#!/usr/bin/env python3 """Generate the v2 subtitle contract sample recordings (HEL-879). Drives the REAL seam implementation (seam.SubtitleBus / AssistantInterimPublisher / speak_proactive_row's event shape) offline — zero livekit imports, zero model calls — and writes the JSONL sequences the visual author wires against: docs/rework/hel879/subtitle-samples/normal-turn.jsonl docs/rework/hel879/subtitle-samples/interrupt.jsonl docs/rework/hel879/subtitle-samples/proactive.jsonl Each line is exactly one cg.subtitle payload as it would be published on the room topic (see docs/voice-subtitle-contract-v2.md). """ from __future__ import annotations import json import sys from pathlib import Path ROOT = Path(__file__).resolve().parents[1] sys.path.insert(0, str(ROOT / "src")) from cybergril.voice.seam import ( # noqa: E402 AssistantInterimPublisher, SubtitleBus, ) OUT = ROOT / "docs/rework/hel879/subtitle-samples" def record(name: str, payloads: list[dict]) -> Path: OUT.mkdir(parents=True, exist_ok=True) path = OUT / name path.write_text( "".join(json.dumps(p, ensure_ascii=False) + "\n" for p in payloads), encoding="utf-8") return path def normal_turn() -> list[dict]: payloads: list[dict] = [] bus = SubtitleBus(payloads.append) interim = AssistantInterimPublisher(bus) bus.emit("interim", role="user", text="你在听的") bus.emit("user_final", role="user", text="你在听吗?") interim.begin("speech_normal") interim.feed("speech_normal", "在听呢,") interim.feed("speech_normal", "在听呢,你刚才说到一半的那件事我还在想。") interim.finish("speech_normal", turn_id="0e2f-demo-turn", text="在听呢,你刚才说到一半的那件事我还在想。", message_id=None) return payloads def interrupt_turn() -> list[dict]: payloads: list[dict] = [] bus = SubtitleBus(payloads.append) interim = AssistantInterimPublisher(bus) interim.begin("speech_cut") interim.feed("speech_cut", "我正想跟你说,今天下午") # barge-in: the turn dies without a final; the next user turn starts clean interim.cancel("speech_cut", "interrupted") bus.emit("interim", role="user", text="等一下") bus.emit("user_final", role="user", text="等一下,先听我说。") interim.begin("speech_next") interim.feed("speech_next", "好,你先说。") interim.finish("speech_next", turn_id="0e2f-demo-next", text="好,你先说。") return payloads def proactive() -> list[dict]: payloads: list[dict] = [] bus = SubtitleBus(payloads.append) # spoken to the end (same-source message_id 17) bus.emit("proactive_start", role="assistant", speech_id="speech_pro1", text="我看到一句很适合现在的话,先念给你听。", message_id=17) bus.emit("proactive_end", role="assistant", speech_id="speech_pro1", message_id=17) # interrupted variant (message_id 18) bus.emit("proactive_start", role="assistant", speech_id="speech_pro2", text="还有一件事想告诉你——", message_id=18) bus.emit("proactive_cancel", role="assistant", speech_id="speech_pro2", message_id=18, reason="interrupted") return payloads def main() -> int: for name, fn in (("normal-turn.jsonl", normal_turn), ("interrupt.jsonl", interrupt_turn), ("proactive.jsonl", proactive)): path = record(name, fn()) seqs = [json.loads(line)["seq"] for line in path.read_text(encoding="utf-8").splitlines()] assert seqs == sorted(seqs) and len(set(seqs)) == len(seqs), (name, seqs) print(f"{path} ({len(seqs)} payloads, seq 1..{seqs[-1]})") return 0 if __name__ == "__main__": sys.exit(main())