Starting the upstream timeout after the outbound queue let a request run
up to about 19 s, past the Directions layer's 15 s; the budget again runs
from arrival, queue wait included, and a budget spent before the request
leaves the queue answers 429 "routing busy" rather than an outage.
plan_route threw "Routing HTTP 502" for an outage, and voice passes only
the message on; it now throws "Routing service unavailable (HTTP 502)".
Co-Authored-By: Claude Opus 5.5 <[email protected]>
When the OSRM routing service failed (a 5xx, a 403 block, a 404), answered
with a body that was not JSON, or did not answer at all (timeout, network
error), /api/route returned HTTP 200 with 'no route found' or 'route proxy
error'. plan_route turned that into invalid_arguments ("No walk route from
...: no route found"), blaming the caller for an outage, and the directions
layer reported "No route found between A and B".
The proxy now answers all of these with 502 {ok:false, error:'routing
service unavailable'}: a rejected upstream fetch, any failure status but
400, a non-JSON content type, and a body read that fails or does not parse.
An exception in the proxy's own code after that point is still a 200 'route
proxy error'. createRouteService throws for a 5xx before reading the body's
ok:false, so plan_route reports unavailable, and the directions source
treats any 5xx as "Routing unavailable (HTTP n)", also when the failure
page in front of the proxy is not JSON. OSRM's own refusal (a 400 such as
NoRoute, or a 200 without a route) still reads "no route found".
The 12 s upstream timeout now starts when the request leaves rather than
before it waits for an outbound slot, so a wait in the proxy's own queue
(up to about 8 s at the 1 s spacing) is not reported as an outage.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
The place cache shared one lookup between callers but started it without a
signal or deadline, so a cancelled request kept running and stayed cached.
A shared lookup now has its own deadline, is cancelled when every caller has
given up, and only a successful answer is kept.
Brief sections received a named place as its bounding box, so they centered
on the box's middle: Tokyo's aircraft were sorted from a point in the
Pacific. Sections now receive the place name and resolve it like a direct
query, and place lookups are cached briefly so a brief resolves it once.
A place's bounds can reach far from the place itself; Tokyo's include
remote Pacific islands, so the middle of its box is open ocean. Keep the
geocoder's point for a named place and use it as the area's center,
while bounds still decide what lies inside the area.
Add search_places and places_nearby over the app's Google Places routes,
and plan_route over its OpenStreetMap routing. The place search service
reports when no search key is configured, so an unconfigured server is
not mistaken for an empty result, and rate limits become retry_later.
Route endpoints accept a place name or coordinates.
Define tools that answer questions from the app's data once, independent
of the surface that exposes them. A tool declares its arguments and the
services it reads; applications compose tools with their own services and
optional call interceptors. Queries reuse the layers' portable source
factories, so they run wherever an application routes /api requests.
The first queries are get_earthquakes, get_active_fires and
get_recent_launches, with a shared area argument (place name, bounding
box, or point and radius) and capped lists.
gods-eye-view/tools/mcp adapts a catalog to the Model Context Protocol
with a small JSON-RPC handler and a stateless HTTP transport, adding no
dependencies. npm run mcp serves Core's tools over stdio to local clients
such as Claude Code, reading from a running app. Both exports are
portable and checked by check:boundaries; the app does not import them.