Spaces:
Paused
Paused
| """ | |
| Specialist tool registry. | |
| Phase 4 (P0). Satisfies PS requirement: "select one or more models or | |
| tools from a predefined registry." | |
| This registry is deliberately just data — no model code lives here yet. | |
| Each entry describes what a task NEEDS (image count / modality / role) | |
| and WHICH tool would be invoked once Phases 5-8 wire in real specialist | |
| models. The router (router.py) uses this to validate inputs and to | |
| report a selected_tool name in the execution trace. | |
| Do not add model inference code to this file — it's a lookup table. | |
| """ | |
| from __future__ import annotations | |
| from enum import Enum | |
| from typing import Optional, TypedDict | |
| class TaskType(str, Enum): | |
| vqa = "vqa" | |
| captioning = "captioning" | |
| grounding = "grounding" | |
| change_detection = "change_detection" | |
| change_vqa = "change_vqa" | |
| optical_sar = "optical_sar" | |
| # Phase 16: follow-up chain hops 2 and 3 (uisuggestions.docx "Ask | |
| # Follow-up" / LEFT.md §3). NOT independently PS-mandatory — these | |
| # only ever get selected via agent/followup.py's followup_intent(), | |
| # never via agent/router.py's keyword classifier, because they only | |
| # make sense as a continuation of a previous grounding/change turn. | |
| area_estimate = "area_estimate" | |
| sar_cross_check = "sar_cross_check" | |
| class TaskSpec(TypedDict): | |
| label: str | |
| ps_requirement: str | |
| min_images: int | |
| max_images: int | |
| allowed_roles: set[str] | |
| allowed_modalities: set[str] | |
| required_modalities: Optional[set[str]] # if set, ALL of these must be present across inputs | |
| tool: str | |
| TASK_REGISTRY: dict[TaskType, TaskSpec] = { | |
| TaskType.vqa: { | |
| "label": "Visual Question Answering", | |
| "ps_requirement": "Single-image VQA (mandatory baseline)", | |
| "min_images": 1, | |
| # Phase 9: up to 2 allowed (optical + SAR of the same scene) so the | |
| # Evidence Sufficiency Engine can pick whichever is usable — the | |
| # model itself still only ever looks at ONE image per call. | |
| "max_images": 2, | |
| "allowed_roles": {"single"}, | |
| "allowed_modalities": {"optical", "sar"}, | |
| "required_modalities": None, | |
| "tool": "vqa_model (BLIP-VQA-base, BigEarthNet-adapted where available) — Phase 5", | |
| }, | |
| TaskType.captioning: { | |
| "label": "Scene Captioning", | |
| "ps_requirement": "Additional single-image task: captioning/scene description", | |
| "min_images": 1, | |
| "max_images": 2, # Phase 9: same optical+SAR allowance as VQA, see above | |
| "allowed_roles": {"single"}, | |
| "allowed_modalities": {"optical", "sar"}, | |
| "required_modalities": None, | |
| "tool": "captioning_model — not yet integrated (Phase 5)", | |
| }, | |
| TaskType.grounding: { | |
| "label": "Text-Guided Region Grounding", | |
| "ps_requirement": "Additional single-image task: text-guided region grounding", | |
| "min_images": 1, | |
| "max_images": 2, # Phase 9: same optical+SAR allowance as VQA, see above | |
| "allowed_roles": {"single"}, | |
| "allowed_modalities": {"optical", "sar"}, | |
| "required_modalities": None, | |
| "tool": "grounding_model (OWL-ViT open-vocabulary detector) — Phase 6", | |
| }, | |
| TaskType.change_detection: { | |
| "label": "Bi-Temporal Change Detection", | |
| "ps_requirement": "Multi-image change analysis (mandatory): change description/change map", | |
| "min_images": 2, | |
| # Phase 12: up to 4 allowed — one optical Before/After pair PLUS | |
| # one SAR Before/After pair — so the Evidence Sufficiency Engine | |
| # can fail over to the SAR pair when the optical pair is cloudy, | |
| # the same way VQA/grounding already fail over to a single SAR | |
| # image. The model itself still only ever runs on ONE pair per | |
| # call (see evidence/sufficiency.py decide_temporal_evidence()). | |
| "max_images": 4, | |
| "allowed_roles": {"before", "after"}, | |
| "allowed_modalities": {"optical", "sar"}, | |
| "required_modalities": None, | |
| "tool": "change_model (pixel-diff z-score change map + rule-based description) — Phase 7", | |
| }, | |
| TaskType.change_vqa: { | |
| "label": "Change-Based Visual Question Answering", | |
| "ps_requirement": "Multi-image change analysis (mandatory): change-based VQA", | |
| "min_images": 2, | |
| "max_images": 4, # Phase 12: same optical+SAR before/after allowance as above | |
| "allowed_roles": {"before", "after"}, | |
| "allowed_modalities": {"optical", "sar"}, | |
| "required_modalities": None, | |
| "tool": "change_vqa_model (composite before|after image through BLIP-VQA + change map) — Phase 7", | |
| }, | |
| TaskType.optical_sar: { | |
| "label": "Optical–SAR Cross-Modal Analysis", | |
| "ps_requirement": "Cross-modal pair analysis (mandatory): optical+SAR complementary extraction", | |
| "min_images": 2, | |
| "max_images": 2, | |
| "allowed_roles": {"single"}, | |
| "allowed_modalities": {"optical", "sar"}, | |
| "required_modalities": {"optical", "sar"}, | |
| "tool": "optical_sar_fusion_model (percentile-threshold agreement fusion) — Phase 8", | |
| }, | |
| TaskType.area_estimate: { | |
| "label": "Follow-up: Area Estimate", | |
| "ps_requirement": ( | |
| "NOT PS-mandatory — hop 2 of the follow-up chain " | |
| "(uisuggestions.docx 'Ask Follow-up'), only reachable via " | |
| "agent/followup.py after a prior grounding turn" | |
| ), | |
| "min_images": 1, | |
| "max_images": 2, | |
| "allowed_roles": {"single"}, | |
| "allowed_modalities": {"optical", "sar"}, | |
| "required_modalities": None, | |
| "tool": "area_from_geotiff_gsd (pixel-box -> km\u00b2 via source GeoTIFF georeferencing) — Phase 16", | |
| }, | |
| TaskType.sar_cross_check: { | |
| "label": "Follow-up: SAR Cross-Check", | |
| "ps_requirement": ( | |
| "NOT PS-mandatory — hop 3 of the follow-up chain " | |
| "(uisuggestions.docx 'Ask Follow-up'), only reachable via " | |
| "agent/followup.py after a prior grounding turn" | |
| ), | |
| "min_images": 1, | |
| "max_images": 2, | |
| "allowed_roles": {"single"}, | |
| "allowed_modalities": {"optical", "sar"}, | |
| "required_modalities": {"sar"}, | |
| "tool": "grounding_model (google/owlvit-base-patch32), re-run on the SAR image — Phase 16", | |
| }, | |
| } | |