? да или нет.",
|
||||
ActWhich: "какую команду для {name}: {items}?",
|
||||
ActFail: "не получилось выполнить команду.",
|
||||
ActFailOut: "не получилось выполнить команду: {out}",
|
||||
ActFailEntity: "не получилось выполнить команду для {name}.",
|
||||
ActServerDown: "инструмент есть, но сервер не подключён.",
|
||||
ActWithdrawn: "сервер больше не отдаёт этот инструмент — сняла его с разрешённых, посмотри /tools.",
|
||||
ActNeedsArgs: "тут нужны аргументы, из голоса не соберу. угадывать не буду.",
|
||||
ActNeedsAuthedSurface: "это из голоса не выполню — после него ничего не вернуть. запусти сам.",
|
||||
|
||||
EcoDenied: "{name} отклоняет доступ, проверь токен.",
|
||||
EcoDown: "{name} не отвечает, попробуй ещё раз.",
|
||||
EcoAmbiguous: "что именно: {items}?",
|
||||
EcoUnknownEntity: "не знаю, что это.",
|
||||
EcoNoNexus: "не с чем связать — Nexus не настроен.",
|
||||
EcoAboutWhat: "про что именно?",
|
||||
EcoRecall: "я помню: {items}",
|
||||
|
||||
AttentionNone: "ничего не требует внимания.",
|
||||
AttentionList: "требует внимания: {items}",
|
||||
AttentionFail: "не могу сейчас узнать, что требует внимания.",
|
||||
AttentionNoneEntity: "по «{name}» ничего нет.",
|
||||
AttentionListEntity: "по «{name}»: {items}",
|
||||
AttentionFailEntity: "не могу сейчас узнать, что требует внимания по «{name}».",
|
||||
ChangesNone: "изменений нет.",
|
||||
ChangesList: "изменения: {items}",
|
||||
ChangesFail: "не могу сейчас узнать об изменениях.",
|
||||
HomeUnreachable: "дом не отвечает.",
|
||||
HomeEmpty: "дом ничего не отдаёт.",
|
||||
HomeOn: "включено: {items}",
|
||||
HomeDark: "не отвечают: {count} {word}.",
|
||||
}
|
||||
|
||||
// Acts picks a hand-written Russian act reply. Safe for concurrent use.
|
||||
type Acts struct{ d *say.Deck }
|
||||
|
||||
// LoadActs reads the embedded file. Pass a source to make the picking
|
||||
// reproducible in tests; nil seeds from the clock.
|
||||
func LoadActs(src rand.Source) (*Acts, error) {
|
||||
d, err := say.Load(actJSON, ActSchemaVersion, actKeys, actFloor, src)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
// The entries that name what ran or what he has to choose between. A
|
||||
// variant that dropped the name would confirm an act without saying which.
|
||||
for _, req := range []struct{ key, ph string }{
|
||||
{ActDoneOut, "{out}"}, {ActDoneEntity, "{name}"}, {ActFailOut, "{out}"},
|
||||
{ActFailEntity, "{name}"}, {ActConfirm, "{name}"},
|
||||
{ActConfirmEntity, "{name}"}, {ActConfirmEntity, "{name_entity}"},
|
||||
{ActWhich, "{name}"}, {ActWhich, "{items}"},
|
||||
{EcoAmbiguous, "{items}"}, {EcoRecall, "{items}"},
|
||||
{AttentionList, "{items}"}, {ChangesList, "{items}"}, {HomeOn, "{items}"},
|
||||
{EcoDenied, "{name}"}, {EcoDown, "{name}"},
|
||||
{HomeDark, "{count}"}, {HomeDark, "{word}"},
|
||||
{AttentionNoneEntity, "{name}"}, {AttentionListEntity, "{name}"},
|
||||
{AttentionListEntity, "{items}"}, {AttentionFailEntity, "{name}"},
|
||||
} {
|
||||
if err := d.RequirePlaceholder(req.key, req.ph); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
return &Acts{d: d}, nil
|
||||
}
|
||||
|
||||
// deck reads through a nil *Acts, which is the unloadable-file case.
|
||||
func (a *Acts) deck() *say.Deck {
|
||||
if a == nil {
|
||||
return say.FloorDeck(actFloor)
|
||||
}
|
||||
return a.d
|
||||
}
|
||||
|
||||
// Say returns one line for key, with the names filled into the frame.
|
||||
func (a *Acts) Say(key string, vars map[string]string) string {
|
||||
return a.deck().Text(key, vars)
|
||||
}
|
||||
|
||||
// Variants returns every line the file can produce, for the persona scorer.
|
||||
func (a *Acts) Variants() []string { return a.deck().Variants() }
|
||||
|
||||
var (
|
||||
actOnce sync.Once
|
||||
actsDeck *Acts
|
||||
)
|
||||
|
||||
// DefaultActs returns the shared instance, loading it on first use. A broken
|
||||
// file logs once and leaves a nil *Acts, which still answers from actFloor.
|
||||
func DefaultActs() *Acts {
|
||||
actOnce.Do(func() {
|
||||
a, err := LoadActs(nil)
|
||||
if err != nil {
|
||||
log.Printf("phraser: act replies unavailable, using the built-in lines: %v", err)
|
||||
return
|
||||
}
|
||||
actsDeck = a
|
||||
})
|
||||
return actsDeck
|
||||
}
|
||||
|
||||
// A — one act reply, the way every caller says it.
|
||||
func A(key string, vars map[string]string) string { return DefaultActs().Say(key, vars) }
|
||||
|
||||
// IsA reports whether text is a line key could have produced, for the tests.
|
||||
func IsA(key string, vars map[string]string, text string) bool {
|
||||
return DefaultActs().deck().Matches(key, vars, text)
|
||||
}
|
||||
@@ -0,0 +1,145 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"name": "russian act and smart-home replies v1",
|
||||
"notes": [
|
||||
"What she says when a capability ran, refused, or could not be reached. Edit the wording here, no Go changes needed.",
|
||||
"Rules: she is feminine about herself, he is a man addressed as ты. Never вы/вас/ваш, never он/его about him. No pet names.",
|
||||
"\"it ran\", \"it was refused\", \"a service is down\" and \"I could not work out what you meant\" are four different truths. They keep four entries, because one variant set would let a failure report itself as a success.",
|
||||
"She says what he would say. No schema words out loud: not «сущность», not «экосистема», not a capability id, not a config key. She is talking about a lamp or a server.",
|
||||
"A service that is down or refusing is named. \"не отвечает\" with no subject tells him nothing he can act on, and Nexus, Praxis and Hexis fail independently.",
|
||||
"Placeholders: {name} an entity or capability the caller resolved, {name_entity} the entity an act runs against when {name} is already the capability, {out} the command's own output, {items} a joined list, {count} a number, {word} the counted noun in the form {count} needs. Entity names and capability ids are interpolated Go-side.",
|
||||
"A count never carries a hardcoded noun. Russian inflects it — 1 устройство, 2 устройства, 5 устройств — so the number goes in {count} and the noun comes from the Go helper through {word}.",
|
||||
"An entry that only exists to read a list back must never be reached with an empty list. The caller routes an empty list to the matching _none entry, because a single-variant placeholder-only line has no shorter wording to fall back to.",
|
||||
"fixed: true means exactly one variant and no picking. Used where the wording carries an instruction he has to act on — a confirmation, a pointer at /tools — and for the lines that report an act as done, because a success report that reworded itself is harder to trust and harder to test."
|
||||
],
|
||||
"entries": {
|
||||
"act_done": {
|
||||
"fixed": true,
|
||||
"variants": ["готово."]
|
||||
},
|
||||
"act_done_out": {
|
||||
"variants": ["готово: {out}", "сделала: {out}"]
|
||||
},
|
||||
"act_done_entity": {
|
||||
"fixed": true,
|
||||
"variants": ["готово: {name}."]
|
||||
},
|
||||
"act_confirm": {
|
||||
"fixed": true,
|
||||
"variants": ["выполнить «{name}»? да или нет."]
|
||||
},
|
||||
"act_confirm_entity": {
|
||||
"fixed": true,
|
||||
"variants": ["выполнить «{name}» для {name_entity}? да или нет."]
|
||||
},
|
||||
"act_which": {
|
||||
"fixed": true,
|
||||
"variants": ["какую команду для {name}: {items}?"]
|
||||
},
|
||||
"act_fail": {
|
||||
"fixed": true,
|
||||
"variants": ["не получилось выполнить команду."]
|
||||
},
|
||||
"act_fail_out": {
|
||||
"fixed": true,
|
||||
"variants": ["не получилось выполнить команду: {out}"]
|
||||
},
|
||||
"act_fail_entity": {
|
||||
"fixed": true,
|
||||
"variants": ["не получилось выполнить команду для {name}."]
|
||||
},
|
||||
"act_server_down": {
|
||||
"fixed": true,
|
||||
"variants": ["инструмент есть, но сервер не подключён."]
|
||||
},
|
||||
"act_withdrawn": {
|
||||
"fixed": true,
|
||||
"variants": ["сервер больше не отдаёт этот инструмент — сняла его с разрешённых, посмотри /tools."]
|
||||
},
|
||||
"act_needs_args": {
|
||||
"fixed": true,
|
||||
"variants": ["тут нужны аргументы, из голоса не соберу. угадывать не буду."]
|
||||
},
|
||||
"act_needs_authed_surface": {
|
||||
"fixed": true,
|
||||
"variants": ["это из голоса не выполню — после него ничего не вернуть. запусти сам."]
|
||||
},
|
||||
"eco_denied": {
|
||||
"fixed": true,
|
||||
"variants": ["{name} отклоняет доступ, проверь токен."]
|
||||
},
|
||||
"eco_down": {
|
||||
"fixed": true,
|
||||
"variants": ["{name} не отвечает, попробуй ещё раз."]
|
||||
},
|
||||
"eco_ambiguous": {
|
||||
"fixed": true,
|
||||
"variants": ["что именно: {items}?"]
|
||||
},
|
||||
"eco_unknown_entity": {
|
||||
"variants": ["не знаю, что это.", "такого у меня нет."]
|
||||
},
|
||||
"eco_no_nexus": {
|
||||
"fixed": true,
|
||||
"variants": ["не с чем связать — Nexus не настроен."]
|
||||
},
|
||||
"eco_about_what": {
|
||||
"fixed": true,
|
||||
"variants": ["про что именно?"]
|
||||
},
|
||||
"eco_recall": {
|
||||
"fixed": true,
|
||||
"variants": ["я помню: {items}"]
|
||||
},
|
||||
"attention_none": {
|
||||
"fixed": true,
|
||||
"variants": ["ничего не требует внимания."]
|
||||
},
|
||||
"attention_list": {
|
||||
"fixed": true,
|
||||
"variants": ["требует внимания: {items}"]
|
||||
},
|
||||
"attention_fail": {
|
||||
"fixed": true,
|
||||
"variants": ["не могу сейчас узнать, что требует внимания."]
|
||||
},
|
||||
"attention_none_entity": {
|
||||
"variants": ["по «{name}» ничего нет.", "по «{name}» пока пусто."]
|
||||
},
|
||||
"attention_list_entity": {
|
||||
"fixed": true,
|
||||
"variants": ["по «{name}»: {items}"]
|
||||
},
|
||||
"attention_fail_entity": {
|
||||
"fixed": true,
|
||||
"variants": ["не могу сейчас узнать, что требует внимания по «{name}»."]
|
||||
},
|
||||
"changes_none": {
|
||||
"fixed": true,
|
||||
"variants": ["изменений нет."]
|
||||
},
|
||||
"changes_list": {
|
||||
"fixed": true,
|
||||
"variants": ["изменения: {items}"]
|
||||
},
|
||||
"changes_fail": {
|
||||
"fixed": true,
|
||||
"variants": ["не могу сейчас узнать об изменениях."]
|
||||
},
|
||||
"home_unreachable": {
|
||||
"variants": ["дом не отвечает.", "не достучалась до дома."]
|
||||
},
|
||||
"home_empty": {
|
||||
"fixed": true,
|
||||
"variants": ["дом ничего не отдаёт."]
|
||||
},
|
||||
"home_on": {
|
||||
"fixed": true,
|
||||
"variants": ["включено: {items}"]
|
||||
},
|
||||
"home_dark": {
|
||||
"fixed": true,
|
||||
"variants": ["не отвечают: {count} {word}."]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -6,6 +6,8 @@ import (
|
||||
"strings"
|
||||
"unicode"
|
||||
"unicode/utf8"
|
||||
|
||||
"github.com/kami/maven/internal/morph"
|
||||
)
|
||||
|
||||
// The check names, in report order. Every check is a string or length test — no
|
||||
@@ -67,6 +69,19 @@ func RunChecks(c Case, body, mood string) []Result {
|
||||
}
|
||||
}
|
||||
|
||||
// Feminine, HisGender and Address expose three checks one at a time, so the
|
||||
// daemon can run them on a phrased message before he hears it (Vikunja #399).
|
||||
// Only these three: they are unambiguous string tests with nothing to compare
|
||||
// against, while length is path-specific and ontopic needs the fixture's
|
||||
// expected fragments, which do not exist at runtime.
|
||||
func Feminine(body string) Result { return checkFeminine(body) }
|
||||
|
||||
// HisGender — see checkHisGender.
|
||||
func HisGender(body string) Result { return checkHisGender(body) }
|
||||
|
||||
// Address — see checkAddress.
|
||||
func Address(body string) Result { return checkAddress(body) }
|
||||
|
||||
func checkMood(mood string) Result {
|
||||
if Moods[mood] {
|
||||
return Result{CheckMood, true, ""}
|
||||
@@ -127,24 +142,25 @@ var masculinePredicative = map[string]bool{
|
||||
"обязан": true, "сам": true, "занят": true, "прав": true,
|
||||
}
|
||||
|
||||
// nounsEndingInL — the false positives of "ends in л ⇒ masculine past tense".
|
||||
// Small on purpose: it only has to cover nouns a nudge might actually use.
|
||||
var nounsEndingInL = map[string]bool{
|
||||
"стол": true, "стул": true, "пол": true, "зал": true, "гол": true,
|
||||
"узел": true, "отдел": true, "файл": true, "канал": true, "угол": true,
|
||||
"футбол": true, "вокзал": true, "металл": true, "интервал": true,
|
||||
"уровень": true, "мускул": true, "апрель": true, "июль": true, "рубль": true,
|
||||
}
|
||||
|
||||
// masculinePast reports whether a word looks like a masculine past-tense verb.
|
||||
// Russian past tense is gendered by suffix: -л (m), -ла (f). A 0.8B with weak
|
||||
// Russian defaults to the masculine form, which is the exact drift being
|
||||
// measured.
|
||||
// masculinePast reports whether a word is a masculine past-tense verb. Russian
|
||||
// past tense is gendered by suffix: -л for him, -ла for her. A small model with
|
||||
// weak Russian defaults to the masculine form, which is the exact drift this
|
||||
// check measures.
|
||||
//
|
||||
// The ending is only half the test, and the other half used to be a hand list of
|
||||
// nineteen nouns that end in л — стол, файл, апрель — kept "small on purpose",
|
||||
// which means incomplete on purpose. A list of exceptions to a pattern is the
|
||||
// pattern conceding it is wrong, so the second half is now a dictionary lookup:
|
||||
// ends in -л AND is a form of a verb (Vikunja #526). Every noun the list held is
|
||||
// correctly not a verb, and so are the ones it had not got round to.
|
||||
func masculinePast(w string) bool {
|
||||
if len([]rune(w)) < 3 || nounsEndingInL[w] {
|
||||
if len([]rune(w)) < 3 {
|
||||
return false
|
||||
}
|
||||
return strings.HasSuffix(w, "л") || strings.HasSuffix(w, "лся")
|
||||
if !strings.HasSuffix(w, "л") && !strings.HasSuffix(w, "лся") {
|
||||
return false
|
||||
}
|
||||
return morph.IsVerbForm(w)
|
||||
}
|
||||
|
||||
func checkFeminine(body string) Result {
|
||||
|
||||
@@ -0,0 +1,70 @@
|
||||
package eval
|
||||
|
||||
import (
|
||||
"math/rand"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/say"
|
||||
)
|
||||
|
||||
// TestFallbackPersona scores every line in every hand-written family on the
|
||||
// persona checks the nudges already pass. These lines are heard out loud and
|
||||
// they live in a JSON file now, so a reworded variant that says "рад" or "вы"
|
||||
// would otherwise reach him with nothing in between.
|
||||
//
|
||||
// Only the persona checks run. Mood and topic belong to a nudge, and these are
|
||||
// not nudges.
|
||||
func TestFallbackPersona(t *testing.T) {
|
||||
fb, err := phraser.LoadFallbacks(rand.NewSource(20260804))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadFallbacks: %v", err)
|
||||
}
|
||||
// No CheckHisGender. It reads a feminine verb near a second-person pronoun
|
||||
// as addressing him as a woman, which is right for a nudge and wrong here:
|
||||
// "не знаю — не нашла у тебя такой записи" is her own verb in her own
|
||||
// sentence. CheckFeminine still holds her side of the rule.
|
||||
persona := map[string]bool{
|
||||
CheckLang: true, CheckFeminine: true,
|
||||
CheckAddress: true, CheckCringe: true, CheckLength: true,
|
||||
}
|
||||
ack, err := phraser.LoadAcks(rand.NewSource(20260804))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadAcks: %v", err)
|
||||
}
|
||||
qry, err := phraser.LoadQueries(rand.NewSource(20260804))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadQueries: %v", err)
|
||||
}
|
||||
variants := append(fb.Variants(), ack.Variants()...)
|
||||
variants = append(variants, qry.Variants()...)
|
||||
act, err := phraser.LoadActs(rand.NewSource(20260804))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadActs: %v", err)
|
||||
}
|
||||
variants = append(variants, act.Variants()...)
|
||||
sum, err := say.LoadSummaries(rand.NewSource(20260804))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadSummaries: %v", err)
|
||||
}
|
||||
variants = append(variants, sum.Variants()...)
|
||||
if len(variants) == 0 {
|
||||
t.Fatal("no variants — the file loaded empty")
|
||||
}
|
||||
for _, v := range variants {
|
||||
// The placeholders stand for his own words and carry no persona.
|
||||
body := v
|
||||
for _, ph := range []string{"{sources}", "{key}", "{value}", "{fn}", "{text}", "{when}", "{items}",
|
||||
"{location}", "{temp}", "{condition}", "{tail}", "{out}", "{name}",
|
||||
"{entity}", "{count}", "{word}",
|
||||
"{date}", "{line}", "{n}", "{day}", "{sat}", "{sun}", "{span}", "{gloss}", "{time}"} {
|
||||
body = strings.ReplaceAll(body, ph, "вода")
|
||||
}
|
||||
for _, r := range RunChecks(Case{}, body, "neutral") {
|
||||
if persona[r.Name] && !r.Pass {
|
||||
t.Errorf("%q fails %s: %s", v, r.Name, r.Detail)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -78,6 +78,12 @@ type TalkCase struct {
|
||||
Note string `json:"note,omitempty"`
|
||||
}
|
||||
|
||||
// TalkSchemaVersion — the version this loader understands. Separate from the
|
||||
// nudge fixture's SchemaVersion: the two fixtures have different shapes and
|
||||
// change on different days, and one shared constant would force a bump on the
|
||||
// fixture that did not move.
|
||||
const TalkSchemaVersion = 1
|
||||
|
||||
// TalkFixture — the versioned envelope, same gating as Fixture.
|
||||
type TalkFixture struct {
|
||||
SchemaVersion int `json:"schema_version"`
|
||||
@@ -92,8 +98,8 @@ func LoadTalk() (TalkFixture, error) {
|
||||
if err := json.Unmarshal(talkFixtureJSON, &f); err != nil {
|
||||
return TalkFixture{}, fmt.Errorf("parse talk fixture: %w", err)
|
||||
}
|
||||
if f.SchemaVersion != SchemaVersion {
|
||||
return TalkFixture{}, fmt.Errorf("talk fixture schema_version %d, want %d", f.SchemaVersion, SchemaVersion)
|
||||
if f.SchemaVersion != TalkSchemaVersion {
|
||||
return TalkFixture{}, fmt.Errorf("talk fixture schema_version %d, want %d", f.SchemaVersion, TalkSchemaVersion)
|
||||
}
|
||||
if len(f.Cases) == 0 {
|
||||
return TalkFixture{}, fmt.Errorf("talk fixture has no cases")
|
||||
|
||||
@@ -142,19 +142,13 @@ func TestLLMTalkBaseline(t *testing.T) {
|
||||
p := phraser.NewLLMPhraserAt(base, cfg)
|
||||
defer p.Close()
|
||||
|
||||
// Unreachable server is fatal here, not a logged warning, and that differs
|
||||
// from the nudge test on purpose. PhraseNudge returns its errors, so a dead
|
||||
// server there shows up honestly in the Errors column. PhraseChat and
|
||||
// PhraseQuery do NOT: they swallow every failure and return a canned string
|
||||
// ("поговорили.", "не знаю.", "вот что я нашла: …"). So on these three paths
|
||||
// a dead server produces a full report with 0 errors and a terrible score —
|
||||
// a number that looks like bad phrasing and is really no phrasing at all.
|
||||
// Refusing to score without a confirmed model is the only guard available
|
||||
// until the phraser reports its failures (Vikunja #397).
|
||||
// The model id names the run in the report. Since Vikunja #397 every path
|
||||
// returns its errors, so a server that dies mid-run shows up in the Errors
|
||||
// column instead of scoring as bad phrasing — the before-and-after probe that
|
||||
// used to stand in for that is gone.
|
||||
model, err := llm.ModelID(ctx, base)
|
||||
if err != nil {
|
||||
t.Fatalf("no model at %s: %v — refusing to score, these paths hide their errors "+
|
||||
"and would report a plausible-looking result off a dead server", base, err)
|
||||
t.Fatalf("no model at %s: %v", base, err)
|
||||
}
|
||||
t.Logf("scoring model %s at %s", model, base)
|
||||
|
||||
@@ -169,10 +163,11 @@ func TestLLMTalkBaseline(t *testing.T) {
|
||||
}
|
||||
t.Log("\n" + rep.String() + "\nreplies:\n" + rep.Replies() + "\nfailures:\n" + rep.Failures())
|
||||
|
||||
// And again afterwards: the run takes minutes, and a server that died or got
|
||||
// OOM-killed halfway through would leave the first cases scored and the rest
|
||||
// silently canned. Checking only at the start would not catch that.
|
||||
if _, err := llm.ModelID(ctx, base); err != nil {
|
||||
t.Fatalf("model at %s went away during the run: %v — the score above is not trustworthy", base, err)
|
||||
// A run where nothing was phrased is not a low score, it is no measurement.
|
||||
if rep.Errors == rep.Total {
|
||||
t.Fatalf("every case errored — nothing was measured, the score above is not a phrasing result")
|
||||
}
|
||||
if rep.Errors > 0 {
|
||||
t.Logf("%d/%d cases errored — those are model failures, not phrasing failures", rep.Errors, rep.Total)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,80 @@
|
||||
package phraser
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// isFallback — the text she says is picked from that entry's variants, so a test
|
||||
// pins the entry rather than the wording. Pinning one line would make editing
|
||||
// fallbacks_ru_v1.json break Go tests, which is the coupling this file removed.
|
||||
func isFallback(t *testing.T, key, sources, got string) bool {
|
||||
t.Helper()
|
||||
return DefaultFallbacks().deck().Matches(key, map[string]string{"sources": sources}, got)
|
||||
}
|
||||
|
||||
// A dead server must be distinguishable from bad phrasing. Both PhraseChat and
|
||||
// PhraseQuery keep the turn alive with canned text — and every one of those
|
||||
// lines is also a legitimate reply, so the text alone cannot say which happened.
|
||||
// The error is the only signal, and before Vikunja #397 it was dropped: the talk
|
||||
// scorer reported a full run with zero errors off a server that answered nothing.
|
||||
func TestPhrasingReportsTheFailureWithTheFallback(t *testing.T) {
|
||||
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
http.Error(w, "model not loaded", http.StatusServiceUnavailable)
|
||||
}))
|
||||
t.Cleanup(srv.Close)
|
||||
p := NewLLMPhraserAt(srv.URL, Config{})
|
||||
|
||||
cases := []struct {
|
||||
name string
|
||||
call func() (string, error)
|
||||
key string
|
||||
sources string
|
||||
}{
|
||||
{"chat", func() (string, error) {
|
||||
return p.PhraseChat(context.Background(), "как дела", nil)
|
||||
}, fbChat, ""},
|
||||
{"knowledge", func() (string, error) {
|
||||
return p.PhraseQuery(context.Background(), "кто написал войну и мир", nil)
|
||||
}, fbQueryUnknown, ""},
|
||||
{"evidence", func() (string, error) {
|
||||
return p.PhraseQuery(context.Background(), "сколько воды я выпил", []string{"два литра"})
|
||||
}, fbQuerySources, "два литра"},
|
||||
}
|
||||
for _, c := range cases {
|
||||
t.Run(c.name, func(t *testing.T) {
|
||||
got, err := c.call()
|
||||
if err == nil {
|
||||
t.Fatalf("no error from a dead server; the scorer would count this as bad phrasing")
|
||||
}
|
||||
if !isFallback(t, c.key, c.sources, got) {
|
||||
t.Errorf("fallback text = %q, want a %q variant — the daemon still has to say something", got, c.key)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// An empty answer is a failure too: the server is up and produced no tokens,
|
||||
// which is not an answer and must not score as one.
|
||||
func TestEmptyKnowledgeAnswerIsAnError(t *testing.T) {
|
||||
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
w.Write([]byte(`{"choices":[{"message":{"content":""}}]}`))
|
||||
}))
|
||||
t.Cleanup(srv.Close)
|
||||
p := NewLLMPhraserAt(srv.URL, Config{})
|
||||
|
||||
got, err := p.PhraseQuery(context.Background(), "кто написал войну и мир", nil)
|
||||
if err == nil {
|
||||
t.Fatal("an empty response scored as an answer")
|
||||
}
|
||||
if !isFallback(t, fbQueryUnknown, "", got) {
|
||||
t.Errorf("fallback text = %q, want a %q variant", got, fbQueryUnknown)
|
||||
}
|
||||
if !strings.Contains(err.Error(), "empty") {
|
||||
t.Errorf("error = %v; want it to name the empty response", err)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,140 @@
|
||||
package phraser
|
||||
|
||||
// The phrasing fallbacks — what she says when the model gave her nothing usable.
|
||||
//
|
||||
// They were four string literals spread across phraser.go, llmphraser.go and
|
||||
// cmd/mavend/worldmodel.go. Every one of them is a line he hears out loud, so
|
||||
// rewording one was a Go edit, a rebuild and a redeploy for what is product copy.
|
||||
//
|
||||
// The floor under the floor is deliberate. These strings exist because something
|
||||
// already failed, so a broken template file must not be able to take the last
|
||||
// words she has: every accessor falls back to the literal it replaced.
|
||||
|
||||
import (
|
||||
_ "embed"
|
||||
"log"
|
||||
"math/rand"
|
||||
"sync"
|
||||
|
||||
"github.com/kami/maven/internal/say"
|
||||
)
|
||||
|
||||
//go:embed fallbacks_ru_v1.json
|
||||
var fallbackJSON []byte
|
||||
|
||||
// FallbackSchemaVersion — the version this code understands. Its own constant,
|
||||
// not shared with the nudge templates or the eval fixtures: two files that change
|
||||
// on different days cannot be versioned by one number (Vikunja #397).
|
||||
const FallbackSchemaVersion = 1
|
||||
|
||||
// The entry keys. Every one of them is read by a method below, so a typo in the
|
||||
// file is caught at load rather than at the moment she needs the words.
|
||||
const (
|
||||
fbChat = "chat"
|
||||
fbQueryUnknown = "query_unknown"
|
||||
fbQuerySources = "query_sources"
|
||||
fbWorldGap = "world_gap"
|
||||
)
|
||||
|
||||
// fbKeys — every key the code requires the file to define.
|
||||
var fbKeys = []string{fbChat, fbQueryUnknown, fbQuerySources, fbWorldGap}
|
||||
|
||||
// hardFloor — the literal each key falls back to when the file is unusable.
|
||||
// These are the exact strings that lived in Go before this file existed.
|
||||
var hardFloor = map[string]string{
|
||||
fbChat: "даже не знаю, что сказать.",
|
||||
fbQueryUnknown: "не знаю.",
|
||||
fbQuerySources: "вот что я нашла: {sources}",
|
||||
fbWorldGap: "сейчас не могу ответить — большая модель недоступна, а придумывать не хочу.",
|
||||
}
|
||||
|
||||
// Fallbacks picks a hand-written Russian fallback line. Safe for concurrent use.
|
||||
type Fallbacks struct{ d *say.Deck }
|
||||
|
||||
// LoadFallbacks reads the embedded file. Pass a source to make the picking
|
||||
// reproducible in tests; nil seeds from the clock.
|
||||
func LoadFallbacks(src rand.Source) (*Fallbacks, error) {
|
||||
d, err := say.Load(fallbackJSON, FallbackSchemaVersion, fbKeys, hardFloor, src)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
// query_sources is the one entry whose whole job is to read something back.
|
||||
if err := d.RequirePlaceholder(fbQuerySources, "{sources}"); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return &Fallbacks{d: d}, nil
|
||||
}
|
||||
|
||||
// deck reads through a nil *Fallbacks, which is the unloadable-file case.
|
||||
func (f *Fallbacks) deck() *say.Deck {
|
||||
if f == nil {
|
||||
return say.FloorDeck(hardFloor)
|
||||
}
|
||||
return f.d
|
||||
}
|
||||
|
||||
// Chat — nothing usable came back on the chat path.
|
||||
func (f *Fallbacks) Chat() string { return f.deck().Text(fbChat, nil) }
|
||||
|
||||
// Unknown — a question she cannot answer and will not guess at.
|
||||
func (f *Fallbacks) Unknown() string { return f.deck().Text(fbQueryUnknown, nil) }
|
||||
|
||||
// FromSources — read back what she was handed, because phrasing it failed.
|
||||
func (f *Fallbacks) FromSources(sources string) string {
|
||||
return f.deck().Text(fbQuerySources, map[string]string{"sources": sources})
|
||||
}
|
||||
|
||||
// WorldGap — the world model is the one configured to answer and it is not
|
||||
// answering. Fixed wording: it names a specific gap, and a variant set here
|
||||
// would let "the big model is asleep" drift into "I don't know".
|
||||
func (f *Fallbacks) WorldGap() string { return f.deck().Text(fbWorldGap, nil) }
|
||||
|
||||
// Variants returns every line the file can produce, for the persona scorer.
|
||||
func (f *Fallbacks) Variants() []string { return f.deck().Variants() }
|
||||
|
||||
// The process-wide instance. Package-level because these lines are needed on
|
||||
// paths that have no phraser to hand — cmd/mavend names the world gap without
|
||||
// one — and because a template file that is embedded and validated at load has
|
||||
// nothing per-instance to configure.
|
||||
var (
|
||||
fallbackOnce sync.Once
|
||||
fallbacks *Fallbacks
|
||||
)
|
||||
|
||||
// DefaultFallbacks returns the shared instance, loading it on first use. A
|
||||
// broken file logs once and leaves a nil *Fallbacks, which still answers from
|
||||
// hardFloor — a daemon must not fail to boot over its own copy deck.
|
||||
func DefaultFallbacks() *Fallbacks {
|
||||
fallbackOnce.Do(func() {
|
||||
fb, err := LoadFallbacks(nil)
|
||||
if err != nil {
|
||||
log.Printf("phraser: fallbacks unavailable, using the built-in lines: %v", err)
|
||||
return
|
||||
}
|
||||
fallbacks = fb
|
||||
})
|
||||
return fallbacks
|
||||
}
|
||||
|
||||
// ChatFallback — what she says when the chat path produced nothing.
|
||||
func ChatFallback() string { return DefaultFallbacks().Chat() }
|
||||
|
||||
// UnknownFallback — what she says when she has no answer and will not invent one.
|
||||
func UnknownFallback() string { return DefaultFallbacks().Unknown() }
|
||||
|
||||
// SourcesFallback — read the sources back rather than ship a broken fragment.
|
||||
func SourcesFallback(sources string) string { return DefaultFallbacks().FromSources(sources) }
|
||||
|
||||
// WorldGap — what he hears when the world model is configured and unreachable.
|
||||
func WorldGap() string { return DefaultFallbacks().WorldGap() }
|
||||
|
||||
// IsUnknownFallback reports whether text is one of her "I do not know" lines.
|
||||
// The daemon tests read it to tell an answer from a shrug.
|
||||
func IsUnknownFallback(text string) bool {
|
||||
return DefaultFallbacks().deck().Matches(fbQueryUnknown, nil, text)
|
||||
}
|
||||
|
||||
// IsSourcesFallback reports whether text is sources read back verbatim.
|
||||
func IsSourcesFallback(text, sources string) bool {
|
||||
return DefaultFallbacks().deck().Matches(fbQuerySources, map[string]string{"sources": sources}, text)
|
||||
}
|
||||
@@ -0,0 +1,42 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"name": "russian phrasing fallbacks v1",
|
||||
"notes": [
|
||||
"What she says when the model gave her nothing usable. Edit the wording here, no Go changes needed.",
|
||||
"Rules: she is feminine about herself, he is a man addressed as ты. Never вы/вас/ваш, never plural imperatives, never он/его about him. No pet names.",
|
||||
"These are heard after a failure, so they stay short and admit the gap. None of them may claim knowledge she does not have.",
|
||||
"Placeholders: {sources} the notes or passages she was handed. A variant whose placeholder has no value is skipped, so every entry needs at least one variant with no placeholder — except query_sources, which exists only to read sources back.",
|
||||
"fixed: true means exactly one variant and no picking. Used where the wording is load-bearing and must not drift between turns."
|
||||
],
|
||||
"entries": {
|
||||
"chat": {
|
||||
"variants": [
|
||||
"даже не знаю, что сказать.",
|
||||
"не могу найти слов.",
|
||||
"мысль ускользнула, повтори?",
|
||||
"у меня сейчас пусто в голове."
|
||||
]
|
||||
},
|
||||
"query_unknown": {
|
||||
"variants": [
|
||||
"не знаю.",
|
||||
"не знаю, честно.",
|
||||
"тут я пас.",
|
||||
"не скажу, не знаю."
|
||||
]
|
||||
},
|
||||
"query_sources": {
|
||||
"variants": [
|
||||
"вот что я нашла: {sources}",
|
||||
"нашла вот это: {sources}",
|
||||
"есть только это: {sources}"
|
||||
]
|
||||
},
|
||||
"world_gap": {
|
||||
"fixed": true,
|
||||
"variants": [
|
||||
"сейчас не могу ответить — большая модель недоступна, а придумывать не хочу."
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,74 @@
|
||||
package phraser
|
||||
|
||||
import (
|
||||
"math/rand"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// The embedded file must load, or the daemon speaks from hardFloor and nobody
|
||||
// finds out until he hears the wrong words.
|
||||
func TestFallbacksLoad(t *testing.T) {
|
||||
fb, err := LoadFallbacks(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadFallbacks: %v", err)
|
||||
}
|
||||
if got := fb.FromSources("два литра"); !strings.Contains(got, "два литра") {
|
||||
t.Errorf("FromSources = %q, want the sources in it", got)
|
||||
}
|
||||
if fb.WorldGap() != hardFloor[fbWorldGap] {
|
||||
t.Errorf("WorldGap = %q, want the fixed wording %q", fb.WorldGap(), hardFloor[fbWorldGap])
|
||||
}
|
||||
}
|
||||
|
||||
// A broken or missing file must not take her last words away: every accessor
|
||||
// answers from the literal it replaced.
|
||||
func TestNilFallbacksAnswerFromTheHardFloor(t *testing.T) {
|
||||
var fb *Fallbacks
|
||||
if got := fb.Chat(); got != hardFloor[fbChat] {
|
||||
t.Errorf("Chat = %q, want %q", got, hardFloor[fbChat])
|
||||
}
|
||||
if got := fb.Unknown(); got != hardFloor[fbQueryUnknown] {
|
||||
t.Errorf("Unknown = %q, want %q", got, hardFloor[fbQueryUnknown])
|
||||
}
|
||||
if got := fb.FromSources("два литра"); got != "вот что я нашла: два литра" {
|
||||
t.Errorf("FromSources = %q", got)
|
||||
}
|
||||
if got := fb.WorldGap(); got != hardFloor[fbWorldGap] {
|
||||
t.Errorf("WorldGap = %q", got)
|
||||
}
|
||||
}
|
||||
|
||||
// Hearing the identical words every time a request fails is how a failure stops
|
||||
// registering as one.
|
||||
func TestFallbacksDoNotRepeat(t *testing.T) {
|
||||
fb, err := LoadFallbacks(rand.NewSource(7))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadFallbacks: %v", err)
|
||||
}
|
||||
prev := fb.Chat()
|
||||
for i := 0; i < 20; i++ {
|
||||
got := fb.Chat()
|
||||
if got == prev {
|
||||
t.Fatalf("chat repeated %q on turn %d", got, i)
|
||||
}
|
||||
prev = got
|
||||
}
|
||||
}
|
||||
|
||||
// The acknowledgements load, fill his words into the frame, and answer from the
|
||||
// floor when the file is gone.
|
||||
func TestAcksLoad(t *testing.T) {
|
||||
a, err := LoadAcks(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadAcks: %v", err)
|
||||
}
|
||||
got := a.Say(AckFactValue, map[string]string{"key": "вода", "value": "2л"})
|
||||
if !strings.Contains(got, "вода") || !strings.Contains(got, "2л") {
|
||||
t.Errorf("Say(%s) = %q, want his key and value in it", AckFactValue, got)
|
||||
}
|
||||
var nilAcks *Acks
|
||||
if got := nilAcks.Say(AckNote, nil); got != ackFloor[AckNote] {
|
||||
t.Errorf("nil Acks said %q, want the floor %q", got, ackFloor[AckNote])
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,38 @@
|
||||
package phraser
|
||||
|
||||
import (
|
||||
"math/rand"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// The other four families, held to the rule internal/say holds the fifth to:
|
||||
// one variant means fixed. Reported per family, because a failure that names
|
||||
// "some file" is a failure nobody acts on.
|
||||
func TestEverySingleVariantEntryIsFixed(t *testing.T) {
|
||||
f, err := LoadFallbacks(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadFallbacks: %v", err)
|
||||
}
|
||||
a, err := LoadAcks(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadAcks: %v", err)
|
||||
}
|
||||
q, err := LoadQueries(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadQueries: %v", err)
|
||||
}
|
||||
acts, err := LoadActs(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadActs: %v", err)
|
||||
}
|
||||
for name, keys := range map[string][]string{
|
||||
"fallbacks": f.d.UnfixedSingles(),
|
||||
"acks": a.d.UnfixedSingles(),
|
||||
"queries": q.d.UnfixedSingles(),
|
||||
"acts": acts.d.UnfixedSingles(),
|
||||
} {
|
||||
if len(keys) > 0 {
|
||||
t.Errorf("%s: single-variant entries not marked fixed: %v", name, keys)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -5,6 +5,7 @@ import (
|
||||
"bytes"
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"log"
|
||||
@@ -26,6 +27,11 @@ import (
|
||||
|
||||
var listenRE = regexp.MustCompile(`listening on (https?://\S+)`)
|
||||
|
||||
// errEmptyResponse — the server answered and said nothing. Separate from a
|
||||
// transport failure: the model is up and produced no tokens, which is still not
|
||||
// an answer and must not score as one.
|
||||
var errEmptyResponse = errors.New("phraser: empty response from the model")
|
||||
|
||||
type LLMPhraser struct {
|
||||
cfg Config
|
||||
client *http.Client
|
||||
@@ -428,8 +434,11 @@ func (p *LLMPhraser) PhraseNudge(ctx context.Context, c loop.Candidate) (deliver
|
||||
}
|
||||
|
||||
// PhraseQuery prompts the LLM with the user's utterance and matching notes to
|
||||
// compose a natural answer. Falls back to "вот что я нашла: <notes>" on any
|
||||
// LLM error — better to give the raw data than silence.
|
||||
// compose a natural answer. On any LLM error it returns the fallback text —
|
||||
// "вот что я нашла: <notes>", or "не знаю." with no notes — and the error
|
||||
// together. The daemon uses the text and keeps the turn alive; a caller that is
|
||||
// measuring counts the failure. Until Vikunja #397 the error was dropped, so a
|
||||
// dead server scored as bad phrasing.
|
||||
func (p *LLMPhraser) PhraseQuery(ctx context.Context, utterance string, notes []string) (string, error) {
|
||||
// Blank sources are no sources. A caller that hands over one empty string —
|
||||
// a page that fetched to nothing, a snippet trimmed away — used to take the
|
||||
@@ -439,13 +448,15 @@ func (p *LLMPhraser) PhraseQuery(ctx context.Context, utterance string, notes []
|
||||
if len(notes) == 0 {
|
||||
sys, prompt := p.knowledgePrompt(utterance)
|
||||
resp, err := p.chatWithSystem(ctx, sys, prompt, 768)
|
||||
if err != nil || resp == "" {
|
||||
return "не знаю.", nil
|
||||
if err != nil {
|
||||
return UnknownFallback(), fmt.Errorf("phrase query (knowledge): %w", err)
|
||||
}
|
||||
if resp == "" {
|
||||
return UnknownFallback(), errEmptyResponse
|
||||
}
|
||||
text, _, perr := parseResponseMood(resp)
|
||||
if perr != nil {
|
||||
log.Printf("phraser: PhraseQuery: %v", perr)
|
||||
return "не знаю.", nil
|
||||
return UnknownFallback(), fmt.Errorf("phrase query (knowledge): %w", perr)
|
||||
}
|
||||
if text != "" {
|
||||
return text, nil
|
||||
@@ -457,13 +468,12 @@ func (p *LLMPhraser) PhraseQuery(ctx context.Context, utterance string, notes []
|
||||
text, _, perr := parseResponseMood(resp)
|
||||
if err != nil || perr != nil {
|
||||
// Read the notes out rather than ship a broken fragment.
|
||||
if perr != nil {
|
||||
log.Printf("phraser: PhraseQuery: %v", perr)
|
||||
cause := err
|
||||
if cause == nil {
|
||||
cause = perr
|
||||
}
|
||||
if len(notes) == 1 {
|
||||
return "вот что я нашла: " + notes[0], nil
|
||||
}
|
||||
return "вот что я нашла: " + strings.Join(notes, "; "), nil
|
||||
return SourcesFallback(strings.Join(notes, "; ")),
|
||||
fmt.Errorf("phrase query (evidence): %w", cause)
|
||||
}
|
||||
if text != "" {
|
||||
return text, nil
|
||||
@@ -472,8 +482,9 @@ func (p *LLMPhraser) PhraseQuery(ctx context.Context, utterance string, notes []
|
||||
}
|
||||
|
||||
// PhraseChat uses the LLM to respond conversationally, building a multi-turn
|
||||
// message array from dialogue history + the current user utterance. Falls back
|
||||
// to a simple greeting on any LLM error — better to say something than nothing.
|
||||
// message array from dialogue history + the current user utterance. On any LLM
|
||||
// error it returns both ChatFallback and the error, on the same rule as
|
||||
// PhraseQuery: the fallback keeps the turn alive, the error stays visible.
|
||||
func (p *LLMPhraser) PhraseChat(ctx context.Context, utterance string, history []dialogue.Turn) (string, error) {
|
||||
sys := chatSystemPrompt(p.cfg.ContextBlock)
|
||||
msgs := []chatMsg{
|
||||
@@ -490,13 +501,11 @@ func (p *LLMPhraser) PhraseChat(ctx context.Context, utterance string, history [
|
||||
|
||||
resp, err := p.chatWithMessages(ctx, msgs, 768)
|
||||
if err != nil {
|
||||
log.Printf("phraser: PhraseChat: %v", err)
|
||||
return "поговорили.", nil
|
||||
return ChatFallback(), fmt.Errorf("phrase chat: %w", err)
|
||||
}
|
||||
text, _, perr := parseResponseMood(resp)
|
||||
if perr != nil {
|
||||
log.Printf("phraser: PhraseChat: %v", perr)
|
||||
return "поговорили.", nil
|
||||
return ChatFallback(), fmt.Errorf("phrase chat: %w", perr)
|
||||
}
|
||||
if text != "" {
|
||||
return text, nil
|
||||
|
||||
@@ -18,6 +18,8 @@ import (
|
||||
"fmt"
|
||||
"math/rand"
|
||||
"regexp"
|
||||
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
@@ -210,13 +212,11 @@ func capitalizeFirst(s string) string {
|
||||
}
|
||||
|
||||
// hourWords — hours spelled out. "3 ч" is fine on a screen and wrong in a
|
||||
// Russian voice, so the number goes out as words.
|
||||
var hourWords = []string{
|
||||
"ноль", "один", "два", "три", "четыре", "пять", "шесть", "семь", "восемь",
|
||||
"девять", "десять", "одиннадцать", "двенадцать", "тринадцать",
|
||||
"четырнадцать", "пятнадцать", "шестнадцать", "семнадцать", "восемнадцать",
|
||||
"девятнадцать", "двадцать", "двадцать один", "двадцать два", "двадцать три",
|
||||
}
|
||||
// Russian voice, so the number goes out as words. Closed set, indexed by the
|
||||
// hour, kept in internal/lexicon (Vikunja #525).
|
||||
func hourWord(h int) string { return lexicon.HourSpoken(h) }
|
||||
|
||||
const hoursSpoken = 24
|
||||
|
||||
// hourPlural — час / часа / часов by Russian counting rules.
|
||||
func hourPlural(h int) string {
|
||||
@@ -245,7 +245,7 @@ func ruSinceWords(d time.Duration) string {
|
||||
h++
|
||||
m = 0
|
||||
}
|
||||
if h >= len(hourWords) {
|
||||
if h >= hoursSpoken {
|
||||
return "больше суток"
|
||||
}
|
||||
if h == 1 {
|
||||
@@ -255,7 +255,7 @@ func ruSinceWords(d time.Duration) string {
|
||||
return "час"
|
||||
}
|
||||
if m >= 15 {
|
||||
return hourWords[h] + " с половиной часа"
|
||||
return hourWord(h) + " с половиной часа"
|
||||
}
|
||||
return hourWords[h] + " " + hourPlural(h)
|
||||
return hourWord(h) + " " + hourPlural(h)
|
||||
}
|
||||
|
||||
@@ -70,18 +70,15 @@ func NewStub() *Stub { return &Stub{} }
|
||||
// prompted response from the model. The history parameter is accepted but
|
||||
// ignored at the stub level (the production impl uses it for multi-turn).
|
||||
func (s *Stub) PhraseChat(_ context.Context, _ string, _ []dialogue.Turn) (string, error) {
|
||||
return "поговорили.", nil
|
||||
return ChatFallback(), nil
|
||||
}
|
||||
|
||||
// PhraseQuery returns a deterministic summary of the best matching notes.
|
||||
func (s *Stub) PhraseQuery(_ context.Context, _ string, notes []string) (string, error) {
|
||||
if len(notes) == 0 {
|
||||
return "не знаю.", nil
|
||||
return UnknownFallback(), nil
|
||||
}
|
||||
if len(notes) == 1 {
|
||||
return "вот что я нашла: " + notes[0], nil
|
||||
}
|
||||
return "вот что я нашла: " + strings.Join(notes, "; "), nil
|
||||
return SourcesFallback(strings.Join(notes, "; ")), nil
|
||||
}
|
||||
|
||||
// Close implements Phraser.Close (no-op for the stub).
|
||||
|
||||
@@ -0,0 +1,19 @@
|
||||
package phraser
|
||||
|
||||
// The counted noun, for callers that already speak through this package.
|
||||
//
|
||||
// The rule itself lives in internal/say, next to the line files that carry the
|
||||
// {word} placeholder, because internal/say sits under phraser in the import
|
||||
// graph and internal/memory and internal/tasks need it too. These are the same
|
||||
// three functions under the names cmd/mavend already calls.
|
||||
|
||||
import "github.com/kami/maven/internal/say"
|
||||
|
||||
// CountWord picks between the three forms a Russian count needs.
|
||||
func CountWord(n int, one, few, many string) string { return say.CountWord(n, one, few, many) }
|
||||
|
||||
// Degrees — the noun for a temperature.
|
||||
func Degrees(temp float64) string { return say.Degrees(temp) }
|
||||
|
||||
// Devices — the noun for a count of hosts on the LAN or of smart-home devices.
|
||||
func Devices(n int) string { return say.Devices(n) }
|
||||
@@ -0,0 +1,32 @@
|
||||
package phraser
|
||||
|
||||
import "testing"
|
||||
|
||||
// The bug the helper exists for: the weather line said "градусов" for every
|
||||
// reading, which is wrong for 1-4 and for every number ending in 1-4.
|
||||
func TestDegreesAgreeWithTheReading(t *testing.T) {
|
||||
for temp, want := range map[float64]string{
|
||||
1: "градус", 1.4: "градус", 2: "градуса", 4: "градуса", 5: "градусов",
|
||||
0: "градусов", 11: "градусов", 14: "градусов", 21: "градус",
|
||||
22: "градуса", 25: "градусов", 101: "градус",
|
||||
// Minus does not change the noun, and a reading rounds to the number
|
||||
// she is about to say: -2.4° is "-2 градуса", not "-2 градусов".
|
||||
-1: "градус", -2.4: "градуса", -5: "градусов", -11: "градусов",
|
||||
} {
|
||||
if got := Degrees(temp); got != want {
|
||||
t.Errorf("Degrees(%v) = %q, want %q", temp, got, want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestDevicesAgreeWithTheCount(t *testing.T) {
|
||||
for n, want := range map[int]string{
|
||||
1: "устройство", 2: "устройства", 4: "устройства", 5: "устройств",
|
||||
11: "устройств", 12: "устройств", 21: "устройство", 22: "устройства",
|
||||
25: "устройств", 111: "устройств", 101: "устройство", 0: "устройств",
|
||||
} {
|
||||
if got := Devices(n); got != want {
|
||||
t.Errorf("Devices(%d) = %q, want %q", n, got, want)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,171 @@
|
||||
package phraser
|
||||
|
||||
// The query answers and gaps — what a query source says when it answers from
|
||||
// something other than the model, and what it says when it has nothing.
|
||||
//
|
||||
// Third family on the shared deck (deck.go), after the fallbacks and the
|
||||
// acknowledgements. They were literals spread across actions_query.go and
|
||||
// netscan.go, where the largest single site held two dozen of them.
|
||||
//
|
||||
// QueryUnknown is not the phraser's UnknownFallback, even though the two read
|
||||
// the same today. Here she looked and found nothing; there she failed to phrase
|
||||
// an answer she had. Two files, two entries, so rewording one leaves the other.
|
||||
|
||||
import (
|
||||
_ "embed"
|
||||
"log"
|
||||
"math/rand"
|
||||
"sync"
|
||||
|
||||
"github.com/kami/maven/internal/say"
|
||||
)
|
||||
|
||||
//go:embed query_ru_v1.json
|
||||
var queryJSON []byte
|
||||
|
||||
// QuerySchemaVersion — this family's own version.
|
||||
const QuerySchemaVersion = 1
|
||||
|
||||
// The entry keys.
|
||||
const (
|
||||
QueryUnknown = "query_unknown"
|
||||
QueryOtherDay = "other_day"
|
||||
QueryPersonalNone = "personal_none"
|
||||
QueryFactWhen = "fact_when"
|
||||
QueryFactValue = "fact_value"
|
||||
QueryFound = "found"
|
||||
QueryPageText = "page_text"
|
||||
QueryPageBlocked = "page_blocked"
|
||||
QueryPageEmpty = "page_empty"
|
||||
QueryFeedsOff = "feeds_off"
|
||||
QueryFeedsNew = "feeds_new"
|
||||
QueryFeedsEmpty = "feeds_empty"
|
||||
QueryFeedsTopic = "feeds_empty_topic"
|
||||
QueryWeatherNow = "weather_now"
|
||||
QueryWeatherOff = "weather_off"
|
||||
QueryWeatherWhere = "weather_nolocation"
|
||||
QueryNetEmpty = "net_empty"
|
||||
QueryNetOff = "net_off"
|
||||
QueryPageOff = "page_off"
|
||||
|
||||
QueryFailPlan = "fail_plan"
|
||||
QueryFailNotes = "fail_notes"
|
||||
QueryFailFeeds = "fail_feeds"
|
||||
QueryFailCalendar = "fail_calendar"
|
||||
QueryFailWeather = "fail_weather"
|
||||
QueryFailAnswer = "fail_answer"
|
||||
QueryFailPage = "fail_page"
|
||||
QueryFailNetscan = "fail_netscan"
|
||||
)
|
||||
|
||||
var queryKeys = []string{
|
||||
QueryUnknown, QueryOtherDay, QueryPersonalNone, QueryFactWhen, QueryFactValue,
|
||||
QueryFound, QueryPageText, QueryPageBlocked, QueryPageEmpty,
|
||||
QueryFeedsOff, QueryFeedsNew, QueryFeedsEmpty, QueryFeedsTopic,
|
||||
QueryWeatherNow, QueryWeatherOff, QueryWeatherWhere, QueryNetEmpty, QueryNetOff, QueryPageOff,
|
||||
QueryFailPlan, QueryFailNotes, QueryFailFeeds, QueryFailCalendar,
|
||||
QueryFailWeather, QueryFailAnswer, QueryFailPage, QueryFailNetscan,
|
||||
}
|
||||
|
||||
// queryFloor — the literal each key falls back to when the file is unusable.
|
||||
// It started as the exact strings that lived in Go before this file existed and
|
||||
// now tracks the file's first variant instead, because a floor that keeps the
|
||||
// wording review threw out would say it back on the one turn nobody is watching.
|
||||
var queryFloor = map[string]string{
|
||||
QueryUnknown: "ничего не нашла.",
|
||||
QueryOtherDay: "про другой день так не отвечу — спроси целиком.",
|
||||
QueryPersonalNone: "не знаю — не нашла у тебя такой записи.",
|
||||
QueryFactWhen: "записала это {when}",
|
||||
QueryFactValue: "у меня записано: {key} — {value}",
|
||||
QueryFound: "вот что я нашла: {text}",
|
||||
QueryPageText: "вот что на странице: {text}",
|
||||
QueryPageBlocked: "эта страница закрыта для чтения — сам сайт это запрещает.",
|
||||
QueryPageEmpty: "страница открылась, но читать там нечего.",
|
||||
QueryFeedsOff: "ленты не настроены.",
|
||||
QueryFeedsNew: "вот что нового: {items}",
|
||||
QueryFeedsEmpty: "в лентах пока ничего нового.",
|
||||
QueryFeedsTopic: "по этой теме в лентах пока ничего.",
|
||||
QueryWeatherNow: "в {location} сейчас {temp} {word}, {condition}.",
|
||||
QueryWeatherOff: "погода не настроена.",
|
||||
QueryWeatherWhere: "для какого города?",
|
||||
QueryNetEmpty: "в сети никого не нашла.",
|
||||
QueryNetOff: "сканирование сети не настроено.",
|
||||
QueryPageOff: "я не читаю страницы — это не настроено.",
|
||||
|
||||
QueryFailPlan: "не получилось собрать план.",
|
||||
QueryFailNotes: "не получилось посмотреть записи.",
|
||||
QueryFailFeeds: "не получилось посмотреть ленты.",
|
||||
QueryFailCalendar: "не получилось проверить календарь.",
|
||||
QueryFailWeather: "не получилось узнать погоду.",
|
||||
QueryFailAnswer: "не получилось найти ответ.",
|
||||
QueryFailPage: "не получилось прочитать страницу.",
|
||||
QueryFailNetscan: "не получилось просканировать сеть.",
|
||||
}
|
||||
|
||||
// Queries picks a hand-written Russian query line. Safe for concurrent use.
|
||||
type Queries struct{ d *say.Deck }
|
||||
|
||||
// LoadQueries reads the embedded file. Pass a source to make the picking
|
||||
// reproducible in tests; nil seeds from the clock.
|
||||
func LoadQueries(src rand.Source) (*Queries, error) {
|
||||
d, err := say.Load(queryJSON, QuerySchemaVersion, queryKeys, queryFloor, src)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
// The entries that exist to read something back. A variant without the
|
||||
// placeholder would answer the question by dropping the answer.
|
||||
for _, req := range []struct{ key, ph string }{
|
||||
{QueryFactWhen, "{when}"}, {QueryFactValue, "{key}"}, {QueryFactValue, "{value}"},
|
||||
{QueryFound, "{text}"}, {QueryPageText, "{text}"}, {QueryFeedsNew, "{items}"},
|
||||
{QueryWeatherNow, "{location}"}, {QueryWeatherNow, "{temp}"},
|
||||
{QueryWeatherNow, "{word}"}, {QueryWeatherNow, "{condition}"},
|
||||
} {
|
||||
if err := d.RequirePlaceholder(req.key, req.ph); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
return &Queries{d: d}, nil
|
||||
}
|
||||
|
||||
// deck reads through a nil *Queries, which is the unloadable-file case.
|
||||
func (q *Queries) deck() *say.Deck {
|
||||
if q == nil {
|
||||
return say.FloorDeck(queryFloor)
|
||||
}
|
||||
return q.d
|
||||
}
|
||||
|
||||
// Say returns one line for key, with the values filled into the frame.
|
||||
func (q *Queries) Say(key string, vars map[string]string) string {
|
||||
return q.deck().Text(key, vars)
|
||||
}
|
||||
|
||||
// Variants returns every line the file can produce, for the persona scorer.
|
||||
func (q *Queries) Variants() []string { return q.deck().Variants() }
|
||||
|
||||
var (
|
||||
queryOnce sync.Once
|
||||
queries *Queries
|
||||
)
|
||||
|
||||
// DefaultQueries returns the shared instance, loading it on first use. A broken
|
||||
// file logs once and leaves a nil *Queries, which still answers from queryFloor.
|
||||
func DefaultQueries() *Queries {
|
||||
queryOnce.Do(func() {
|
||||
q, err := LoadQueries(nil)
|
||||
if err != nil {
|
||||
log.Printf("phraser: query lines unavailable, using the built-in ones: %v", err)
|
||||
return
|
||||
}
|
||||
queries = q
|
||||
})
|
||||
return queries
|
||||
}
|
||||
|
||||
// Q — one query line, the way every caller says it.
|
||||
func Q(key string, vars map[string]string) string { return DefaultQueries().Say(key, vars) }
|
||||
|
||||
// IsQ reports whether text is a line key could have produced, for the tests.
|
||||
func IsQ(key string, vars map[string]string, text string) bool {
|
||||
return DefaultQueries().deck().Matches(key, vars, text)
|
||||
}
|
||||
@@ -0,0 +1,107 @@
|
||||
package phraser
|
||||
|
||||
import (
|
||||
"math/rand"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestQueriesLoad(t *testing.T) {
|
||||
q, err := LoadQueries(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadQueries: %v", err)
|
||||
}
|
||||
for _, k := range queryKeys {
|
||||
if got := q.Say(k, nil); got == "" {
|
||||
t.Errorf("%s says nothing", k)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The bug: net_empty carried {tail} in every variant, and a scan that finished
|
||||
// the whole range has no caveat to put there. Whatever the file says, an answer
|
||||
// he can hear has to come out — never braces, never nothing.
|
||||
func TestNetEmptySaysSomethingWithNoTail(t *testing.T) {
|
||||
q, err := LoadQueries(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadQueries: %v", err)
|
||||
}
|
||||
for _, vars := range []map[string]string{nil, {"tail": ""}} {
|
||||
for i := 0; i < 20; i++ {
|
||||
got := q.Say(QueryNetEmpty, vars)
|
||||
if got == "" || strings.ContainsAny(got, "{}") {
|
||||
t.Fatalf("net_empty with vars %v said %q", vars, got)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The other half: a caveat he was given is not dropped for a shorter wording.
|
||||
func TestNetEmptyKeepsTheTailItIsGiven(t *testing.T) {
|
||||
q, err := LoadQueries(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadQueries: %v", err)
|
||||
}
|
||||
const tail = ", но успела посмотреть не всю сеть"
|
||||
for i := 0; i < 20; i++ {
|
||||
if got := q.Say(QueryNetEmpty, map[string]string{"tail": tail}); !strings.Contains(got, tail) {
|
||||
t.Fatalf("net_empty dropped the tail: %q", got)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// query_unknown means she looked and found nothing. The phraser's fallback
|
||||
// means she failed to phrase an answer she had. Two causes, two sentences, or
|
||||
// the distinction the two files exist for is unobservable from the outside.
|
||||
func TestQueryUnknownNeverRepeatsAPhrasingFallback(t *testing.T) {
|
||||
q, err := LoadQueries(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadQueries: %v", err)
|
||||
}
|
||||
f, err := LoadFallbacks(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadFallbacks: %v", err)
|
||||
}
|
||||
failures := map[string]bool{}
|
||||
for _, v := range f.Variants() {
|
||||
failures[v] = true
|
||||
}
|
||||
for _, v := range q.d.VariantsOf(QueryUnknown) {
|
||||
if failures[v] {
|
||||
t.Errorf("query_unknown variant %q is also a phrasing failure line", v)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The weather line splits the count into a number and a noun, so a variant that
|
||||
// says the temperature without {word} is the hardcoded "градусов" coming back.
|
||||
func TestWeatherLineCountsWithTheHelper(t *testing.T) {
|
||||
q, err := LoadQueries(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadQueries: %v", err)
|
||||
}
|
||||
for _, v := range q.d.VariantsOf(QueryWeatherNow) {
|
||||
if strings.Contains(v, "градус") {
|
||||
t.Errorf("weather_now variant %q spells the noun out instead of using {word}", v)
|
||||
}
|
||||
}
|
||||
got := q.Say(QueryWeatherNow, map[string]string{
|
||||
"location": "Москва", "temp": "1", "word": Degrees(1), "condition": "ясно",
|
||||
})
|
||||
if !strings.Contains(got, "1 градус,") {
|
||||
t.Errorf("weather_now said %q, want the singular noun", got)
|
||||
}
|
||||
}
|
||||
|
||||
// No line spoken to him names a config key. She asks instead.
|
||||
func TestNoQueryLineRecitesAConfigPath(t *testing.T) {
|
||||
q, err := LoadQueries(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadQueries: %v", err)
|
||||
}
|
||||
for _, v := range q.Variants() {
|
||||
if strings.Contains(v, "voice.") || strings.Contains(v, "_location") {
|
||||
t.Errorf("variant %q says a config path out loud", v)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,115 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"name": "russian query answers and gaps v1",
|
||||
"notes": [
|
||||
"What a query source says when it answers from something other than the model, and what it says when it has nothing. Edit the wording here, no Go changes needed.",
|
||||
"Rules: she is feminine about herself, he is a man addressed as ты. Never вы/вас/ваш, never он/его about him. No pet names.",
|
||||
"A gap names its own gap. \"the feeds are not configured\", \"the search failed\" and \"I do not know\" are different sentences and must never collapse into one entry.",
|
||||
"query_unknown here is a real answer — she looked and found nothing. The phraser's identical-looking line in fallbacks_ru_v1.json is a failure to phrase. Two files, two entries, on purpose, so no variant here may repeat a string from there.",
|
||||
"Placeholders: {key} {value} a stored fact, {when} when she wrote it, {items} what she found, {text} a passage, {location} {temp} {condition} the weather, {word} the counted noun in the form {temp} needs, {tail} a caveat about how the answer was gathered.",
|
||||
"A count never carries a hardcoded noun. Russian inflects it — 1 градус, 2 градуса, 5 градусов — so the number goes in {temp} and the noun comes from the Go helper through {word}.",
|
||||
"{tail} is optional, and an entry that can be said without it needs one variant carrying no placeholder at all. Otherwise nothing is fillable and she says nothing, which he hears as a hang.",
|
||||
"fixed: true means exactly one variant and no picking. Used where the wording is load-bearing: the personal boundary, and the refusal to re-ask a question for another day."
|
||||
],
|
||||
"entries": {
|
||||
"query_unknown": {
|
||||
"variants": ["ничего не нашла.", "искала — не нашла."]
|
||||
},
|
||||
"other_day": {
|
||||
"fixed": true,
|
||||
"variants": ["про другой день так не отвечу — спроси целиком."]
|
||||
},
|
||||
"personal_none": {
|
||||
"fixed": true,
|
||||
"variants": ["не знаю — не нашла у тебя такой записи."]
|
||||
},
|
||||
"fact_when": {
|
||||
"fixed": true,
|
||||
"variants": ["записала это {when}"]
|
||||
},
|
||||
"fact_value": {
|
||||
"variants": ["у меня записано: {key} — {value}", "вот что записано: {key} — {value}"]
|
||||
},
|
||||
"found": {
|
||||
"variants": ["вот что я нашла: {text}", "нашла вот это: {text}", "есть такое: {text}"]
|
||||
},
|
||||
"page_text": {
|
||||
"variants": ["вот что на странице: {text}", "на странице вот это: {text}"]
|
||||
},
|
||||
"page_blocked": {
|
||||
"fixed": true,
|
||||
"variants": ["эта страница закрыта для чтения — сам сайт это запрещает."]
|
||||
},
|
||||
"page_empty": {
|
||||
"fixed": true,
|
||||
"variants": ["страница открылась, но читать там нечего."]
|
||||
},
|
||||
"feeds_off": {
|
||||
"fixed": true,
|
||||
"variants": ["ленты не настроены."]
|
||||
},
|
||||
"feeds_new": {
|
||||
"variants": ["вот что нового: {items}", "нового вот что: {items}"]
|
||||
},
|
||||
"feeds_empty": {
|
||||
"variants": ["в лентах пока ничего нового.", "в лентах тихо."]
|
||||
},
|
||||
"feeds_empty_topic": {
|
||||
"variants": ["по этой теме в лентах пока ничего.", "по этой теме в лентах тихо."]
|
||||
},
|
||||
"weather_now": {
|
||||
"variants": ["в {location} сейчас {temp} {word}, {condition}.", "{location}: {temp} {word}, {condition}."]
|
||||
},
|
||||
"weather_off": {
|
||||
"fixed": true,
|
||||
"variants": ["погода не настроена."]
|
||||
},
|
||||
"weather_nolocation": {
|
||||
"fixed": true,
|
||||
"variants": ["для какого города?"]
|
||||
},
|
||||
"net_off": {
|
||||
"fixed": true,
|
||||
"variants": ["сканирование сети не настроено."]
|
||||
},
|
||||
"page_off": {
|
||||
"fixed": true,
|
||||
"variants": ["я не читаю страницы — это не настроено."]
|
||||
},
|
||||
"net_empty": {
|
||||
"variants": ["в сети никого не нашла.", "в сети никого не нашла{tail}."]
|
||||
},
|
||||
"fail_plan": {
|
||||
"fixed": true,
|
||||
"variants": ["не получилось собрать план."]
|
||||
},
|
||||
"fail_notes": {
|
||||
"fixed": true,
|
||||
"variants": ["не получилось посмотреть записи."]
|
||||
},
|
||||
"fail_feeds": {
|
||||
"fixed": true,
|
||||
"variants": ["не получилось посмотреть ленты."]
|
||||
},
|
||||
"fail_calendar": {
|
||||
"fixed": true,
|
||||
"variants": ["не получилось проверить календарь."]
|
||||
},
|
||||
"fail_weather": {
|
||||
"fixed": true,
|
||||
"variants": ["не получилось узнать погоду."]
|
||||
},
|
||||
"fail_answer": {
|
||||
"fixed": true,
|
||||
"variants": ["не получилось найти ответ."]
|
||||
},
|
||||
"fail_page": {
|
||||
"fixed": true,
|
||||
"variants": ["не получилось прочитать страницу."]
|
||||
},
|
||||
"fail_netscan": {
|
||||
"fixed": true,
|
||||
"variants": ["не получилось просканировать сеть."]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -215,10 +215,12 @@ func TestSwap_RollbackFailureLeavesNoBackendAndDegrades(t *testing.T) {
|
||||
if _, _, aerr := p.acquire(); !errors.Is(aerr, ErrNoBackend) {
|
||||
t.Errorf("acquire error = %v; want ErrNoBackend", aerr)
|
||||
}
|
||||
// Phrasing degrades to its fallback instead of failing the turn.
|
||||
// Phrasing degrades to its fallback instead of failing the turn, and since
|
||||
// Vikunja #397 it reports the error next to that fallback so a measuring
|
||||
// caller can tell "no model" from "bad phrasing".
|
||||
got, err := p.PhraseChat(context.Background(), "привет", nil)
|
||||
if err != nil {
|
||||
t.Fatalf("PhraseChat after a total failure returned an error: %v", err)
|
||||
if !errors.Is(err, ErrNoBackend) {
|
||||
t.Errorf("PhraseChat error = %v; want ErrNoBackend alongside the fallback", err)
|
||||
}
|
||||
if got == "" {
|
||||
t.Error("PhraseChat returned empty; the fallback must still say something")
|
||||
|
||||
@@ -76,6 +76,29 @@ func TestAgendaGrammarSparesStatements(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// The two shapes that carried no question mark and no interrogative, so the
|
||||
// model saw them first and called them facts (Vikunja #498).
|
||||
func TestNarrativeGrammarsRouteToQuery(t *testing.T) {
|
||||
r := agendaRouter(t)
|
||||
r.grammars = append(r.grammars, NarrativeQueryGrammars()...)
|
||||
for _, u := range []string{
|
||||
"что дальше?",
|
||||
"и что там дальше",
|
||||
"what's next?",
|
||||
"расскажи про битву при Ватерлоо",
|
||||
"объясни как работает дизель",
|
||||
"опиши Ватерлоо",
|
||||
} {
|
||||
d, err := r.Route(context.Background(), u, refNow())
|
||||
if err != nil {
|
||||
t.Fatalf("%q: %v", u, err)
|
||||
}
|
||||
if d.Intent != IntentQuery || d.Stage != 0 {
|
||||
t.Errorf("%q routed intent=%s stage=%d, want query at stage 0", u, d.Intent, d.Stage)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The tomorrow form and the bare event noun. Both were measured answering
|
||||
// "пока не умею" on the deployed daemon, 02-08-2026, while the same question
|
||||
// about today worked — the first rule set needed "у меня" or a calendar noun
|
||||
@@ -101,6 +124,20 @@ func TestAgendaCoversOtherDaysAndNamedEvents(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// A narrative verb next to a capture verb is him asking for a note. Stage 0
|
||||
// declines and the extractor gets its turn.
|
||||
func TestNarrativeGrammarLeavesCapturesAlone(t *testing.T) {
|
||||
r := agendaRouter(t)
|
||||
r.grammars = append(r.grammars, NarrativeQueryGrammars()...)
|
||||
d, err := r.Route(context.Background(), "расскажи и запиши что я пил воду", refNow())
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if d.Stage == 0 && d.Intent == IntentQuery {
|
||||
t.Errorf("stage 0 claimed a capture: %+v", d)
|
||||
}
|
||||
}
|
||||
|
||||
// The two new rules are narrow on purpose. A world question that opens with
|
||||
// "когда" is not an agenda question, and telling her about a plan is not
|
||||
// asking about one.
|
||||
|
||||
@@ -236,6 +236,7 @@ func newBaselineRouter(t *testing.T, emb router.Embedder, llmR *router.LLMRouter
|
||||
// Same order as buildRouter (voicewire.go). The fixture is only worth
|
||||
// anything while its grammar set is the daemon's grammar set.
|
||||
grammars = append(grammars, router.AgendaQueryGrammars()...)
|
||||
grammars = append(grammars, router.NarrativeQueryGrammars()...)
|
||||
grammars = append(grammars, router.ReminderGrammar())
|
||||
return router.New(router.Config{
|
||||
Grammars: grammars,
|
||||
|
||||
@@ -30,6 +30,8 @@
|
||||
{ "id": "ru-query-016", "utterance": "покажи давление за неделю", "lang": "ru", "intent": "query", "tags": ["hard", "imperative"], "note": "imperative form but a read — must not route to act" },
|
||||
{ "id": "ru-query-017", "utterance": "чем я занимался в среду", "lang": "ru", "intent": "query", "tags": ["hard", "chat-shaped"] },
|
||||
{ "id": "ru-query-018", "utterance": "хватает ли места под новые бэкапы", "lang": "ru", "intent": "query", "tags": ["homelab"] },
|
||||
{ "id": "ru-query-020", "utterance": "что дальше?", "lang": "ru", "intent": "query", "tags": ["agenda", "hard"], "note": "the rest of the day, with no interrogative the model can read as a question — it routed fact until a stage 0 rule claimed it (V-498)" },
|
||||
{ "id": "ru-query-021", "utterance": "расскажи про битву при Ватерлоо", "lang": "ru", "intent": "query", "tags": ["world", "hard"], "note": "a world question phrased as an instruction. It routed fact, and the fact gate had to catch the write (V-498)" },
|
||||
{ "id": "en-query-001", "utterance": "did I take my vitamins today", "lang": "en", "intent": "query", "tags": ["fact-shaped"] },
|
||||
{ "id": "en-query-002", "utterance": "how long since the last backup finished", "lang": "en", "intent": "query", "tags": ["temporal"] },
|
||||
{ "id": "en-query-003", "utterance": "show me this week's weight", "lang": "en", "intent": "query", "tags": ["imperative"] },
|
||||
|
||||
@@ -0,0 +1,247 @@
|
||||
package router
|
||||
|
||||
import (
|
||||
"regexp"
|
||||
"strings"
|
||||
)
|
||||
|
||||
// Standing lists, matched deterministically (Vikunja #453).
|
||||
//
|
||||
// Same posture as task capture in task.go and for the same reason: the intent
|
||||
// enum is a contract shared with the relabelling prompt, so a list is not an
|
||||
// eighth intent. It is a note-shaped or query-shaped utterance carrying an
|
||||
// explicit marker, and the marker is a lookup.
|
||||
//
|
||||
// The markers are deliberately explicit. "молоко закончилось" is an
|
||||
// observation about the world and belongs in a note; only an instruction to
|
||||
// put something on a list puts it there.
|
||||
|
||||
// listStems — the lists he can name, by the stem every case form shares.
|
||||
// Russian declines the tag ("список покупок", "в покупки", "в покупках"), so
|
||||
// matching a stem is what makes those the same list.
|
||||
var listStems = []struct{ stem, list string }{
|
||||
{"покуп", "покупки"},
|
||||
{"продукт", "покупки"},
|
||||
{"магазин", "покупки"},
|
||||
{"аптек", "аптека"},
|
||||
{"хозяйств", "хозяйство"},
|
||||
{"shopping", "покупки"},
|
||||
{"groceries", "покупки"},
|
||||
{"pharmacy", "аптека"},
|
||||
}
|
||||
|
||||
// listCapturePrefixes — an instruction to add to a list. Longest match wins.
|
||||
var listCapturePrefixes = []string{
|
||||
"добавь в список",
|
||||
"добавь в покупки",
|
||||
"добавь к покупкам",
|
||||
"запиши в список",
|
||||
"внеси в список",
|
||||
"положи в список",
|
||||
"в список покупок",
|
||||
"add to the list",
|
||||
"add to my list",
|
||||
"add to the shopping list",
|
||||
"put on the list",
|
||||
}
|
||||
|
||||
// listQueryPrefixes — an ask to read a list back.
|
||||
var listQueryPrefixes = []string{
|
||||
"что в списке",
|
||||
"что в покупках",
|
||||
"что мне купить",
|
||||
"что нужно купить",
|
||||
"что надо купить",
|
||||
"покажи список",
|
||||
"прочитай список",
|
||||
"список покупок",
|
||||
"мой список",
|
||||
"what is on the list",
|
||||
"what's on the list",
|
||||
"read me the list",
|
||||
"show me the list",
|
||||
"shopping list",
|
||||
}
|
||||
|
||||
// listClearPhrases — the whole list is got. One sentence, one turn.
|
||||
var listClearPhrases = []string{
|
||||
"всё купил",
|
||||
"все купил",
|
||||
"всё взял",
|
||||
"все взял",
|
||||
"очисти список",
|
||||
"очисти покупки",
|
||||
"список пустой",
|
||||
"got everything",
|
||||
"clear the list",
|
||||
}
|
||||
|
||||
// listRemovePrefixes — one item off the list.
|
||||
var listRemovePrefixes = []string{
|
||||
"вычеркни",
|
||||
"убери из списка",
|
||||
"убери со списка",
|
||||
"купил",
|
||||
"взял",
|
||||
"cross off",
|
||||
"remove from the list",
|
||||
}
|
||||
|
||||
// listTrimCut — punctuation and connectives to strip off a parsed remainder.
|
||||
const listTrimCut = " .,;:!?—-"
|
||||
|
||||
// ListCapture — a parsed list instruction: which list, and the item.
|
||||
type ListCapture struct {
|
||||
List string
|
||||
Item string
|
||||
}
|
||||
|
||||
// ParseListCapture reports whether an utterance puts something on a list, and
|
||||
// returns the list tag and the item. A marker with nothing usable after it is
|
||||
// not a capture: there is no item in "добавь в список покупок".
|
||||
func ParseListCapture(text string) (ListCapture, bool) {
|
||||
rest, ok := afterLongestPrefix(text, listCapturePrefixes)
|
||||
if !ok {
|
||||
return ListCapture{}, false
|
||||
}
|
||||
list, rest := takeListTag(rest)
|
||||
rest = strings.Trim(rest, listTrimCut)
|
||||
if rest == "" {
|
||||
return ListCapture{}, false
|
||||
}
|
||||
return ListCapture{List: list, Item: rest}, true
|
||||
}
|
||||
|
||||
// ParseListQuery reports whether an utterance asks for a list, and which one.
|
||||
func ParseListQuery(text string) (string, bool) {
|
||||
rest, ok := afterLongestPrefix(text, listQueryPrefixes)
|
||||
if !ok {
|
||||
return "", false
|
||||
}
|
||||
list, _ := takeListTag(rest)
|
||||
return list, true
|
||||
}
|
||||
|
||||
// ParseListClear reports whether an utterance crosses off a whole list.
|
||||
func ParseListClear(text string) (string, bool) {
|
||||
lower := strings.ToLower(strings.Trim(strings.TrimSpace(text), listTrimCut))
|
||||
for _, p := range listClearPhrases {
|
||||
if lower == p || strings.HasPrefix(lower, p+" ") {
|
||||
list, _ := takeListTag(strings.TrimSpace(lower[len(p):]))
|
||||
return list, true
|
||||
}
|
||||
}
|
||||
return "", false
|
||||
}
|
||||
|
||||
// ParseListRemove reports whether an utterance takes one named item off a
|
||||
// list, and returns the list and the item.
|
||||
//
|
||||
// The item is required. "купил" on its own is him reporting he shopped, which
|
||||
// ParseListClear reads first, and it must not fall through to here and remove
|
||||
// nothing while sounding like it did.
|
||||
func ParseListRemove(text string) (ListCapture, bool) {
|
||||
rest, ok := afterLongestPrefix(text, listRemovePrefixes)
|
||||
if !ok {
|
||||
return ListCapture{}, false
|
||||
}
|
||||
list, rest := takeListTag(rest)
|
||||
rest = strings.Trim(rest, listTrimCut)
|
||||
for _, lead := range []string{"из списка ", "со списка ", "из ", "from the list "} {
|
||||
rest = strings.TrimPrefix(rest, lead)
|
||||
}
|
||||
rest = strings.Trim(rest, listTrimCut)
|
||||
if rest == "" {
|
||||
return ListCapture{}, false
|
||||
}
|
||||
return ListCapture{List: list, Item: rest}, true
|
||||
}
|
||||
|
||||
// afterLongestPrefix matches the longest prefix in the table and returns what
|
||||
// follows it, trimmed. Lowercasing does not change the byte length of Russian
|
||||
// or English letters, so the index carries over to the original text.
|
||||
func afterLongestPrefix(text string, prefixes []string) (string, bool) {
|
||||
trimmed := strings.TrimSpace(text)
|
||||
lower := strings.ToLower(trimmed)
|
||||
best := ""
|
||||
for _, p := range prefixes {
|
||||
if strings.HasPrefix(lower, p) && len(p) > len(best) {
|
||||
best = p
|
||||
}
|
||||
}
|
||||
if best == "" {
|
||||
return "", false
|
||||
}
|
||||
return strings.Trim(trimmed[len(best):], listTrimCut), true
|
||||
}
|
||||
|
||||
// takeListTag reads a list name off the front of the remainder and returns the
|
||||
// list plus what is left. A remainder naming no list is the default list, and
|
||||
// nothing is consumed — "добавь в список молоко" names no list and the item is
|
||||
// молоко.
|
||||
func takeListTag(rest string) (string, string) {
|
||||
fields := strings.Fields(rest)
|
||||
if len(fields) == 0 {
|
||||
return "покупки", ""
|
||||
}
|
||||
head := strings.ToLower(strings.Trim(fields[0], listTrimCut))
|
||||
// "в список покупок" leaves "покупок"; "в списке" leaves nothing.
|
||||
if head == "список" || head == "списке" || head == "списка" || head == "list" {
|
||||
fields = fields[1:]
|
||||
if len(fields) == 0 {
|
||||
return "покупки", ""
|
||||
}
|
||||
head = strings.ToLower(strings.Trim(fields[0], listTrimCut))
|
||||
}
|
||||
for _, s := range listStems {
|
||||
if strings.HasPrefix(head, s.stem) {
|
||||
return s.list, strings.Join(fields[1:], " ")
|
||||
}
|
||||
}
|
||||
return "покупки", strings.Join(fields, " ")
|
||||
}
|
||||
|
||||
// ListGrammars — stage 0 for the list (Vikunja #453).
|
||||
//
|
||||
// Both patterns match everything and the Build functions are the real filter,
|
||||
// the shape the wake-word act grammar already uses: the parsers above are the
|
||||
// definition of a list utterance and duplicating them as regexps would give
|
||||
// two answers to one question.
|
||||
//
|
||||
// Why stage 0 at all: an add and a read-back are deterministic and cheap, and
|
||||
// leaving them to the model means "добавь в список покупок молоко" lands as an
|
||||
// act or a fact on the turns the model has a bad day. The action handlers still
|
||||
// re-parse, so a list turn that arrives by any other route still works.
|
||||
func ListGrammars() []Grammar {
|
||||
anything := regexp.MustCompile(`(?s)^(.*)$`)
|
||||
return []Grammar{
|
||||
{
|
||||
Name: "list-query",
|
||||
Pattern: anything,
|
||||
Build: func(m []string) (Decision, bool) {
|
||||
if _, ok := ParseListQuery(m[1]); !ok {
|
||||
return Decision{}, false
|
||||
}
|
||||
return Decision{Stage: 0, Intent: IntentQuery, Confidence: 1.0}, true
|
||||
},
|
||||
},
|
||||
{
|
||||
Name: "list-capture",
|
||||
Pattern: anything,
|
||||
Build: func(m []string) (Decision, bool) {
|
||||
text := m[1]
|
||||
_, add := ParseListCapture(text)
|
||||
_, clear := ParseListClear(text)
|
||||
if !add && !clear {
|
||||
return Decision{}, false
|
||||
}
|
||||
return Decision{
|
||||
Stage: 0,
|
||||
Intent: IntentNote,
|
||||
Confidence: 1.0,
|
||||
Slots: Slots{Text: strings.TrimSpace(text)},
|
||||
}, true
|
||||
},
|
||||
},
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,89 @@
|
||||
package router
|
||||
|
||||
import "testing"
|
||||
|
||||
func TestParseListCaptureReadsListAndItem(t *testing.T) {
|
||||
cases := []struct {
|
||||
utterance string
|
||||
list string
|
||||
item string
|
||||
}{
|
||||
{"добавь в список покупок молоко", "покупки", "молоко"},
|
||||
{"добавь в список молоко", "покупки", "молоко"},
|
||||
{"Добавь в покупки хлеб и яйца", "покупки", "хлеб и яйца"},
|
||||
{"запиши в список аптеки бинт", "аптека", "бинт"},
|
||||
{"добавь в список хозяйства лампочки.", "хозяйство", "лампочки"},
|
||||
{"add to the shopping list milk", "покупки", "milk"},
|
||||
}
|
||||
for _, c := range cases {
|
||||
got, ok := ParseListCapture(c.utterance)
|
||||
if !ok {
|
||||
t.Errorf("ParseListCapture(%q) did not claim it", c.utterance)
|
||||
continue
|
||||
}
|
||||
if got.List != c.list || got.Item != c.item {
|
||||
t.Errorf("ParseListCapture(%q) = %+v; want list %q item %q", c.utterance, got, c.list, c.item)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// A marker with no item is not a capture, and an utterance that only mentions
|
||||
// shopping is not one either.
|
||||
func TestParseListCapturePasses(t *testing.T) {
|
||||
for _, u := range []string{
|
||||
"добавь в список покупок",
|
||||
"добавь в список",
|
||||
"молоко закончилось",
|
||||
"надо бы съездить в магазин",
|
||||
"добавь в задачи купить молоко",
|
||||
} {
|
||||
if got, ok := ParseListCapture(u); ok {
|
||||
t.Errorf("ParseListCapture(%q) claimed it as %+v", u, got)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestParseListQueryNamesTheList(t *testing.T) {
|
||||
cases := []struct{ utterance, list string }{
|
||||
{"что в списке покупок?", "покупки"},
|
||||
{"что в списке", "покупки"},
|
||||
{"что мне купить", "покупки"},
|
||||
{"покажи список аптеки", "аптека"},
|
||||
{"what's on the list", "покупки"},
|
||||
}
|
||||
for _, c := range cases {
|
||||
list, ok := ParseListQuery(c.utterance)
|
||||
if !ok {
|
||||
t.Errorf("ParseListQuery(%q) did not claim it", c.utterance)
|
||||
continue
|
||||
}
|
||||
if list != c.list {
|
||||
t.Errorf("ParseListQuery(%q) = %q; want %q", c.utterance, list, c.list)
|
||||
}
|
||||
}
|
||||
if _, ok := ParseListQuery("какие у меня задачи"); ok {
|
||||
t.Error("ParseListQuery claimed a task question")
|
||||
}
|
||||
}
|
||||
|
||||
func TestParseListClearAndRemove(t *testing.T) {
|
||||
if list, ok := ParseListClear("всё купил"); !ok || list != "покупки" {
|
||||
t.Errorf("ParseListClear = %q, %v; want покупки, true", list, ok)
|
||||
}
|
||||
if list, ok := ParseListClear("очисти список аптеки"); !ok || list != "аптека" {
|
||||
t.Errorf("ParseListClear = %q, %v; want аптека, true", list, ok)
|
||||
}
|
||||
if _, ok := ParseListClear("купил молоко"); ok {
|
||||
t.Error("ParseListClear claimed a single item")
|
||||
}
|
||||
got, ok := ParseListRemove("вычеркни молоко")
|
||||
if !ok || got.Item != "молоко" || got.List != "покупки" {
|
||||
t.Errorf("ParseListRemove = %+v, %v; want молоко on покупки", got, ok)
|
||||
}
|
||||
if got, ok := ParseListRemove("убери из списка аптеки бинт"); !ok || got.Item != "бинт" || got.List != "аптека" {
|
||||
t.Errorf("ParseListRemove = %+v, %v; want бинт on аптека", got, ok)
|
||||
}
|
||||
if _, ok := ParseListRemove("вычеркни"); ok {
|
||||
t.Error("ParseListRemove claimed a marker with no item")
|
||||
}
|
||||
}
|
||||
+23
-25
@@ -1,32 +1,30 @@
|
||||
package router
|
||||
|
||||
import "strings"
|
||||
import (
|
||||
"strings"
|
||||
|
||||
// interrogatives — the question words that mark an utterance as asking rather
|
||||
// than telling. Tokenized, never substring: "что" inside "чтобы" and "как"
|
||||
// inside "какао" are not questions.
|
||||
var interrogatives = []string{
|
||||
"что", "чего", "какой", "какая", "какое", "какие", "каких",
|
||||
"кто", "кого", "кому", "чей", "почему", "зачем", "отчего",
|
||||
"где", "куда", "откуда", "когда", "сколько", "как",
|
||||
"what", "who", "whom", "why", "when", "where", "which", "how",
|
||||
}
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
)
|
||||
|
||||
// narrativeRequests — "tell me about X" asks for knowledge Maven does not
|
||||
// hold about him. It carries no question mark and no interrogative, which is
|
||||
// how "расскажи про битву при Ватерлоо" reached the fact store (#470).
|
||||
var narrativeRequests = []string{
|
||||
"расскажи", "объясни", "опиши", "перечисли",
|
||||
"tell", "explain", "describe",
|
||||
}
|
||||
|
||||
// captureVerbs — an explicit instruction to record something. These win over
|
||||
// every test below, because "запиши что я пил воду" contains an interrogative
|
||||
// and is still a capture: the word he said is "запиши".
|
||||
var captureVerbs = []string{
|
||||
"запиши", "запомни", "отметь", "заметь", "добавь", "сохрани",
|
||||
"note", "remember", "log", "save",
|
||||
}
|
||||
// The three word sets this file tests against are closed classes, so they live
|
||||
// complete in internal/lexicon rather than inline here (Vikunja #525). The
|
||||
// inline lists were short: no "чем", no "чём", no "кем", no declined "какой",
|
||||
// so "чем ты занята" carried no interrogative at all and read as a statement.
|
||||
//
|
||||
// interrogatives mark an utterance as asking rather than telling.
|
||||
// narrativeRequests are "tell me about X", which asks for knowledge Maven does
|
||||
// not hold about him and carries neither a question mark nor an interrogative —
|
||||
// that is how "расскажи про битву при Ватерлоо" reached the fact store (#470).
|
||||
// captureVerbs win over both, because "запиши что я пил воду" contains an
|
||||
// interrogative and is still a capture: the word he said is "запиши".
|
||||
//
|
||||
// All three are matched over tokens, never as substrings: "что" inside "чтобы"
|
||||
// and "как" inside "какао" are not questions.
|
||||
var (
|
||||
interrogatives = lexicon.Interrogatives()
|
||||
narrativeRequests = lexicon.NarrativeRequests()
|
||||
captureVerbs = lexicon.CaptureVerbs()
|
||||
)
|
||||
|
||||
// IsQuestionShaped reports whether text asks for something rather than
|
||||
// records it. It is a deterministic offline test over tokens, so it costs
|
||||
|
||||
@@ -1,6 +1,10 @@
|
||||
package router
|
||||
|
||||
import "strings"
|
||||
import (
|
||||
"strings"
|
||||
|
||||
"github.com/kami/maven/internal/morph"
|
||||
)
|
||||
|
||||
// thinSingleToken — is a one-word utterance thin evidence, or is it a whole
|
||||
// sentence?
|
||||
@@ -17,13 +21,15 @@ import "strings"
|
||||
//
|
||||
// - a closed lexicon of social and command singles, which are complete by
|
||||
// definition ("привет", "спасибо", "стоп", "yes");
|
||||
// - a suffix test for an inflected predicate — past tense, 2nd person,
|
||||
// reflexive. Verbs carry their own subject, so a verb IS a sentence.
|
||||
// - a dictionary lookup for a verb form. A verb carries its own subject,
|
||||
// tense and gender, so a verb IS a sentence.
|
||||
//
|
||||
// The suffix test is deliberately loose about nouns that happen to end the
|
||||
// same way ("канал" reads as past tense here). That direction of error only
|
||||
// costs a clarify we would not have asked for; the other direction — treating
|
||||
// a real report as thin — is the bug being fixed.
|
||||
// The dictionary lookup replaced a list of 24 letter endings (Vikunja #526). The
|
||||
// list was loose in a direction its own comment named: "канал" ends in -ал and
|
||||
// read as past tense, and short words needed a length exemption so "нос" and
|
||||
// "лес" would survive a two-letter suffix. Asking a morphological dictionary
|
||||
// costs one map lookup and has no such errors — grammar is what a dictionary is
|
||||
// for.
|
||||
func thinSingleToken(utterance string) bool {
|
||||
f := strings.Fields(utterance)
|
||||
if len(f) != 1 {
|
||||
@@ -36,7 +42,7 @@ func thinSingleToken(utterance string) bool {
|
||||
if completeSingles[w] {
|
||||
return false
|
||||
}
|
||||
return !looksInflected(w)
|
||||
return !morph.IsVerbForm(w)
|
||||
}
|
||||
|
||||
// completeSingles — one-word utterances that need no second half. Greetings,
|
||||
@@ -58,33 +64,3 @@ var completeSingles = map[string]bool{
|
||||
"sure": true, "right": true, "stop": true, "cancel": true, "help": true,
|
||||
"repeat": true, "continue": true,
|
||||
}
|
||||
|
||||
// inflectedSuffixes — endings that mark a finite or past-tense Russian verb.
|
||||
// Ordered longest-first is unnecessary (any match wins), but each entry is
|
||||
// chosen to be long enough that common nouns rarely collide.
|
||||
var inflectedSuffixes = []string{
|
||||
// reflexive — strongly verbal whatever precedes it
|
||||
"ся", "сь",
|
||||
// past tense
|
||||
"ал", "ял", "ил", "ел", "ыл", "ул", "ёл", "ала", "яла", "ила", "ела",
|
||||
"ыла", "ула", "али", "яли", "или", "ели",
|
||||
// 2nd person singular
|
||||
"ешь", "ишь", "ёшь",
|
||||
// 1st/2nd person plural, 3rd person plural
|
||||
"аем", "яем", "уем", "аете", "ите", "ают", "яют", "уют", "ат", "ят",
|
||||
}
|
||||
|
||||
// looksInflected — does the word carry a verb ending? Short words are exempt:
|
||||
// a three-letter token is not enough stem to trust a two-letter suffix on
|
||||
// ("газ" would otherwise never match, but "нос" and "лес" would).
|
||||
func looksInflected(w string) bool {
|
||||
if len([]rune(w)) < 5 {
|
||||
return false
|
||||
}
|
||||
for _, s := range inflectedSuffixes {
|
||||
if strings.HasSuffix(w, s) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
+18
-29
@@ -5,6 +5,8 @@ import (
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
)
|
||||
|
||||
// DateTimeParser — resolves relative→absolute AT CAPTURE ("in 4h" → now+4h),
|
||||
@@ -348,26 +350,17 @@ func leadingDigits(s string) (int, string, bool) {
|
||||
return n, s[i:], true
|
||||
}
|
||||
|
||||
// wordNumbers — small set, enough for natural test seeds ("four hours",
|
||||
// "thirty minutes"). Production dateparser handles the full ru/en range.
|
||||
var wordNumbers = map[string]int{
|
||||
"one": 1, "two": 2, "three": 3, "four": 4, "five": 5,
|
||||
"six": 6, "seven": 7, "eight": 8, "nine": 9, "ten": 10,
|
||||
"eleven": 11, "twelve": 12, "fifteen": 15, "twenty": 20,
|
||||
"thirty": 30, "forty": 40, "fifty": 50, "sixty": 60,
|
||||
// Russian word numbers (gender variants cover natural речи)
|
||||
"один": 1, "одна": 1, "одно": 1,
|
||||
"два": 2, "две": 2, "три": 3, "четыре": 4,
|
||||
"пять": 5, "шесть": 6, "семь": 7, "восемь": 8,
|
||||
"девять": 9, "десять": 10,
|
||||
}
|
||||
// leadingWordNumber reads a spoken number off the front of a phrase — "два
|
||||
// часа", "twenty minutes". The number words are a closed class and live in
|
||||
// internal/lexicon, complete: the inline table here stopped at "десять" in
|
||||
// Russian, so "пятнадцать минут" was not a duration (Vikunja #525).
|
||||
|
||||
func leadingWordNumber(s string) (int, string, bool) {
|
||||
toks := strings.Fields(s)
|
||||
if len(toks) == 0 {
|
||||
return 0, "", false
|
||||
}
|
||||
n, ok := wordNumbers[toks[0]]
|
||||
n, ok := lexicon.Cardinal(toks[0])
|
||||
if !ok {
|
||||
return 0, "", false
|
||||
}
|
||||
@@ -450,24 +443,20 @@ func (AnaphoraResolver) Resolve(text string) (ref string, ok bool) {
|
||||
}
|
||||
|
||||
// ParseCalendarDate detects RU/EN calendar day words in text and returns
|
||||
// midnight of that day in now's own time zone. Handles "сегодня", "завтра",
|
||||
// "послезавтра", "вчера" (and the English words). Returns zero time + false
|
||||
// if no match.
|
||||
// midnight of that day in now's own time zone. Returns zero time + false if no
|
||||
// match.
|
||||
//
|
||||
// "послезавтра" is checked before "завтра" because it contains it.
|
||||
// The day words are a closed class and live in internal/lexicon, so this is a
|
||||
// lookup rather than an ordered switch (Vikunja #525). The switch it replaced
|
||||
// had to test "послезавтра" before "завтра" by hand, because one contains the
|
||||
// other — and it matched on substrings, so "завтраком" was tomorrow. The lexicon
|
||||
// matches on word boundaries and gained "позавчера", which was never here.
|
||||
func ParseCalendarDate(text string, now time.Time) (time.Time, bool) {
|
||||
lower := strings.ToLower(text)
|
||||
switch {
|
||||
case strings.Contains(lower, "сегодня") || strings.Contains(lower, "today"):
|
||||
return midnight(now, 0), true
|
||||
case strings.Contains(lower, "послезавтра") || strings.Contains(lower, "day after tomorrow"):
|
||||
return midnight(now, 2), true
|
||||
case strings.Contains(lower, "завтра") || strings.Contains(lower, "tomorrow"):
|
||||
return midnight(now, 1), true
|
||||
case strings.Contains(lower, "вчера") || strings.Contains(lower, "yesterday"):
|
||||
return midnight(now, -1), true
|
||||
days, ok := lexicon.DayOffsetIn(text)
|
||||
if !ok {
|
||||
return time.Time{}, false
|
||||
}
|
||||
return time.Time{}, false
|
||||
return midnight(now, days), true
|
||||
}
|
||||
|
||||
// midnight returns the start of the day that is `days` away from now, in
|
||||
|
||||
+134
-3
@@ -3,6 +3,9 @@ package router
|
||||
import (
|
||||
"regexp"
|
||||
"strings"
|
||||
"unicode"
|
||||
|
||||
"github.com/kami/maven/internal/lexicon"
|
||||
)
|
||||
|
||||
// Grammar — one stage-0 exact-match pattern. Wake-word + known command grammar
|
||||
@@ -208,11 +211,139 @@ func AgendaQueryGrammars() []Grammar {
|
||||
}
|
||||
}
|
||||
|
||||
// NarrativeQueryGrammars — stage-0 grammars for the two question shapes that
|
||||
// carry no question mark and no interrogative, and so reached the resident
|
||||
// model with nothing deterministic in front of them (Vikunja #498).
|
||||
//
|
||||
// Both were routed IntentFact by the model. The fact gate catches the write and
|
||||
// re-runs the turn as a query, so nothing breaks today; what they cost is a full
|
||||
// model round trip to reach a decision two patterns can make offline, and a
|
||||
// wrong row on the routing fixture.
|
||||
//
|
||||
// Wired after the agenda grammars, which is where their overlap resolves:
|
||||
// "расскажи, что у меня сегодня" is claimed here as a query either way.
|
||||
func NarrativeQueryGrammars() []Grammar {
|
||||
return []Grammar{
|
||||
{
|
||||
// "что дальше?" — the rest of the day. IsRestOfDayQuery already
|
||||
// recognises it downstream in the query chain, but that runs after
|
||||
// the routing decision, and the routing decision was fact.
|
||||
Name: "rest-of-day-query",
|
||||
Pattern: regexp.MustCompile(`(?i)(^|\s)(что|чего)\s+(там\s+|потом\s+)?дальше(\s|[?!.]|$)|(^|\s)what'?s?\s+next(\s|[?!.]|$)`),
|
||||
Build: agendaQueryBuild,
|
||||
},
|
||||
{
|
||||
// "расскажи про X" — a world question phrased as an instruction.
|
||||
// The lexicon is narrativeRequests, already written for the
|
||||
// question-shaped test in question.go.
|
||||
//
|
||||
// Anchored at the start: "запиши что мне рассказали" is a capture,
|
||||
// and a narrative verb buried mid-utterance is not the shape.
|
||||
Name: "narrative-query",
|
||||
Pattern: narrativeQueryPattern,
|
||||
Build: narrativeQueryBuild,
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
// entertainmentNouns — what "расскажи" asks for when it is not asking for
|
||||
// knowledge. "расскажи анекдот про программистов" is chat: he wants her to make
|
||||
// something up, which is the one case where inventing is the right answer
|
||||
// (fixture ru-chat-003).
|
||||
var entertainmentNouns = []string{
|
||||
"анекдот", "анекдоты", "шутку", "шутки", "историю", "сказку", "сказки",
|
||||
"joke", "jokes", "story",
|
||||
}
|
||||
|
||||
// narrativeQueryBuild — the narrative shape is a query unless he also said one
|
||||
// of the capture verbs, or asked for entertainment. "расскажи и запиши" is him
|
||||
// asking for a note, and stage 0 must not take either off the cascade.
|
||||
func narrativeQueryBuild(m []string) (Decision, bool) {
|
||||
rest := ""
|
||||
if len(m) > 3 {
|
||||
rest = m[3]
|
||||
}
|
||||
for _, t := range planTokens(rest) {
|
||||
for _, v := range captureVerbs {
|
||||
if t == v {
|
||||
return Decision{}, false
|
||||
}
|
||||
}
|
||||
for _, v := range entertainmentNouns {
|
||||
if t == v {
|
||||
return Decision{}, false
|
||||
}
|
||||
}
|
||||
}
|
||||
return agendaQueryBuild(m)
|
||||
}
|
||||
|
||||
// narrativeQueryPattern — "расскажи про X", built from the lexicon rather than
|
||||
// spelled out here (Vikunja #527). The verbs used to be a second copy of
|
||||
// lexicon.NarrativeRequests, and a second copy of a closed set is a set that
|
||||
// drifts: adding "поясни" in the data file left this rule not knowing it.
|
||||
//
|
||||
// Anchored at the start, which was the point of the old literal and still is:
|
||||
// "запиши что мне рассказали" is a capture, and a narrative verb buried
|
||||
// mid-utterance is not the shape.
|
||||
var narrativeQueryPattern = regexp.MustCompile(
|
||||
`(?i)^\s*(` + strings.Join(lexicon.NarrativeRequests(), "|") + `)(\s+(.*))?$`)
|
||||
|
||||
// dayWordPattern — the day words an agenda question can name. Weekdays appear
|
||||
// in the accusative and prepositional forms the questions actually use ("в
|
||||
// среду", "на среде"), which is why the stems carry an inflection tail rather
|
||||
// than a fixed ending.
|
||||
const dayWordPattern = `(сегодня|завтра|послезавтра|выходн[а-я]+|недел[а-я]+|понедельник[а-я]*|вторник[а-я]*|сред[ауые][а-я]*|четверг[а-я]*|пятниц[ауые][а-я]*|суббот[ауые][а-я]*|воскресень[ея][а-я]*)`
|
||||
// среду", "на среде"), so each one contributes its stem plus an inflection
|
||||
// tail; the relative day words are exact.
|
||||
//
|
||||
// Built from the lexicon for the same reason as above. The literal that stood
|
||||
// here spelled all seven weekdays out a second time, in a third file after
|
||||
// cmd/mavend/voice.go and internal/ttsnorm.
|
||||
var dayWordPattern = buildDayWordPattern()
|
||||
|
||||
// buildDayWordPattern — one alternation over the relative day words, the
|
||||
// weekday stems, and the two period words that are in no closed set ("на
|
||||
// выходных", "на неделе" name a span, not a day).
|
||||
func buildDayWordPattern() string {
|
||||
alts := []string{`выходн[а-я]+`, `недел[а-я]+`}
|
||||
for _, w := range lexicon.DayOffsetWords() {
|
||||
if strings.Contains(w, " ") || !isCyrillic(w) {
|
||||
// Multi-word and English members belong to the offset lookup, not
|
||||
// to a Russian agenda pattern.
|
||||
continue
|
||||
}
|
||||
alts = append(alts, regexp.QuoteMeta(w))
|
||||
}
|
||||
for i := 0; i < 7; i++ {
|
||||
day := lexicon.Weekday(i)
|
||||
if day == "" {
|
||||
continue
|
||||
}
|
||||
alts = append(alts, weekdayStem(day)+`[а-я]*`)
|
||||
}
|
||||
return `(` + strings.Join(alts, "|") + `)`
|
||||
}
|
||||
|
||||
// weekdayStem trims the nominative ending off a weekday so the pattern matches
|
||||
// the case forms an agenda question uses: "среда" has to reach "в среду", and
|
||||
// "понедельник" already ends on its stem.
|
||||
func weekdayStem(day string) string {
|
||||
r := []rune(day)
|
||||
switch r[len(r)-1] {
|
||||
case 'а', 'я', 'е', 'о', 'ь':
|
||||
return string(r[:len(r)-1])
|
||||
}
|
||||
return day
|
||||
}
|
||||
|
||||
// isCyrillic reports whether every rune is Cyrillic. Used to keep the English
|
||||
// members of a bilingual lexicon set out of a Russian-only pattern.
|
||||
func isCyrillic(s string) bool {
|
||||
for _, r := range s {
|
||||
if !unicode.Is(unicode.Cyrillic, r) {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return s != ""
|
||||
}
|
||||
|
||||
// agendaQueryBuild — shared Build for the agenda grammars. Confidence 1.0 on
|
||||
// the intent only: the utterance travels intact and the query chain's own
|
||||
|
||||
@@ -0,0 +1,265 @@
|
||||
package say
|
||||
|
||||
// Package say holds the mechanics every family of hand-written Russian lines
|
||||
// shares. The families themselves live next to the code that speaks them.
|
||||
//
|
||||
// Deck — the mechanics every family of hand-written Russian lines shares.
|
||||
//
|
||||
// A family is one embedded JSON file: schema-versioned, several variants per
|
||||
// entry, never the same variant twice running, and a hard floor of Go literals
|
||||
// under it so a broken file cannot take her words away. fallbacks.go was the
|
||||
// first family (Vikunja #501) and acks.go the second, at which point copying
|
||||
// eighty lines of loader per family stopped being defensible.
|
||||
//
|
||||
// What stays per family: the file, the keys, the floor literals, the accessor
|
||||
// names, and any validation only that family can state.
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"math/rand"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
)
|
||||
|
||||
// Entry — one line she can say, in as many wordings as the file gives.
|
||||
type Entry struct {
|
||||
// Fixed — one variant, never picked between. For wording that must not
|
||||
// drift from turn to turn, like a phrase naming one specific gap.
|
||||
Fixed bool `json:"fixed"`
|
||||
Variants []string `json:"variants"`
|
||||
}
|
||||
|
||||
type file struct {
|
||||
SchemaVersion int `json:"schema_version"`
|
||||
Name string `json:"name"`
|
||||
Notes []string `json:"notes"`
|
||||
Entries map[string]Entry `json:"entries"`
|
||||
}
|
||||
|
||||
// Deck picks a line. Safe for concurrent use. A Deck with no entries answers
|
||||
// from the floor, which is what an unloadable file leaves behind (FloorDeck).
|
||||
type Deck struct {
|
||||
mu sync.Mutex
|
||||
rnd *rand.Rand
|
||||
last map[string]string
|
||||
file file
|
||||
keys []string
|
||||
floor map[string]string
|
||||
}
|
||||
|
||||
// loadDeck parses raw, checks the version and every required key, and seeds the
|
||||
// picker. Pass a source to make the picking reproducible in tests; nil seeds
|
||||
// from the clock.
|
||||
func Load(raw []byte, version int, keys []string, floor map[string]string, src rand.Source) (*Deck, error) {
|
||||
var f file
|
||||
if err := json.Unmarshal(raw, &f); err != nil {
|
||||
return nil, fmt.Errorf("parse: %w", err)
|
||||
}
|
||||
if f.SchemaVersion != version {
|
||||
return nil, fmt.Errorf("schema_version %d, want %d", f.SchemaVersion, version)
|
||||
}
|
||||
for _, k := range keys {
|
||||
e, ok := f.Entries[k]
|
||||
if !ok || len(e.Variants) == 0 {
|
||||
return nil, fmt.Errorf("entry %q is missing or empty", k)
|
||||
}
|
||||
if e.Fixed && len(e.Variants) != 1 {
|
||||
return nil, fmt.Errorf("entry %q is fixed but has %d variants", k, len(e.Variants))
|
||||
}
|
||||
}
|
||||
if src == nil {
|
||||
src = rand.NewSource(time.Now().UnixNano())
|
||||
}
|
||||
return &Deck{rnd: rand.New(src), last: map[string]string{}, file: f, keys: keys, floor: floor}, nil
|
||||
}
|
||||
|
||||
// requirePlaceholder fails the load when a variant of key does not use ph. For
|
||||
// an entry whose whole job is to read something back, a variant without the
|
||||
// placeholder silently drops it.
|
||||
func (d *Deck) RequirePlaceholder(key, ph string) error {
|
||||
for _, v := range d.file.Entries[key].Variants {
|
||||
if !strings.Contains(v, ph) {
|
||||
return fmt.Errorf("%q variant %q does not use %s", key, v, ph)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// text returns one variant for key with the placeholders filled in. A nil
|
||||
// receiver answers from the floor, so no caller checks whether the file loaded.
|
||||
func (d *Deck) Text(key string, vars map[string]string) string {
|
||||
tmpl := ""
|
||||
if d != nil {
|
||||
if e, ok := d.file.Entries[key]; ok && len(e.Variants) > 0 {
|
||||
tmpl = d.pick(key, fillable(e.Variants, vars))
|
||||
}
|
||||
}
|
||||
if tmpl == "" {
|
||||
tmpl = floorOf(d, key)
|
||||
}
|
||||
return fill(tmpl, vars)
|
||||
}
|
||||
|
||||
// matches reports whether text is a line key could have produced. A caller that
|
||||
// has to recognise one of these lines cannot compare against a literal any more.
|
||||
func (d *Deck) Matches(key string, vars map[string]string, text string) bool {
|
||||
if fill(floorOf(d, key), vars) == text {
|
||||
return true
|
||||
}
|
||||
if d == nil {
|
||||
return false
|
||||
}
|
||||
for _, v := range d.file.Entries[key].Variants {
|
||||
if fill(v, vars) == text {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// variants returns every line the file can produce, in key order, for the
|
||||
// persona scorer. Stable order so a failure names the same variant twice.
|
||||
func (d *Deck) Variants() []string {
|
||||
if d == nil {
|
||||
return nil
|
||||
}
|
||||
var out []string
|
||||
for _, k := range d.keys {
|
||||
out = append(out, d.file.Entries[k].Variants...)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// VariantsOf returns the wordings the file gives for one key, for a test that
|
||||
// has something to say about every one of them.
|
||||
func (d *Deck) VariantsOf(key string) []string {
|
||||
if d == nil {
|
||||
return nil
|
||||
}
|
||||
return d.file.Entries[key].Variants
|
||||
}
|
||||
|
||||
// UnfixedSingles lists the keys with exactly one variant that are not marked
|
||||
// fixed. Nothing breaks on one — the picker has nothing to pick either way — but
|
||||
// the flag is what a reader goes by, and parallel entries disagreeing about it
|
||||
// is how a family stops being readable. Load already rejects the other half of
|
||||
// the rule, fixed with more than one variant, so this is the pair to it.
|
||||
func (d *Deck) UnfixedSingles() []string {
|
||||
if d == nil {
|
||||
return nil
|
||||
}
|
||||
var out []string
|
||||
for _, k := range d.keys {
|
||||
if e := d.file.Entries[k]; len(e.Variants) == 1 && !e.Fixed {
|
||||
out = append(out, k)
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// fillable narrows variants to the ones this call can actually say, which is
|
||||
// the rule an optional placeholder needs: a caller with nothing to put in
|
||||
// {tail} must not be handed a variant that has one. Two passes, because both
|
||||
// halves matter. The first keeps only variants whose every placeholder has a
|
||||
// non-empty value, so an absent optional never reaches him as braces. The
|
||||
// second prefers, among those, the variants using the most of what the caller
|
||||
// supplied, so a caveat he was given is not dropped for a shorter wording.
|
||||
// Nothing fillable leaves the list alone, and the unfilled placeholder shows
|
||||
// up in the answer rather than turning it into silence.
|
||||
func fillable(variants []string, vars map[string]string) []string {
|
||||
if len(variants) < 2 {
|
||||
return variants
|
||||
}
|
||||
best, bestUsed := make([]string, 0, len(variants)), -1
|
||||
for _, v := range variants {
|
||||
used := 0
|
||||
ok := true
|
||||
for _, ph := range placeholders(v) {
|
||||
if vars[ph] == "" {
|
||||
ok = false
|
||||
break
|
||||
}
|
||||
used++
|
||||
}
|
||||
if !ok || used < bestUsed {
|
||||
continue
|
||||
}
|
||||
if used > bestUsed {
|
||||
best, bestUsed = best[:0], used
|
||||
}
|
||||
best = append(best, v)
|
||||
}
|
||||
if len(best) == 0 {
|
||||
return variants
|
||||
}
|
||||
return best
|
||||
}
|
||||
|
||||
// placeholders lists the {name}s in tmpl, in order.
|
||||
func placeholders(tmpl string) []string {
|
||||
var out []string
|
||||
for {
|
||||
i := strings.IndexByte(tmpl, '{')
|
||||
if i < 0 {
|
||||
return out
|
||||
}
|
||||
j := strings.IndexByte(tmpl[i:], '}')
|
||||
if j < 0 {
|
||||
return out
|
||||
}
|
||||
out = append(out, tmpl[i+1:i+j])
|
||||
tmpl = tmpl[i+j+1:]
|
||||
}
|
||||
}
|
||||
|
||||
// pick chooses at random, skipping whatever this entry said last time.
|
||||
func (d *Deck) pick(key string, variants []string) string {
|
||||
d.mu.Lock()
|
||||
defer d.mu.Unlock()
|
||||
|
||||
choices := variants
|
||||
if len(choices) > 1 {
|
||||
fresh := make([]string, 0, len(choices))
|
||||
for _, v := range choices {
|
||||
if v != d.last[key] {
|
||||
fresh = append(fresh, v)
|
||||
}
|
||||
}
|
||||
if len(fresh) > 0 {
|
||||
choices = fresh
|
||||
}
|
||||
}
|
||||
got := choices[d.rnd.Intn(len(choices))]
|
||||
d.last[key] = got
|
||||
return got
|
||||
}
|
||||
|
||||
// floorOf reads the Go literal behind key. Every deck carries its own family's
|
||||
// map, including the floor-only deck an unloadable file leaves behind, so no
|
||||
// lookup ever crosses families. It used to go through one global map keyed by
|
||||
// bare entry name, which two families both calling an entry query_unknown
|
||||
// silently shared: whichever registered last answered for both (Vikunja #521).
|
||||
func floorOf(d *Deck, key string) string {
|
||||
if d == nil {
|
||||
return ""
|
||||
}
|
||||
return d.floor[key]
|
||||
}
|
||||
|
||||
// FloorDeck — the deck a family falls back to when its file will not load. It
|
||||
// has no entries, so every read drops through to the floor literals, and it is
|
||||
// a real *Deck so no accessor has to know which case it is in.
|
||||
func FloorDeck(floor map[string]string) *Deck {
|
||||
return &Deck{last: map[string]string{}, floor: floor}
|
||||
}
|
||||
|
||||
// fill substitutes {name} for each var. A placeholder with no value is left
|
||||
// alone rather than blanked, so a missing value is visible instead of silent.
|
||||
func fill(tmpl string, vars map[string]string) string {
|
||||
for k, v := range vars {
|
||||
tmpl = strings.ReplaceAll(tmpl, "{"+k+"}", v)
|
||||
}
|
||||
return tmpl
|
||||
}
|
||||
@@ -0,0 +1,55 @@
|
||||
package say
|
||||
|
||||
// The counted noun, in the form the number in front of it demands.
|
||||
//
|
||||
// Russian inflects a noun after a numeral, and the form depends on the last two
|
||||
// digits: 1 градус, 2 градуса, 5 градусов, 11 градусов, 21 градус, 22 градуса.
|
||||
// A line file cannot spell that out, so a count in a template splits into two
|
||||
// placeholders — the number, and {word} filled from here.
|
||||
//
|
||||
// The rule lived once as hostWord in cmd/mavend/netscan.go and once as
|
||||
// pluralDaysRU in internal/memory, which meant the weather line said "градусов"
|
||||
// for every temperature and the task list said "дн." — a written abbreviation
|
||||
// read aloud. One helper, every count site (Vikunja #521).
|
||||
|
||||
import "math"
|
||||
|
||||
// CountWord picks between the three forms n needs: one for 1, few for 2-4, many
|
||||
// for 0, 5-20 and anything ending in those. A negative count reads its own
|
||||
// magnitude, since minus does not change the noun: -2 градуса.
|
||||
func CountWord(n int, one, few, many string) string {
|
||||
if n < 0 {
|
||||
n = -n
|
||||
}
|
||||
if n%100 >= 11 && n%100 <= 14 {
|
||||
return many
|
||||
}
|
||||
switch n % 10 {
|
||||
case 1:
|
||||
return one
|
||||
case 2, 3, 4:
|
||||
return few
|
||||
default:
|
||||
return many
|
||||
}
|
||||
}
|
||||
|
||||
// Degrees — the noun for a temperature. Takes the reading as it arrives from a
|
||||
// weather provider and counts by the whole degrees she is about to say, so the
|
||||
// noun agrees with the number in the same sentence rather than with the reading
|
||||
// behind it.
|
||||
func Degrees(temp float64) string {
|
||||
return CountWord(int(math.Round(temp)), "градус", "градуса", "градусов")
|
||||
}
|
||||
|
||||
// Devices — the noun for a count of hosts on the LAN or of smart-home devices.
|
||||
func Devices(n int) string {
|
||||
return CountWord(n, "устройство", "устройства", "устройств")
|
||||
}
|
||||
|
||||
// Days — the noun for a stretch of days. This is what replaces «дн.» in the
|
||||
// overdue and due-soon reasons: an abbreviation is written shorthand, and every
|
||||
// one of these lines is spoken.
|
||||
func Days(n int) string {
|
||||
return CountWord(n, "день", "дня", "дней")
|
||||
}
|
||||
@@ -0,0 +1,16 @@
|
||||
package say
|
||||
|
||||
import "testing"
|
||||
|
||||
// The day forms, kept from internal/memory when the helper moved: 21 takes the
|
||||
// singular and 11 does not, which is the whole reason this is not n == 1.
|
||||
func TestDays(t *testing.T) {
|
||||
for _, c := range []struct {
|
||||
n int
|
||||
want string
|
||||
}{{1, "день"}, {2, "дня"}, {5, "дней"}, {11, "дней"}, {21, "день"}, {22, "дня"}, {114, "дней"}} {
|
||||
if got := Days(c.n); got != c.want {
|
||||
t.Errorf("Days(%d) = %q, want %q", c.n, got, c.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,192 @@
|
||||
package say
|
||||
|
||||
// The summary sentences — what she says around aggregated data: the morning
|
||||
// plan, the ranked task list, and the habits read back out of behaviour records.
|
||||
//
|
||||
// Fifth family on the deck, and the first one outside internal/phraser. It
|
||||
// lives here because its three callers — internal/morning, internal/tasks and
|
||||
// internal/memory — sit under phraser in the import graph and cannot reach it.
|
||||
//
|
||||
// The "I have not seen enough yet" sentences are the load-bearing ones. Three
|
||||
// days of taps and a year of them produce the same "обычно ты ...", and only one
|
||||
// of those is worth believing, so the empty cases say she has not seen a
|
||||
// pattern rather than that he has none.
|
||||
|
||||
import (
|
||||
_ "embed"
|
||||
"log"
|
||||
"math/rand"
|
||||
"sync"
|
||||
)
|
||||
|
||||
//go:embed summary_ru_v1.json
|
||||
var summaryJSON []byte
|
||||
|
||||
// SummarySchemaVersion — this family's own version.
|
||||
const SummarySchemaVersion = 1
|
||||
|
||||
// The entry keys.
|
||||
const (
|
||||
PlanRestEmpty = "plan_rest_empty"
|
||||
PlanDayEmpty = "plan_day_empty"
|
||||
PlanDay = "plan_day"
|
||||
PlanUncertain = "plan_uncertain"
|
||||
|
||||
TasksNone = "tasks_none"
|
||||
TasksFirst = "tasks_first"
|
||||
TasksCandidates = "tasks_candidates"
|
||||
|
||||
ReasonOverdue = "reason_overdue"
|
||||
ReasonOverdueDays = "reason_overdue_days"
|
||||
ReasonToday = "reason_today"
|
||||
ReasonTomorrow = "reason_tomorrow"
|
||||
ReasonInDays = "reason_in_days"
|
||||
ReasonImportant = "reason_important"
|
||||
ReasonUrgent = "reason_urgent"
|
||||
ReasonStale = "reason_stale"
|
||||
|
||||
HabitWeekday = "habit_weekday"
|
||||
HabitWeekdaySame = "habit_weekday_same"
|
||||
HabitWeekdayNone = "habit_weekday_none"
|
||||
HabitWeekendBoth = "habit_weekend_both"
|
||||
HabitWeekendSat = "habit_weekend_sat"
|
||||
HabitWeekendSun = "habit_weekend_sun"
|
||||
HabitWeekendSame = "habit_weekend_same"
|
||||
HabitWeekendNone = "habit_weekend_none"
|
||||
HabitOverall = "habit_overall"
|
||||
HabitOverallNone = "habit_overall_none"
|
||||
HabitSpanToday = "habit_span_today"
|
||||
HabitSpanDays = "habit_span_days"
|
||||
HabitUnglossed = "habit_unglossed"
|
||||
HabitAt = "habit_at"
|
||||
)
|
||||
|
||||
var summaryKeys = []string{
|
||||
PlanRestEmpty, PlanDayEmpty, PlanDay, PlanUncertain,
|
||||
TasksNone, TasksFirst, TasksCandidates,
|
||||
ReasonOverdue, ReasonOverdueDays, ReasonToday, ReasonTomorrow,
|
||||
ReasonInDays, ReasonImportant, ReasonUrgent, ReasonStale,
|
||||
HabitWeekday, HabitWeekdaySame, HabitWeekdayNone,
|
||||
HabitWeekendBoth, HabitWeekendSat, HabitWeekendSun, HabitWeekendSame, HabitWeekendNone,
|
||||
HabitOverall, HabitOverallNone, HabitSpanToday, HabitSpanDays,
|
||||
HabitUnglossed, HabitAt,
|
||||
}
|
||||
|
||||
// summaryFloor — the literal each key falls back to when the file is unusable.
|
||||
// It started as the exact strings that lived in Go before this file existed and
|
||||
// now tracks the file's first variant instead, because a floor that keeps the
|
||||
// wording review threw out would say it back on the one turn nobody is watching.
|
||||
var summaryFloor = map[string]string{
|
||||
PlanRestEmpty: "на сегодня больше ничего не запланировано.",
|
||||
PlanDayEmpty: "на {date} ничего не запланировано.",
|
||||
PlanDay: "план на {date}: {items}",
|
||||
PlanUncertain: "похоже, {line}",
|
||||
|
||||
TasksNone: "задач нет.",
|
||||
TasksFirst: "сначала: {items}",
|
||||
TasksCandidates: "нашла ещё, но ты не подтверждал: {items}",
|
||||
|
||||
ReasonOverdue: "просрочено",
|
||||
ReasonOverdueDays: "просрочено на {n} {word}",
|
||||
ReasonToday: "сегодня",
|
||||
ReasonTomorrow: "завтра",
|
||||
ReasonInDays: "через {n} {word}",
|
||||
ReasonImportant: "важно",
|
||||
ReasonUrgent: "срочно",
|
||||
ReasonStale: "давно в списке",
|
||||
|
||||
HabitWeekday: "по {day} ты обычно {items}.",
|
||||
HabitWeekdaySame: "по {day} всё как обычно — то же, что и в остальные дни: {items}.",
|
||||
HabitWeekdayNone: "по {day} я пока не вижу ничего постоянного.",
|
||||
HabitWeekendBoth: "по субботам ты обычно {items_sat}, по воскресеньям — {items_sun}.",
|
||||
HabitWeekendSat: "по субботам ты обычно {items}, а по воскресеньям постоянного нет.",
|
||||
HabitWeekendSun: "по воскресеньям ты обычно {items}, а по субботам постоянного нет.",
|
||||
HabitWeekendSame: "по выходным всё как обычно — то же, что и в остальные дни: {items}.",
|
||||
HabitWeekendNone: "по выходным я пока не вижу ничего постоянного.",
|
||||
HabitOverall: "обычно ты {items} — {span}.",
|
||||
HabitOverallNone: "записей пока мало, про привычки не скажу.",
|
||||
HabitSpanToday: "по записям за сегодня",
|
||||
HabitSpanDays: "по записям за последние {n} {word}",
|
||||
HabitUnglossed: "отмечаешь «{key}»",
|
||||
HabitAt: "{gloss} около {time}",
|
||||
}
|
||||
|
||||
// Summaries picks a hand-written Russian summary sentence. Safe for concurrent
|
||||
// use.
|
||||
type Summaries struct{ d *Deck }
|
||||
|
||||
// LoadSummaries reads the embedded file. Pass a source to make the picking
|
||||
// reproducible in tests; nil seeds from the clock.
|
||||
func LoadSummaries(src rand.Source) (*Summaries, error) {
|
||||
d, err := Load(summaryJSON, SummarySchemaVersion, summaryKeys, summaryFloor, src)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
// The entries that exist to read the aggregate back. A variant without the
|
||||
// placeholder would summarise the data by dropping it.
|
||||
for _, req := range []struct{ key, ph string }{
|
||||
{PlanDayEmpty, "{date}"}, {PlanDay, "{date}"}, {PlanDay, "{items}"},
|
||||
{PlanUncertain, "{line}"},
|
||||
{TasksFirst, "{items}"}, {TasksCandidates, "{items}"},
|
||||
{ReasonOverdueDays, "{n}"}, {ReasonOverdueDays, "{word}"},
|
||||
{ReasonInDays, "{n}"}, {ReasonInDays, "{word}"},
|
||||
{HabitWeekday, "{day}"}, {HabitWeekday, "{items}"},
|
||||
{HabitWeekdaySame, "{day}"}, {HabitWeekdaySame, "{items}"},
|
||||
{HabitWeekdayNone, "{day}"},
|
||||
{HabitWeekendBoth, "{items_sat}"}, {HabitWeekendBoth, "{items_sun}"},
|
||||
{HabitWeekendSat, "{items}"}, {HabitWeekendSun, "{items}"},
|
||||
{HabitWeekendSame, "{items}"},
|
||||
{HabitOverall, "{items}"}, {HabitOverall, "{span}"},
|
||||
{HabitSpanDays, "{n}"}, {HabitSpanDays, "{word}"},
|
||||
{HabitUnglossed, "{key}"}, {HabitAt, "{gloss}"}, {HabitAt, "{time}"},
|
||||
} {
|
||||
if err := d.RequirePlaceholder(req.key, req.ph); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
return &Summaries{d: d}, nil
|
||||
}
|
||||
|
||||
// deck reads through a nil *Summaries, which is the unloadable-file case.
|
||||
func (s *Summaries) deck() *Deck {
|
||||
if s == nil {
|
||||
return FloorDeck(summaryFloor)
|
||||
}
|
||||
return s.d
|
||||
}
|
||||
|
||||
// Say returns one line for key, with the values filled into the frame.
|
||||
func (s *Summaries) Say(key string, vars map[string]string) string {
|
||||
return s.deck().Text(key, vars)
|
||||
}
|
||||
|
||||
// Variants returns every line the file can produce, for the persona scorer.
|
||||
func (s *Summaries) Variants() []string { return s.deck().Variants() }
|
||||
|
||||
var (
|
||||
summaryOnce sync.Once
|
||||
summaries *Summaries
|
||||
)
|
||||
|
||||
// DefaultSummaries returns the shared instance, loading it on first use. A
|
||||
// broken file logs once and leaves a nil *Summaries, which still answers from
|
||||
// summaryFloor.
|
||||
func DefaultSummaries() *Summaries {
|
||||
summaryOnce.Do(func() {
|
||||
s, err := LoadSummaries(nil)
|
||||
if err != nil {
|
||||
log.Printf("say: summary lines unavailable, using the built-in ones: %v", err)
|
||||
return
|
||||
}
|
||||
summaries = s
|
||||
})
|
||||
return summaries
|
||||
}
|
||||
|
||||
// S — one summary sentence, the way every caller says it.
|
||||
func S(key string, vars map[string]string) string { return DefaultSummaries().Say(key, vars) }
|
||||
|
||||
// IsS reports whether text is a line key could have produced, for the tests.
|
||||
func IsS(key string, vars map[string]string, text string) bool {
|
||||
return DefaultSummaries().deck().Matches(key, vars, text)
|
||||
}
|
||||
@@ -0,0 +1,143 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"name": "russian summary sentences v1",
|
||||
"notes": [
|
||||
"The sentences she builds around aggregated data: the morning plan, the ranked task list, and the habits she reads back out of behaviour records.",
|
||||
"Rules: she is feminine about herself, he is a man addressed as ты. Never вы/вас/ваш, never он/его about him. No pet names.",
|
||||
"\"I have not seen enough yet\" and \"there is nothing there\" are different claims, and the habit entries keep the first. Three days of taps do not license a statement about his life, so habit_*_none says she does not see a pattern, never that he has no habits.",
|
||||
"She reports on the records, not on him. «всё как обычно» is a claim about what she has stored; «у тебя нет ничего особенного» is a verdict on his life, and she does not pass those.",
|
||||
"Placeholders: {date} a formatted date, {items} a joined list, {items_sat} and {items_sun} the same for one weekend day each, {day} a weekday name, {span} the stretch of records a habit claim rests on, {line} one already-rendered plan line, {key} a behaviour key she has no gloss for, {gloss} the readable name of one, {time} a clock time, {n} a count, {word} the Russian count form for {n}, built Go-side.",
|
||||
"Three parallel entries share one scheme: habit_weekend_both names its two lists {items_sat} and {items_sun}, and habit_weekend_sat and habit_weekend_sun each use {items}, because each of them says one list.",
|
||||
"The count forms (день/дня/дней) are morphology, not copy. They stay in Go and arrive here through {word}. An abbreviation is not an option: «дн.» is written shorthand and every line here is spoken, so it reads as garbage or gets spelled out letter by letter.",
|
||||
"{line} in plan_uncertain is another rendered line, so the join reads as one sentence only while what arrives starts lowercase. The caller asserts that.",
|
||||
"A joined list arrives with its own punctuation, so the entries that end on {items} carry no trailing period. The habit entries keep theirs, because there the list sits mid-sentence.",
|
||||
"fixed: true means exactly one variant and no picking. Parallel entries agree on it, and a single-variant entry is fixed — in this file and in every other family. A test holds that."
|
||||
],
|
||||
"entries": {
|
||||
"plan_rest_empty": {
|
||||
"fixed": true,
|
||||
"variants": ["на сегодня больше ничего не запланировано."]
|
||||
},
|
||||
"plan_day_empty": {
|
||||
"fixed": true,
|
||||
"variants": ["на {date} ничего не запланировано."]
|
||||
},
|
||||
"plan_day": {
|
||||
"fixed": true,
|
||||
"variants": ["план на {date}: {items}"]
|
||||
},
|
||||
"plan_uncertain": {
|
||||
"fixed": true,
|
||||
"variants": ["похоже, {line}"]
|
||||
},
|
||||
|
||||
"tasks_none": {
|
||||
"fixed": true,
|
||||
"variants": ["задач нет."]
|
||||
},
|
||||
"tasks_first": {
|
||||
"fixed": true,
|
||||
"variants": ["сначала: {items}"]
|
||||
},
|
||||
"tasks_candidates": {
|
||||
"fixed": true,
|
||||
"variants": ["нашла ещё, но ты не подтверждал: {items}"]
|
||||
},
|
||||
|
||||
"reason_overdue": {
|
||||
"fixed": true,
|
||||
"variants": ["просрочено"]
|
||||
},
|
||||
"reason_overdue_days": {
|
||||
"fixed": true,
|
||||
"variants": ["просрочено на {n} {word}"]
|
||||
},
|
||||
"reason_today": {
|
||||
"fixed": true,
|
||||
"variants": ["сегодня"]
|
||||
},
|
||||
"reason_tomorrow": {
|
||||
"fixed": true,
|
||||
"variants": ["завтра"]
|
||||
},
|
||||
"reason_in_days": {
|
||||
"fixed": true,
|
||||
"variants": ["через {n} {word}"]
|
||||
},
|
||||
"reason_important": {
|
||||
"fixed": true,
|
||||
"variants": ["важно"]
|
||||
},
|
||||
"reason_urgent": {
|
||||
"fixed": true,
|
||||
"variants": ["срочно"]
|
||||
},
|
||||
"reason_stale": {
|
||||
"fixed": true,
|
||||
"variants": ["давно в списке"]
|
||||
},
|
||||
|
||||
"habit_weekday": {
|
||||
"fixed": true,
|
||||
"variants": ["по {day} ты обычно {items}."]
|
||||
},
|
||||
"habit_weekday_same": {
|
||||
"fixed": true,
|
||||
"variants": ["по {day} всё как обычно — то же, что и в остальные дни: {items}."]
|
||||
},
|
||||
"habit_weekday_none": {
|
||||
"variants": [
|
||||
"по {day} я пока не вижу ничего постоянного.",
|
||||
"по {day} постоянного пока не вижу — записей мало."
|
||||
]
|
||||
},
|
||||
"habit_weekend_both": {
|
||||
"fixed": true,
|
||||
"variants": ["по субботам ты обычно {items_sat}, по воскресеньям — {items_sun}."]
|
||||
},
|
||||
"habit_weekend_sat": {
|
||||
"fixed": true,
|
||||
"variants": ["по субботам ты обычно {items}, а по воскресеньям постоянного нет."]
|
||||
},
|
||||
"habit_weekend_sun": {
|
||||
"fixed": true,
|
||||
"variants": ["по воскресеньям ты обычно {items}, а по субботам постоянного нет."]
|
||||
},
|
||||
"habit_weekend_same": {
|
||||
"fixed": true,
|
||||
"variants": ["по выходным всё как обычно — то же, что и в остальные дни: {items}."]
|
||||
},
|
||||
"habit_weekend_none": {
|
||||
"variants": [
|
||||
"по выходным я пока не вижу ничего постоянного.",
|
||||
"по выходным постоянного пока не вижу — записей мало."
|
||||
]
|
||||
},
|
||||
"habit_overall": {
|
||||
"fixed": true,
|
||||
"variants": ["обычно ты {items} — {span}."]
|
||||
},
|
||||
"habit_overall_none": {
|
||||
"variants": [
|
||||
"записей пока мало, про привычки не скажу.",
|
||||
"пока мало записей, чтобы говорить о привычках."
|
||||
]
|
||||
},
|
||||
"habit_span_today": {
|
||||
"fixed": true,
|
||||
"variants": ["по записям за сегодня"]
|
||||
},
|
||||
"habit_span_days": {
|
||||
"fixed": true,
|
||||
"variants": ["по записям за последние {n} {word}"]
|
||||
},
|
||||
"habit_unglossed": {
|
||||
"fixed": true,
|
||||
"variants": ["отмечаешь «{key}»"]
|
||||
},
|
||||
"habit_at": {
|
||||
"fixed": true,
|
||||
"variants": ["{gloss} около {time}"]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,62 @@
|
||||
package say
|
||||
|
||||
import (
|
||||
"math/rand"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// The file has to load, and every key the code names has to be in it.
|
||||
func TestSummariesLoad(t *testing.T) {
|
||||
s, err := LoadSummaries(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("load: %v", err)
|
||||
}
|
||||
for _, key := range summaryKeys {
|
||||
if got := s.Say(key, nil); got == "" {
|
||||
t.Errorf("%s says nothing", key)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// A nil *Summaries is the unloadable-file case, and it must still speak. The
|
||||
// habit sentences are the ones that matter here: falling back must not turn
|
||||
// "I have not seen enough" into silence.
|
||||
func TestNilSummariesAnswerFromTheFloor(t *testing.T) {
|
||||
var s *Summaries
|
||||
if got, want := s.Say(HabitOverallNone, nil), summaryFloor[HabitOverallNone]; got != want {
|
||||
t.Errorf("got %q, want %q", got, want)
|
||||
}
|
||||
if got := s.Say(PlanDay, map[string]string{"date": "03.08.2026", "items": "x"}); !strings.Contains(got, "03.08.2026") {
|
||||
t.Errorf("the floor dropped the date: %q", got)
|
||||
}
|
||||
}
|
||||
|
||||
// The empty cases claim she has not seen enough, never that he has no habits.
|
||||
// Every variant has to hold that line, since the picker treats them as equals.
|
||||
func TestHabitGapsSaySheHasNotSeenEnough(t *testing.T) {
|
||||
s, err := LoadSummaries(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("load: %v", err)
|
||||
}
|
||||
for _, key := range []string{HabitWeekdayNone, HabitWeekendNone, HabitOverallNone} {
|
||||
for _, v := range s.d.file.Entries[key].Variants {
|
||||
if !strings.Contains(v, "пока") && !strings.Contains(v, "ещё") {
|
||||
t.Errorf("%s variant %q reads as a fact about him, not as a gap in her records", key, v)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// One variant means fixed, in this file and in the four in internal/phraser.
|
||||
// Nothing breaks on the flag being absent, but parallel entries disagreeing
|
||||
// about it is how the file stops telling a reader which wording is load-bearing.
|
||||
func TestEverySingleVariantEntryIsFixed(t *testing.T) {
|
||||
s, err := LoadSummaries(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("load: %v", err)
|
||||
}
|
||||
if got := s.d.UnfixedSingles(); len(got) > 0 {
|
||||
t.Errorf("single-variant entries not marked fixed: %v", got)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,194 @@
|
||||
package store
|
||||
|
||||
import (
|
||||
"context"
|
||||
"database/sql"
|
||||
"errors"
|
||||
"fmt"
|
||||
"strings"
|
||||
"time"
|
||||
)
|
||||
|
||||
// List items — the fourth append-only shape (Vikunja #453).
|
||||
//
|
||||
// A list is a standing set of short strings under a tag: покупки, аптека,
|
||||
// хозяйство. It is not work and it is not a claim about the world, which is
|
||||
// why it is neither a task nor a fact. Nothing here is prioritised, nothing
|
||||
// nudges about it, and the digestion worker does not read it. The only two
|
||||
// things a list does are grow and shrink.
|
||||
//
|
||||
// The consequence that made it worth a table: because no predicate touches a
|
||||
// list item, several people adding to the same list at once cost nothing. There
|
||||
// is no ranking to disagree about and no lifecycle beyond crossed-off.
|
||||
const (
|
||||
// ListItemOpen — on the list.
|
||||
ListItemOpen = "open"
|
||||
// ListItemDone — bought, taken, crossed off.
|
||||
ListItemDone = "done"
|
||||
// ListItemDropped — removed without being got.
|
||||
ListItemDropped = "dropped"
|
||||
)
|
||||
|
||||
// DefaultList — the list a capture lands on when he names none. Almost every
|
||||
// spoken list item is groceries, and asking "в какой список?" for the common
|
||||
// case would be a nag.
|
||||
const DefaultList = "покупки"
|
||||
|
||||
// ListItem — one line on one list.
|
||||
type ListItem struct {
|
||||
ID int64
|
||||
CreatedTs time.Time
|
||||
List string
|
||||
Item string
|
||||
Source string
|
||||
Status string
|
||||
ResolvedTs *time.Time
|
||||
}
|
||||
|
||||
var (
|
||||
ErrListItemNotFound = errors.New("store: list item not found")
|
||||
ErrListItemEmpty = errors.New("store: list item is empty")
|
||||
ErrListItemStatus = errors.New("store: invalid list item status")
|
||||
)
|
||||
|
||||
// NormalizeListName folds a list tag to its dedupe form. Lists are named out
|
||||
// loud, so "Покупки" and "покупки " are the same list.
|
||||
func NormalizeListName(s string) string {
|
||||
n := NormalizeTaskText(s)
|
||||
if n == "" {
|
||||
return DefaultList
|
||||
}
|
||||
return n
|
||||
}
|
||||
|
||||
// AddListItem puts an item on a list, or returns the existing row when the same
|
||||
// item is already on it. Created says which happened, so the caller can say
|
||||
// "уже есть" instead of pretending it wrote something.
|
||||
func (s *Store) AddListItem(ctx context.Context, li ListItem) (CaptureResult, error) {
|
||||
item := strings.TrimSpace(li.Item)
|
||||
if item == "" {
|
||||
return CaptureResult{}, ErrListItemEmpty
|
||||
}
|
||||
list := NormalizeListName(li.List)
|
||||
norm := NormalizeTaskText(item)
|
||||
created := li.CreatedTs
|
||||
if created.IsZero() {
|
||||
created = time.Now()
|
||||
}
|
||||
res, err := s.db.ExecContext(ctx,
|
||||
`INSERT INTO list_items (created_ts, list, item, norm, source, status)
|
||||
VALUES (?,?,?,?,?,?)
|
||||
ON CONFLICT DO NOTHING`,
|
||||
created.UnixMilli(), list, item, norm, li.Source, ListItemOpen)
|
||||
if err != nil {
|
||||
return CaptureResult{}, fmt.Errorf("add list item: %w", err)
|
||||
}
|
||||
n, err := res.RowsAffected()
|
||||
if err != nil {
|
||||
return CaptureResult{}, fmt.Errorf("add list item: rows affected: %w", err)
|
||||
}
|
||||
if n > 0 {
|
||||
id, err := res.LastInsertId()
|
||||
if err != nil {
|
||||
return CaptureResult{}, fmt.Errorf("add list item: last insert id: %w", err)
|
||||
}
|
||||
return CaptureResult{ID: id, Created: true}, nil
|
||||
}
|
||||
var id int64
|
||||
err = s.db.QueryRowContext(ctx,
|
||||
`SELECT id FROM list_items WHERE list = ? AND norm = ? AND status = ?`,
|
||||
list, norm, ListItemOpen).Scan(&id)
|
||||
if errors.Is(err, sql.ErrNoRows) {
|
||||
return CaptureResult{}, ErrListItemNotFound
|
||||
}
|
||||
if err != nil {
|
||||
return CaptureResult{}, fmt.Errorf("add list item: lookup: %w", err)
|
||||
}
|
||||
return CaptureResult{ID: id}, nil
|
||||
}
|
||||
|
||||
// ListItems reads one list in the order it was added. An empty status reads the
|
||||
// open items, which is what reading the list aloud means.
|
||||
func (s *Store) ListItems(ctx context.Context, list, status string) ([]ListItem, error) {
|
||||
if status == "" {
|
||||
status = ListItemOpen
|
||||
}
|
||||
rows, err := s.db.QueryContext(ctx,
|
||||
`SELECT id, created_ts, list, item, source, status, resolved_ts
|
||||
FROM list_items WHERE list = ? AND status = ?
|
||||
ORDER BY created_ts, id`,
|
||||
NormalizeListName(list), status)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("list items: %w", err)
|
||||
}
|
||||
defer rows.Close()
|
||||
var out []ListItem
|
||||
for rows.Next() {
|
||||
var (
|
||||
li ListItem
|
||||
created int64
|
||||
resolved sql.NullInt64
|
||||
)
|
||||
if err := rows.Scan(&li.ID, &created, &li.List, &li.Item, &li.Source, &li.Status, &resolved); err != nil {
|
||||
return nil, fmt.Errorf("list items: scan: %w", err)
|
||||
}
|
||||
li.CreatedTs = time.UnixMilli(created)
|
||||
if resolved.Valid {
|
||||
t := time.UnixMilli(resolved.Int64)
|
||||
li.ResolvedTs = &t
|
||||
}
|
||||
out = append(out, li)
|
||||
}
|
||||
if err := rows.Err(); err != nil {
|
||||
return nil, fmt.Errorf("list items: %w", err)
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
// SetListItemStatus crosses an item off, or removes it. Moving an item that is
|
||||
// already resolved is not an error — crossing off twice is the same list.
|
||||
func (s *Store) SetListItemStatus(ctx context.Context, id int64, status string, at time.Time) error {
|
||||
if status != ListItemOpen && status != ListItemDone && status != ListItemDropped {
|
||||
return fmt.Errorf("%w: %q", ErrListItemStatus, status)
|
||||
}
|
||||
var resolved sql.NullInt64
|
||||
if status != ListItemOpen {
|
||||
if at.IsZero() {
|
||||
at = time.Now()
|
||||
}
|
||||
resolved = sql.NullInt64{Int64: at.UnixMilli(), Valid: true}
|
||||
}
|
||||
res, err := s.db.ExecContext(ctx,
|
||||
`UPDATE list_items SET status = ?, resolved_ts = ? WHERE id = ?`,
|
||||
status, resolved, id)
|
||||
if err != nil {
|
||||
return fmt.Errorf("set list item status: %w", err)
|
||||
}
|
||||
n, err := res.RowsAffected()
|
||||
if err != nil {
|
||||
return fmt.Errorf("set list item status: rows affected: %w", err)
|
||||
}
|
||||
if n == 0 {
|
||||
return ErrListItemNotFound
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// ClearList crosses off every open item on a list and reports how many. This is
|
||||
// "всё купил", which is one sentence and must not become one turn per item.
|
||||
func (s *Store) ClearList(ctx context.Context, list string, at time.Time) (int, error) {
|
||||
if at.IsZero() {
|
||||
at = time.Now()
|
||||
}
|
||||
res, err := s.db.ExecContext(ctx,
|
||||
`UPDATE list_items SET status = ?, resolved_ts = ? WHERE list = ? AND status = ?`,
|
||||
ListItemDone, at.UnixMilli(), NormalizeListName(list), ListItemOpen)
|
||||
if err != nil {
|
||||
return 0, fmt.Errorf("clear list: %w", err)
|
||||
}
|
||||
n, err := res.RowsAffected()
|
||||
if err != nil {
|
||||
return 0, fmt.Errorf("clear list: rows affected: %w", err)
|
||||
}
|
||||
return int(n), nil
|
||||
}
|
||||
@@ -0,0 +1,149 @@
|
||||
package store
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
var listNow = time.Date(2026, 8, 4, 12, 0, 0, 0, time.UTC)
|
||||
|
||||
func TestAddListItemDedupesTheOpenList(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
s := newTestStore(t)
|
||||
|
||||
first, err := s.AddListItem(ctx, ListItem{Item: "молоко", Source: "tap:voice", CreatedTs: listNow})
|
||||
if err != nil {
|
||||
t.Fatalf("add: %v", err)
|
||||
}
|
||||
if !first.Created {
|
||||
t.Fatal("the first молоко did not create a row")
|
||||
}
|
||||
again, err := s.AddListItem(ctx, ListItem{Item: " Молоко ", Source: "tap:voice", CreatedTs: listNow})
|
||||
if err != nil {
|
||||
t.Fatalf("add again: %v", err)
|
||||
}
|
||||
if again.Created {
|
||||
t.Error("молоко was added twice")
|
||||
}
|
||||
if again.ID != first.ID {
|
||||
t.Errorf("second add points at %d; want the existing %d", again.ID, first.ID)
|
||||
}
|
||||
if _, err := s.AddListItem(ctx, ListItem{Item: " "}); !errors.Is(err, ErrListItemEmpty) {
|
||||
t.Errorf("empty item: %v; want ErrListItemEmpty", err)
|
||||
}
|
||||
}
|
||||
|
||||
// A crossed-off item does not block the next one: buying milk again next week
|
||||
// is a new line, the way saying an errand again is a new task.
|
||||
func TestCrossedOffItemComesBack(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
s := newTestStore(t)
|
||||
|
||||
first, err := s.AddListItem(ctx, ListItem{Item: "молоко", CreatedTs: listNow})
|
||||
if err != nil {
|
||||
t.Fatalf("add: %v", err)
|
||||
}
|
||||
if err := s.SetListItemStatus(ctx, first.ID, ListItemDone, listNow); err != nil {
|
||||
t.Fatalf("cross off: %v", err)
|
||||
}
|
||||
next, err := s.AddListItem(ctx, ListItem{Item: "молоко", CreatedTs: listNow.Add(time.Hour)})
|
||||
if err != nil {
|
||||
t.Fatalf("add after: %v", err)
|
||||
}
|
||||
if !next.Created || next.ID == first.ID {
|
||||
t.Errorf("second молоко reused row %d; want a new one", next.ID)
|
||||
}
|
||||
open, err := s.ListItems(ctx, "", "")
|
||||
if err != nil {
|
||||
t.Fatalf("list: %v", err)
|
||||
}
|
||||
if len(open) != 1 || open[0].ID != next.ID {
|
||||
t.Errorf("open list %+v; want only the new row", open)
|
||||
}
|
||||
}
|
||||
|
||||
// Lists are separate stores under one table: the same word on two lists is two
|
||||
// items, and reading one never reads the other.
|
||||
func TestListsDoNotSeeEachOther(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
s := newTestStore(t)
|
||||
|
||||
if _, err := s.AddListItem(ctx, ListItem{List: "покупки", Item: "вода", CreatedTs: listNow}); err != nil {
|
||||
t.Fatalf("add: %v", err)
|
||||
}
|
||||
if _, err := s.AddListItem(ctx, ListItem{List: "Аптека", Item: "вода", CreatedTs: listNow}); err != nil {
|
||||
t.Fatalf("add: %v", err)
|
||||
}
|
||||
for _, c := range []struct{ list, want string }{
|
||||
{"покупки", "покупки"},
|
||||
{"аптека", "аптека"},
|
||||
{"", "покупки"},
|
||||
} {
|
||||
got, err := s.ListItems(ctx, c.list, "")
|
||||
if err != nil {
|
||||
t.Fatalf("list %q: %v", c.list, err)
|
||||
}
|
||||
if len(got) != 1 {
|
||||
t.Fatalf("list %q has %d items; want 1", c.list, len(got))
|
||||
}
|
||||
if got[0].List != c.want {
|
||||
t.Errorf("list %q returned tag %q; want %q", c.list, got[0].List, c.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestClearListCrossesOffEverythingOpen(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
s := newTestStore(t)
|
||||
|
||||
for _, item := range []string{"молоко", "хлеб", "яйца"} {
|
||||
if _, err := s.AddListItem(ctx, ListItem{Item: item, CreatedTs: listNow}); err != nil {
|
||||
t.Fatalf("add %s: %v", item, err)
|
||||
}
|
||||
}
|
||||
if _, err := s.AddListItem(ctx, ListItem{List: "аптека", Item: "бинт", CreatedTs: listNow}); err != nil {
|
||||
t.Fatalf("add: %v", err)
|
||||
}
|
||||
n, err := s.ClearList(ctx, "покупки", listNow)
|
||||
if err != nil {
|
||||
t.Fatalf("clear: %v", err)
|
||||
}
|
||||
if n != 3 {
|
||||
t.Errorf("cleared %d; want 3", n)
|
||||
}
|
||||
left, err := s.ListItems(ctx, "покупки", "")
|
||||
if err != nil {
|
||||
t.Fatalf("list: %v", err)
|
||||
}
|
||||
if len(left) != 0 {
|
||||
t.Errorf("%d items still open; want none", len(left))
|
||||
}
|
||||
done, err := s.ListItems(ctx, "покупки", ListItemDone)
|
||||
if err != nil {
|
||||
t.Fatalf("list done: %v", err)
|
||||
}
|
||||
if len(done) != 3 || done[0].ResolvedTs == nil {
|
||||
t.Errorf("done list %+v; want 3 rows carrying a resolved time", done)
|
||||
}
|
||||
other, err := s.ListItems(ctx, "аптека", "")
|
||||
if err != nil {
|
||||
t.Fatalf("list: %v", err)
|
||||
}
|
||||
if len(other) != 1 {
|
||||
t.Error("clearing покупки touched аптека")
|
||||
}
|
||||
}
|
||||
|
||||
func TestSetListItemStatusRejectsWhatIsNotAStatus(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
s := newTestStore(t)
|
||||
|
||||
if err := s.SetListItemStatus(ctx, 1, "куплено", listNow); !errors.Is(err, ErrListItemStatus) {
|
||||
t.Errorf("bad status: %v; want ErrListItemStatus", err)
|
||||
}
|
||||
if err := s.SetListItemStatus(ctx, 999, ListItemDone, listNow); !errors.Is(err, ErrListItemNotFound) {
|
||||
t.Errorf("missing row: %v; want ErrListItemNotFound", err)
|
||||
}
|
||||
}
|
||||
@@ -219,8 +219,29 @@ ALTER TABLE reminders ADD COLUMN next_fire_ts INTEGER;`, // #2
|
||||
// event, and the old rows would otherwise be recited as extra meetings.
|
||||
// The filter is exact — it keeps any key whose summary part still has a
|
||||
// letter or a digit in it.
|
||||
`CREATE TABLE IF NOT EXISTS list_items (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
created_ts INTEGER NOT NULL,
|
||||
list TEXT NOT NULL,
|
||||
item TEXT NOT NULL,
|
||||
norm TEXT NOT NULL,
|
||||
source TEXT NOT NULL,
|
||||
status TEXT NOT NULL DEFAULT 'open' CHECK (status IN ('open','done','dropped')),
|
||||
resolved_ts INTEGER
|
||||
);
|
||||
CREATE UNIQUE INDEX IF NOT EXISTS idx_list_items_live ON list_items (list, norm) WHERE status = 'open';
|
||||
CREATE INDEX IF NOT EXISTS idx_list_items_list ON list_items (list, status, created_ts);`,
|
||||
// #19 — standing lists (Vikunja #453). The fourth append-only shape, after
|
||||
// facts, notes and tasks, and the reason it is its own table rather than a
|
||||
// tag on tasks: milk on the shopping list is not work. Nothing prioritises
|
||||
// it, nothing nudges about it, and the prioritiser must not start counting
|
||||
// groceries as outstanding errands.
|
||||
//
|
||||
// The live-only unique index is the tasks one, per list: saying "молоко"
|
||||
// twice before the shop keeps one row, saying it again next week after the
|
||||
// last one was crossed off writes a new one.
|
||||
|
||||
// #19 — unstick the routines accepted before the fire-forever fix
|
||||
// #20 — unstick the routines accepted before the fire-forever fix
|
||||
// (Vikunja #377, follow-up to #366). Accepting used to leave accepted_ts
|
||||
// NULL and a live one-shot reminder behind, and the tick loop skips a row
|
||||
// with no accepted_ts, so every non-weekly routine accepted before that fix
|
||||
|
||||
@@ -114,8 +114,10 @@ func TestStuckRoutinesAreBackfilled(t *testing.T) {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
if _, err := s.db.ExecContext(ctx, migrations[18]); err != nil {
|
||||
t.Fatalf("migration 19: %v", err)
|
||||
// Index 19, version 20: standing lists landed on the same number first
|
||||
// (Vikunja #453), so this one moved down one.
|
||||
if _, err := s.db.ExecContext(ctx, migrations[19]); err != nil {
|
||||
t.Fatalf("migration 20: %v", err)
|
||||
}
|
||||
|
||||
accepted, err := s.ListAcceptedRoutines(ctx)
|
||||
|
||||
+32
-33
@@ -19,8 +19,11 @@ package tasks
|
||||
import (
|
||||
"fmt"
|
||||
"sort"
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/say"
|
||||
)
|
||||
|
||||
// Status values, mirroring internal/store so a caller can rank ipc.Task rows
|
||||
@@ -117,21 +120,25 @@ func score(it Item, now time.Time) (float64, string) {
|
||||
bonus = scoreOverdueCap
|
||||
}
|
||||
total += scoreOverdue + bonus
|
||||
reason = "просрочено"
|
||||
if late == 1 {
|
||||
reason = "просрочено на день"
|
||||
} else if late > 1 {
|
||||
reason = fmt.Sprintf("просрочено на %d дн.", late)
|
||||
reason = say.S(say.ReasonOverdue, nil)
|
||||
if late > 0 {
|
||||
// One day needs no arm of its own: «просрочено на 1 день»
|
||||
// falls out of the count helper like every other number.
|
||||
reason = say.S(say.ReasonOverdueDays, map[string]string{
|
||||
"n": strconv.Itoa(late), "word": say.Days(late),
|
||||
})
|
||||
}
|
||||
case days == 0:
|
||||
total += scoreDueToday
|
||||
reason = "сегодня"
|
||||
reason = say.S(say.ReasonToday, nil)
|
||||
case days == 1:
|
||||
total += scoreDueTomorrow
|
||||
reason = "завтра"
|
||||
reason = say.S(say.ReasonTomorrow, nil)
|
||||
case days <= 7:
|
||||
total += scoreDueWeek
|
||||
reason = fmt.Sprintf("через %d дн.", days)
|
||||
reason = say.S(say.ReasonInDays, map[string]string{
|
||||
"n": strconv.Itoa(days), "word": say.Days(days),
|
||||
})
|
||||
default:
|
||||
total += scoreDueLater
|
||||
}
|
||||
@@ -147,9 +154,9 @@ func score(it Item, now time.Time) (float64, string) {
|
||||
// The rungs get their own words. The reason string is the one place
|
||||
// the ranking explains itself, and reading "важно" back at a task
|
||||
// he flagged "срочно" reports a word he did not say.
|
||||
reason = "важно"
|
||||
reason = say.S(say.ReasonImportant, nil)
|
||||
if w >= MaxWeight {
|
||||
reason = "срочно"
|
||||
reason = say.S(say.ReasonUrgent, nil)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -163,7 +170,7 @@ func score(it Item, now time.Time) (float64, string) {
|
||||
}
|
||||
total += age
|
||||
if reason == "" && weeks >= 2 {
|
||||
reason = "давно в списке"
|
||||
reason = say.S(say.ReasonStale, nil)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -210,22 +217,28 @@ func FormatRU(ranked []Ranked) string {
|
||||
}
|
||||
}
|
||||
if len(open) == 0 && len(cands) == 0 {
|
||||
return "задач нет."
|
||||
return say.S(say.TasksNone, nil)
|
||||
}
|
||||
|
||||
var b strings.Builder
|
||||
if len(open) > 0 {
|
||||
b.WriteString("сначала: ")
|
||||
b.WriteString(joinRU(open, SpokenLimit, true))
|
||||
b.WriteString(".")
|
||||
b.WriteString(say.S(say.TasksFirst, map[string]string{
|
||||
"items": joinRU(open, SpokenLimit, true),
|
||||
}))
|
||||
}
|
||||
if len(cands) > 0 {
|
||||
// Two sentences, and the first one ends on a joined list that carries
|
||||
// whatever punctuation its last task had — usually none. So the break
|
||||
// is the caller's to make, not the line file's (Vikunja #521).
|
||||
if b.Len() > 0 {
|
||||
if !strings.HasSuffix(b.String(), ".") {
|
||||
b.WriteString(".")
|
||||
}
|
||||
b.WriteString(" ")
|
||||
}
|
||||
b.WriteString("ещё я нашла, но ты не подтвердил: ")
|
||||
b.WriteString(joinRU(cands, SpokenLimit, false))
|
||||
b.WriteString(".")
|
||||
b.WriteString(say.S(say.TasksCandidates, map[string]string{
|
||||
"items": joinRU(cands, SpokenLimit, false),
|
||||
}))
|
||||
}
|
||||
return b.String()
|
||||
}
|
||||
@@ -250,21 +263,7 @@ func joinRU(rs []Ranked, limit int, withReasons bool) string {
|
||||
s := strings.Join(parts, "; ")
|
||||
if rest > 0 {
|
||||
// With the noun. Spoken, a bare number trails off mid-sentence.
|
||||
s += fmt.Sprintf("; и ещё %d %s", rest, pluralTasksRU(rest))
|
||||
s += fmt.Sprintf("; и ещё %d %s", rest, say.CountWord(rest, "задача", "задачи", "задач"))
|
||||
}
|
||||
return s
|
||||
}
|
||||
|
||||
// pluralTasksRU — the right form of "задача" for a count. Russian needs three.
|
||||
func pluralTasksRU(n int) string {
|
||||
if n%100 >= 11 && n%100 <= 14 {
|
||||
return "задач"
|
||||
}
|
||||
switch n % 10 {
|
||||
case 1:
|
||||
return "задача"
|
||||
case 2, 3, 4:
|
||||
return "задачи"
|
||||
}
|
||||
return "задач"
|
||||
}
|
||||
|
||||
@@ -4,6 +4,8 @@ import (
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/say"
|
||||
)
|
||||
|
||||
func at(y int, m time.Month, d int) *time.Time {
|
||||
@@ -123,10 +125,12 @@ func TestRankOverdueDaysAreCounted(t *testing.T) {
|
||||
if got[0].Text != "давно" {
|
||||
t.Errorf("order = %v, want the later-overdue task first", texts(got))
|
||||
}
|
||||
if got[0].Reason != "просрочено на 12 дн." {
|
||||
if got[0].Reason != "просрочено на 12 дней" {
|
||||
t.Errorf("reason = %q", got[0].Reason)
|
||||
}
|
||||
if got[1].Reason != "просрочено на день" {
|
||||
// One day goes through the same entry as twelve: «на 1 день» is what the
|
||||
// count helper says, so there is no reason_overdue_day any more.
|
||||
if got[1].Reason != "просрочено на 1 день" {
|
||||
t.Errorf("reason = %q", got[1].Reason)
|
||||
}
|
||||
}
|
||||
@@ -141,7 +145,7 @@ func TestFormatRUNamesReasonsAndSeparatesCandidates(t *testing.T) {
|
||||
if !strings.HasPrefix(got, "сначала: оплатить интернет (сегодня)") {
|
||||
t.Errorf("reply = %q", got)
|
||||
}
|
||||
if !strings.Contains(got, "не подтвердил: продлить страховку") {
|
||||
if !strings.Contains(got, "не подтверждал: продлить страховку") {
|
||||
t.Errorf("candidate not named as unconfirmed: %q", got)
|
||||
}
|
||||
// A candidate's due date is Maven's reading of a mail, not his statement.
|
||||
@@ -178,7 +182,7 @@ func TestFormatRUEmpty(t *testing.T) {
|
||||
|
||||
// A due date read back from the store is a UTC instant, so comparing calendar
|
||||
// days in ITS location put every date a day out east of Greenwich: the row said
|
||||
// "сегодня" for a task due tomorrow, and "просрочено на день" on the due date
|
||||
// "сегодня" for a task due tomorrow, and "просрочено на 1 день" on the due date
|
||||
// itself while the due column one cell over said otherwise.
|
||||
func TestRankComparesDaysInTheCallersLocation(t *testing.T) {
|
||||
tz := time.FixedZone("UTC+4", 4*3600)
|
||||
@@ -238,8 +242,8 @@ func TestFormatRUTailCarriesTheNoun(t *testing.T) {
|
||||
t.Errorf("reply = %q, want the count with its noun", got)
|
||||
}
|
||||
for n, want := range map[int]string{1: "задача", 2: "задачи", 5: "задач", 11: "задач", 21: "задача"} {
|
||||
if got := pluralTasksRU(n); got != want {
|
||||
t.Errorf("pluralTasksRU(%d) = %q, want %q", n, got, want)
|
||||
if got := say.CountWord(n, "задача", "задачи", "задач"); got != want {
|
||||
t.Errorf("CountWord(%d) = %q, want %q", n, got, want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,194 @@
|
||||
package tool
|
||||
|
||||
import (
|
||||
"strings"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/mcp"
|
||||
"github.com/kami/maven/internal/smarthome"
|
||||
)
|
||||
|
||||
// Risk tiers (Vikunja #449).
|
||||
//
|
||||
// What existed before this file was a mechanism and no policy: one
|
||||
// `Destructive` boolean per row, set by whoever ticked the checkbox on /tools.
|
||||
// Nothing said which acts are destructive, whether a confirmed act stays
|
||||
// confirmed, or what a new tool domain inherits — so every domain answered
|
||||
// those questions for itself, and two of them answered differently.
|
||||
//
|
||||
// The tiers below are the policy. They are derived from the row, not stored:
|
||||
// a derivation can be argued with and corrected in one place, while a column
|
||||
// is whatever the last person to enable the tool believed.
|
||||
//
|
||||
// The three questions, answered once:
|
||||
//
|
||||
// - WHICH ACTS ARE DESTRUCTIVE. A house row always is, because there is no
|
||||
// read-only way to turn the heating off. A row whose argv names one of the
|
||||
// irreversible verbs always is, whatever the checkbox says. Everything else
|
||||
// is what the row was enabled as.
|
||||
// - DOES A CONFIRMED ACT STAY CONFIRMED. No. Never, at any tier. A
|
||||
// confirmation binds one capability, one target and one argument list, and
|
||||
// it expires with the parked turn (confirmTTL, 90s). "Same act again" is a
|
||||
// new act and costs a new turn. A sticky confirm is a standing grant, and
|
||||
// nothing on the voice path may hold one.
|
||||
// - WHAT A NEW DOMAIN INHERITS. The default is TierDestructive, not
|
||||
// TierSafe. A dispatch shape this file does not recognise gets the confirm
|
||||
// turn — a new domain must argue its way DOWN to running freely, never up
|
||||
// to needing a confirm.
|
||||
type Risk string
|
||||
|
||||
const (
|
||||
// TierSafe — a read, or a mutation the owner can undo by saying the
|
||||
// opposite. Runs on first hearing.
|
||||
TierSafe Risk = "safe"
|
||||
// TierDestructive — it changes something real and undoing it takes work.
|
||||
// One confirm turn, every time, never remembered.
|
||||
TierDestructive Risk = "destructive"
|
||||
// TierIrreversible — the thing it acts on does not come back: a wipe, a
|
||||
// format, a delete with no bin behind it. A confirm turn is not enough,
|
||||
// because the whole chain that proposed it — an STT guess, a router guess,
|
||||
// a fuzzy allowlist match — has a spoken "да" as its only check. She names
|
||||
// the gap and he runs it himself.
|
||||
TierIrreversible Risk = "irreversible"
|
||||
)
|
||||
|
||||
// Policy — what a tier requires of the act path.
|
||||
//
|
||||
// There is deliberately no "sticky for" field. Non-stickiness is the policy,
|
||||
// and a knob that could turn it off would be the thing to argue with instead
|
||||
// of the rule.
|
||||
type Policy struct {
|
||||
// Confirm — the act does not run on first hearing.
|
||||
Confirm bool
|
||||
// VoiceMayRun — a spoken confirmation is enough authority to run it.
|
||||
VoiceMayRun bool
|
||||
}
|
||||
|
||||
// PolicyFor returns the requirements of a tier. An unknown tier is treated as
|
||||
// destructive, for the same reason the default derivation is.
|
||||
func PolicyFor(r Risk) Policy {
|
||||
switch r {
|
||||
case TierSafe:
|
||||
return Policy{Confirm: false, VoiceMayRun: true}
|
||||
case TierIrreversible:
|
||||
return Policy{Confirm: true, VoiceMayRun: false}
|
||||
default:
|
||||
return Policy{Confirm: true, VoiceMayRun: true}
|
||||
}
|
||||
}
|
||||
|
||||
// irreversibleVerbs — argv heads and subcommands that destroy the thing they
|
||||
// name. Matched as whole argv elements, never as substrings: "rm" must not
|
||||
// fire on "/usr/bin/rmdir-report" and "drop" must not fire on "dropbox".
|
||||
//
|
||||
// The list is short on purpose. It is not a sandbox and it does not try to be
|
||||
// one — an enabled row can already run anything the daemon's user can run.
|
||||
// What it is, is the set of words that mean "and then it is gone", so that the
|
||||
// one act nobody can walk back is the one act a spoken "да" cannot authorise.
|
||||
var irreversibleVerbs = map[string]bool{
|
||||
"rm": true, "rmdir": true, "shred": true, "srm": true,
|
||||
"mkfs": true, "fdisk": true, "parted": true, "wipefs": true,
|
||||
"dd": true, "format": true,
|
||||
"drop": true, "drop-database": true, "destroy": true, "purge": true,
|
||||
"prune": true, "truncate": true,
|
||||
}
|
||||
|
||||
// RiskOfCapability — the tier of a Hexis capability, which Hexis decides.
|
||||
//
|
||||
// Everything below this comment in RiskOf is a derivation, and a derivation is
|
||||
// only honest where nobody else holds the answer. Hexis does hold it: the
|
||||
// capability carries risk, read_only and requires_confirmation, and its own
|
||||
// contract says requires_confirmation is server-derived from the tier and never
|
||||
// settable by a caller. Deriving a second opinion here is the same defect as
|
||||
// inventing a local fact key for something Nexus resolves — two answers, one of
|
||||
// them stale, and the wrong one authorising an act (Vikunja #523).
|
||||
//
|
||||
// So this reads rather than decides. The three arguments are Capability.Risk,
|
||||
// Capability.ReadOnly and Capability.RequiresConfirmation, passed as plain
|
||||
// values so internal/tool keeps no dependency on the Hexis client.
|
||||
//
|
||||
// The one judgement left is what to do with an answer we cannot read. It goes
|
||||
// up, never down: an unrecognised tier gets the confirm turn, the same default
|
||||
// a dispatch shape RiskOf does not know gets. And requires_confirmation may
|
||||
// only raise — a capability that calls itself safe and then asks for a confirm
|
||||
// is telling us two things, and the cautious one wins.
|
||||
func RiskOfCapability(risk string, readOnly, requiresConfirmation bool) Risk {
|
||||
switch Risk(strings.ToLower(strings.TrimSpace(risk))) {
|
||||
case TierIrreversible:
|
||||
return TierIrreversible
|
||||
case TierDestructive:
|
||||
return TierDestructive
|
||||
case TierSafe:
|
||||
// Safe and mutating is a contradiction, and so is safe with a confirm
|
||||
// required. Either way the act changes something.
|
||||
if requiresConfirmation || !readOnly {
|
||||
return TierDestructive
|
||||
}
|
||||
return TierSafe
|
||||
case "":
|
||||
// No tier declared. Fall back to the shape Hexis did give us: a
|
||||
// read-only capability that wants no confirm is a read, and anything
|
||||
// else takes the confirm turn.
|
||||
if readOnly && !requiresConfirmation {
|
||||
return TierSafe
|
||||
}
|
||||
return TierDestructive
|
||||
default:
|
||||
// A word this file has never seen. It is not safe by default.
|
||||
return TierDestructive
|
||||
}
|
||||
}
|
||||
|
||||
// RiskOf derives the tier of a locally enabled tool row — a shell command, an
|
||||
// MCP call or a house service. Nothing here is a Hexis capability, and nothing
|
||||
// upstream has an opinion about a row the owner ticked on /tools, which is why
|
||||
// this one derives and RiskOfCapability reads.
|
||||
func RiskOf(t ipc.Tool) Risk {
|
||||
if isIrreversible(t.Cmd) {
|
||||
return TierIrreversible
|
||||
}
|
||||
// A house row is a physical change to the flat, and the confirm turn on it
|
||||
// is structural rather than a column: /tools writes the checkbox straight
|
||||
// through on enable, so unticking it once turned an unlock into a row that
|
||||
// ran on first hearing. Nothing any surface writes removes the second turn
|
||||
// from a physical device.
|
||||
if _, _, ok := smarthome.ParseCmd(t.Cmd); ok {
|
||||
return TierDestructive
|
||||
}
|
||||
// An MCP row is a call to somebody else's server. It is enabled with a
|
||||
// fingerprint of what it declared at approval time (Vikunja #251), and the
|
||||
// tier tracks the same flag every other row uses — the point of this branch
|
||||
// is that it is NOT special-cased into running freely.
|
||||
if _, _, ok := mcp.ParseCmd(t.Cmd); ok {
|
||||
if t.Destructive {
|
||||
return TierDestructive
|
||||
}
|
||||
return TierSafe
|
||||
}
|
||||
if t.Destructive {
|
||||
return TierDestructive
|
||||
}
|
||||
if len(t.Cmd) == 0 {
|
||||
// Not a shape this file knows how to read. The default is the confirm
|
||||
// turn: a new domain argues its way down, not up.
|
||||
return TierDestructive
|
||||
}
|
||||
return TierSafe
|
||||
}
|
||||
|
||||
// isIrreversible reports whether any argv element is one of the verbs that
|
||||
// destroys what it names. Every element, not just the head: "sudo rm" and
|
||||
// "docker volume prune" both hide the verb behind a wrapper.
|
||||
func isIrreversible(cmd []string) bool {
|
||||
for _, arg := range cmd {
|
||||
word := strings.ToLower(strings.TrimSpace(arg))
|
||||
// Take the last path element, so /bin/rm reads as rm.
|
||||
if i := strings.LastIndex(word, "/"); i >= 0 {
|
||||
word = word[i+1:]
|
||||
}
|
||||
if irreversibleVerbs[word] {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
@@ -0,0 +1,111 @@
|
||||
package tool
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
)
|
||||
|
||||
func TestRiskOfReadsTheRow(t *testing.T) {
|
||||
cases := []struct {
|
||||
name string
|
||||
tool ipc.Tool
|
||||
want Risk
|
||||
}{
|
||||
{"a plain read", ipc.Tool{Cmd: []string{"systemctl", "status"}}, TierSafe},
|
||||
{"the checkbox", ipc.Tool{Cmd: []string{"systemctl", "restart"}, Destructive: true}, TierDestructive},
|
||||
{"a wipe", ipc.Tool{Cmd: []string{"rm", "-rf"}}, TierIrreversible},
|
||||
{"a wipe behind a wrapper", ipc.Tool{Cmd: []string{"sudo", "/bin/rm"}}, TierIrreversible},
|
||||
{"a prune behind a subcommand", ipc.Tool{Cmd: []string{"docker", "volume", "prune"}}, TierIrreversible},
|
||||
{"the house", ipc.Tool{Cmd: []string{"smarthome", "light.kitchen", "turn_off"}}, TierDestructive},
|
||||
{"the house with the box unticked", ipc.Tool{Cmd: []string{"smarthome", "lock.front", "unlock"}}, TierDestructive},
|
||||
{"an mcp read", ipc.Tool{Cmd: []string{"mcp", "vikunja", "list_tasks"}}, TierSafe},
|
||||
{"an mcp write", ipc.Tool{Cmd: []string{"mcp", "vikunja", "delete_task"}, Destructive: true}, TierDestructive},
|
||||
{"a shape nobody wrote yet", ipc.Tool{}, TierDestructive},
|
||||
}
|
||||
for _, c := range cases {
|
||||
if got := RiskOf(c.tool); got != c.want {
|
||||
t.Errorf("%s: RiskOf = %q; want %q", c.name, got, c.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The default is the confirm turn. A tier this file does not know is not a
|
||||
// tier that runs freely.
|
||||
func TestPolicyForDefaultsToConfirming(t *testing.T) {
|
||||
for _, r := range []Risk{TierDestructive, Risk("whatever-lands-here-next")} {
|
||||
p := PolicyFor(r)
|
||||
if !p.Confirm || !p.VoiceMayRun {
|
||||
t.Errorf("PolicyFor(%q) = %+v; want a confirm turn she may run", r, p)
|
||||
}
|
||||
}
|
||||
if p := PolicyFor(TierSafe); p.Confirm || !p.VoiceMayRun {
|
||||
t.Errorf("PolicyFor(safe) = %+v; want it to run", p)
|
||||
}
|
||||
if p := PolicyFor(TierIrreversible); !p.Confirm || p.VoiceMayRun {
|
||||
t.Errorf("PolicyFor(irreversible) = %+v; want voice refused", p)
|
||||
}
|
||||
}
|
||||
|
||||
// An irreversible act is refused whether or not he said "да", because there is
|
||||
// no second answer that changes what it would do.
|
||||
func TestExecRefusesIrreversibleEvenConfirmed(t *testing.T) {
|
||||
api := fakeAPI{tools: map[string]ipc.Tool{
|
||||
"wipe": {Name: "wipe", Status: "enabled", Cmd: []string{"rm", "-rf"}, Destructive: true},
|
||||
}}
|
||||
e := NewExecutor(api, 0)
|
||||
ran := false
|
||||
e.run = func(context.Context, []string) (string, error) { ran = true; return "", nil }
|
||||
for _, confirmed := range []bool{false, true} {
|
||||
if _, err := e.Exec(context.Background(), "wipe", []string{"/data"}, confirmed); !errors.Is(err, ErrNeedsAuthedSurface) {
|
||||
t.Errorf("confirmed=%v: %v; want ErrNeedsAuthedSurface", confirmed, err)
|
||||
}
|
||||
}
|
||||
if ran {
|
||||
t.Fatal("an irreversible act ran from the voice path")
|
||||
}
|
||||
}
|
||||
|
||||
// A row with no cmd at all is not a shape this file reads, and it must not
|
||||
// slide through as safe.
|
||||
func TestExecConfirmsAnUnreadableRow(t *testing.T) {
|
||||
api := fakeAPI{tools: map[string]ipc.Tool{
|
||||
"mystery": {Name: "mystery", Status: "enabled"},
|
||||
}}
|
||||
e := NewExecutor(api, 0)
|
||||
if _, err := e.Exec(context.Background(), "mystery", nil, false); !errors.Is(err, ErrNeedsConfirm) {
|
||||
t.Errorf("%v; want ErrNeedsConfirm", err)
|
||||
}
|
||||
}
|
||||
|
||||
// Hexis owns the tier of a Hexis capability, so this reads rather than derives
|
||||
// (Vikunja #523). The cases that matter are the ones where the three fields
|
||||
// disagree, or where the tier is a word this package has never seen: every one
|
||||
// of those goes up to a confirm, never down to running freely.
|
||||
func TestRiskOfCapabilityReadsHexis(t *testing.T) {
|
||||
for _, c := range []struct {
|
||||
name string
|
||||
risk string
|
||||
ro bool
|
||||
confirm bool
|
||||
want Risk
|
||||
}{
|
||||
{"hexis says irreversible", "irreversible", false, true, TierIrreversible},
|
||||
{"case and space do not change the tier", " Irreversible ", false, true, TierIrreversible},
|
||||
{"hexis says destructive", "destructive", false, true, TierDestructive},
|
||||
{"a read hexis calls safe", "safe", true, false, TierSafe},
|
||||
{"safe but mutating is a contradiction", "safe", false, false, TierDestructive},
|
||||
{"safe but wants a confirm is a contradiction", "safe", true, true, TierDestructive},
|
||||
{"no tier, read-only, no confirm", "", true, false, TierSafe},
|
||||
{"no tier and mutating", "", false, false, TierDestructive},
|
||||
{"no tier but hexis wants a confirm", "", true, true, TierDestructive},
|
||||
{"a word we have never seen", "spicy", true, false, TierDestructive},
|
||||
} {
|
||||
if got := RiskOfCapability(c.risk, c.ro, c.confirm); got != c.want {
|
||||
t.Errorf("%s: RiskOfCapability(%q, ro=%v, confirm=%v) = %q; want %q",
|
||||
c.name, c.risk, c.ro, c.confirm, got, c.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user