Repository navigation
New test to port (done with test_chaining_distance_piscine_caen.py but maybe too complex) #38
Description
On geocontext, PR ignfab/geocontext#207 added a new behavior and e2e test:
testName: "should find that Sivom swimming pool in Mondeville is the nearest pool to the LUX cinema in Caen, and that the walking distance is 29 minutes",
userInput: "Quel est le temps de marche exact entre le cinéma LUX, situé au sud-est de Caen, et la piscine la plus proche ?",
toolMode: "mcp",
requiredToolCalls: ["geocode", "gpf_search_types", "gpf_describe_type", "gpf_get_features", "distance"],
expectedResponseFragments: ["Sivom", "Mondeville"],
assertScenarioResult: ({ normalizedFinalMessage }) => {
expect(containsNumberInRange(normalizedFinalMessage, 25, 35)).toBe(true);
},Can it be ported in geocontext-test?
Metadata
Metadata
Assignees
Labels
No labels
Activity
mborne commentedon Oct 5, 2026
Proposal: close this issue in favour of the new, more focused issues on 0.10.x test coverage:
distancetool: the LUX cinema / Sivom pool scenario from Addtimemetric andcarandpedestrianprofiles toDistanceToolgeocontext#207 is now tracked there, alongside a simplergeocode+distancetest.travel_time_filter, Test E2E - add a test for intersects_feature_filter (0.10.x) #42intersects_feature_filter, Test E2E - add tests for gpf_get_features_layer and gpf_get_feature_by_id_layer (0.10.x) #43_layertools, Test E2E - add tests for spatial_extras (0.10.x) #44spatial_extras/order_by/select.Any objection?
mborne commentedon Oct 5, 2026
The scenario is ported in #47 (
test_chaining_distance_piscine_caen.py), but it is too complex for the goal of these tests: checking that the tools work properly with different models, not testing the models' reasoning capabilities.To pass it, the model has to resolve an ambiguous place ("cinéma LUX", where
geocodereturns a tram station), discover the right WFS table, search for the nearest pool, then calldistance. A failure therefore says more about the model's reasoning than about the tools. For example, claude-haiku-4-5 fails because it takes the first pool returned bygeocode(Campus 1, 52 min), while claude-sonnet-4-6 passes (Sivom, Mondeville, 29.5 min).The simpler
geocode→distancetest (test_chaining_geocode_distance.py) fits the purpose of this repository better.[-]New test to port[/-][+]New test to port (done with test_chaining_distance_piscine_caen.py but maybe too complex)[/+]