feat(dankvoice): speak the cloned voices in the TUI (Refs #21)
Every speak-aloud path in the harness gates `--voice` against the bundled Kokoro enum, so the frank-tts cloned voices could only ever produce files. `agent/extensions/` auto-loads, so one tracked extension adds the missing transport: `/say <text>`, `/say on|off` (narrate the final answer at `agent_end`, silent when the harness schedules a continuation), `/say voice|voices|stop|status` — OpenAI speech POST plus playback through pw-play/paplay/ffplay. The endpoint and served id come from the `api: openai-speech` row of `agent/models.yml`, so the file carries no host and no secret; markdown is stripped, over-long utterances are cut at a sentence bound, and the temp WAV dir is always removed. Verified live in a real TUI session on the workstation (roster narrator1/narrator2/narrator3; 2.08 s and 1.44 s WAVs played; auto-speak spoke each finished answer, 1.20 s WAV; unknown voice answers with the roster). Black-box seam `tests/dankvoice.bats` (12 tests) drives the extension against a fixture speech endpoint and a stub player. cwd: /home/blank/.omp/wt/feat-21-dankvoice session: wt-20261017-181502-6d1fc1f
This commit is contained in:
Frank
Executable
+263
@@ -0,0 +1,263 @@
|
||||
#!/usr/bin/env bats
|
||||
# tests/dankvoice.bats — black-box tests for agent/extensions/dankvoice.ts
|
||||
#
|
||||
# The extension's contract, from outside: it registers a `say` command and an
|
||||
# `agent_end` listener; what is observable is (a) the JSON it POSTs to the
|
||||
# speech route, (b) the file it hands to the player, and (c) the notification
|
||||
# text it prints. A fixture HTTP server stands in for frank-tts (it answers the
|
||||
# speech route with a fixed WAV, the roster route with a JSON array, and
|
||||
# everything else with 404) and a stub player stands in for pw-play: it records
|
||||
# the path it was given and copies the bytes it was told to play.
|
||||
#
|
||||
# Driven by env: DV_EXT (extension under test), DV_STUB / DV_STUB_LOG / DV_COPY
|
||||
# (player fixture), DV_MODELS (models.yml fixture), DV_EMPTY_BIN (a PATH with no
|
||||
# players), DV_MODE (the harness mode reported to the extension).
|
||||
|
||||
setup() {
|
||||
REPO="$(cd "$BATS_TEST_DIRNAME/.." && pwd)"
|
||||
WORK="$(mktemp -d)"
|
||||
|
||||
export DV_EXT="$REPO/agent/extensions/dankvoice.ts"
|
||||
export DV_STUB="$WORK/player.sh"
|
||||
export DV_STUB_LOG="$WORK/player.log"
|
||||
export DV_COPY="$WORK/played.wav"
|
||||
export DV_EMPTY_BIN="$WORK/emptybin"
|
||||
mkdir -p "$DV_EMPTY_BIN"
|
||||
|
||||
cat > "$DV_STUB" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
printf '%s\n' "$1" >> "$DV_STUB_LOG"
|
||||
cp "$1" "$DV_COPY"
|
||||
sleep 0.1
|
||||
SH
|
||||
chmod +x "$DV_STUB"
|
||||
|
||||
# models.yml fixture: a chat provider first, the speech provider second
|
||||
export DV_MODELS="$WORK/models.yml"
|
||||
cat > "$DV_MODELS" <<'YML'
|
||||
providers:
|
||||
"chat (box)":
|
||||
baseUrl: http://10.0.0.1:9999/v1
|
||||
models:
|
||||
- id: chatmodel
|
||||
api: openai-completions
|
||||
"speech (box)":
|
||||
baseUrl: http://127.0.0.1:1/v1
|
||||
auth: none
|
||||
models:
|
||||
- id: speechmodel
|
||||
api: openai-speech
|
||||
YML
|
||||
|
||||
cat > "$WORK/driver.ts" <<'TS'
|
||||
// Black-box driver: stand up the frank-tts fixture, load the extension against
|
||||
// it, invoke one scenario, print what the endpoint received and what got played.
|
||||
import { createServer } from "node:http";
|
||||
import { existsSync, readFileSync, statSync } from "node:fs";
|
||||
|
||||
const scenario = process.argv[2] ?? "speak";
|
||||
const AUDIO = Buffer.from([0x52, 0x49, 0x46, 0x46, 8, 0, 0, 0, 0x57, 0x41, 0x56, 0x45, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]);
|
||||
const received: Array<{ url: string | undefined; body: string }> = [];
|
||||
|
||||
const server = createServer((req, res) => {
|
||||
const chunks: Buffer[] = [];
|
||||
req.on("data", (chunk: Buffer) => chunks.push(chunk));
|
||||
req.on("end", () => {
|
||||
const body = Buffer.concat(chunks).toString("utf8");
|
||||
received.push({ url: req.url, body });
|
||||
if (req.url?.endsWith("/audio/voices")) {
|
||||
res.setHeader("content-type", "application/json");
|
||||
res.end(JSON.stringify(["narrator1", "narrator2"]));
|
||||
return;
|
||||
}
|
||||
if (req.url?.endsWith("/audio/speech")) {
|
||||
res.setHeader("content-type", "audio/wav");
|
||||
res.end(AUDIO);
|
||||
return;
|
||||
}
|
||||
res.statusCode = 404;
|
||||
res.end("{}");
|
||||
});
|
||||
});
|
||||
await new Promise<void>((resolve) => server.listen(0, "127.0.0.1", resolve));
|
||||
const port = (server.address() as { port: number }).port;
|
||||
|
||||
if (scenario === "endpoint") {
|
||||
process.env.DANKVOICE_MODELS = process.env.DV_MODELS;
|
||||
} else {
|
||||
process.env.DANKVOICE_URL = `http://127.0.0.1:${port}/v1`;
|
||||
}
|
||||
if (scenario === "noplayer") process.env.PATH = process.env.DV_EMPTY_BIN ?? "/nonexistent-bin";
|
||||
process.env.DANKVOICE_PLAYER = scenario === "noplayer" ? "" : process.env.DV_STUB;
|
||||
|
||||
const extension = await import(process.env.DV_EXT as string);
|
||||
const commands = new Map<string, { handler: (args: string, ctx: unknown) => Promise<void> }>();
|
||||
const events = new Map<string, (event: unknown, ctx: unknown) => Promise<void> | void>();
|
||||
extension.default({
|
||||
registerCommand: (name: string, options: { handler: (args: string, ctx: unknown) => Promise<void> }) => commands.set(name, options),
|
||||
on: (event: string, handler: (event: unknown, ctx: unknown) => Promise<void> | void) => events.set(event, handler),
|
||||
});
|
||||
const ctx = {
|
||||
mode: process.env.DV_MODE ?? "tui",
|
||||
ui: {
|
||||
notify: (message: string, level?: string) => console.log(`NOTIFY ${level ?? "info"} ${message}`),
|
||||
setStatus: (key: string, text?: string) => console.log(`STATUS ${key} ${text ?? ""}`),
|
||||
},
|
||||
};
|
||||
const say = commands.get("say");
|
||||
const agentEnd = events.get("agent_end");
|
||||
const answer = (text: string) => ({ messages: [{ role: "assistant", content: [{ type: "text", text }] }] });
|
||||
const settle = () => new Promise((resolve) => setTimeout(resolve, 800));
|
||||
|
||||
if (!say) {
|
||||
console.log("COMMANDS none");
|
||||
} else {
|
||||
console.log(`COMMANDS ${[...commands.keys()].join(",")} EVENTS ${[...events.keys()].join(",")}`);
|
||||
switch (scenario) {
|
||||
case "speak":
|
||||
await say.handler("hello world", ctx);
|
||||
break;
|
||||
case "voice":
|
||||
await say.handler("voice narrator2", ctx);
|
||||
await say.handler("good morning", ctx);
|
||||
break;
|
||||
case "auto":
|
||||
await say.handler("on", ctx);
|
||||
await agentEnd?.(answer("the answer"), ctx);
|
||||
await settle();
|
||||
await say.handler("off", ctx);
|
||||
await agentEnd?.(answer("the second answer"), ctx);
|
||||
break;
|
||||
case "continuation":
|
||||
await say.handler("on", ctx);
|
||||
await agentEnd?.({ ...answer("not yet"), willContinue: true }, ctx);
|
||||
await settle();
|
||||
await agentEnd?.(answer("the settled answer"), ctx);
|
||||
break;
|
||||
case "printmode":
|
||||
await say.handler("on", ctx);
|
||||
await agentEnd?.(answer("quiet"), ctx);
|
||||
break;
|
||||
case "voices":
|
||||
await say.handler("voices", ctx);
|
||||
break;
|
||||
case "endpoint":
|
||||
await say.handler("status", ctx);
|
||||
break;
|
||||
case "markdown":
|
||||
await say.handler("## Title\n\nUse `pw-play` here.\n\n```bash\nnpm i x\n```\n\nsee [docs](http://example.test) and **bold**\n- a\n- b", ctx);
|
||||
break;
|
||||
case "truncate":
|
||||
await say.handler("Sentence one is here. ".repeat(40), ctx);
|
||||
break;
|
||||
case "noplayer":
|
||||
await say.handler("speak anyway", ctx);
|
||||
break;
|
||||
}
|
||||
await settle();
|
||||
}
|
||||
|
||||
for (const call of received) {
|
||||
const parsed: unknown = JSON.parse(call.body === "" ? "{}" : call.body);
|
||||
const field = (key: string): string => {
|
||||
if (parsed && typeof parsed === "object" && key in parsed) {
|
||||
const value = parsed[key];
|
||||
if (typeof value === "string") return value;
|
||||
}
|
||||
return "-";
|
||||
};
|
||||
console.log(`CALL ${call.url} model=${field("model")} format=${field("response_format")} voice=${field("voice")} input=${field("input")}`);
|
||||
}
|
||||
console.log(`CALLS ${received.length}`);
|
||||
const log = process.env.DV_STUB_LOG && existsSync(process.env.DV_STUB_LOG) ? readFileSync(process.env.DV_STUB_LOG, "utf8").trim() : "";
|
||||
console.log(`PLAYS ${log === "" ? 0 : log.split("\n").length}`);
|
||||
if (process.env.DV_COPY && existsSync(process.env.DV_COPY)) console.log(`COPIED ${statSync(process.env.DV_COPY).size}`);
|
||||
server.close();
|
||||
TS
|
||||
|
||||
export DV_DRIVER="$WORK/driver.ts"
|
||||
}
|
||||
|
||||
teardown() {
|
||||
rm -rf "$WORK"
|
||||
}
|
||||
|
||||
say_run() {
|
||||
run bun "$DV_DRIVER" "$1"
|
||||
}
|
||||
|
||||
@test "the extension registers the say command and an agent_end listener" {
|
||||
say_run speak
|
||||
[ "$status" -eq 0 ]
|
||||
[[ "$output" == *"COMMANDS say EVENTS agent_end"* ]]
|
||||
}
|
||||
|
||||
@test "speaking posts the text to the speech route" {
|
||||
say_run speak
|
||||
[ "$status" -eq 0 ]
|
||||
[[ "$output" == *"CALL /v1/audio/speech model=frank-tts format=wav voice=- input=hello world"* ]]
|
||||
}
|
||||
|
||||
@test "one utterance is played once, as exactly the bytes the endpoint sent" {
|
||||
say_run speak
|
||||
[[ "$output" == *"PLAYS 1"* ]]
|
||||
[[ "$output" == *"COPIED 24"* ]]
|
||||
}
|
||||
|
||||
@test "the voice is named in the request only when the user chose one" {
|
||||
say_run speak
|
||||
[[ "$output" == *"voice=- input=hello world"* ]]
|
||||
say_run voice
|
||||
[[ "$output" == *"voice=narrator2 input=good morning"* ]]
|
||||
[[ "$output" == *"NOTIFY info dankvoice: voice = narrator2"* ]]
|
||||
}
|
||||
|
||||
@test "auto-speak narrates the final answer once and stays silent after it is disarmed" {
|
||||
say_run auto
|
||||
[[ "$output" == *"PLAYS 1"* ]]
|
||||
[[ "$output" == *"input=the answer"* ]]
|
||||
[[ "$output" != *"the second answer"* ]]
|
||||
[[ "$output" == *"STATUS dankvoice 🔊"* ]]
|
||||
}
|
||||
|
||||
@test "auto-speak stays silent outside the interactive modes" {
|
||||
DV_MODE=print say_run printmode
|
||||
[[ "$output" == *"PLAYS 0"* ]]
|
||||
[[ "$output" != *"input=quiet"* ]]
|
||||
}
|
||||
|
||||
@test "the voice list comes from the endpoint roster route" {
|
||||
say_run voices
|
||||
[[ "$output" == *"CALL /v1/audio/voices"* ]]
|
||||
[[ "$output" == *"dankvoice voices: narrator1, narrator2"* ]]
|
||||
}
|
||||
|
||||
@test "the endpoint is taken from the speech row of the models file, never the chat provider" {
|
||||
say_run endpoint
|
||||
[[ "$output" == *"http://127.0.0.1:1/v1/audio/speech"* ]]
|
||||
[[ "$output" != *"10.0.0.1"* ]]
|
||||
}
|
||||
|
||||
@test "markdown never reaches the speech engine" {
|
||||
say_run markdown
|
||||
[[ "$output" == *"input=Title Use pw-play here. see docs and bold a b"* ]]
|
||||
}
|
||||
|
||||
@test "an over-long utterance is bounded and cut at a sentence boundary" {
|
||||
DANKVOICE_MAX=60 say_run truncate
|
||||
[[ "$output" == *"here. …"* ]]
|
||||
[ "$(grep -o 'Sentence one is here\.' <<<"$output" | wc -l)" -le 4 ]
|
||||
}
|
||||
|
||||
@test "a missing player is reported, not swallowed" {
|
||||
say_run noplayer
|
||||
[[ "$output" == *"NOTIFY error dankvoice: no audio player found"* ]]
|
||||
[[ "$output" == *"PLAYS 0"* ]]
|
||||
}
|
||||
|
||||
@test "a scheduled continuation is never narrated as the final answer" {
|
||||
say_run continuation
|
||||
[[ "$output" == *"PLAYS 1"* ]]
|
||||
[[ "$output" == *"input=the settled answer"* ]]
|
||||
[[ "$output" != *"input=not yet"* ]]
|
||||
}
|
||||
Reference in New Issue
Block a user