Merge upstream main into denis/rail-layer

server/providers/openai/instructions.js

@@ -38,7 +38,7 @@ function realtimeDirectives(
     'READING THE VIEW: with no selected object or overlay entities, answer from get_entity_context\'s basemap context (tiles source, centre target, reverse-geocoded place, altitude, style, enabled layers); say there is nothing only when that is unavailable too. Prefer, in order: a nearby knownLandmarks name ("Eiffel Tower"); at local zoom nearbyPlaces, place.labels and viewportPlaces visible and street labels; viewportPlaces dominantCountry/Region/Locality over raw coordinates; the majority of viewportSamples over one reverse-geocoded address. Legible labels in an attached screenshot count too, but at global or regional viewScale never name a precise street or city from one centre pixel.',
     'Do not mention disabled layers or stale selections.',
     'POINTING: pointer_context says what the cursor is on (pointing:<kind>: resolved by the tools; target "none": not pointing). For "this/that/here/that one" with no name, pass "pointer": get_entity_context scope, track_entity/fly_to_location query, analyst_query scope.kind ("around here" is pointer, not view), annotate_map target, find_imagery area. "The second/last one" is referent:n from the last numbered list. Without a pointer, ask or follow WHERE.',
-    'PREAMBLES: for instant commands (layers, styles, HUD, detection, zoom, panels, basemap, radio controls, camera nudges, and lookups such as get_entity_context) call the tool without speaking first. Only for slow or multi-step work (annotate_map, resolve_area, find_imagery, a searched fly_to_location, select_nearest_aircraft, analyst_query over a named place, or two or more tools) you may first say ONE sentence of at most 12 words naming the actual steps ("Finding the Capitol, then outlining its grounds."), then call the tools at once in the same response.',
+    'PREAMBLES: for instant commands (layers, styles, HUD, detection, zoom, panels, basemap, radio controls, camera nudges, and lookups such as get_entity_context) call the tool without speaking first. Only for slow or multi-step work (annotate_map, resolve_area, find_imagery, a searched fly_to_location, select_nearest_aircraft, show_street_level, analyst_query over a named place, or two or more tools) you may first say ONE sentence of at most 12 words naming the actual steps ("Finding the Capitol, then outlining its grounds."), then call the tools at once in the same response.',
     'When one request contains MULTIPLE changes, call ALL the corresponding tools before the confirmation. Never confirm a partial subset; if one fails, say which.',
     'AFTER TOOLS: speak the result\'s say line once, lightly rephrased at most, never repeating your preamble. For a requested analyst list or ranking, also name up to three returned items with the relevant returned values; keep their order. A count alone does not answer that request; if say is null, finish any remaining requested tools before confirming. Never add a count, list or action claim that the executed tool results do not support. Sources, notes and caveats are on the voice card: speak a caveat only when it changes the answer, or when asked why, how sure or which source. Lower bounds ("at least 500"), partial answers, approximate outlines and stale, degraded or unavailable feed states in say are part of the answer — always preserve them. No filler or hedges ("let me check", "keep in mind", "it seems", "based on the data available"), and never add "approximately" to an exact tool number.',
     'For "show/open/turn on" layer requests, enable the matching layer. For "hide/close/turn off", disable it.',
@@ -65,6 +65,7 @@ function realtimeDirectives(
     '"Track/follow <something specific>" (a callsign, ship name, satellite name) uses track_entity. "Take me to the biggest fire" uses track_entity with query "biggest fire" (the fires layer must be enabled). Bare "orbit" means camera orbit of the current landmark. "Stop following/tracking" uses stop_tracking.',
     '"Show me which planes are overhead"/"frame the ships"/"show me the satellites above" use frame_overhead with the matching target.',
     'Confirmations echo the RESULTING state, never the request: "HUD minimal layout", "Density twenty-five percent", "Bing aerial imagery", "Tracking UAL428", "Framed fourteen aircraft". On ok=false, state the failure plainly: "Nothing matched UAL999", "No ships within 120 kilometers". Never claim an action without ok=true in the tool result.',
+    'STREET LEVEL: "X on Street View/Mapillary/KartaView/Panoramax", "street view of X" → show_street_level once, not fly_to_location; no place = view centre. Street View is never a basemap.',
     'For destination requests such as "take me to Italy", "go to NYC", or "show me the Eiffel Tower", call fly_to_location. Prefer known city IDs when available; otherwise pass the plain place query.',
     'Navigation-only requests ("take me to X", "go to X", "fly to X") are NOT descriptions: call fly_to_location alone and do NOT also call annotate_map, unless the user explicitly asks to mark the place or you go on to explain specific places there. Never drop a point pin on a region-scale natural feature (a mountain range, desert, sea, or forest) — a single point in the middle of the Rockies is meaningless. If the user explicitly asks to mark such a region, prefer type=area.',
     'For country and city destinations, omit rangeM so GEV frames the whole country or city in view. For landmarks and buildings, omit rangeM so GEV chooses a close landmark view.',

server/providers/openai/toolDescriptions.js

@@ -65,6 +65,28 @@ export const ACTION_DESCRIPTIONS = {
       },
     },
   },
+  show_street_level: {
+    description:
+      'Fly to a place and open its nearest street-level photo; Street View switches to Google 3D (billed). No query: view centre.',
+    $position: 1,
+    parameters: {
+      properties: {
+        query: {
+          description: 'Place or address; "pointer" = under the cursor.',
+          $position: 1,
+        },
+        provider: {
+          description:
+            'google = Street View; others by name; omit: the lit source.',
+          $position: 1,
+        },
+        referent: {
+          description: 'Numbered item n from the last result list.',
+          $position: 1,
+        },
+      },
+    },
+  },
   adjust_camera_zoom: {
     description:
       'Move the current Cesium camera closer to or farther from what it is presently looking at. Use for relative zoom requests without changing location.',