| 1 | # Document Query Plugin DOX |
| 2 | |
| 3 | ## Purpose |
| 4 | |
| 5 | - Own document loading, parsing, indexing, and Q&A over local and remote documents. |
| 6 | |
| 7 | ## Ownership |
| 8 | |
| 9 | - `tools/document_query.py` owns the agent-facing query tool. |
| 10 | - `helpers/` owns fetching, parser routing, indexing, and query orchestration. |
| 11 | - `prompts/` owns document-query tool and optimization prompts. |
| 12 | - `hooks.py`, `default_config.yaml`, `plugin.yaml`, `skills/`, `extensions/`, and `webui/` own dependency bootstrap, settings, metadata, skill guidance, hooks, and UI. |
| 13 | |
| 14 | ## Local Contracts |
| 15 | |
| 16 | - Respect configured size, timeout, retry, parser concurrency, and OCR limits. |
| 17 | - Fetch local and remote resources safely and avoid leaking document contents beyond intended prompt/tool use. |
| 18 | - Keep optional dependency installation targeted to the framework runtime. |
| 19 | |
| 20 | ## Work Guidance |
| 21 | |
| 22 | - Coordinate parser changes with timeout handling and fallback behavior. |
| 23 | - Keep prompt and skill guidance clear that image files, screenshots, scans, charts, photos, and diagrams should go to vision tools first when available; `document_query` image OCR is a text-focused fallback when vision is unavailable or cannot read the needed text. |
| 24 | |
| 25 | ## Verification |
| 26 | |
| 27 | - Smoke-test representative PDF, text/HTML, image/OCR, and remote-document queries after parser changes. |
| 28 | |
| 29 | ## Child DOX Index |
| 30 | |
| 31 | No child DOX files. |