Document RAG retrieves from parser outputs, yet parsers are commonly selected by intrinsic measures of transcription fidelity and boundary quality rather than by retrieval performance. We introduce the Retrieval-Conditional Parsing Score (RCPS), a training-free protocol that ranks parser–chunker combinations on a fixed held-out Q–A retrieval probe. RCPS averages mean reciprocal rank (MRR) across specified retrievers and retrieval depths, using the same format-normalised exact-span relevance rule for every candidate. On KoGovDoc-RAG, table-enabled MinerU-on has a higher Boundary Clarity score than our production parser, Prod (0.713 versus 0.610). Yet its Hit@1 is 42.6 percentage points lower (0.123 versus 0.549). Across five parsers evaluated on all 294 pages, RCPS ranges from 0.137 to 0.584. With Prod fixed, the four chunkers score between 0.535 and 0.593. A retriever-free coverage diagnostic finds no normalised exact match for 20.2% of reference spans in Prod output. No tested chunker splits more than 2.3%. On source-aligned OHR-Bench data, semantic noise lowers retrieval while Boundary Clarity remains stable or changes non-monotonically. In a secondary parser-training study, two direct preference optimization checkpoints improve Hit@5 by only 0.95 and 1.15 percentage points over Prod on an audited compatibility subset; a matched edit-distance control performs similarly. The workflow therefore selects with RCPS, diagnoses with coverage, and trains only if needed. We release the 663-Q–A KoGovDoc-RAG probe and an RCPS reference implementation.

Real-time speech translation with large language models (LLMs) has become feasible in controlled wideband settings—mobile apps, web browsers, and end-to-end full-duplex systems pushing latency below 200 ms—where developers can assume client-side echo cancellation. However, deploying such systems over the Public Switched Telephone Network (PSTN) remains challenging due to narrowband G.711 audio, unpredictable round-trip delays, and absence of client-side signal processing. We present WIGVO (WIGTN Voice-Only), a server-side relay system that enables bidirectional LLM-based speech translation over ordinary telephone calls without requiring app installation or carrier integration. A central contribution is addressing what we term echo-induced self-reinforcing translation loops: synthesized speech echoing back through the PSTN gets re-ingested and repeatedly translated. WIGVO solves this through a dual-session architecture with deterministic silence injection and energy-based voice activity detection (VAD) gating. We evaluate WIGVO on 155 Korean–English PSTN calls (148 instrumented, 147 completed) across three communication modes—voice-to-voice (V2V), text-to-voice (T2V), and full-agent—observing 555 ms median caller-to-callee latency and 2,684 ms median callee-to-caller latency, zero echo-induced translation loops, COMET semantic adequacy of 0.71 (en→ko) and 0.62 (ko→en) against offline LLM references, and USD 0.28 per minute cost. The system is deployed at https://wigvo.wigtn.com, with a video walkthrough at https://youtu.be/4Uf6zMPOInY. Evaluation scripts and anonymized call logs are available in the open-source repository.