benmichael/gods-eye-view
1
0 Fork 0
mirror of https://github.com/bilawalsidhu/gods-eye-view.git synced 2026-11-04 10:24:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into feat/cctv-vegvesen-kartverket-heights

Browse Source
This commit is contained in:
trygvehhh authored and GitHub committed 2026-10-11 13:23:17 +02:00
2 parents 939264d30e 591f299d11
commit a15747ca61
182 files changed
+21688 -1249
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

.env.example
+15 -1
View File
@@ -55,8 +55,14 @@ GOOGLE_MAPS_SERVER_API_KEY=
# CLIENT-EXPOSED — use a public assets:read token with URL restrictions.
CESIUM_ION_TOKEN=
# Optional: OpenAI Realtime voice control. Do not prefix with VITE_.
# Optional: OpenAI Realtime voice control. API key is the default cloud auth.
# Provider Settings can instead opt voice into the signed-in local
# ChatGPT/Codex OAuth session; the browser still receives only a short-lived
# Realtime client secret. Do not prefix with VITE_.
OPENAI_API_KEY=
# Optional: forbid API-key voice sessions. Select ChatGPT OAuth in Provider
# Settings; missing or expired Codex sign-in then fails closed.
# GEV_PREFER_CODEX_OAUTH=true
OPENAI_REALTIME_MODEL=gpt-realtime-2
# Cheaper voice tier, used when the GEV MIC panel's MINI toggle is on.
# Model ids and prices are external facts that drift — if OpenAI moves this id,
@@ -67,6 +73,14 @@ OPENAI_REALTIME_REASONING_EFFORT=low
# Keep only a short conversational window. Current map state is fetched live.
OPENAI_REALTIME_CONTEXT_TOKENS=3000
OPENAI_REALTIME_CONTEXT_RETENTION=0.5
# Voice-card captions of what you said. Billed separately by OpenAI and
# counted in the session cost meter and cap; off disables them.
OPENAI_REALTIME_TRANSCRIBE_MODEL=gpt-4o-mini-transcribe
# The voice debug log (.gev-logs/realtime-conversations.jsonl, rotated at
# 32 MB, never expired) omits transcripts, typed or spoken text, and tool
# arguments/results (including serialized outputs) by default. Set to 1 to
# keep them while debugging; delete the log when you are done.
GEV_VOICE_LOG_CONTENT=
OPENAI_HUD_SUMMARY_MODEL=gpt-5-nano
# Per-IP rate limit for the OpenAI cost endpoints
# (/api/realtime/token + /api/openai/hud-summary), in requests per minute.
CHANGELOG.md
+140 -2
View File
@@ -1,7 +1,120 @@
# Changelog
- Treat explicitly current, complete empty vessel coverage as a successful update,
clearing obsolete contacts while retaining stale or incomplete snapshots.
- Custom Street Level provider switches survive share links and stored state
using URL-safe stable provider IDs and a shared boolean-switch codec; existing
Mapillary links keep their meaning. Explicit provider toggles reach durable
state without adopting unrelated live switch changes.
- Directions and Recent Imagery accept replaceable acquisition sources, including
route transport, imagery catalog, thumbnails, tile templates and attribution.
Explicitly removing either source leaves its layer unavailable; standalone
defaults preserve the existing providers.
- Catalog source availability no longer modifies layer objects; unavailable
tooltips use layer display names.
- Street Level with no providers uses the shared unavailable state and refuses
activation before initialization, while keeping its layer identity visible.
- Application source configuration accepts replacements and explicit removal.
Missing catalog feeds leave their layers unavailable without blocking startup
or making fallback requests; malformed supplied feeds remain configuration errors.
- Street Level providers are optional in application composition. Omitting a
Mapillary source no longer prevents startup; callers can inject a different
provider list or an empty list without changing layer identities or share links.
- Vector tile sources take their allowed tile origin from the configured
`tileJsonUrl`, so repointing only that URL at a mirror loads tiles from the
mirror or fails visibly instead of silently using OpenFreeMap. Thanks to
[daikaginza](https://github.com/daikaginza) (#935).
- MCP setup examples use the app's default port, `4173`. Thanks to
[Huanyi Xie](https://github.com/xiehuanyi) (#934) and
[shirunjies8-png](https://github.com/shirunjies8-png) (#959) for the same fix.
- Voice revisits numbered analyst records through current layer snapshots and
preserves resolved pin coordinates. Requested analyst lists and rankings can
speak returned items alongside the exact count and coverage caveats. Failed
actions settle the voice card without reviving cancelled turns. Coverage
benchmarks reject invalid calls before accepting semantic matches.
- Street Level is included in the voice layer manifest for visibility toggles;
imagery is not exposed as countable analyst records.
- Voice debug logs omit complete tool-result bodies and serialized function
outputs by default, including location queries and generated spoken replies.
`GEV_VOICE_LOG_CONTENT=1` retains them for explicit content debugging.
- Unqualified Alps searches use the bundled European range for navigation
and annotations instead of a same-named peak returned by a geocoder.
Coordinates, supplied presets and geographically qualified place names
keep their precedence; annotation proximity and containment guards remain.
- Contacts analyst follow-ups retain the snapshot's distance ranking rather
than switching to the camera. Requested radii and explicit scopes remain
authoritative, and a request for a list still requires an analyst query.
Analyst speech names stale or degraded feeds and withholds authoritative
counts when unavailable. The existing NOTES disclosure preserves complete,
deduplicated coverage and source caveats, including crowded results.
- The voice card shows analyst counts ("At least 250,000 aircraft …") with
their scope, feed window and caveats, and marks partial answers. Analyst
speech uses the same deterministic headline, preserves lower bounds and says
when an answer is partial. Follow-ups retain unanswered-layer coverage, and
keep the original scope label when they narrow a remembered result.
Contacts-window answers read one immutable panel snapshot, mark a 20,000-row
layer cap as a lower bound, and commit that displayed cohort only after
cancellation checks pass. Concurrent analyst calls from one model response
remain independent; a stopped or replaced user turn still cancels them.
- Voice answers are shorter and fill slow work instead of going silent. Slow
or multi-step requests may open with one short spoken plan; instant ones
just happen. Tool results carry a code-built `say` line and a `display`
card: sources and notes stay on screen, a caveat is spoken only when it
changes the answer, and "at least" and partial answers are always said. A card above the mic shows captions, the plan's steps and the
result. When a tool that reports steps (layers, place lookups, outlines,
nearest-aircraft) is still running after 1.5 s its current step is spoken
once; others say "still working" once after 8 s. A soft
tick plays in push-to-talk. Holding Space while the assistant talks cuts it
off. Each turn writes latency and speech figures to the debug log
(`node scripts/voice-turn-spans.mjs`). Captions of what you say are
counted in the voice cost meter; the debug log leaves out what was said
unless `GEV_VOICE_LOG_CONTENT=1`.
- Point and ask: hold Space with the cursor on an aircraft, ship or spot on
the map and say "what's that", "track that one" or "how many flights
around here". A reticle marks the point and the voice card shows what
"this" meant. In open mic it works when you have just moved the cursor
there. "The second one" picks from the last numbered list. Asking about
"the last one" resolves to the last of the five rows actually shown, and
referent-only tracking calls are accepted while empty targets are rejected.
Asking about
bare ground up close gives the assistant a small crop of the map around the
point. A slow render gets one bounded second frame request, while hidden,
stale, moved-camera, invalid and oversized captures still fail closed.
## [Unreleased]
- Add an experimental ChatGPT/Codex OAuth option for cloud voice in Provider
Settings. API-key voice remains the default. Local sign-in can start from
the auth button and reports completion, failure, timeout, or expired
credentials. OAuth credentials stay on the server; local routes require
loopback access and same-site requests. OAuth sessions retain usage data
and show unknown cost; caption transcriptions are counted rather than
priced into the API-key cap. The auth button keeps keyboard focus after a
mode change, and pending sign-in does not discard text in the key fields.
Thanks to [Shayan Khan](https://github.com/devv-shayan) for #621 and
[TheSmokeDev](https://github.com/TheSmokeDev) for the credential handling
from #653.
- Stdio servers from one install share a panel key so a page read from one
process can make requests through another. Concurrent malformed-key repairs
now select one winner; unavailable storage or a busy repair retains the
logged per-process fallback. Thanks to [Jibran Tahir](https://github.com/jibraaan)
for #958, [MarvinNL046](https://github.com/MarvinNL046) for the report and
proposed diagnosis in #927, and [kvnloo](https://github.com/kvnloo) for identifying
the repair race. Windows/Claude Desktop Cowork confirmation remains outstanding.
- Street Level: a street-level imagery layer modelled on the iD editor's photo
overlay, with Mapillary as its first provider (free client token, CC BY-SA 4.0
imagery). One right-rail panel holds a chip per provider, shared 360°/flat and
@@ -326,6 +439,32 @@
(`src/ui/imagerySplit.js`, `src/maps/imageryComparison.js`), and
`MapSourceController.subscribe()` reports every settled map switch.
## Unreleased — voice reaches every layer; honest analyst answers
- Voice can switch on every shipped data layer (the two scene-driven
Bhote Koshi layers stay scene-only), including transit, Recent
Imagery, wind, the weather layers, cyclones and mapped installations, and
understands their spoken names ("buses", "hurricanes", "military bases").
One voice manifest (`src/voice/layerManifest.js`) generates the tool enums
and aliases, and a unit test fails when a new layer has no entry.
- `analyst_query` counts up to 250,000 loaded records per layer instead of the
first 2,000, and says when a layer went past that (`complete: false`). It
also answers over bikeshare stations, transit vehicles, rocket launches,
cyclones, ALPR cameras, mapped installations, local ADS-B aircraft and fire perimeters; fire
records carry their sensor (VIIRS or MODIS).
- Unknown fields, operators, units, value types, scope kinds and invalid
centres are refused with the allowed values instead of answering zero or widening to anywhere. A
layer that is off, still loading or unavailable is reported as such, not
as a count of zero; a partly answerable query is marked `partial`.
Distance sorts honour `sortDir`, a written unit such as `altitudeM(ft)`
converts, and large rankings no longer sort the whole set.
- Results carry `lat`/`lon` for each item and a `display` object with the
scope, the feed window (earthquakes and fires cover the last 24 h) and any
caveat for the screen. The model is asked to answer in one short phrase.
- The weather and Recent Imagery panels can be opened by voice.
## Unreleased — local receiver feeds
### Local receiver feeds
- The Local ADS-B layer also reads local 1090 MHz and 978 MHz UAT decoder
@@ -468,6 +607,7 @@
Add feed provenance to analyst/view answers and HUD context while retaining existing response fields and runner ownership (Matt Van Horn, #347).
Analyst records for loaded satellites, datacenters and dams, with explicit bounded count/rank coverage (Matt Van Horn, #351).
- New Fire Perimeters layer (Events group): live NIFC WFIGS interagency
wildfire incident perimeters as ground-clamped polygons with a
containment-colored fire line, refreshed every 5 minutes from the public
@@ -744,7 +884,6 @@ of current runtime behavior, see [`docs/CURRENT-STATE.md`](docs/CURRENT-STATE.md
### Other changes
- Add ECMWF IFS model selection to Wind (#464, thanks @beneduzi), with model-scoped forecast-step caches, cancellation of replaced requests, and separate issue/valid timestamps.
- Add bounded Director feature actions with accessible controls, explicit camera/layer admission and cancellation; restore pack geometry on same-shot seek. Preserve existing scenes and content attribution.
@@ -1553,4 +1692,3 @@ represent previously published GitHub Releases.
## [0.1.0] — 2026-02-09
- Initial project version.
README.md
+12 -6
View File
@@ -235,7 +235,13 @@ _Why cockpit mode exists: you're riding a real aircraft over real terrain — an
## 🎙️ Talk to It
> Voice needs an **OpenAI key**. Without one the entire app still runs — the mic button just reports voice is unavailable. The same key drives the **AI HUD summary**: a terse, five-word intelligence-style readout of the current view that regenerates as you move.
> Voice can use an **OpenAI API key** or, on the same machine, an opt-in signed-in **ChatGPT/Codex OAuth** session. The API-key path remains the default. Selecting ChatGPT OAuth in Provider Settings reuses an existing local sign-in or starts the Codex browser sign-in flow and selects OAuth when it completes. The OpenAI key still drives the **AI HUD summary**: a terse, five-word intelligence-style readout of the current view that regenerates as you move.
The OAuth option is experimental. OpenAI documents ChatGPT plan usage for the [Responses API](https://developers.openai.com/siwc/token-sharing-open-source/models-and-inference); a supported third-party Realtime contract for reusing Codex tokens has not been confirmed. A successful token mint does not establish billing or support terms.
GEV reads Codex's file credentials but does not write or refresh them. It checks token shape and expiry, and reports expired sign-in as requiring re-authentication. The login button runs `codex login`, permits one pending attempt, and reports exit failures or a two-minute timeout. `CODEX_HOME` must match the directory that Codex uses. If `CODEX_AUTH_JSON` points elsewhere, sign in separately or fix that mismatch before using the button. Codex credential storage must use `auth.json`; Keychain-only and in-memory storage are not readable by GEV. On Windows, the login button may not be able to start an npm-installed Codex; run `codex login` yourself, then select OAuth. See [Codex credential storage](https://learn.chatgpt.com/docs/auth#credential-storage).
For a live voice check, run `node scripts/qa-voice-auth.mjs http://127.0.0.1:4189 oauth microphone.wav` against your local dev server. Use a WAV with three seconds of leading silence followed by a short spoken reply request. Replace `oauth` with `api-key` to check the API-key path. The check verifies audio input, a completed spoken reply, usage, resource cleanup, and reconnect. It saves screenshots and credential-free results under `.gev-logs/voice-auth/`.
Click **GEV MIC**, grant the microphone, and just talk. This is more than a voice-controlled remote:
@@ -243,9 +249,9 @@ Click **GEV MIC**, grant the microphone, and just talk. This is more than a voic
- **🎯 Entity Q&A.** Click any plane, ship, or datacenter and ask _"what's this?"_ It answers using the object's live telemetry.
- **👁️ Visual grounding.** At street level, it reads a viewport screenshot to identify legible signage and building names, and is instructed never to hallucinate labels.
- **🎬 Cinematic framing.** _"Show me the planes overhead"_ pulls the camera back, angles it, and frames the live traffic like a director.
- **🔒 Honest and secure.** The agent only confirms actions that succeeded. Your `OPENAI_API_KEY` never touches the browser; the client only gets a short-lived session token.
- **🔒 Honest and secure.** The agent only confirms actions that succeeded. Your `OPENAI_API_KEY` never touches the browser; the client only gets a short-lived session token. If you choose **USE CHATGPT OAUTH** in Provider Settings, the local server uses that sign-in only to mint the same kind of short-lived Realtime credential, and refuses the OAuth path for non-loopback clients.
Twenty-nine tools, four jobs — the commands below come straight from the product's voice test suite and tool playbook:
Thirty tools, four jobs — the commands below come straight from the product's voice test suite and tool playbook:
**🎥 Direct it** — drone-operator camera verbs:
@@ -395,7 +401,7 @@ src/
├── hud.js # Intelligence HUD + AI scene summary
├── keySetup.js # POWER UP panel — in-app provider keys (dev server only)
├── mapStackController.js # Basemap switching — Google 3D / Esri / OSM / ion stacks
├── voice/ # OpenAI Realtime session + 29 voice tools
├── voice/ # OpenAI Realtime session + 30 voice tools
├── layers/ # Layer components — weather, wind, cyclones, transit, ALPR, …
├── data/ # One module per layer + orchestration + context store
│ ├── iconOrientation.js # Screen-projected headings + horizon cull
@@ -429,7 +435,7 @@ Seven keys. Five have a free tier, and the two 🔴 ones are metered:
| --- | --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 🟡 | **Cesium ion** | 🗺️ Google Photorealistic 3D, world terrain, and additional ion-hosted imagery stacks. The free Community plan is for eligible individual, personal/non-commercial use and has quotas | [cesium.com/ion](https://cesium.com/ion) — use a public `assets:read` token and check current [pricing/eligibility](https://cesium.com/platform/cesium-ion/pricing/) |
| 🔴 | **Google Maps** | Direct Google Photorealistic 3D + Google place search ([Map Tiles API](https://developers.google.com/maps/documentation/tile)) | [Google Cloud Console](https://console.cloud.google.com/) — URL-restrict it |
| 🔴 | **OpenAI** | 🎙️ The voice experience + AI HUD summary. The mini model works; the standard model is noticeably smarter. Want Gemini or another provider behind the mic? PRs welcome | [platform.openai.com](https://platform.openai.com) — metered, see costs below |
| 🔴 | **OpenAI** | 🎙️ Voice + AI HUD summary through an API key. Provider Settings also offers **USE CHATGPT OAUTH** for cloud voice without removing the API-key option | [platform.openai.com](https://platform.openai.com) — API-key usage is metered, see costs below |
| 🟡 | **AISStream** | 🚢 Live global ships | [aisstream.io](https://aisstream.io) — free signup |
| 🟡 | **NASA FIRMS** | 🔥 Live active fires | [firms.modaps.eosdis.nasa.gov](https://firms.modaps.eosdis.nasa.gov/api/map_key/) — free |
| 🟡 | **TomTom** | 🚦 Live flow speeds and congestion colors for the simulated traffic layer | [my.tomtom.com](https://my.tomtom.com/keys) — free tier available |
@@ -508,7 +514,7 @@ Honest numbers, roughly, as of mid-2026 — always check the provider pricing pa
| **🟢 Most layers** | **$0, no signup.** OpenSky anon, USGS, CelesTrak, adsb.lol, city CCTV, Radio Browser, GBFS, Launch Library 2, transit feeds, OSRM routing, NOAA and ECMWF weather, OpenStreetMap ALPR mapping, bundled datasets. |
| **🟡 The free-key tier** | **$0 with a signup.** AISStream, FIRMS, TomTom, OpenSky, plus Cesium ion for eligible personal/non-commercial use. Provider quotas and eligibility still apply. |
| **🗺️ Google 3D tiles** | **Free through an eligible Cesium ion Community account within its quota; metered through a direct Google key.** Use the direct route for Google place search or commercial deployment, verify current provider terms, and set budget alerts where billing is enabled. |
| **🔴 OpenAI voice** | **The one that costs real money — so the app meters it for you.** Realtime audio runs a few cents per active minute; an evening of heavy use is single-digit dollars. A live session-spend readout sits next to the mic, with an STD/MINI model toggle, a $2 warning, and a **$5 hard cap that ends the session**. The voice context window is kept deliberately short too. |
| **🔴 OpenAI voice** | API-key sessions keep the live spend readout, STD/MINI model toggle, $2 warning, and **$5 hard cap**. ChatGPT OAuth is an explicit choice in Provider Settings. Its usage is tracked without an API-dollar estimate or spend cap. The voice context window stays deliberately short. |
Google's direct 3D route is surprisingly generous: the first 1,000 Photorealistic
3D Tiles sessions each month are currently free, and one root request supports
SECURITY.md
+2
View File
@@ -18,6 +18,7 @@ The golden rule: **secret-bearing API keys stay on the server side.** The dev/pr
| Key | Where it lives | How the browser uses it |
|-----|----------------|--------------------------|
| `OPENAI_API_KEY` | Server only | Browser fetches a short-lived **ephemeral** Realtime session token from `/api/realtime/token`; the real key never ships |
| ChatGPT sign-in through Codex (optional, experimental) | Codex's own `auth.json` (`CODEX_HOME`, default `~/.codex`); GEV reads it server-side and never writes or refreshes it | Only after **USE CHATGPT OAUTH** is selected in Provider Settings: the server mints the same ephemeral Realtime token with the ChatGPT access token, for loopback clients only |
| `AISSTREAM_API_KEY` | Server only | Server holds the AISStream websocket; browser polls the same-origin `/api/vessels` cache |
| OpenSky OAuth (`OPENSKY_CLIENT_ID/SECRET`) | Server only | Server mints + refreshes the token behind `/api/flights` |
| `GOOGLE_MAPS_SERVER_API_KEY` (optional, #33) | Server only | Server calls Places (`/api/google/nearby-places`, `/api/google/text-search`) and the Street View fallback with this key; falls back to `GOOGLE_MAPS_API_KEY` when unset |
@@ -74,6 +75,7 @@ The data proxies under `server/providers/` are written so the browser cannot tur
- **Redacted debug logging.** The voice debug log (`.gev-logs/`, gitignored) strips API keys, bearer tokens, client secrets, and image data URLs before writing.
- **Cross-site gate on cost/log endpoints.** The cost-bearing (`/api/realtime/token`, `/api/openai/hud-summary`, `/api/google/nearby-places`, `/api/google/text-search`), quota-bearing (`/api/mapillary/*`, with a per-IP limit on tiles) and log (`/api/realtime/debug-log`) endpoints refuse cross-site browser requests: a foreign or opaque `Origin`, a `Sec-Fetch-Site` other than `same-origin`/`none` (this is what blocks an `<img>`/navigation that carries no `Origin`), or any reverse-proxy/CDN forwarding header returns `403`. Non-browser loopback tools (the repo QA harnesses POST the token endpoint with no `Origin`) and the explicit `HOST=0.0.0.0` LAN opt-in keep working — the gate deliberately does not require a loopback remote address; that stricter requirement belongs only to the credential panel (`admitKeySetupRequest`). The Host check (`allowedHosts`, applied by `hostCheckPlugin` ahead of every route, since Vite's own check runs only after plugin middleware) rejects a rebinding `Host` before any handler runs, in every mode, and the gate is defense in depth behind it: the LAN opt-in keeps that check and accepts only IP addresses, `localhost` and names listed in `GEV_ALLOWED_HOSTS`. **Limit:** a name you list there is trusted like the app's own address, so list only names you control.
- **Full Content-Security-Policy.** The dev and preview servers send a real CSP (`script-src 'self' 'unsafe-eval' blob:` plus the YouTube, Facebook and X scripts the Nepal event's embedded media loads, with a matching `frame-src` for their players and posts: no inline script and no other script origin; `blob:` covers the object URLs Cesium's bundled workers bootstrap through in the built app), alongside the existing `X-Frame-Options: DENY` and `frame-ancestors 'none'`. `'unsafe-eval'` stays because Knockout, bundled inside Cesium's widgets package, resolves the global object with `eval` at load time and the globe does not initialize without it; styles permit `'unsafe-inline'` and Google Fonts because Vite's dev client injects `<style>` elements.
- **ChatGPT OAuth voice reuses the local Codex sign-in.** `/api/realtime/oauth-status`, `/api/realtime/oauth-login` and `/api/realtime/token?auth=oauth` answer only loopback connections, behind the same cross-site gate as the token endpoint; the login route also refuses a foreign `Origin`. None of them returns the access token. The login route runs `codex login` (or the executable named by `CODEX_BIN`) with an allowlisted environment that leaves out GEV's provider keys, keeps one attempt pending at a time and cancels it after two minutes or when the server stops. **Limits:** any program on this machine that can reach the server can mint Realtime sessions on the signed-in ChatGPT account, as it can with the API key; a local reverse proxy that hides the client's address defeats the loopback check; and OpenAI has not documented this use of Codex credentials for Realtime, so it may stop working or fall outside the account's terms.
## Network exposure — the operator threat model
docs/CURRENT-STATE.md
+167 -17
View File
@@ -1,5 +1,49 @@
# God's Eye View Current State
Vessel sources can report healthy empty coverage using a current, complete
snapshot with zero raw rows, a healthy transport and a positive last-message
time. This clears obsolete contacts and settles startup without manufacturing
position timestamps. Stale, incomplete and malformed empty results retain the
existing recovery behavior.
Catalog source contracts and their consuming layers are declared in
`src/app/sourceComposition.js`. Omitted or null acquisition sources preserve layer
registration and serialization, report unavailable, and are refused by the existing
visibility lifecycle before initialization. Availability is held in an explicit
catalog lookup supplied to the lifecycle, without modifying layer instances;
unavailable reasons use the layer display name. Invalid supplied methods still fail
construction. `createStandaloneApplication` and `createStandaloneCatalog` accept
`sources` overrides; unspecified entries retain
standalone defaults, and null entries explicitly remove a source. Street Level
continues to accept an explicit provider list. An empty Street Level provider
list uses the same unavailable lifecycle and disabled layer toggle. Directions (`getRoute`) and
Recent Imagery (`searchHls`, `getThumbnail`, `getTileTemplate`) use the same source
configuration boundary. Standalone selects their default adapters; layers retain
route normalization, imagery selection and rendering. Recent Imagery adapters
consume the existing HLS/VIIRS product schema and provide their own tile attribution.
The source factories are exported at `layers/directions/source` and
`layers/recent-imagery/source`. Configuration is applied at construction time;
this does not introduce live source replacement.
Application catalog composition accepts an optional `streetLevelProviders` list.
An explicit list replaces the default Mapillary provider; an empty list removes
all imagery providers. Without that option, Mapillary is registered only when
`sources.mapillary` is supplied. An absent source leaves Street Level registered
with a truthful no-provider state, preserving layer controls and share tokens.
Malformed selected sources and provider definitions still fail validation.
An explicit provider list bypasses the unused Mapillary source, including its
validation. Layer share identities and the legacy Mapillary `m` option remain
stable. Custom provider switches use the `r` option (`example-1*panoramax-0`),
with URL-safe separators and a shared layer-neutral boolean-switch codec, sorted by provider ID rather
than registration order, and round-trip through links and stored state. A receiver
applies only switches for its registered providers; absent custom switches leave
current defaults unchanged. Explicit provider toggles persist only their requested
switch IDs through the state coordinator; unrelated live values remain transient.
The custom switch field is bounded to 256 characters;
provider registration rejects compositions that cannot fit rather than truncating
identities. A malformed or duplicate entry invalidates the complete custom-switch
field. Existing whole-link size limits still apply.
## God's Eye View in conversations — October 2, 2026
Tool answers that can be shown in God's Eye View include a view: camera, layers,
@@ -14,6 +58,19 @@ new views from the page that frames it; framing is off unless
`GEV_EMBED_FRAME_ANCESTORS` allows the framing page. MCP leads with the tools that find
what to show. See [tools and the MCP server](TOOLS.md).
Stdio processes from one install share the panel key in
`.gev-cache/mcp-panel-key`, resolved from the checkout rather than the client's
working directory. First creation is atomic; malformed-file repairs select one
winner and concurrent processes re-read it. A busy repair waits at most two
seconds before falling back. If the cache cannot be read/written or repair remains
busy, stderr reports the fallback to a per-process key; cross-process panels can
still fail in that mode. An abandoned `.repair-lock` is left intact: after
confirming no repair process is running, remove it to allow repair on restart.
HTTP MCP servers retain per-server keys. This key is a panel routing guard, not
authentication. Large-response continuations remain process-local and require
consistent tool-call routing. Two-process reproduction is covered locally;
Windows/Claude Desktop Cowork confirmation remains outstanding (#927).
## Tools and local MCP server — October 1, 2026
`gods-eye-view/tools` defines queries that answer questions from the app's data,
@@ -278,7 +335,7 @@ Consult the linked official advisory for safety decisions.
Voice and HUD snapshots reuse the existing feedState classifier. Analyst follow-ups retain their original data provenance; current-view results append provenance without replacing legacy fields. HUD context and deterministic telemetry include non-nominal feed state.
Satellite and local infrastructure layers expose on-demand analyst records through their current factory owners. Analyst counts and ranks explicitly cover only bounded examined loaded records (default 2,000 per new layer, core satellite rows before dense extras); omitted records can change nearest/count and satellite distance is ground distance. Existing tools and result fields remain available.
Analyst records come on demand from each layer's `getAnalystRecords`: flights, military, local ADS-B, vessels, satellites, launches, earthquakes, FIRMS (VIIRS and MODIS, with a `sensor` field), fire perimeters, cyclones, transit, bikeshare, ALPR cameras, mapped installations, datacenters and dams. `analyst_query` counts the whole loaded set (up to 250,000 records per layer; past that `coverage.records` reports `returned`, `total` and `truncated: true` and the result carries `complete: false`). Ranking keeps a top-k and scans in 20,000-row slices that yield to the page and stop when superseded. It refuses unknown fields, operators, units that do not convert (`altitudeM(ft)` converts), wrong-typed values, invalid centres, unknown scope kinds and sort fields with `code` and `allowed`, refuses a follow-up with no previous answer (`NO_RESULT_CONTEXT`) or naming other layers than that answer (`FOLLOW_UP_MISMATCH`), and tells `LAYER_OFF`, `NOT_READY` and `FEED_UNAVAILABLE` apart from a real zero; when only some layers can answer the result is `partial` with `unanswered` ids. The Contacts-window path applies the same filters, ranking and item shape to one immutable panel snapshot. Each aircraft layer retains at most 20,000 rows; reaching that bound sets `complete: false` and the spoken/card count becomes “At least”, never an exact claim. A superseded query never replaces follow-up memory, while sibling analyst calls from one assistant response do not cancel one another. Items carry `lat`/`lon`; the feed window (earthquakes and FIRMS: last 24 h), the precise scope and any caveat sit in `display`, which is on-screen detail rather than something the model recites. "In view" is still a radius around the view centre, not the visible footprint. Satellite distance is ground distance.
Keyless terrain tiles retry when Re:Earth throttles them. The browser fetches
`terrain.reearth.land/cesium-mesh/ellipsoid/{z}/{x}/{y}.terrain` directly; no
@@ -353,6 +410,71 @@ replacement session; audio meters release failed initialization and reject revok
frames. Delayed action results and post-capture continuations cannot resume a
stopped conversation or send output into a replacement. See [voice ownership](VOICE-OWNERSHIP.md).
Contacts nearest-aircraft follow-ups retain the snapshot's distance basis even
after the camera moves. An explicit new scope replaces that basis. Provider
instructions require an analyst query for requested lists and use the requested
radius rather than substituting the panel's fixed window. Analyst speech carries
stale/degraded feed status and does not speak an authoritative unavailable count.
The existing NOTES disclosure deduplicates coverage/source caveats and retains
their full text in at most six rows, grouping analyst overflow in the final row;
ordinary tool-card limits are unchanged.
Voice speech: `src/voice/speech.js` adds `{ say, display, referents?, schedule? }`
to layer toggles, fly_to_location, frame_overhead, select_nearest_aircraft,
get_entity_context, annotate_map and analyst_query. Analyst speech and the card
share one deterministic count/scope headline; lower bounds use "At least" and
partial answers name the unanswered layers. `get_current_view_state` lists enabled layers only.
The voice card nested in the mic control (`voiceCard.js`) shows captions, plan
steps and the result. `resultDisplay.js` is the one adapter from a result to
the card: builder results show as built, and analyst results show a title
with their scope, window and caveats. Caveats are on the card; the model speaks
one only when it changes the answer, and always says lower bounds and partial
answers. `narration.js` speaks one
code-authored line for the current step of a tool still running at 1.5 s
(out of band, never after the result). Tools that report steps: layer
toggles, place lookups, select_nearest_aircraft and annotate_map (finding,
outlining). Other tools get one "still working" line at 8 s. The
earcon plays in push-to-talk only. A claimed Space hold while the assistant
speaks is a barge-in (WebRTC cancel + audio clear), refused while Radio holds
the speaker (`mayVoiceClaimSpeaker()`). Progress lines stay outside the reply
lifecycle and Radio handoff. `turn.span` debug records carry generation and
playback latency, silence, preamble and word-count figures. Caption
transcription (`OPENAI_REALTIME_TRANSCRIBE_MODEL`, default on) is metered into
the session cost and cap in API-key sessions; ChatGPT OAuth sessions count
captions without pricing them. The debug log omits transcripts, text, tool arguments
and complete tool-result bodies (including serialized function outputs) unless
`GEV_VOICE_LOG_CONTENT=1`.
Tool names, call IDs, protocol event metadata and usage remain available.
Numbered analyst targets resolve from current layer records, including layers
without pick/context lookup; numbered annotations retain their resolved coordinates.
Requested analyst lists and rankings may speak up to three returned items and
values in result order alongside the count and its caveats. A rejected current
action emits a failure result to settle its card; cancelled turns remain silent.
Coverage grading validates calls before accepting an expected capability match.
The voice manifest includes Street Level visibility toggles; its imagery has no
analyst query or entity-context records.
Point and ask: `pointerContext.js` reads what the cursor is on. A Space hold
is the pointing gesture: its keydown snapshot (released with the key) is sent
as an inert `pointer_context` item with the target, with reticle and chip.
Open-mic speech and typed turns count only a pointer that moved on the map in
the last 5 s and send only the kind (`pointing:"aircraft"`/`"ground"`); the chip appears when a tool
resolves it. Losing the pointer sends one `target:"none"` item. `deixis.js` resolves `'pointer'` in
track_entity/fly_to_location queries, get_entity_context scope, analyst_query
`scope.kind` and annotate_map targets, plus `referent:n` from the latest
numbered result (`referents.js`, cleared at session end). A new result set (an analyst count) replaces
the numbered list even when it is empty. Only the five rows numbered on the
card are resolvable; `-1` means the fifth/last visible row. `track_entity`
accepts either a named query or a referent, while an empty target is rejected. A reticle marks the
point during the turn and the voice card shows "THIS"/"HERE"; both hide in
Clean-UI and recording. A ground-only pointer lookup at local/city scale sends a ringed 512 px crop in
the one retained image slot, dropped if the camera moved or a newer capture or
turn started. The pointer path makes at most two bounded fresh-frame requests so
a slow render loop can recover without accepting a stale frame; a missing camera
identity, expired snapshot, invalid geometry, black frame or oversized payload
still fails closed. screenX/screenY against the crop are mapped back to the canvas. Harness: `qa-voice-routing.mjs --layer deixis`,
`--layer deixis-live`, `--layer behavior --deixis-only`.
The application shell composes focused state owners for navigation, destination
lookup/orbit, Cockpit, visual settings, panel layout, aircraft display and layer
bindings. Keyboard/display subscriptions have a separate lifetime; existing
@@ -419,9 +541,11 @@ Reference feed construction is exported through `sources/reference`; the cable s
Source factories have dedicated `layers/<family>/source` exports. ALPR and earthquake record normalization and CCTV source policy no longer pull rendering into source consumers. Catalog construction and voice feed reads use their focused owners; compatibility entries remain available. Settings filesystem hardening lives under `server/standalone/`. Import-direction checks complement export ownership checks; source behavior, settings policy and rendering are unchanged.
Voice controls bind to a protocol-independent session factory. The default WebRTC adapter preserves the existing Realtime connection, push-to-talk, cost controls and radio handoff. Session subscriptions expose state, transcript, action call/result, interruption and completion events; stopping or replacing a session cancels pending actions. Alternate adapters can use the same controls and action runner.
Voice controls bind to a protocol-independent session factory. The default WebRTC adapter preserves the existing Realtime connection, push-to-talk, cost controls and radio handoff. Session subscriptions expose state, transcript, action call/progress/result, interruption, completion and turn-metrics events; stopping or replacing a session cancels pending actions. Alternate adapters can use the same controls and action runner.
Voice action argument schemas have one portable owner under `src/voice/actionSchemas.js`. The Realtime provider builds 29 tools, retaining the existing 28 names and argument contracts apart from the three additive analyst-layer enum values using separate description-only metadata. Description customization cannot replace argument types, enum values or required fields.
Voice action argument schemas have one portable owner under `src/voice/actionSchemas.js`. The Realtime provider builds 30 tools using separate description-only metadata. Description customization cannot replace argument types, enum values or required fields.
`src/voice/layerManifest.js` declares each catalog layer's voice capabilities: spoken aliases, `toggle`, in-view `context`, `track`, and analyst `query` fields with type and unit, or `noQuery` with the reason. The `set_layer_visibility`, `show_data_layers_menu`, `get_entity_context` and `analyst_query` layer enums, the runner's alias table and the analyst field hints are generated from it. `src/voice/layerManifest.test.mjs` fails when a catalog layer is neither listed nor named in `VOICE_OFF_LAYERS` (today only the two scene-driven Bhote Koshi layers). Global Context is listed with `toggle: false`; `set_context_mode` reaches it. `set_panel_open` also opens `weather-panel` and `recent-imagery-panel`.
Portable source exports provide Radio Browser station normalization, CCTV feed types and regional records independently of HTTP middleware. Radio normalization accepts an explicit URL policy; the standalone directory retains its existing HTTPS rules. Tile coordinate validation accepts explicit zoom bounds with unchanged traffic defaults. Cache, request and rendering owners remain unchanged.
@@ -464,7 +588,18 @@ clears caches and removes map-stack listeners. Standalone setup supplies the
existing service clients. HUD summaries, regional brief, cockpit weather, location
framing and annotation boundaries receive their service instances explicitly.
Compatibility entrypoints retain defaults for direct callers; normal startup does
not change global service slots. Analyst follow-up memory belongs to its voice runner.
not change global service slots. Analyst follow-up memory belongs to its voice
runner and ends with the voice session: stopping voice invalidates writes still in
flight and forgets the last answer, the pointer and the numbered list; removing
voice disposes the runner.
Analyst result memory is committed only after any Contacts-window projection
finishes and the call is still current. Cancelled or superseded queries cannot
return success or replace follow-up memory; Contacts follow-ups filter the same
cohort that was shown, and partial/unanswered coverage remains attached when a
remembered result is narrowed.
The narrowed answer retains the remembered scope label and detail, including
the Contacts-window attribution, unless the follow-up supplies a new scope.
Application startup constructs fresh layer instances from explicit source objects.
Standalone composition selects the existing providers. Controls, launch orbit
@@ -1474,10 +1609,10 @@ This is the current runtime/source-of-truth snapshot for the project.
> samples, `enabling` throughout, panel non-numeric) and across a failing
> one. Its `status: 'idle'` is not what saves it — the lifecycle is; the
> module has no `loading` status at all.
> Any new dependency that can be slow must report `loading` and `lastUpdate`
> honestly for the contract to hold, and must be pinned against the shape its
> own module really returns — a fixture that invents a status the module cannot
> emit guards nothing (that is exactly how a hole here survived a green suite).
> Any new dependency that can be slow must report `loading` and `lastUpdate`
> honestly for the contract to hold, and must be pinned against the shape its
> own module really returns — a fixture that invents a status the module cannot
> emit guards nothing (that is exactly how a hole here survived a green suite).
> - **A held ground snap is dropped when measured ground contradicts it
> (2026-08-23):** the WARM hold described below answers on DISTANCE travelled,
> which is only a proxy for whether the value still describes the ground. A
@@ -2872,7 +3007,7 @@ test:track` 43 tracking invariants · headless QA harnesses under
> ISS pass prediction, and per-layer data attribution. Gate at close: unit 98/98, build clean,
> track 19/19, + five QA harnesses (heading 16/16, sprites 9/9, cctv 5/5, failstate 5/5,
> attribution 18/18). New modules: `src/data/{motionModel,aircraftMeta,aircraftClass,aircraftIcons,issPass,routePlausible,dataCredits}.js`.
> The live runtime now declares 29 voice tools; the 17→20 count above is retained only as milestone history.
> The live runtime now declares 30 voice tools; the 17→20 count above is retained only as milestone history.
## Canonical Docs Order
@@ -3945,9 +4080,9 @@ and unreachable upstream (502/504) separately from road geometry.
`GEV MIC` button (bottom UI) starts an OpenAI Realtime session over WebRTC:
- **Token flow**: browser fetches a short-lived client secret from `/api/realtime/token`; the Vite middleware holds `OPENAI_API_KEY` and posts the full session config (instructions, tool schemas, VAD, truncation) to `api.openai.com/v1/realtime/client_secrets`. SDP exchange goes directly to `api.openai.com/v1/realtime/calls` with the ephemeral token.
- **Token flow**: browser fetches a short-lived client secret from `/api/realtime/token`; the Vite middleware uses `OPENAI_API_KEY` by default, or the signed-in local ChatGPT/Codex OAuth access token when OAuth was explicitly selected in Provider Settings, and posts the full session config (instructions, tool schemas, VAD, truncation) to `api.openai.com/v1/realtime/client_secrets`. Both long-lived credentials stay server-side; OAuth minting is loopback-only. SDP exchange goes directly to `api.openai.com/v1/realtime/calls` with the ephemeral token.
- **Session defaults** (env-tunable): model `gpt-realtime-2` (or `gpt-realtime-2.1-mini` when the MINI tier is selected — see the model-tier entry below), voice `marin`, reasoning effort `low`, semantic VAD with low eagerness, no response interruption, context window truncated to ~3,000 post-instruction tokens with 0.5 retention ratio — the conversational window stays short because map state is fetched live per turn.
- **Twenty-nine tools** (argument schemas in `src/voice/actionSchemas.js`, served with their descriptions by `server/providers/openai/tools.js`, executed client-side in `src/voice/gevActions.js`): `fly_to_location`, `select_nearest_aircraft`, `adjust_camera_zoom`, `zoom_to_globe`, `set_layer_visibility`, `show_data_layers_menu`, `set_panel_open`, `set_visual_style`, `get_entity_context`, `get_current_view_state`, `set_hud`, `set_detection`, `set_map_stack`, `set_post_processing`, `control_scene`, `control_cctv`, `set_context_mode`, `control_cockpit`, `control_radio`, `track_entity`, `stop_tracking`, `frame_overhead`, `annotate_map`, `clear_annotations`, `move_camera`, `fly_route`, `analyst_query`, `next_iss_pass`, and `next_satellite_pass`.
- **Thirty tools** (argument schemas in `src/voice/actionSchemas.js`, served with their descriptions by `server/providers/openai/tools.js`, executed client-side in `src/voice/gevActions.js`): `fly_to_location`, `select_nearest_aircraft`, `adjust_camera_zoom`, `zoom_to_globe`, `set_layer_visibility`, `show_data_layers_menu`, `set_panel_open`, `set_visual_style`, `get_entity_context`, `get_current_view_state`, `set_hud`, `set_cyber_sonar`, `set_detection`, `set_map_stack`, `set_post_processing`, `control_scene`, `control_cctv`, `set_context_mode`, `control_cockpit`, `control_radio`, `track_entity`, `stop_tracking`, `frame_overhead`, `annotate_map`, `clear_annotations`, `move_camera`, `fly_route`, `analyst_query`, `next_iss_pass`, and `next_satellite_pass`.
> **Reading `npm test` totals:** the count depends on the Node major. The two
> GC-bracketed allocation microbenchmarks (`src/data/focusAllocations.test.mjs`
@@ -3969,7 +4104,7 @@ and unreachable upstream (502/504) separately from road geometry.
- **Analyst → track handoff carries a key, not just a label** (2026-08-21). `analyst_query` items include `icao24`/`mmsi` alongside the display `id`, and contact lookup uses the shared tiered ranking in `src/data/contactMatch.js`: hex exact → callsign exact → registration exact → callsign prefix → registration prefix → callsign substring → registration substring. The tiers keep an exact callsign ahead of a colliding registration regardless of feed order, and registrations compare separator-insensitively (`G-ABCD`/`GABCD`, `05-8152`/`058152`, `N123AB`/`N-123AB`).
- **A typed command supersedes the turn it interrupts** (2026-08-21). `sendTextCommand` defers its `response.create` behind an active response instead of colliding with it, marks that response superseded so a late function call from it is refused rather than dispatched, and drops the old turn's queued follow-up. A refused call is still ANSWERED — a terminal `{ok:false, superseded:true}` `function_call_output` — because an unanswered `function_call` strands a pending call and deadlocks the model; the refusal creates no response of its own. A burst of typed commands coalesces into one response while keeping both conversation items.
- **Subject reconciliation across satellite catalog rebuilds** (2026-08-21). A dense↔core toggle or TLE refresh clears and repopulates the catalog, so the published subject is re-resolved against the new satrec; a subject that did NOT survive releases the slot. The per-frame refresh cannot do this itself — `_getTrackedFramePosition` returns early once the satellite has no catalog entry — so the reconcile runs at rebuild completion. An empty catalog is a rebuild in flight, not a disappearance.
- **One aircraft-proximity engine** (2026-08-22). `collectAircraftProximityWindow` (`src/data/militaryAwareness.js`) is the single computation behind both the Contacts panel window and the voice analyst's entity-centred "how many nearby", so the panel readout and the spoken count for one centre are identical by construction. **Invariant: do not re-derive a proximity count anywhere else.** They diverged before because the panel read live billboard positions (20,000 cap) while the analyst used last-fix coordinates over a 2,000-record slice — 111 on screen, 15 spoken. Explicit regions and arbitrary points deliberately keep the general record engine. Entity-centred results carry `window: {engine:'contacts-window', centeredOn, radiusKm, flights, military, aircraft}`.
- **One aircraft-proximity snapshot** (2026-08-22; hardened 2026-09-30). `collectAircraftProximityWindow` (`src/data/militaryAwareness.js`) computes the Contacts panel cohort once. The voice analyst reads the exact retained snapshot and evaluation timestamp instead of re-scanning live layers, so the panel readout and spoken count for one centre cannot cross snapshots. **Invariant: do not re-derive a proximity count anywhere else.** Each layer retains 20,000 rows and samples one row beyond the cap; a saturated cohort reports `complete:false`, `truncated:true`, and is spoken as a lower bound. They diverged before because the panel read live billboard positions while the analyst used last-fix coordinates over a 2,000-record slice — 111 on screen, 15 spoken. Explicit regions, arbitrary points, and a radius different from the panel radius deliberately keep the general record engine. Entity-centred results carry `window: {engine:'contacts-window', centeredOn, radiusKm, flights, military, aircraft, complete, evaluatedAt}`.
- **Centre precedence for nearby asks**: explicit place in the question > Contacts subject (a selected non-contact entity never silently becomes the centre) > an entity the user names > the current view, said aloud. Contacts active with no subject uses the view rather than reading an empty panel.
- **Contact-match ties break on hex ascending.** `track_entity` is a mutation fulfilling "follow that one", and the model's observed answer to a non-ok track result is to retry with guesses rather than ask, so the lookup always commits rather than returning an ambiguity. What it owes the caller is stability: hex is unique and always present, so the same query resolves to the same contact for as long as both are loaded.
- **Visual grounding**: at `local` view scale with no structured identity, the client captures the Cesium canvas (≤1200px JPEG, black-frame detection, double-render for freshness) and sends it as `input_image` with a strict "do not invent labels" instruction.
@@ -3986,12 +4121,15 @@ and unreachable upstream (502/504) separately from road geometry.
- **Reliability**: tool-call dedupe (2.5s window across call/item/args keys); response-create queueing that respects active responses and defers follow-ups when the user starts speaking; per-tool follow-up instructions so the agent confirms only what actually happened (zoom confirms only on `ok=true`).
- **Aircraft identity honesty:** “What is this aircraft?” reads callsign, operator, registration, type, and route only from the selected contact context. Missing operator, route, or type enrichment is named explicitly rather than silently omitted or inferred from the callsign.
- **Diagnostics**: every client/server event is posted to `/api/realtime/debug-log` and appended to `.gev-logs/realtime-conversations.jsonl` (gitignored) with secret/image redaction; last 30 errors persist in `localStorage` (`gev-realtime-errors`); `window.__gevVoiceCommands.getDiagnostics()` in the console.
- **Counting semantics ("near")** — a CONTRACT; new count-bearing tool work inherits it. Three honest numbers exist for one question: the Contacts cohort (250 km around the subject, what the panel shows), `analyst_query`'s count of _currently-loaded_ records for the requested scope, and the layer-wide loaded total in `coverage.layersQueried[].records`. They diverge legitimately — the flights layer loads by viewport, so after a camera dive the loaded set can hold a fraction of the cohort (field case: panel 42, analyst 8). The contract:
1. **Contacts ACTIVE** → "near / nearby / how many aircraft" means the **Contacts window** — the panel's numbers, spoken verbatim. Mechanism: `contactsWindow` (`{centeredOn, radiusKm, flights, military, vessels}`), carried by both `analyst_query` and `get_current_view_state`, derived by `contactsWindowFromSnapshot()` from the same snapshot the panel renders so the two cannot drift. A cohort whose feed cannot answer reports `'unknown'`, never a confident zero.
- **Counting semantics ("near")** — a CONTRACT; new count-bearing tool work inherits it. Three honest numbers exist for one question: the Contacts cohort (250 km around the subject, what the panel shows), `analyst_query`'s count of _currently-loaded_ records for the requested scope, and the layer-wide loaded total in `coverage.layersQueried[].total`. They diverge legitimately — the flights layer loads by viewport, so after a camera dive the loaded set can hold a fraction of the cohort (field case: panel 42, analyst 8). The contract:
1. **Contacts ACTIVE** → "near / nearby / how many aircraft" means the **Contacts window** — the panel's numbers, spoken verbatim. Mechanism: `contactsWindow` (`{centeredOn, radiusKm, flights, military, vessels, complete}`), carried by both `analyst_query` and `get_current_view_state`, derived by `contactsWindowFromSnapshot()` from the same snapshot the panel renders so the two cannot drift. Voice filtering and follow-up memory use that immutable snapshot too. A cohort whose feed cannot answer reports `'unknown'`, never a confident zero; a cohort at the 20,000-row retention bound reports a lower bound.
2. **Contacts OFF** → "nearby" means **in view**; "near \<place\>" means a radius around that place. A radius query with Contacts active and no explicit centre is centred on the **active contact**, not the camera.
3. **Every count names its scope in words** — "42 in your window", "8 in view", "about 30 within 250 km of Austin" — never a bare number. `analyst_query` returns `scopeLabel` so this is mechanical. Two different numbers with named scopes are not a contradiction.
4. **The loaded-data caveat is stated once when relevant**: counts cover loaded data, and the flights layer loads where you look (appended to `coverage.note` for radius/view scopes over viewport-loaded layers).
- **Degradation**: without `OPENAI_API_KEY`, `/api/realtime/token` returns 503 and the mic button surfaces the error; the rest of the app is unaffected.
- **Degradation**: API-key mode without `OPENAI_API_KEY` returns 503 as before. Selecting OAuth without a usable local ChatGPT/Codex sign-in starts the local `codex login` browser flow, polls for the resulting local token, and selects OAuth when sign-in completes. If the Codex login flow cannot start or does not complete, the rest of the app is unaffected.
- **Login lifecycle and storage**: one pending Codex login is shared by the login and status routes. Process failure, success without readable credentials, and a two-minute timeout each report a clear failure; timeout and server shutdown cancel the owned process. The launcher resolves `CODEX_HOME` before changing directories and refuses a mismatched `CODEX_AUTH_JSON`. GEV reads file credentials only, never writes or refreshes them, and does not require the vendor refresh token. Expired access tokens report `CODEX_OAUTH_REAUTH_REQUIRED`. OAuth status and login routes also use the same-site request gate.
- **Auth button focus**: changing voice auth updates the existing controls in place. Enter, Space, and mouse selection keep focus on the auth button; Tab then follows the normal control order. Pending sign-in blocks repeated activation without removing the button from the focus order. Completion does not take focus from another control or discard text in the key fields. `scripts/qa-voice-auth-focus.mjs` checks these paths in Chromium with fixture sign-in responses.
- **Support boundary**: the local OAuth option is experimental. OpenAI's documented Sign in with ChatGPT plan-sharing inference endpoint is `/v1/responses`; support for third-party reuse of Codex credentials at `/v1/realtime/client_secrets` remains unconfirmed. Technical success does not establish a supported auth or billing contract.
### AI HUD Summary (June 2026)
@@ -4060,6 +4198,15 @@ are omitted rather than framing the wrong part of the globe.
retrying. Missing capability never synthesizes an outline from a radius.
Manual geometry, bundled neighborhoods, Natural Earth regions and bundled
state/province/county outlines remain.
- The shared default place search resolves unqualified `Alps`, `the Alps`
and the `Alps mountains` forms from the bundled European Natural Earth
range before network geocoders. Navigation uses its contained anchor and
region viewport; annotations still require the existing proximity and
outline-containment checks. Coordinates and supplied presets keep priority;
geographic qualifiers, local POI names, other ranges and custom geocoder
arrays retain their existing resolution. A failed Alps pack load reports a
search failure rather than caching an unrelated peak as the range, and the
bundled loader retains its normal retry cooldown.
- County queries rank eligible US counties and international admin-1 units together, retaining exact aliases and country/state qualifiers.
- Bundled administrative outlines (`src/data/adminBoundaries.js`): states and
provinces worldwide (Natural Earth admin-1,
@@ -4202,7 +4349,7 @@ are omitted rather than framing the wrong part of the globe.
- GBFS proxy refuses upstream redirects (`redirect: 'manual'`; any 3xx becomes a 502 and the redirect target is logged server-side only) and enforces its 5 MB response cap while the body streams, cancelling the upstream read past the cap; CCTV health map is bounded.
- Proxy error payloads are sanitized (no internal error details returned to clients).
- That holds for the OpenAI and CCTV media paths too: `/api/openai/hud-summary` never relays OpenAI's own `error.message`, `/api/realtime/token` passes successful ephemeral-token responses through but answers with a fixed error when minting fails or upstream rejects the request, and a failed CCTV media fetch stores a fixed camera health `message` — `GET /api/cctv/health` serializes that field and the CCTV panel renders it as a status label, so it is a client surface as much as the response body is.
- `OPENAI_API_KEY` is server-side only; the browser receives ephemeral Realtime client secrets from `/api/realtime/token`.
- `OPENAI_API_KEY` remains server-side only and remains the default voice credential. The optional OAuth mode reads the local ChatGPT/Codex access token server-side on loopback only; the browser receives only ephemeral Realtime client secrets from `/api/realtime/token`.
- `AISSTREAM_API_KEY` is server-side only; the browser reads the same-origin `/api/vessels` cache.
- `/api/google/nearby-places` keeps the Google key out of Places requests issued for voice scene context.
- `/api/google/text-search` keeps the Google key server-side for view-biased Places recovery used by annotation resolution.
@@ -4605,6 +4752,10 @@ easier to meet (detection is now on more often), but does not create it.
shown dot against the allowed source classes and records phase timings.
Positions and segment distances are precomputed, with no new animation-loop
allocation. Visible-globe roads use cached terrain without offscreen mesh picks. The road-source label names the geometry being drawn, with partial/unavailable states shown plainly.
- Vector tile sources accept tiles only from an allowed origin, which defaults
to the configured `tileJsonUrl` origin; an explicit `allowedOrigin` overrides
it. Repointing only `tileJsonUrl` loads tiles from that host or fails with an
origin error rather than silently falling back to OpenFreeMap.
- TileJSON caches successful metadata. Transient failures retry after a
five-second cooldown; invalid metadata/origins stay unavailable until the
source is cleared. Clear resets metadata and cancels pending requests.
@@ -4922,7 +5073,6 @@ Temperature uses stronger fixed −40..50°C colors; the underlying 1° forecast
numeric inspection values are unchanged. No volumetric cloud height or local rain
arrival prediction is claimed. NOAA source limits are documented in DATA_SOURCES.
Traffic source refinements: ALPR admits z9-z12 detail only when the view fits 16 tiles,
returning explicit zoom guidance before I/O and allowing the next smaller view to
load normally. Outside the US/Canada extracts the row reads “No ALPR data for this
docs/MCP_SETUP.md
+7 -7
View File
@@ -9,7 +9,7 @@ one before going on.
```sh
npm install
npm run build:panel # the in-conversation globe; rerun after app changes
npm run dev # http://localhost:5173, keep it running
npm run dev # http://localhost:4173, keep it running
```
The MCP server reads from this app.
@@ -21,15 +21,15 @@ The server is `server/mcp/stdio.js` in this checkout. Use absolute paths
| Client | How |
| --- | --- |
| Claude Code | `claude mcp add gods-eye-view -- node /abs/path/gods-eye-view/server/mcp/stdio.js --api-base http://localhost:5173` |
| Codex CLI | `codex mcp add gods-eye-view -- node /abs/path/gods-eye-view/server/mcp/stdio.js --api-base http://localhost:5173` |
| Claude Code | `claude mcp add gods-eye-view -- node /abs/path/gods-eye-view/server/mcp/stdio.js --api-base http://localhost:4173` |
| Codex CLI | `codex mcp add gods-eye-view -- node /abs/path/gods-eye-view/server/mcp/stdio.js --api-base http://localhost:4173` |
| Codex and ChatGPT desktop | Same `~/.codex/config.toml` as the CLI (block below), or Settings → MCP servers → Add server (STDIO). |
| Claude Desktop | Settings → Developer → Edit Config, then add the JSON below. |
```toml
[mcp_servers.gods-eye-view]
command = "node"
args = ["/abs/path/gods-eye-view/server/mcp/stdio.js", "--api-base", "http://localhost:5173"]
args = ["/abs/path/gods-eye-view/server/mcp/stdio.js", "--api-base", "http://localhost:4173"]
```
```json
@@ -37,7 +37,7 @@ args = ["/abs/path/gods-eye-view/server/mcp/stdio.js", "--api-base", "http://loc
"mcpServers": {
"gods-eye-view": {
"command": "node",
"args": ["/abs/path/gods-eye-view/server/mcp/stdio.js", "--api-base", "http://localhost:5173"]
"args": ["/abs/path/gods-eye-view/server/mcp/stdio.js", "--api-base", "http://localhost:4173"]
}
}
}
@@ -45,7 +45,7 @@ args = ["/abs/path/gods-eye-view/server/mcp/stdio.js", "--api-base", "http://loc
**Windows with the checkout in WSL:** use `"command": "wsl.exe"` and put
`"-e"` and the absolute Linux path to `node` first in `args`, for example
`["-e", "/home/you/.local/share/mise/installs/node/24/bin/node", "/home/you/gods-eye-view/server/mcp/stdio.js", "--api-base", "http://localhost:5173"]`.
`["-e", "/home/you/.local/share/mise/installs/node/24/bin/node", "/home/you/gods-eye-view/server/mcp/stdio.js", "--api-base", "http://localhost:4173"]`.
## 3. Restart and try it
@@ -60,7 +60,7 @@ Diego in God's Eye View with military flights on."*
## Troubleshooting
- **The server does not appear:** run the command from step 2 in a terminal;
it should print `God's Eye View MCP server reading http://localhost:5173`
it should print `God's Eye View MCP server reading http://localhost:4173`
and wait. A path or `args` mistake fails here.
- **The panel says it could not load:** `npm run build:panel` was not run, or
the dev server is down.
docs/VOICE-OWNERSHIP.md
+7 -1
View File
@@ -14,6 +14,12 @@ The session adapter, action runner and backend interfaces remain unchanged.
| `realtimeCost.js` | Next-session preferences and the current session's model-bound meter |
| `realtimeViewport.js` | One retained image, bounded deletion identities and capture generation |
| `realtimeDiagnostics.js` | Bounded error history and sanitized optional diagnostics |
| `turnMetrics.js` | Per-turn latency and speech spans written to the debug log |
| `narration.js` | Progress lines and the earcon while tools run; spoken through the turns owner |
| `pointerContext.js` | Pointer position, dwell pick and the current turn's pointer snapshot (session-scoped) |
| `referents.js` | Numbered items from the latest result for `referent:n` (session-scoped) |
| `resultDisplay.js` | What the voice card shows for a result and which items it numbers (read by the card and `referents.js`) |
| `gevActions.js` runner | Analyst follow-up memory (session: `resetConversation()` on stop, `dispose()` on removal) |
Pure input policy, preferences and protocol-response policy have separate modules.
Owners receive named readers, operations or focused collaborators. Cross-owner
@@ -29,7 +35,7 @@ Action and post-capture continuations retain their conversation identity before
publishing output, queueing a response or changing status.
Behavioral invariants remain in force: a 500 ms Space hold claims push-to-talk;
short control taps and text entry remain native; a click-started session stays
short control taps and text entry remain native; a claimed hold while the assistant speaks interrupts it (never during a Radio handoff); a click-started session stays
open-mic. Every accepted or refused tool call receives its terminal output once.
New typed input supersedes old intent. Radio waits for the spoken confirmation and
verified muted playback. A live cost meter stays bound to its negotiated model,
package.json
+2
View File
@@ -163,6 +163,7 @@
"./layers/vessels": "./src/layers/vessels/index.js",
"./layers/earthquakes": "./src/layers/earthquakes/index.js",
"./layers/recent-imagery": "./src/layers/recentImagery/index.js",
"./layers/recent-imagery/source": "./src/layers/recentImagery/source.js",
"./layers/perimeters": "./src/layers/perimeters/index.js",
"./sources/firms-csv": "./src/data/firmsCsv.js",
"./layers/firms": "./src/layers/firms/index.js",
@@ -173,6 +174,7 @@
"./layers/traffic": "./src/layers/traffic/index.js",
"./layers/bikeshare": "./src/layers/bikeshare/index.js",
"./layers/directions": "./src/layers/directions/index.js",
"./layers/directions/source": "./src/layers/directions/source.js",
"./layers/cctv": "./src/layers/cctv/index.js",
"./layers/alpr": "./src/layers/alpr/index.js",
"./layers/radio": "./src/layers/radio/index.js",
scripts/dev-fresh.sh
+1 -1
View File
@@ -347,7 +347,7 @@ case "${OPENSKY_AUTH_MODE}" in
echo "OpenSky auth: disabled (anonymous mode)"
;;
esac
[[ -n "${OPENAI_API_KEY}" ]] && echo "OpenAI key (voice + HUD summary): configured" || echo "OpenAI key (voice + HUD summary): not set — GEV MIC disabled"
[[ -n "${OPENAI_API_KEY}" ]] && echo "OpenAI key (voice + HUD summary): configured" || echo "OpenAI key (voice + HUD summary): not set — GEV MIC off unless a Codex ChatGPT sign-in is selected in Provider Settings (experimental)"
[[ -n "${AISSTREAM_API_KEY}" ]] && echo "AISStream key (live vessels): configured" || echo "AISStream key (live vessels): not set — ships layer empty"
if [[ -n "${GOOGLE_MAPS_API_KEY}" ]]; then
echo "Startup map: Google Photorealistic 3D Tiles (direct)"
scripts/format-scope.json
+5
View File
@@ -36,6 +36,10 @@
"src/main.js",
"docs/APPLICATION.md",
"scripts/qa-application.mjs",
"scripts/qa-voice-auth.mjs",
"scripts/qa-voice-auth-focus.mjs",
"src/codexOauthRealtime.test.mjs",
"src/voice/cloudVoiceAuth.test.mjs",
"scripts/qa-panel-resize.mjs",
"scripts/qa-panelDrag.mjs",
"src/tooling/panelResizeQa.test.mjs",
@@ -940,6 +944,7 @@
"src/tools/queries/queries.test.mjs",
"src/tools/mcp/mcp.test.mjs",
"src/tools/localServer.test.mjs",
"src/tools/mcpPanelKey.test.mjs",
"src/tools/queries/aviation.test.mjs",
"src/tools/queries/space.test.mjs",
"src/tools/queries/media.test.mjs",
scripts/package-boundaries.json
+92 -4
View File
@@ -295,6 +295,7 @@
"server/providers/common/request.js",
"server/providers/common/source-root.js",
"server/providers/openai.js",
"server/providers/openai/codex-auth.js",
"server/providers/openai/constants.js",
"server/providers/openai/debug-log.js",
"server/providers/openai/hud-summary.js",
@@ -311,6 +312,7 @@
"server/providers/common/same-site.js",
"src/localRequestGate.mjs",
"src/voice/actionSchemas.js",
"src/voice/layerManifest.js",
"server/providers/openai/toolDescriptions.js",
"src/sources/rateLimit.js"
],
@@ -339,12 +341,18 @@
"src/search/geospatial.js",
"src/search/http.js",
"src/search/defaults.js",
"src/search/alpsGeocoder.js",
"src/search/coordinateGeocoder.js",
"src/search/coordinateParser.js",
"src/search/presetGeocoder.js",
"src/search/nominatim.js",
"src/nominatimGeocode.js",
"src/data/regionalModel.js",
"src/data/naturalEarthRegions.js",
"src/data/bundledJson.js",
"src/data/retryableLoad.js",
"src/data/local_data/natural_earth/regions.json",
"src/data/local_data/natural_earth/marine.json",
"src/sources/httpBody.js",
"src/sources/nominatim.js"
],
@@ -544,6 +552,7 @@
"src/contextModePolicy.js",
"src/data/detectionPolicy.js",
"src/data/installationFeedback.js",
"src/data/idSwitches.js",
"src/data/layerState.js",
"src/data/layerStateCoordinator.js",
"src/data/layerStateTokenReservations.json",
@@ -686,6 +695,7 @@
"src/ui/styles/command-dock-trays.css",
"src/ui/styles/command-dock-sliding.css",
"src/ui/styles/voice-cost.css",
"src/ui/styles/voice-card.css",
"src/ui/styles/first-run.css",
"src/ui/styles/provider-settings.css",
"src/ui/styles/weather.css",
@@ -791,6 +801,7 @@
"src/data/cockpitContactDot.js",
"src/data/contactMatch.js",
"src/data/iconOrientation.js",
"src/data/idSwitches.js",
"src/data/layerState.js",
"src/data/layerStateTokenReservations.json",
"src/data/modelVisualAnchor.js",
@@ -833,6 +844,7 @@
"src/data/cockpitContactDot.js",
"src/data/contactMatch.js",
"src/data/iconOrientation.js",
"src/data/idSwitches.js",
"src/data/layerState.js",
"src/data/layerStateTokenReservations.json",
"src/data/modelVisualAnchor.js",
@@ -870,6 +882,7 @@
"src/data/cockpitContactDot.js",
"src/data/contactMatch.js",
"src/data/iconOrientation.js",
"src/data/idSwitches.js",
"src/data/layerState.js",
"src/data/layerStateCoordinator.js",
"src/data/layerStateTokenReservations.json",
@@ -925,6 +938,7 @@
"exports": ["./layers/recent-imagery"],
"modules": [
"src/layers/recentImagery/index.js",
"src/layers/recentImagery/source.js",
"src/layers/recentImagery/model.js",
"src/layers/recentImagery/catalog.js",
"src/layers/recentImagery/rendering.js",
@@ -1194,6 +1208,7 @@
"src/layers/streetLevel/groundCast.js",
"src/layers/streetLevel/meshSampler.js",
"src/layers/streetLevel/pickRouter.js",
"src/data/idSwitches.js",
"src/layers/streetLevel/params.js",
"src/layers/streetLevel/registry.js",
"src/layers/streetLevel/filter.js",
@@ -1239,6 +1254,7 @@
"exports": ["./layers/radio"],
"modules": [
"src/data/iconOrientation.js",
"src/data/idSwitches.js",
"src/data/layerState.js",
"src/data/layerStateTokenReservations.json",
"src/data/radioCountry.js",
@@ -1347,6 +1363,7 @@
"modules": [
"src/voice/realtimeController.js",
"src/voice/realtimeBackend.js",
"src/voice/cloudVoiceAuth.js",
"src/voice/control.js",
"src/voice/layerSummary.js",
"src/voice/voiceCost.js",
@@ -1365,7 +1382,19 @@
"src/voice/realtimeFacade.js",
"src/voice/realtimeRadio.js",
"src/voice/realtimeTurns.js",
"src/voice/realtimeConnection.js"
"src/voice/realtimeConnection.js",
"src/voice/turnMetrics.js",
"src/voice/speechLint.js",
"src/voice/voiceCard.js",
"src/voice/voiceCardPresentation.js",
"src/voice/resultDisplay.js",
"src/voice/referents.js",
"src/voice/layerManifest.js",
"src/voice/speech.js",
"src/voice/narration.js",
"src/voice/earcon.js",
"src/voice/pointerContext.js",
"src/voice/pointerReticle.js"
],
"external": []
},
@@ -1412,6 +1441,7 @@
"src/annotations/worldAnnotationRenderer.js",
"src/app/catalog.js",
"src/app/constructCatalog.js",
"src/app/sourceComposition.js",
"src/app/controls.js",
"src/app/data.js",
"src/app/errors.js",
@@ -1465,6 +1495,7 @@
"src/data/aisLiveVessels.js",
"src/data/alprCameras.js",
"src/data/analystEngine.js",
"src/voice/layerManifest.js",
"src/data/bikeshare.js",
"src/data/cctv.js",
"src/data/cctvCards.js",
@@ -1512,6 +1543,7 @@
"src/data/installationFeedback.js",
"src/data/issPass.js",
"src/data/labelArbiter.js",
"src/data/idSwitches.js",
"src/data/layerState.js",
"src/data/layerStateCoordinator.js",
"src/data/layerStateTokenReservations.json",
@@ -1827,6 +1859,7 @@
"src/scenes/recipes.js",
"src/scenes/scenePolicy.js",
"src/scopeMask.js",
"src/search/alpsGeocoder.js",
"src/search/defaults.js",
"src/search/geospatial.js",
"src/search/google.js",
@@ -1938,8 +1971,17 @@
"src/voice/commands.js",
"src/voice/control.js",
"src/voice/gevActions.js",
"src/voice/speech.js",
"src/voice/earcon.js",
"src/voice/narration.js",
"src/voice/turnMetrics.js",
"src/voice/speechLint.js",
"src/voice/voiceCard.js",
"src/voice/voiceCardPresentation.js",
"src/voice/resultDisplay.js",
"src/voice/gevRealtime.js",
"src/voice/layerSummary.js",
"src/voice/cloudVoiceAuth.js",
"src/voice/realtimeBackend.js",
"src/voice/realtimeController.js",
"src/voice/voiceCost.js",
@@ -1960,6 +2002,7 @@
"src/annotations/drawTool.js",
"src/data/routeSteps.js",
"src/layers/directions/index.js",
"src/layers/directions/source.js",
"src/data/directions.js",
"src/app/layers/directions.js",
"src/search/coordinateGeocoder.js",
@@ -2094,6 +2137,7 @@
"src/ui/localSdrPresentation.js",
"src/app/layers/recentImagery.js",
"src/layers/recentImagery/index.js",
"src/layers/recentImagery/source.js",
"src/layers/recentImagery/model.js",
"src/layers/recentImagery/catalog.js",
"src/layers/recentImagery/rendering.js",
@@ -2101,6 +2145,12 @@
"src/maps/imageryHost.js",
"src/ui/recentImagery.js",
"src/ui/imageryBoxTool.js",
"src/voice/pointerContext.js",
"src/voice/pointerReticle.js",
"src/voice/deixis.js",
"src/voice/referents.js",
"src/voice/pointerPick.js",
"src/data/pickedContext.js",
"src/ui/streetLevelControls.js",
"src/ui/streetLevelPresentation.js",
"src/layers/streetLevel/index.js",
@@ -2183,6 +2233,7 @@
"src/annotations/resolver.js",
"src/app/catalog.js",
"src/app/constructCatalog.js",
"src/app/sourceComposition.js",
"src/layers/wind/index.js",
"src/layers/wind/model.js",
"src/layers/wind/fields.js",
@@ -2242,6 +2293,7 @@
"src/data/issPass.js",
"src/data/satellitePass.js",
"src/data/labelArbiter.js",
"src/data/idSwitches.js",
"src/data/layerState.js",
"src/data/layerStateTokenReservations.json",
"src/data/localGeojson.js",
@@ -2504,6 +2556,7 @@
"src/overlays/worldOverlayDraw.js",
"src/overlays/worldOverlayTokens.js",
"src/renderGovernor.js",
"src/search/alpsGeocoder.js",
"src/search/defaults.js",
"src/search/geospatial.js",
"src/search/google.js",
@@ -2531,6 +2584,7 @@
"src/services/groundFloor.js",
"src/data/routeSteps.js",
"src/layers/directions/index.js",
"src/layers/directions/source.js",
"src/services/terrainHeights.js",
"src/data/terrainHeights.js",
"src/data/groundFloor.js",
@@ -2619,6 +2673,7 @@
"src/data/modelEligibility.js",
"src/app/layers/recentImagery.js",
"src/layers/recentImagery/index.js",
"src/layers/recentImagery/source.js",
"src/layers/recentImagery/model.js",
"src/layers/recentImagery/catalog.js",
"src/layers/recentImagery/rendering.js",
@@ -2705,6 +2760,7 @@
"src/layers/firms/anchors.js",
"src/locations.js",
"src/cameraGroundGuard.js",
"src/search/alpsGeocoder.js",
"src/search/defaults.js",
"src/search/geospatial.js",
"src/search/google.js",
@@ -2759,6 +2815,7 @@
"exports": ["./ui/share-restoration"],
"modules": [
"src/data/installationFeedback.js",
"src/data/idSwitches.js",
"src/data/layerState.js",
"src/data/layerStateCoordinator.js",
"src/data/layerStateTokenReservations.json",
@@ -2872,9 +2929,27 @@
],
"external": []
},
"directions-source": {
"exports": ["./layers/directions/source"],
"modules": ["src/layers/directions/source.js"],
"external": []
},
"recent-imagery-source": {
"exports": ["./layers/recent-imagery/source"],
"modules": [
"src/layers/recentImagery/source.js",
"src/layers/recentImagery/catalog.js",
"src/layers/recentImagery/model.js"
],
"external": []
},
"directions-layer": {
"exports": ["./layers/directions"],
"modules": ["src/layers/directions/index.js", "src/data/routeSteps.js"],
"modules": [
"src/layers/directions/index.js",
"src/layers/directions/source.js",
"src/data/routeSteps.js"
],
"external": ["cesium"]
},
"radio-browser-source": {
@@ -2894,7 +2969,11 @@
},
"voice-action-schemas": {
"exports": ["./voice/action-schemas"],
"modules": ["src/voice/actionSchemas.js", "src/hudLayoutPolicy.js"],
"modules": [
"src/voice/actionSchemas.js",
"src/voice/layerManifest.js",
"src/hudLayoutPolicy.js"
],
"external": []
},
"voice-session": {
@@ -2907,7 +2986,14 @@
"modules": [
"src/voice/sessionCommands.js",
"src/voice/session.js",
"src/voice/control.js"
"src/voice/control.js",
"src/voice/voiceCard.js",
"src/voice/voiceCardPresentation.js",
"src/voice/resultDisplay.js",
"src/voice/referents.js",
"src/voice/layerManifest.js",
"src/voice/speech.js",
"src/voice/pointerReticle.js"
],
"external": []
},
@@ -3250,6 +3336,7 @@
"src/tools/queries/brief.js",
"src/tools/queries/maritime.js",
"src/tools/queries/share.js",
"src/data/idSwitches.js",
"src/data/layerState.js",
"src/data/layerStateTokenReservations.json",
"src/sources/gbfsStations.js",
@@ -3372,6 +3459,7 @@
"exports": ["./view"],
"modules": [
"src/view/index.js",
"src/data/idSwitches.js",
"src/data/layerState.js",
"src/data/layerStateTokenReservations.json"
],
scripts/qa-street-level.mjs
+11 -5
View File
@@ -622,11 +622,17 @@ async function main() {
await target.click(
'.panel-collapse-btn[data-collapse-target="street-level-panel"]',
);
await settle(
target,
() =>
getComputedStyle(document.getElementById('sl-body')).display ===
'flex',
assert.ok(
await settle(
target,
() =>
!document
.getElementById('street-level-panel')
.classList.contains('collapsed') &&
getComputedStyle(document.getElementById('sl-body')).display ===
'flex',
),
'Street Level panel did not expand before the timeout',
);
};
await expandStrip();
scripts/qa-voice-auth-focus.mjs
+328
View File
@@ -0,0 +1,328 @@
#!/usr/bin/env node
/**
* Check auth-mode keyboard focus with the real settings template and controls.
* Run: node --test --test-reporter=spec scripts/qa-voice-auth-focus.mjs
* Sign-in responses are fixtures. No credentials or live login are used.
*/
import assert from 'node:assert/strict';
import { existsSync } from 'node:fs';
import { mkdir, readFile, writeFile } from 'node:fs/promises';
import { createServer } from 'node:http';
import { after, before, test } from 'node:test';
import puppeteer from 'puppeteer';
const root = new URL('../', import.meta.url);
const template = await readFile(
new URL('src/ui/templates/provider-settings.html', root),
'utf8',
);
const assets = new Set([
'/src/keySetup.js',
'/src/voice/cloudVoiceAuth.js',
'/src/ui/surfaceKeyboard.js',
'/src/ui/styles/provider-settings.css',
]);
const observations = [];
let server;
let browser;
let origin;
before(async () => {
server = createServer(async (req, res) => {
const pathname = new URL(req.url, 'http://localhost').pathname;
if (pathname === '/') {
res.setHeader('Content-Type', 'text/html; charset=utf-8');
res.end(`<!doctype html><html><head><meta charset="utf-8">
<title>Voice auth keyboard focus test</title>
<link rel="stylesheet" href="/src/ui/styles/provider-settings.css">
</head><body>${template}</body></html>`);
return;
}
if (!assets.has(pathname)) {
res.statusCode = 404;
res.end();
return;
}
try {
res.setHeader(
'Content-Type',
pathname.endsWith('.css') ? 'text/css' : 'text/javascript',
);
res.end(await readFile(new URL(pathname.slice(1), root)));
} catch {
res.statusCode = 500;
res.end('Could not load the test asset');
}
});
await new Promise((resolve, reject) => {
server.once('error', reject);
server.listen(0, '127.0.0.1', resolve);
});
origin = `http://127.0.0.1:${server.address().port}`;
const chrome = '/Applications/Google Chrome.app/Contents/MacOS/Google Chrome';
browser = await puppeteer.launch({
headless: true,
executablePath:
process.env.PUPPETEER_EXECUTABLE_PATH ||
(existsSync(chrome) ? chrome : await puppeteer.executablePath()),
});
});
after(async () => {
await browser?.close();
if (server?.listening) await new Promise((resolve) => server.close(resolve));
const output = new URL('.gev-logs/voice-auth-focus/', root);
await mkdir(output, { recursive: true });
await writeFile(
new URL('results.json', output),
`${JSON.stringify(observations, null, 2)}\n`,
);
});
const scenarios = [
{
name: 'OAuth to API key',
initial: 'oauth',
expected: 'api-key',
flow: 'unused',
},
{
name: 'API key to existing OAuth',
initial: 'api-key',
expected: 'oauth',
flow: 'existing',
},
{
name: 'API key to OAuth ready at login launch',
initial: 'api-key',
expected: 'oauth',
flow: 'login-ready',
},
{
name: 'API key to OAuth ready after polling',
initial: 'api-key',
expected: 'oauth',
flow: 'poll-ready',
},
];
async function mountSettings(page, scenario) {
await page.goto(`${origin}/?setup=1`, {
waitUntil: 'domcontentloaded',
});
await page.evaluate(async ({ initial, flow }) => {
localStorage.clear();
localStorage.setItem('godsEyeView.voice.cloudAuth', initial);
window.__focusTestCalls = [];
let statusReads = 0;
const fetchImpl = async (url) => {
window.__focusTestCalls.push(url);
let payload;
let status = 200;
if (url === '/api/setup/status') {
payload = {
setCount: 0,
total: 1,
keys: [
{
id: 'openai',
title: 'OPENAI',
tier: 'metered',
set: false,
unlocks: 'Voice control',
envVars: ['OPENAI_API_KEY'],
getUrl: 'https://example.invalid/',
},
],
};
} else if (url === '/api/realtime/oauth-status') {
statusReads += 1;
if (flow === 'deferred') {
return await new Promise((resolve) => {
window.__resolveOAuthStatus = (available) =>
resolve(
new Response(
JSON.stringify({ available, error: 'Fixture failure' }),
{
status: available ? 200 : 503,
},
),
);
});
}
payload = {
available:
flow === 'existing' || (flow === 'poll-ready' && statusReads > 1),
};
} else if (url === '/api/realtime/oauth-login') {
const available = flow === 'login-ready';
status = available ? 200 : 202;
payload = { available, pending: !available, started: !available };
} else {
throw new Error(`Unexpected request: ${url}`);
}
return new Response(JSON.stringify(payload), { status });
};
const { initKeySetup } = await import('/src/keySetup.js');
window.__focusTestSettings = await initKeySetup({ fetchImpl });
}, scenario);
await page.waitForFunction(
() =>
document.getElementById('key-setup').classList.contains('visible') &&
document.activeElement.matches('input[data-env-var]'),
);
}
for (const scenario of scenarios) {
for (const key of ['Enter', 'Space', 'Mouse click']) {
test(`${scenario.name} keeps keyboard focus after ${key}`, async (t) => {
const page = await browser.newPage();
try {
await mountSettings(page, scenario);
if (key !== 'Mouse click') {
// Tab from the initial key field to the real auth button.
await page.keyboard.press('Tab');
assert.equal(
await page.evaluate(() =>
document.activeElement.matches('[data-cloud-voice-auth-toggle]'),
),
true,
'Keyboard navigation must reach the auth toggle before activation',
);
}
await page.evaluate(() => {
const toggle = document.querySelector(
'[data-cloud-voice-auth-toggle]',
);
window.__originalFocusToggle = toggle;
window.__focusAtActivation = null;
toggle.addEventListener(
'click',
() => {
window.__focusAtActivation = document.activeElement === toggle;
},
{ capture: true, once: true },
);
});
if (key === 'Mouse click') {
await page.waitForFunction(
() =>
getComputedStyle(document.getElementById('key-setup')).opacity ===
'1',
);
await page.click('[data-cloud-voice-auth-toggle]');
} else {
await page.keyboard.press(key);
}
await page.waitForFunction(
(expected) =>
localStorage.getItem('godsEyeView.voice.cloudAuth') === expected &&
!document.querySelector('[data-cloud-voice-auth-toggle]')
.disabled &&
document
.querySelector('[data-cloud-voice-auth-toggle]')
.getAttribute('aria-disabled') !== 'true',
{},
scenario.expected,
);
const selection = await page.evaluate(() => ({
focusOnToggleAtActivation: window.__focusAtActivation,
focusOnToggle:
document.activeElement ===
document.querySelector('[data-cloud-voice-auth-toggle]'),
activeTag: document.activeElement.tagName,
originalToggleConnected: window.__originalFocusToggle.isConnected,
requests: window.__focusTestCalls,
}));
await page.keyboard.press('Tab');
const nextTab = await page.evaluate(() => ({
focusOnSave: document.activeElement.matches('[data-key-setup-apply]'),
activeLabel:
document.activeElement.getAttribute('aria-label') ||
document.activeElement.textContent.trim(),
}));
const observed = { scenario: scenario.name, key, selection, nextTab };
observations.push(observed);
t.diagnostic(JSON.stringify(observed));
assert.equal(
selection.focusOnToggle,
true,
'Auth selection must keep focus on its usable toggle',
);
assert.equal(
nextTab.focusOnSave,
true,
'Tab must continue to SAVE KEYS rather than restart at Close',
);
} finally {
await page.close();
}
});
}
}
for (const available of [true, false]) {
test(`pending OAuth ${available ? 'success' : 'failure'} blocks repeats without moving focus or losing a key draft`, async () => {
const page = await browser.newPage();
try {
await mountSettings(page, { initial: 'api-key', flow: 'deferred' });
await page.type('input[data-env-var]', 'test-draft-only');
await page.keyboard.press('Tab');
await page.keyboard.press('Enter');
await page.waitForFunction(
() => typeof window.__resolveOAuthStatus === 'function',
);
assert.equal(
await page.evaluate(() =>
document.activeElement.matches('[data-cloud-voice-auth-toggle]'),
),
true,
);
await page.keyboard.press('Enter');
await page.keyboard.press('Space');
assert.equal(
await page.evaluate(
() =>
window.__focusTestCalls.filter(
(url) => url === '/api/realtime/oauth-status',
).length,
),
1,
);
await page.keyboard.press('Tab');
assert.equal(
await page.evaluate(() =>
document.activeElement.matches('[data-key-setup-apply]'),
),
true,
);
await page.evaluate(
(available) => window.__resolveOAuthStatus(available),
available,
);
await page.waitForFunction(
() =>
document
.querySelector('[data-cloud-voice-auth-toggle]')
.getAttribute('aria-disabled') === 'false',
);
const observed = await page.evaluate(() => ({
mode: localStorage.getItem('godsEyeView.voice.cloudAuth'),
focusOnSave: document.activeElement.matches('[data-key-setup-apply]'),
draft: document.querySelector('input[data-env-var]').value,
requests: window.__focusTestCalls,
}));
observations.push({ scenario: 'pending OAuth', available, observed });
assert.equal(observed.mode, available ? 'oauth' : 'api-key');
assert.equal(
observed.focusOnSave,
true,
'Completing a request must not take focus from another control',
);
assert.equal(observed.draft, 'test-draft-only');
} finally {
await page.close();
}
});
}
scripts/qa-voice-auth.mjs
+291
View File
@@ -0,0 +1,291 @@
#!/usr/bin/env node
/**
* Live Realtime auth acceptance with a prerecorded Chromium microphone.
* Run against the local dev server after configuring the selected credential:
* node scripts/qa-voice-auth.mjs http://127.0.0.1:4189 oauth microphone.wav
* Use a short spoken reply request with three seconds of leading silence.
* Saves only usage, transport metadata, and screenshots; never credentials.
*/
import assert from 'node:assert/strict';
import fs from 'node:fs';
import path from 'node:path';
import { fileURLToPath } from 'node:url';
import puppeteer from 'puppeteer';
const root = fileURLToPath(new URL('../', import.meta.url));
const url = new URL(process.argv[2] || 'http://127.0.0.1:4189');
const auth = process.argv[3] || 'oauth';
assert.ok(['oauth', 'api-key'].includes(auth), 'Choose oauth or api-key');
assert.ok(
['127.0.0.1', 'localhost', '[::1]'].includes(url.hostname),
'Use a local server',
);
assert.ok(process.argv[4], 'Provide a prerecorded microphone WAV');
const wav = path.resolve(process.argv[4]);
assert.ok(fs.existsSync(wav), 'Microphone WAV must exist');
url.searchParams.set('welcome', '0');
url.searchParams.set('setup', '1');
const output = path.join(root, '.gev-logs', 'voice-auth');
fs.mkdirSync(output, { recursive: true });
const executablePath =
process.env.PUPPETEER_EXECUTABLE_PATH ||
(fs.existsSync('/Applications/Google Chrome.app/Contents/MacOS/Google Chrome')
? '/Applications/Google Chrome.app/Contents/MacOS/Google Chrome'
: puppeteer.executablePath());
const browser = await puppeteer.launch({
headless: true,
executablePath,
args: [
'--no-sandbox',
'--disable-setuid-sandbox',
'--use-fake-device-for-media-stream',
`--use-file-for-fake-audio-capture=${wav}%noloop`,
'--autoplay-policy=no-user-gesture-required',
'--disable-background-timer-throttling',
'--window-size=1440,900',
],
});
const result = {
ok: false,
auth,
input: 'prerecorded microphone',
mints: [],
negotiations: [],
};
let page;
const readSession = () =>
page.evaluate(async () => {
const voice = window.__godsEyeView.voiceCommands;
const stats = voice.pc ? [...(await voice.pc.getStats()).values()] : [];
const input = stats.find(
(entry) => entry.type === 'outbound-rtp' && entry.kind === 'audio',
);
const source = stats.find(
(entry) => entry.type === 'media-source' && entry.kind === 'audio',
);
const audio = stats.find(
(entry) => entry.type === 'inbound-rtp' && entry.kind === 'audio',
);
const meter = document.getElementById('gev-voice-cost-value');
return {
...window.__voiceAuthEvidence,
connection: voice.pc?.connectionState,
microphoneEnabled: voice.stream
?.getAudioTracks()
.every((track) => track.enabled),
inputBytes: input?.bytesSent || 0,
inputAudioEnergy: source?.totalAudioEnergy ?? null,
outputBytes: audio?.bytesReceived || 0,
outputAudioEnergy: audio?.totalAudioEnergy || 0,
playbackTime: voice.audioEl?.currentTime || 0,
meter: {
text: meter?.textContent,
usage: meter?.title,
visible: Boolean(meter?.getClientRects().length),
},
};
});
try {
await browser
.defaultBrowserContext()
.overridePermissions(url.origin, ['microphone']);
page = await browser.newPage();
await page.setViewport({ width: 1440, height: 900 });
page.on('response', (response) => {
const route = new URL(response.url()).pathname;
if (route === '/api/realtime/token')
result.mints.push({
status: response.status(),
auth: response.headers()['x-gev-voice-auth'],
model: response.headers()['x-gev-voice-model'],
});
if (
route === '/v1/realtime/calls' &&
response.request().method() === 'POST'
)
result.negotiations.push({ status: response.status() });
});
// Observe the application's real transport. Do not replace fetch or replies.
await page.evaluateOnNewDocument(() => {
window.__voiceAuthEvidence = {
speechStopped: 0,
transcripts: [],
replies: [],
responses: [],
errors: [],
eventCounts: {},
};
const create = RTCPeerConnection.prototype.createDataChannel;
RTCPeerConnection.prototype.createDataChannel = function (...args) {
const channel = create.apply(this, args);
channel.addEventListener('message', ({ data }) => {
let event;
try {
event = JSON.parse(data);
} catch {
return;
}
const evidence = window.__voiceAuthEvidence;
evidence.eventCounts[event.type] =
(evidence.eventCounts[event.type] || 0) + 1;
if (event.type === 'input_audio_buffer.speech_stopped')
evidence.speechStopped += 1;
if (
event.type === 'conversation.item.input_audio_transcription.completed'
)
evidence.transcripts.push(event.transcript);
if (event.type === 'response.output_audio_transcript.done')
evidence.replies.push(event.transcript);
if (event.type === 'response.done')
evidence.responses.push({
status: event.response?.status,
inputTokens: event.response?.usage?.input_tokens,
outputTokens: event.response?.usage?.output_tokens,
});
if (event.type === 'error')
evidence.errors.push({ code: event.error?.code });
});
return channel;
};
});
await page.goto(url.href, { waitUntil: 'domcontentloaded', timeout: 30_000 });
await page.waitForFunction(
() =>
window.__godsEyeView?.voiceCommands &&
document.getElementById('loading-screen')?.classList.contains('hidden'),
{ timeout: 45_000 },
);
await page.waitForSelector('[data-cloud-voice-auth-toggle]', {
visible: true,
});
await page.waitForFunction(
() =>
getComputedStyle(document.getElementById('key-setup')).opacity === '1',
);
const selected = await page.evaluate(
() => localStorage.getItem('godsEyeView.voice.cloudAuth') || 'api-key',
);
if (selected !== auth) {
await page.click('[data-cloud-voice-auth-toggle]');
await page.waitForFunction(
(mode) => localStorage.getItem('godsEyeView.voice.cloudAuth') === mode,
{ timeout: 125_000 },
auth,
);
}
await page.click('[data-key-setup-close]');
await page.click('#gev-voice-button');
await page.waitForFunction(
() =>
window.__godsEyeView.voiceCommands.dc?.readyState === 'open' ||
window.__godsEyeView.voiceCommands.status === 'error',
{ timeout: 35_000 },
);
assert.equal(
await page.evaluate(
() => window.__godsEyeView.voiceCommands.dc?.readyState,
),
'open',
'Realtime channel must open',
);
await page.waitForFunction(
() =>
window.__voiceAuthEvidence.speechStopped > 0 &&
window.__voiceAuthEvidence.responses.some(
(response) =>
response.status === 'completed' && response.outputTokens > 0,
),
{ timeout: 45_000 },
);
await page.waitForFunction(
() =>
window.__voiceAuthEvidence.eventCounts['output_audio_buffer.stopped'] > 0,
{ timeout: 30_000 },
);
result.session = await readSession();
assert.ok(
result.session.inputBytes > 0 && result.session.outputBytes > 0,
'Audio must flow in both directions',
);
assert.ok(
result.session.outputAudioEnergy > 0 && result.session.playbackTime > 0,
'Reply audio must play',
);
assert.equal(
result.session.meter.text === 'COST UNKNOWN',
auth === 'oauth',
'Use the correct accounting display',
);
await page.screenshot({ path: path.join(output, `${auth}-usage.png`) });
await page.click('#key-setup-chip');
await page.waitForSelector('[data-cloud-voice-auth-toggle]', {
visible: true,
});
await page.waitForFunction(
() =>
getComputedStyle(document.getElementById('key-setup')).opacity === '1',
);
await page.screenshot({ path: path.join(output, `${auth}-settings.png`) });
await page.click('[data-key-setup-close]');
result.stopped = await page.evaluate(() => {
const voice = window.__godsEyeView.voiceCommands;
const pc = voice.pc;
const tracks = voice.stream?.getTracks() || [];
voice.session.stop();
return (
pc.connectionState === 'closed' &&
tracks.every((track) => track.readyState === 'ended')
);
});
assert.ok(result.stopped, 'Stop must close the peer and microphone tracks');
await page.click('#gev-voice-button');
await page.waitForFunction(
() =>
window.__godsEyeView.voiceCommands.dc?.readyState === 'open' ||
window.__godsEyeView.voiceCommands.status === 'error',
{ timeout: 35_000 },
);
assert.equal(
await page.evaluate(
() => window.__godsEyeView.voiceCommands.dc?.readyState,
),
'open',
'Reconnect must work',
);
assert.equal(
result.mints.length,
2,
'Reconnect must request a fresh client secret',
);
assert.ok(
result.mints.every(
(mint) =>
mint.status === 200 &&
mint.auth === (auth === 'oauth' ? 'codex-oauth' : 'env'),
),
);
assert.ok(result.negotiations.every((entry) => entry.status === 201));
result.ok = true;
} catch (error) {
result.error = error.message;
if (page) {
result.session = await readSession().catch(() => null);
result.detail = await page
.$eval('#gev-voice-detail', (element) => element.textContent)
.catch(() => null);
await page
.screenshot({ path: path.join(output, `${auth}-failure.png`) })
.catch(() => {});
}
} finally {
await page
?.evaluate(() => window.__godsEyeView?.voiceCommands?.session?.stop())
.catch(() => {});
await browser.close();
fs.writeFileSync(
path.join(output, `${auth}-result.json`),
`${JSON.stringify(result, null, 2)}\n`,
);
}
console.log(JSON.stringify(result, null, 2));
if (!result.ok) process.exitCode = 1;
scripts/qa-voice-bench.mjs
+411
View File
@@ -0,0 +1,411 @@
#!/usr/bin/env node
/**
* qa-voice-bench.mjs — provider-neutral TEXT-mode voice-routing benchmark.
*
* Every provider gets the same prompt: production's realtimeInstructions()
* and GEV_REALTIME_TOOLS (the Realtime adapter uses the exact session body the
* token handler mints). Two suites, reported separately:
* core the qa-voice-routing phrase table, graded with its semantics
* (plus benchmark-only typed-argument checks)
* coverage the newer-layers coverage probe, graded correct /
* honest-refusal / hallucinated-capability / wrong-tool
* dialogue two-turn dialogues in one context; turn 2 depends on turn 1
* capability area handles / imagery / OSM / point-and-ask phrases (and two
* dialogues) for the tools added after 4b56d0e9
* Coverage rows are graded twice: v1 (original rubric, 4b56d0e9 tool schema)
* and v2 (rubric for the current tool surface).
*
* Methodology: a fresh context per phrase (new Realtime/Live session, or a
* stateless chat request); stub tool results; continuations until the model
* stops calling tools (max 4). No app page is involved.
*
* Usage:
* node scripts/qa-voice-bench.mjs --provider openai-realtime --model gpt-realtime-2 --reps 2
* node scripts/qa-voice-bench.mjs --provider gemini-live --model gemini-3.8-live
* node scripts/qa-voice-bench.mjs --provider ollama --model gemma4:e4b
* node scripts/qa-voice-bench.mjs --provider openai-chat --base http://localhost:1234/v1 --model <id>
* node scripts/qa-voice-bench.mjs --summarize --out qa-shots/voice-bench/<run>
* Common flags: --out <dir> (reuse one dir to collect several models),
* --suite core,coverage --only <substr> --budget <usd, cloud total>
* --variant <label> --temperature <t> --num-ctx <n> --think --note <text>
* --reps <n> --start-rep <k> (add repetitions k..k+n-1 to an existing run)
* --replace (supersede earlier runs of this model for the suites run)
* --compare <run dir> (add a before → after table against another run)
*
* Output (gitignored): <out>/results.jsonl, summary.json, summary.md.
* Keys come from the environment or the macOS Keychain at runtime only.
*/
import fs from 'node:fs';
import path from 'node:path';
import os from 'node:os';
import { execFileSync } from 'node:child_process';
import { fileURLToPath } from 'node:url';
import {
CORE_PHRASES, COVERAGE_PROBE, DIALOGUES, CAPABILITY_EXTRAS,
dialogueResult, coverageRubric,
} from './voice-bench/phrases.mjs';
import { gradeCore, gradeCoverage, gradeDialogue, expectLabel } from './voice-bench/grade.mjs';
import { stubResult } from './voice-bench/stub.mjs';
import { summarize, renderMarkdown, renderComparison } from './voice-bench/report.mjs';
import { GEV_REALTIME_TOOLS, realtimeInstructions } from './voice-bench/productionConfig.mjs';
import { chatNormalizationDiff } from './voice-bench/toolFormats.mjs';
import { createOpenAiRealtimeAdapter } from './voice-bench/adapters/openaiRealtime.mjs';
import { createGeminiLiveAdapter } from './voice-bench/adapters/geminiLive.mjs';
import { createOpenAiChatAdapter, createOllamaAdapter } from './voice-bench/adapters/localChat.mjs';
const ROOT = path.resolve(path.dirname(fileURLToPath(import.meta.url)), '..');
const argv = process.argv.slice(2);
const opt = (flag, fallback) => {
const i = argv.indexOf(flag);
return i >= 0 && argv[i + 1] !== undefined ? argv[i + 1] : fallback;
};
const has = (flag) => argv.includes(flag);
const PROVIDER = opt('--provider', null);
const MODEL = opt('--model', null);
const CLOUD = PROVIDER === 'openai-realtime' || PROVIDER === 'gemini-live';
const REPS = Number(opt('--reps', CLOUD ? '2' : '1'));
const START_REP = Number(opt('--start-rep', '1'));
const SUITES = opt('--suite', 'core,coverage,dialogue,capability').split(',');
const ONLY = opt('--only', null);
const BUDGET = Number(opt('--budget', '30'));
const VARIANT = opt('--variant', null);
const OUT = path.resolve(ROOT, opt('--out', path.join('qa-shots', 'voice-bench', new Date().toISOString().replace(/[:.]/g, '-'))));
const LEDGER = path.join(ROOT, 'qa-shots', 'voice-bench', 'cloud-spend.json');
fs.mkdirSync(OUT, { recursive: true });
const RESULTS = path.join(OUT, 'results.jsonl');
const NOTES = path.join(OUT, 'notes.json');
function readRows() {
if (!fs.existsSync(RESULTS)) return [];
// Several runs may append to one results file (a cloud run beside a local
// one); skip a line another process is still writing.
return fs.readFileSync(RESULTS, 'utf8').split('\n').filter(Boolean).flatMap((l) => {
try { return [JSON.parse(l)]; } catch { return []; }
});
}
function appendRow(row) {
fs.appendFileSync(RESULTS, `${JSON.stringify(row)}\n`);
}
function readNotes() {
try { return JSON.parse(fs.readFileSync(NOTES, 'utf8')); } catch { return []; }
}
/**
* Re-grade stored turns with the CURRENT phrase tables and grader, so a
* grader fix applies to every model already in the results file. The raw
* calls and text in results.jsonl are the source of truth; `gradeAtRun`
* keeps the verdict recorded at run time.
*/
function regrade(rows) {
const core = new Map(CORE_PHRASES.map((p) => [p.phrase, p]));
const cov = new Map(COVERAGE_PROBE.map((c) => [c.id, c]));
const dia = new Map(DIALOGUES.map((d) => [d.id, d]));
const cap = new Map(CAPABILITY_ITEMS.map((c) => [c.id, c]));
// A run started with --replace supersedes earlier runs of the same
// provider/model/variant for the suites it covers.
const key = (r) => `${r.provider}:${r.model}#${r.variant || ''}`;
const runs = rows.filter((r) => r.type === 'run');
const superseded = new Set();
for (const r of runs.filter((x) => x.replace)) {
for (const older of runs) {
if (older.at < r.at && key(older) === key(r)) superseded.add(`${older.runId}|${(r.suites || []).join(',')}`);
}
}
const isSuperseded = (row) => [...superseded].some((s) => {
const [runId, suites] = s.split('|');
return runId === row.runId && suites.split(',').includes(row.suite);
});
return rows.filter((row) => row.type !== 'turn' || !isSuperseded(row)).map((row) => {
if (row.type !== 'turn') return row;
if (row.suite === 'dialogue' && dia.has(row.phraseId)) {
return { ...row, gradeAtRun: row.grade, grade: gradeDialogue(dia.get(row.phraseId), [row.turn1?.calls || [], row.calls || []]) };
}
if (row.suite === 'core' && core.has(row.phraseId)) {
return { ...row, gradeAtRun: row.grade, grade: gradeCore(core.get(row.phraseId), row.calls || []) };
}
if (row.suite === 'coverage' && cov.has(row.phraseId)) {
const item = cov.get(row.phraseId);
return {
...row,
gradeAtRun: row.grade,
grade: gradeCoverage(item, row.calls || [], row.text, BASELINE_TOOLS),
gradeV2: gradeCoverage(coverageRubric(item, 'v2'), row.calls || [], row.text, GEV_REALTIME_TOOLS),
};
}
if (row.suite === 'capability' && cap.has(row.phraseId)) {
const c = cap.get(row.phraseId);
const grade = c.dialogue ? gradeDialogue(c.dialogue, [row.turn1?.calls || [], row.calls || []]) : gradeCore(c.phrase, row.calls || []);
return { ...row, gradeAtRun: row.grade, grade };
}
return row;
});
}
function readRowsFrom(dir) {
const file = path.join(dir, 'results.jsonl');
if (!fs.existsSync(file)) return [];
return fs.readFileSync(file, 'utf8').split('\n').filter(Boolean).flatMap((l) => {
try { return [JSON.parse(l)]; } catch { return []; }
});
}
function writeSummary() {
const summary = summarize(regrade(readRows()));
// --compare <dir> (remembered in compare-with.txt): a before → after table
// against another run folder, both re-graded with the current grader.
const compareFile = path.join(OUT, 'compare-with.txt');
if (has('--compare')) fs.writeFileSync(compareFile, `${path.resolve(ROOT, opt('--compare', ''))}\n`);
let comparison = '';
if (fs.existsSync(compareFile)) {
const beforeDir = fs.readFileSync(compareFile, 'utf8').trim();
const before = summarize(regrade(readRowsFrom(beforeDir)));
const beforeHead = readRowsFrom(beforeDir).find((r) => r.type === 'run' && r.prompt?.gitHead)?.prompt?.gitHead || '4b56d0e9';
const afterHead = readRows().find((r) => r.type === 'run' && r.prompt?.gitHead)?.prompt?.gitHead || '?';
comparison = renderComparison(before, summary, {
beforeLabel: `${path.relative(ROOT, beforeDir)} (prompt/tools @ ${beforeHead})`,
afterLabel: `${path.relative(ROOT, OUT)} (prompt/tools @ ${afterHead})`,
});
summary.comparison = { beforeDir: path.relative(ROOT, beforeDir), before: before.models.map((m) => ({ key: m.key, coreFull: m.core.fullCallAccuracyPct, coverageV1Pct: m.coverage.acceptablePct, hcV1: m.coverage.counts['hallucinated-capability'], dialogueT2: m.dialogue.turn2FullPct, toolCallP50: m.latencyMs.toolCallP50, promptTokens: m.warmup?.promptTokens ?? m.tokens.inputPerRequestMean })) };
fs.writeFileSync(path.join(OUT, 'comparison.md'), `${comparison}\n`);
}
fs.writeFileSync(path.join(OUT, 'summary.json'), JSON.stringify(summary, null, 2));
const md = renderMarkdown(summary, { notes: readNotes(), payload: payloadChanges() });
fs.writeFileSync(path.join(OUT, 'summary.md'), comparison ? md.replace('## Routing accuracy', `${comparison}\n## Routing accuracy`) : md);
return summary;
}
/** Exactly what each provider receives differently from production's payload. */
function payloadChanges() {
const chat = chatNormalizationDiff(GEV_REALTIME_TOOLS)
.map((c) => `\`${c.path}\`: ${JSON.stringify(c.from)} → ${JSON.stringify(c.to)}`);
return [
`openai-realtime: none — the session body is captured from production's token handler (${GEV_REALTIME_TOOLS.length} tools, instructions, tool_choice auto, reasoning low, truncation). Only difference from a mic session: response.create asks for output_modalities ["text"] (as qa-voice-routing does).`,
'gemini-live: same instructions text as systemInstruction; the same tool schemas passed verbatim as functionDeclarations[].parametersJsonSchema (no keyword changes); tool_choice has no Live equivalent (AUTO is the default); responseModalities AUDIO + outputAudioTranscription (TEXT is rejected by the model).',
`ollama / openai-chat: same instructions as the system message; tools wrapped as {type:"function",function:{name,description,parameters}} with ${chat.length} schema change(s): ${chat.join('; ') || 'none'}. Descriptions, enums and required lists are unchanged; nothing is stringified.`,
];
}
function ledgerSpent() {
try { return JSON.parse(fs.readFileSync(LEDGER, 'utf8')).spentUsd || 0; } catch { return 0; }
}
function ledgerAdd(usd) {
const spent = ledgerSpent() + usd;
fs.mkdirSync(path.dirname(LEDGER), { recursive: true });
fs.writeFileSync(LEDGER, JSON.stringify({ spentUsd: spent, updatedAt: new Date().toISOString() }));
return spent;
}
const sh = (cmd, args) => {
try { return execFileSync(cmd, args, { encoding: 'utf8', stdio: ['ignore', 'pipe', 'ignore'], timeout: 10_000 }).trim(); } catch { return null; }
};
/** Snapshot of what else is using the machine (GPU-heavy servers, load). */
function machineSnapshot() {
const load = os.loadavg().map((x) => x.toFixed(2)).join(' ');
const ollamaPs = sh('ollama', ['ps']);
const procs = sh('ps', ['-Ao', 'pcpu=,rss=,comm=']) || '';
const heavy = procs.split('\n').map((l) => l.trim().split(/\s+/)).filter((p) => Number(p[0]) > 20)
.map((p) => `${path.basename(p.slice(2).join(' '))} ${p[0]}%cpu`).slice(0, 6);
const gpuServers = procs.split('\n').filter((l) => /ollama runner|llama-server|LM Studio|lms|mlx|whisper/i.test(l))
.map((l) => path.basename(l.trim().split(/\s+/).slice(2).join(' '))).slice(0, 6);
return {
at: new Date().toISOString(),
loadavg: load,
ollamaPs,
busyProcesses: heavy,
modelServers: gpuServers,
summary: `load ${load}; busy: ${heavy.join(', ') || 'none'}`,
};
}
// ── Ollama lifecycle ────────────────────────────────────────────────────────
const OLLAMA = opt('--base', 'http://localhost:11434').replace(/\/v1\/?$/, '');
async function ollamaUnloadAll() {
const ps = await fetch(`${OLLAMA}/api/ps`).then((r) => r.json()).catch(() => ({ models: [] }));
for (const m of ps.models || []) {
await fetch(`${OLLAMA}/api/generate`, { method: 'POST', body: JSON.stringify({ model: m.name, keep_alive: 0 }) }).then((r) => r.text()).catch(() => null);
}
return (ps.models || []).map((m) => m.name);
}
async function ollamaLoad(model, numCtx) {
const t = Date.now();
const res = await fetch(`${OLLAMA}/api/generate`, {
method: 'POST',
body: JSON.stringify({ model, keep_alive: '30m', options: { num_ctx: numCtx } }),
signal: AbortSignal.timeout(600_000),
});
const body = await res.json().catch(() => ({}));
if (!res.ok || body.error) throw new Error(`load failed: ${body.error || res.status}`);
return { wallMs: Date.now() - t, loadMs: body.load_duration ? body.load_duration / 1e6 : null };
}
// ── Main ────────────────────────────────────────────────────────────────────
function buildAdapter() {
const temperature = Number(opt('--temperature', '0.8'));
switch (PROVIDER) {
case 'openai-realtime':
return createOpenAiRealtimeAdapter({ model: MODEL });
case 'gemini-live':
return createGeminiLiveAdapter({ model: MODEL, schemaMode: opt('--gemini-schema', 'jsonSchema') });
case 'ollama':
return createOllamaAdapter({ model: MODEL, baseUrl: OLLAMA, temperature, numCtx: Number(opt('--num-ctx', '32768')), think: has('--think') });
case 'openai-chat':
return createOpenAiChatAdapter({ model: MODEL, baseUrl: opt('--base', 'http://localhost:1234/v1'), temperature });
default:
throw new Error(`unknown --provider ${PROVIDER}`);
}
}
const COLD_PHRASE = 'Take me to Tokyo';
/** Capability suite: single phrases (optional pointer context) and dialogues. */
const CAPABILITY_ITEMS = CAPABILITY_EXTRAS.map((c) => (c.turns
? { suite: 'capability', id: c.id, text: c.turns.join(' → '), dialogue: c }
: { suite: 'capability', id: c.context ? `${c.phrase} [pointer]` : c.phrase, text: c.phrase, phrase: c, context: c.context || null }));
/** The 4b56d0e9 tool schema, for grading coverage by the original yardstick. */
const BASELINE_TOOLS = JSON.parse(fs.readFileSync(path.join(ROOT, 'scripts', 'voice-bench', 'baseline-tools-4b56d0e9.json'), 'utf8'));
/** What prompt this run actually sent (so before/after runs are identifiable). */
function promptVersion() {
let head = null;
try { head = execFileSync('git', ['-C', ROOT, 'rev-parse', '--short', 'HEAD'], { encoding: 'utf8' }).trim(); } catch { /* not a checkout */ }
return {
gitHead: head,
tools: GEV_REALTIME_TOOLS.length,
toolJsonChars: JSON.stringify(GEV_REALTIME_TOOLS).length,
instructionsChars: realtimeInstructions().length,
};
}
function workList() {
const items = [];
if (SUITES.includes('core')) {
for (const p of CORE_PHRASES) items.push({ suite: 'core', id: p.phrase, text: p.phrase, phrase: p });
}
if (SUITES.includes('coverage')) {
for (const c of COVERAGE_PROBE) items.push({ suite: 'coverage', id: c.id, text: c.utterance, item: c });
}
if (SUITES.includes('dialogue')) {
for (const d of DIALOGUES) items.push({ suite: 'dialogue', id: d.id, text: d.turns.join(' → '), dialogue: d });
}
if (SUITES.includes('capability')) items.push(...CAPABILITY_ITEMS);
return items.filter((w) => !ONLY || w.text.toLowerCase().includes(ONLY.toLowerCase()));
}
async function main() {
if (has('--note')) {
const notes = readNotes();
notes.push(opt('--note', ''));
fs.writeFileSync(NOTES, JSON.stringify(notes, null, 2));
}
if (has('--summarize') || !PROVIDER) {
writeSummary();
console.log(`summary written to ${path.join(OUT, 'summary.md')}`);
return;
}
if (!MODEL) throw new Error('--model is required');
const adapter = buildAdapter();
await adapter.open();
let warmup = null;
if (PROVIDER === 'ollama') {
const unloaded = await ollamaUnloadAll();
const numCtx = Number(opt('--num-ctx', '32768'));
const load = await ollamaLoad(MODEL, numCtx);
// COLD turn: the first request after load pays the full-prompt prefill.
// It is recorded separately (warmup.cold*) and primes the prefix cache
// the way a live session's first turn would; every benchmark turn after
// it is steady state.
const w = await adapter.runTurn({ text: COLD_PHRASE, onCall: () => ({ ok: true }) });
warmup = { unloaded, loadWallMs: load.wallMs, loadMs: load.loadMs, coldPhrase: COLD_PHRASE, prefillTokS: w.local.prefillTokS, promptTokens: w.local.promptEvalCount, coldFirstTokenMs: w.tFirstTokenMs, coldToolCallMs: w.tFirstCallMs, coldCalls: w.calls.map((c) => c.name), warmupTurnMs: w.tDoneMs, errors: w.errors };
console.log(`warm-up: load ${Math.round(load.wallMs)}ms, prefill ${Math.round(w.local.prefillTokS || 0)} tok/s over ${w.local.promptEvalCount} tokens`);
if (w.errors.length) console.log(` warm-up errors: ${w.errors.join('; ')}`);
} else if (PROVIDER === 'openai-chat') {
const w = await adapter.runTurn({ text: COLD_PHRASE, onCall: () => ({ ok: true }) });
warmup = { loadMs: Number(opt('--load-ms', 'NaN')) || null, coldPhrase: COLD_PHRASE, prefillTokS: w.local.prefillTokS, promptTokens: w.local.promptEvalCount, coldFirstTokenMs: w.tFirstTokenMs, coldToolCallMs: w.tFirstCallMs, coldCalls: w.calls.map((c) => c.name), warmupTurnMs: w.tDoneMs, errors: w.errors };
console.log(`warm-up: ${w.tDoneMs}ms prefill≈${Math.round(w.local.prefillTokS || 0)} tok/s`);
if (w.errors.length) throw new Error(`warm-up failed, not benchmarking: ${w.errors[0]}`);
}
const runId = `${Date.now().toString(36)}`;
const machine = CLOUD ? null : machineSnapshot();
appendRow({ type: 'run', runId, at: new Date().toISOString(), provider: PROVIDER, model: MODEL, variant: VARIANT, reps: REPS, suites: SUITES, settings: adapter.settings, machine, warmup, replace: has('--replace'), prompt: promptVersion(), methodology: 'fresh context per phrase/dialogue; stub tool results (canned results for dialogue turn 1); ≤4 continuations' });
const items = workList();
let stopReason = null;
let turnCosts = [];
outer: for (let rep = START_REP; rep < START_REP + REPS; rep += 1) {
console.log(`\n== ${PROVIDER} ${MODEL}${VARIANT ? ` (${VARIANT})` : ''} — rep ${rep}/${REPS}, ${items.length} phrases`);
for (const w of items) {
if (CLOUD) {
const avg = turnCosts.length ? turnCosts.reduce((a, b) => a + b, 0) / turnCosts.length : 0.1;
if (ledgerSpent() + avg > BUDGET) { stopReason = `cloud budget $${BUDGET} reached (ledger $${ledgerSpent().toFixed(2)})`; break outer; }
}
let r;
let turn1 = null;
let grade;
if (w.dialogue) {
const rs = await adapter.runDialogue({
turns: w.dialogue.turns,
onCall: (c, turn) => dialogueResult(w.dialogue, c.name, turn) ?? stubResult('core', c, GEV_REALTIME_TOOLS),
});
const [a, b] = rs;
turn1 = { text: a.text.slice(0, 400), calls: a.calls, tFirstCallMs: a.tFirstCallMs, tDoneMs: a.tDoneMs, errors: a.errors };
r = {
...b,
errors: [...a.errors, ...b.errors],
timeout: a.timeout || b.timeout,
costUsd: a.costUsd + b.costUsd,
usage: Object.fromEntries(Object.keys(b.usage).map((k) => [k, (a.usage[k] || 0) + (b.usage[k] || 0)])),
setupMs: a.setupMs,
};
grade = gradeDialogue(w.dialogue, [a.calls, b.calls]);
} else {
r = await adapter.runTurn({ text: w.text, context: w.context || undefined, onCall: (c) => stubResult(w.suite, c, GEV_REALTIME_TOOLS) });
grade = w.suite === 'coverage' ? gradeCoverage(w.item, r.calls, r.text, GEV_REALTIME_TOOLS) : gradeCore(w.phrase, r.calls);
}
const row = {
type: 'turn', runId, provider: PROVIDER, model: MODEL, variant: VARIANT, cloud: CLOUD, rep, suite: w.suite,
phraseId: w.id, phrase: w.text,
expect: w.dialogue ? `t1 ${expectLabel(w.dialogue.first)} → t2 ${expectLabel(w.dialogue.second)}` : w.suite === 'coverage' ? w.item.expect : expectLabel(w.phrase),
context: w.context || undefined,
expectNone: Boolean(w.phrase?.expectNone), supported: w.item ? w.item.supported : undefined,
calls: r.calls, text: r.text.slice(0, 800), grade, turn1: turn1 || undefined,
tFirstTokenMs: r.tFirstTokenMs, tFirstCallMs: r.tFirstCallMs, tDoneMs: r.tDoneMs, setupMs: r.setupMs,
responses: r.responses, usage: r.usage, costUsd: r.costUsd, errors: r.errors, timeout: r.timeout,
local: r.local || undefined,
at: new Date().toISOString(),
};
appendRow(row);
if (CLOUD) { ledgerAdd(r.costUsd); turnCosts.push(r.costUsd); }
const verdict = w.suite === 'coverage' ? grade.verdict : (grade.ok ? 'PASS' : 'FAIL');
console.log(` [${verdict}] ${w.text} → ${turn1 ? `${turn1.calls.map((c) => c.name).join(',') || '(none)'} ⇒ ` : ''}${r.calls.map((c) => c.name).join(',') || '(none)'} tool@${r.tFirstCallMs ?? '—'}ms done@${r.tDoneMs}ms $${r.costUsd.toFixed(4)}${r.errors.length ? ` ERR ${r.errors[0]}` : ''}${r.timeout ? ' TIMEOUT' : ''}`);
if (r.errors.some((e) => /HTTP 4\d\d|close 100[78]|invalid|not found|model_not_found|does not exist/i.test(e)) && r.calls.length === 0 && !r.text) {
const same = readRows().filter((x) => x.type === 'turn' && x.runId === runId).slice(-3);
if (same.length === 3 && same.every((x) => x.errors?.length && !x.calls.length)) { stopReason = `3 consecutive hard errors: ${r.errors[0]}`; break outer; }
}
}
writeSummary();
}
await adapter.close();
if (PROVIDER === 'ollama' && !has('--keep-loaded')) {
await fetch(`${OLLAMA}/api/generate`, { method: 'POST', body: JSON.stringify({ model: MODEL, keep_alive: 0 }) }).catch(() => null);
}
if (stopReason) {
console.log(`STOPPED: ${stopReason}`);
appendRow({ type: 'stop', runId, provider: PROVIDER, model: MODEL, reason: stopReason, at: new Date().toISOString() });
}
const summary = writeSummary();
const mine = summary.models.find((m) => m.provider === PROVIDER && m.model === MODEL && (m.variant || null) === (VARIANT || null));
if (mine) console.log(`\n${mine.key}: core ${mine.core.accuracyPct}% | coverage acceptable ${mine.coverage.acceptablePct}% | p50 tool ${mine.latencyMs.toolCallP50}ms | $${mine.costUsd}`);
console.log(`results: ${RESULTS}\nsummary: ${path.join(OUT, 'summary.md')}\ncloud ledger: $${ledgerSpent().toFixed(3)}`);
}
main().catch((e) => {
console.error(e);
process.exitCode = 1;
});
scripts/qa-voice-routing.mjs
+1667 -361
View File
File diff suppressed because it is too large. Load diff
scripts/setup-doctor.mjs
+3 -1
View File
@@ -176,7 +176,9 @@ export function buildCapabilitySummary(
? 'Google Photorealistic 3D Tiles through Cesium ion; Bing and world-terrain stacks available'
: 'Esri World Imagery (keyless satellite basemap) with keyless terrain',
flights,
voice: configured('OPENAI_API_KEY') ? 'available' : 'off until an OpenAI key is added',
voice: configured('OPENAI_API_KEY')
? 'available'
: 'off until an OpenAI key is added, or a Codex ChatGPT sign-in is selected in Provider Settings (experimental)',
vessels: configured('AISSTREAM_API_KEY') ? 'live AISStream feed' : 'off until an AISStream key is added',
fires: configured('FIRMS_MAP_KEY') ? 'live NASA FIRMS feed' : 'off until a FIRMS key is added',
traffic: configured('TOMTOM_API_KEY') ? 'live TomTom flow' : 'built-in traffic simulation',
scripts/voice-bench/adapters/geminiLive.mjs
+179
View File
@@ -0,0 +1,179 @@
/**
* Gemini Live adapter — BidiGenerateContent over WebSocket.
*
* Same prompt as production (system instruction = realtimeInstructions(),
* tools = GEV_REALTIME_TOOLS as functionDeclarations with the production JSON
* schema passed verbatim via parametersJsonSchema). The native-audio Live
* model rejects a TEXT response modality (close 1007), so the session
* requests AUDIO with output transcription on; tool calls arrive as
* `toolCall` messages and the transcript stands in for the final words.
*
* Fresh session per phrase / dialogue. Each toolCall gets stub
* `functionResponses`; the model continues on its own. A turn ends at a
* `turnComplete` whose generation had no toolCall, or after 5 tool rounds
* (mirrors the Realtime adapter's continuation cap), or 12 s of silence after
* a tool round.
*/
import WebSocket from 'ws';
import { providerKey } from '../keys.mjs';
import { realtimeInstructions, GEV_REALTIME_TOOLS } from '../productionConfig.mjs';
import { toGeminiDeclarations } from '../toolFormats.mjs';
import { geminiUsageCostUsd } from '../pricing.mjs';
import { newTurnResult } from './openaiRealtime.mjs';
const ENDPOINT = 'wss://generativelanguage.googleapis.com/ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent';
const MAX_TOOL_ROUNDS = 5;
const IDLE_AFTER_TOOL_MS = 12_000;
export function createGeminiLiveAdapter({ model, schemaMode = 'jsonSchema', turnTimeoutMs = 60_000 }) {
const instructions = realtimeInstructions();
const functionDeclarations = toGeminiDeclarations(GEV_REALTIME_TOOLS, { mode: schemaMode });
const adapter = {
provider: 'gemini-live',
model,
settings: {
responseModalities: ['AUDIO'],
outputAudioTranscription: true,
schemaMode,
temperature: 'server default (not set; production has no Gemini config)',
thinking: 'server default',
input: 'realtimeInput.text',
context: 'fresh session per phrase / dialogue',
},
async open() {},
async close() {},
async runTurn({ text, onCall, context }) {
return (await adapter.runDialogue({ turns: [text], onCall, contexts: [context] }))[0];
},
runDialogue({ turns, onCall, contexts = [] }) {
return new Promise((resolveAll) => {
const tSetup = Date.now();
const ws = new WebSocket(`${ENDPOINT}?key=${providerKey('gemini')}`);
const results = [];
let setupMs = null;
let cur = null;
let closed = false;
const send = (o) => { if (ws.readyState === WebSocket.OPEN) ws.send(JSON.stringify(o)); };
const shutdown = (error) => {
if (closed) return;
closed = true;
if (cur) {
clearTimeout(cur.timer);
clearTimeout(cur.idle);
if (error) cur.r.errors.push(error);
if (cur.r.tDoneMs === null) cur.r.tDoneMs = Date.now() - cur.t0;
results.push(cur.r);
cur = null;
}
while (results.length < turns.length) {
const r = newTurnResult();
r.errors.push(error || 'dialogue aborted');
results.push(r);
}
try { ws.terminate(); } catch { /* noop */ }
resolveAll(results);
};
const startTurn = (turn) => {
const r = newTurnResult();
r.setupMs = turn === 0 ? setupMs : 0;
cur = { r, t0: Date.now(), turn, toolRounds: 0, toolCallThisGeneration: false, idle: null };
cur.timer = setTimeout(() => { cur.r.timeout = true; endTurn(); }, turnTimeoutMs);
// Live has no system-role mid-session item; a context item (pointer_context)
// rides as a JSON line ahead of the user's words in the same text turn.
const ctx = contexts[turn] ? `${JSON.stringify(contexts[turn])}\n` : '';
send({ realtimeInput: { text: `${ctx}${turns[turn]}` } });
};
const endTurn = () => {
if (!cur) return;
clearTimeout(cur.timer);
clearTimeout(cur.idle);
if (cur.r.tDoneMs === null) cur.r.tDoneMs = Date.now() - cur.t0;
results.push(cur.r);
const next = cur.turn + 1;
const timedOut = cur.r.timeout;
cur = null;
if (next < turns.length && !timedOut) startTurn(next);
else shutdown();
};
const mark = (key) => { if (cur && cur.r[key] === null) cur.r[key] = Date.now() - cur.t0; };
ws.on('open', () => {
send({
setup: {
model: `models/${model}`,
generationConfig: { responseModalities: ['AUDIO'] },
systemInstruction: { parts: [{ text: instructions }] },
tools: [{ functionDeclarations }],
outputAudioTranscription: {},
},
});
});
ws.on('unexpected-response', (_req, res) => shutdown(`HTTP ${res.statusCode}`));
ws.on('error', (e) => shutdown(`ws: ${e.message}`));
ws.on('close', (code, reason) => {
shutdown(results.length < turns.length ? `close ${code}: ${reason.toString().slice(0, 200)}` : undefined);
});
ws.on('message', (raw) => {
let m;
try { m = JSON.parse(raw.toString()); } catch { return; }
if (m.setupComplete) {
if (setupMs === null) {
setupMs = Date.now() - tSetup;
startTurn(0);
}
return;
}
if (!cur) return;
clearTimeout(cur.idle);
const r = cur.r;
const lastAt = Date.now();
const sc = m.serverContent;
if (sc?.modelTurn?.parts?.length) {
mark('tFirstTokenMs');
for (const p of sc.modelTurn.parts) if (typeof p.text === 'string' && !p.thought) r.text += p.text;
}
if (sc?.outputTranscription?.text) {
mark('tFirstTokenMs');
r.text += sc.outputTranscription.text;
}
if (m.toolCall?.functionCalls?.length) {
mark('tFirstTokenMs');
mark('tFirstCallMs');
cur.toolCallThisGeneration = true;
cur.toolRounds += 1;
const functionResponses = m.toolCall.functionCalls.map((fc) => {
const c = { name: fc.name, args: fc.args || {}, atMs: Date.now() - cur.t0 };
r.calls.push(c);
return { id: fc.id, name: fc.name, response: onCall(c, cur.turn) };
});
send({ toolResponse: { functionResponses } });
}
if (m.usageMetadata) {
const u = m.usageMetadata;
r.usage.inputTokens += u.promptTokenCount || 0;
r.usage.cachedTokens += u.cachedContentTokenCount || 0;
r.usage.outputTokens += u.responseTokenCount || 0;
r.usage.reasoningTokens += u.thoughtsTokenCount || 0;
r.costUsd += geminiUsageCostUsd(model, u);
}
if (m.goAway) r.errors.push('goAway');
if (sc?.turnComplete) {
r.responses += 1;
if (cur.toolCallThisGeneration && cur.toolRounds < MAX_TOOL_ROUNDS) {
cur.toolCallThisGeneration = false;
if (r.text && !r.text.endsWith(' | ')) r.text += ' | ';
// The follow-up generation normally starts within a second; if
// the model has nothing more to say, end the turn at its last
// message rather than charging the wait to its latency.
const c = cur;
c.idle = setTimeout(() => { if (cur === c) { c.r.tDoneMs = lastAt - c.t0; endTurn(); } }, IDLE_AFTER_TOOL_MS);
return;
}
endTurn();
}
});
});
},
};
return adapter;
}
scripts/voice-bench/adapters/localChat.mjs
+263
View File
@@ -0,0 +1,263 @@
/**
* Local-model adapters: stateless chat requests, so every phrase is a fresh
* context by construction. Same system prompt (realtimeInstructions()) and
* the production tools converted with toChatTools() (schema-normalized).
*
* openai-chat any OpenAI-compatible server (LM Studio :1234/v1, Ollama
* :11434/v1). Streams SSE; timing is client-side.
* ollama Ollama's native /api/chat. Same message and tool formats as
* Chat Completions, but it can set num_ctx (the OpenAI shim
* cannot — the ~15k-token prompt would be silently truncated
* at a small default context) and turn thinking off, and it
* reports server-side prefill/decode/load timings.
*
* Both mirror the Realtime loop: stub tool results, then continue until a
* response has no tool calls, up to 4 continuations.
*/
import { realtimeInstructions, GEV_REALTIME_TOOLS } from '../productionConfig.mjs';
import { toChatTools } from '../toolFormats.mjs';
const MAX_CONTINUATIONS = 4;
function emptyResult() {
return {
calls: [], text: '', errors: [], responses: 0,
usage: { inputTokens: 0, cachedTokens: 0, outputTokens: 0, reasoningTokens: 0 },
costUsd: 0, tFirstTokenMs: null, tFirstCallMs: null, tDoneMs: null, setupMs: 0, timeout: false,
local: { prefillTokS: null, decodeTokS: null, promptEvalCount: null, evalCount: null, loadMs: null, firstResponseMs: null },
};
}
function parseArgs(raw) {
if (raw && typeof raw === 'object') return raw;
try { return JSON.parse(raw || '{}'); } catch { return { __unparsed: String(raw).slice(0, 400) }; }
}
async function* lines(body) {
const decoder = new TextDecoder();
let buf = '';
for await (const chunk of body) {
buf += decoder.decode(chunk, { stream: true });
let i;
while ((i = buf.indexOf('\n')) >= 0) {
yield buf.slice(0, i);
buf = buf.slice(i + 1);
}
}
if (buf.trim()) yield buf;
}
/**
* Shared multi-response loop over one or more user turns in ONE growing
* message history. `request(messages, r, t0, first, deadline)` performs one
* streamed completion and returns `{ content, toolCalls:[{id,name,args}] }`.
*/
async function runChatDialogue({ turns, onCall, request, turnTimeoutMs, contexts = [] }) {
const messages = [{ role: 'system', content: realtimeInstructions() }];
const results = [];
for (let turn = 0; turn < turns.length; turn += 1) {
const r = emptyResult();
if (contexts[turn]) messages.push({ role: 'system', content: JSON.stringify(contexts[turn]) });
messages.push({ role: 'user', content: turns[turn] });
const t0 = Date.now();
const deadline = t0 + turnTimeoutMs;
try {
for (let round = 0; round <= MAX_CONTINUATIONS; round += 1) {
if (Date.now() > deadline) { r.timeout = true; break; }
const out = await request(messages, r, t0, round === 0, deadline);
r.responses += 1;
if (out.content) r.text += (r.text ? ' | ' : '') + out.content.trim();
if (!out.toolCalls.length) {
messages.push({ role: 'assistant', content: out.content || '' });
break;
}
messages.push({ role: 'assistant', content: out.content || '', tool_calls: out.toolCalls.map((tc) => tc.wire) });
for (const tc of out.toolCalls) {
const c = { name: tc.name, args: tc.args, atMs: tc.atMs };
r.calls.push(c);
messages.push({ role: 'tool', tool_call_id: tc.id, tool_name: tc.name, name: tc.name, content: JSON.stringify(onCall(c, turn)) });
}
}
} catch (e) {
if (e?.name === 'TimeoutError' || e?.name === 'AbortError') r.timeout = true;
else r.errors.push(String(e?.message || e).slice(0, 300));
}
r.tDoneMs = Date.now() - t0;
results.push(r);
if (r.timeout || r.errors.length) {
while (results.length < turns.length) {
const skipped = emptyResult();
skipped.errors.push('dialogue aborted after an earlier turn failed');
results.push(skipped);
}
break;
}
}
return results;
}
// ── OpenAI-compatible (SSE) ─────────────────────────────────────────────────
export function createOpenAiChatAdapter({ model, baseUrl, temperature = 0.8, extraBody = {}, turnTimeoutMs = 180_000, apiKey = 'local' }) {
const tools = toChatTools(GEV_REALTIME_TOOLS);
const request = async (messages, r, t0, first, deadline) => {
const res = await fetch(`${baseUrl.replace(/\/$/, '')}/chat/completions`, {
method: 'POST',
signal: AbortSignal.timeout(Math.max(1000, deadline - Date.now())),
headers: { 'Content-Type': 'application/json', Authorization: `Bearer ${apiKey}` },
body: JSON.stringify({
model, messages, tools, tool_choice: 'auto', temperature, stream: true,
stream_options: { include_usage: true }, ...extraBody,
}),
});
if (!res.ok) throw new Error(`HTTP ${res.status}: ${(await res.text()).slice(0, 300)}`);
const tStart = Date.now();
let tFirst = null;
let content = '';
const byIndex = new Map();
let usage = null;
let firstCallDoneAt = null;
for await (const line of lines(res.body)) {
if (!line.startsWith('data:')) continue;
const data = line.slice(5).trim();
if (data === '[DONE]') break;
let m;
try { m = JSON.parse(data); } catch { continue; }
if (m.usage) usage = m.usage;
const choice = m.choices?.[0];
const d = choice?.delta || {};
const now = Date.now();
if ((d.content || d.reasoning_content || d.reasoning || d.tool_calls?.length) && tFirst === null) {
tFirst = now;
if (r.tFirstTokenMs === null) r.tFirstTokenMs = now - t0;
}
if (d.content) content += d.content;
for (const tc of d.tool_calls || []) {
const idx = tc.index ?? byIndex.size;
if (idx > 0 && byIndex.has(0) && firstCallDoneAt === null) firstCallDoneAt = now;
const cur = byIndex.get(idx) || { id: tc.id || `call_${idx}`, name: '', argText: '' };
if (tc.id) cur.id = tc.id;
if (tc.function?.name) cur.name += tc.function.name;
if (tc.function?.arguments) cur.argText += typeof tc.function.arguments === 'string' ? tc.function.arguments : JSON.stringify(tc.function.arguments);
byIndex.set(idx, cur);
}
if (choice?.finish_reason && byIndex.size && firstCallDoneAt === null) firstCallDoneAt = now;
}
const tEnd = Date.now();
if (byIndex.size && firstCallDoneAt === null) firstCallDoneAt = tEnd;
if (byIndex.size && r.tFirstCallMs === null) r.tFirstCallMs = firstCallDoneAt - t0;
if (usage) {
r.usage.inputTokens += usage.prompt_tokens || 0;
r.usage.cachedTokens += usage.prompt_tokens_details?.cached_tokens || 0;
r.usage.outputTokens += usage.completion_tokens || 0;
r.usage.reasoningTokens += usage.completion_tokens_details?.reasoning_tokens || 0;
}
if (first) {
r.local.firstResponseMs = tEnd - tStart;
if (usage && tFirst) {
r.local.promptEvalCount = usage.prompt_tokens ?? null;
r.local.evalCount = usage.completion_tokens ?? null;
// Client-side approximations: prefill ≈ prompt / (request → first token);
// decode ≈ (completion − 1) / (first token → end of stream).
r.local.prefillTokS = usage.prompt_tokens ? usage.prompt_tokens / Math.max(0.001, (tFirst - tStart) / 1000) : null;
r.local.decodeTokS = usage.completion_tokens > 1 && tEnd > tFirst ? (usage.completion_tokens - 1) / ((tEnd - tFirst) / 1000) : null;
r.local.timingSource = 'client';
}
}
const toolCalls = [...byIndex.values()].map((tc) => ({
id: tc.id, name: tc.name, args: parseArgs(tc.argText), atMs: firstCallDoneAt - t0,
wire: { id: tc.id, type: 'function', function: { name: tc.name, arguments: tc.argText || '{}' } },
}));
return { content, toolCalls };
};
return {
provider: 'openai-chat',
model,
settings: { baseUrl, temperature, tool_choice: 'auto', toolSchema: 'normalized (untyped → string|number|boolean)', context: 'stateless request per phrase', ...extraBody },
async open() {},
async close() {},
runDialogue: ({ turns, onCall, contexts }) => runChatDialogue({ turns, onCall, contexts, request, turnTimeoutMs }),
runTurn: async ({ text, onCall, context }) => (await runChatDialogue({ turns: [text], onCall, contexts: [context], request, turnTimeoutMs }))[0],
};
}
// ── Ollama native (/api/chat, NDJSON) ───────────────────────────────────────
export function createOllamaAdapter({ model, baseUrl = 'http://localhost:11434', temperature = 0.8, numCtx = 32768, think = false, keepAlive = '30m', turnTimeoutMs = 300_000 }) {
const tools = toChatTools(GEV_REALTIME_TOOLS);
let thinkParam = think;
const request = async (messages, r, t0, first, deadline) => {
const wireMessages = messages.map((m) => {
if (m.role === 'assistant' && m.tool_calls) {
return { role: 'assistant', content: m.content, tool_calls: m.tool_calls.map((tc) => ({ function: { name: tc.function.name, arguments: parseArgs(tc.function.arguments) } })) };
}
if (m.role === 'tool') return { role: 'tool', tool_name: m.tool_name, content: m.content };
return m;
});
const body = { model, messages: wireMessages, tools, stream: true, keep_alive: keepAlive, options: { temperature, num_ctx: numCtx } };
if (thinkParam !== null) body.think = thinkParam;
const res = await fetch(`${baseUrl}/api/chat`, {
method: 'POST',
signal: AbortSignal.timeout(Math.max(1000, deadline - Date.now())),
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify(body),
});
if (!res.ok) {
const errText = await res.text();
if (/does not support thinking/i.test(errText) && thinkParam !== null) {
thinkParam = null;
return request(messages, r, t0, first, deadline);
}
throw new Error(`HTTP ${res.status}: ${errText.slice(0, 300)}`);
}
let content = '';
const toolCalls = [];
let final = null;
for await (const line of lines(res.body)) {
if (!line.trim()) continue;
let m;
try { m = JSON.parse(line); } catch { continue; }
if (m.error) throw new Error(m.error);
const now = Date.now();
const msg = m.message || {};
if ((msg.content || msg.thinking || msg.tool_calls?.length) && r.tFirstTokenMs === null) r.tFirstTokenMs = now - t0;
if (msg.content) content += msg.content;
for (const tc of msg.tool_calls || []) {
if (r.tFirstCallMs === null) r.tFirstCallMs = now - t0;
const i = `${messages.length}_${toolCalls.length}`;
const args = parseArgs(tc.function?.arguments);
toolCalls.push({
id: `call_${i}`, name: tc.function?.name, args, atMs: now - t0,
wire: { id: `call_${i}`, type: 'function', function: { name: tc.function?.name, arguments: JSON.stringify(args) } },
});
}
if (m.done) final = m;
}
if (final) {
r.usage.inputTokens += final.prompt_eval_count || 0;
r.usage.outputTokens += final.eval_count || 0;
if (first) {
const ns = 1e9;
r.local.promptEvalCount = final.prompt_eval_count ?? null;
r.local.evalCount = final.eval_count ?? null;
r.local.prefillTokS = final.prompt_eval_duration ? final.prompt_eval_count / (final.prompt_eval_duration / ns) : null;
r.local.decodeTokS = final.eval_duration ? final.eval_count / (final.eval_duration / ns) : null;
r.local.loadMs = final.load_duration ? final.load_duration / 1e6 : null;
r.local.firstResponseMs = final.total_duration ? final.total_duration / 1e6 : null;
r.local.timingSource = 'ollama';
}
}
return { content, toolCalls };
};
return {
provider: 'ollama',
model,
get settings() {
return { baseUrl, api: '/api/chat', temperature, num_ctx: numCtx, think: thinkParam === null ? 'unsupported by model (param omitted)' : thinkParam, keep_alive: keepAlive, toolSchema: 'normalized (untyped → string|number|boolean)', context: 'stateless request per phrase' };
},
async open() {},
async close() {},
runDialogue: ({ turns, onCall, contexts }) => runChatDialogue({ turns, onCall, contexts, request, turnTimeoutMs }),
runTurn: async ({ text, onCall, context }) => (await runChatDialogue({ turns: [text], onCall, contexts: [context], request, turnTimeoutMs }))[0],
};
}
scripts/voice-bench/adapters/openaiRealtime.mjs
+167
View File
@@ -0,0 +1,167 @@
/**
* OpenAI Realtime adapter — text turns over the Realtime WebSocket.
*
* Each dialogue (one phrase, or a multi-turn dialogue) opens a FRESH session
* configured with production's exact session body (captured from the token
* handler) and sends its user text items one turn at a time. Each turn
* mirrors qa-voice-routing's loop: every function call gets a stub output, and
* a continuation response is requested after `response.done` (never while a
* response is active), up to 4 continuations.
*/
import WebSocket from 'ws';
import { providerKey } from '../keys.mjs';
import { captureProductionSession } from '../productionConfig.mjs';
import { openAiUsageCostUsd } from '../pricing.mjs';
const MAX_CONTINUATIONS = 4;
export function newTurnResult() {
return {
calls: [], text: '', errors: [], responses: 0,
usage: { inputTokens: 0, cachedTokens: 0, outputTokens: 0, reasoningTokens: 0 },
costUsd: 0, tFirstTokenMs: null, tFirstCallMs: null, tDoneMs: null, setupMs: null, timeout: false,
};
}
export function createOpenAiRealtimeAdapter({ model, turnTimeoutMs = 45_000 }) {
let session = null;
const adapter = {
provider: 'openai-realtime',
model,
settings: {},
async open() {
session = await captureProductionSession(model);
adapter.settings = {
reasoning: session.reasoning,
truncation: session.truncation,
tool_choice: session.tool_choice,
temperature: 'not settable (GA Realtime session has no temperature field)',
output_modalities: ['text'],
context: 'fresh session per phrase / dialogue',
};
},
async close() {},
async runTurn({ text, onCall, context }) {
return (await adapter.runDialogue({ turns: [text], onCall, contexts: [context] }))[0];
},
runDialogue({ turns, onCall, contexts = [] }) {
return new Promise((resolveAll) => {
const tSetup = Date.now();
const ws = new WebSocket(`wss://api.openai.com/v1/realtime?model=${encodeURIComponent(model)}`, {
headers: { Authorization: `Bearer ${providerKey('openai')}` },
});
const results = [];
let setupMs = null;
let cur = null; // { r, t0, continuations, needContinuation, turn, timer }
let closed = false;
const send = (o) => { if (ws.readyState === WebSocket.OPEN) ws.send(JSON.stringify(o)); };
const shutdown = (error) => {
if (closed) return;
closed = true;
if (cur) {
clearTimeout(cur.timer);
if (error) cur.r.errors.push(error);
cur.r.tDoneMs = Date.now() - cur.t0;
results.push(cur.r);
cur = null;
}
while (results.length < turns.length) {
const r = newTurnResult();
r.errors.push(error || 'dialogue aborted');
results.push(r);
}
try { ws.terminate(); } catch { /* noop */ }
resolveAll(results);
};
const startTurn = (turn) => {
const r = newTurnResult();
r.setupMs = turn === 0 ? setupMs : 0;
cur = { r, t0: Date.now(), continuations: 0, needContinuation: false, turn };
cur.timer = setTimeout(() => { cur.r.timeout = true; endTurn(); }, turnTimeoutMs);
// Optional inert system item first (the app's pointer_context shape).
if (contexts[turn]) send({ type: 'conversation.item.create', item: { type: 'message', role: 'system', content: [{ type: 'input_text', text: JSON.stringify(contexts[turn]) }] } });
send({ type: 'conversation.item.create', item: { type: 'message', role: 'user', content: [{ type: 'input_text', text: turns[turn] }] } });
send({ type: 'response.create', response: { output_modalities: ['text'] } });
};
const endTurn = () => {
if (!cur) return;
clearTimeout(cur.timer);
cur.r.tDoneMs = Date.now() - cur.t0;
results.push(cur.r);
const next = cur.turn + 1;
const timedOut = cur.r.timeout;
cur = null;
if (next < turns.length && !timedOut) startTurn(next);
else shutdown();
};
const mark = (key) => { if (cur && cur.r[key] === null) cur.r[key] = Date.now() - cur.t0; };
ws.on('unexpected-response', (_req, res) => shutdown(`HTTP ${res.statusCode}`));
ws.on('error', (e) => shutdown(`ws: ${e.message}`));
ws.on('close', () => shutdown(results.length < turns.length ? 'socket closed' : undefined));
ws.on('message', (raw) => {
let m;
try { m = JSON.parse(raw.toString()); } catch { return; }
if (m.type === 'session.created') {
send({ type: 'session.update', session });
return;
}
if (m.type === 'session.updated' && setupMs === null) {
setupMs = Date.now() - tSetup;
startTurn(0);
return;
}
if (m.type === 'error') {
if (!cur) { shutdown(m.error?.message || 'realtime error'); return; }
cur.r.errors.push(m.error?.message || 'realtime error');
return;
}
if (!cur) return;
const r = cur.r;
if (
m.type === 'response.output_text.delta' ||
m.type === 'response.function_call_arguments.delta' ||
m.type === 'response.output_audio_transcript.delta'
) mark('tFirstTokenMs');
if (m.type === 'response.output_text.delta' || m.type === 'response.output_audio_transcript.delta') {
r.text += m.delta || '';
}
if (m.type === 'response.output_item.done' && m.item?.type === 'function_call') {
mark('tFirstTokenMs');
mark('tFirstCallMs');
let args = {};
try { args = JSON.parse(m.item.arguments || '{}'); } catch { args = { __unparsed: m.item.arguments }; }
const c = { name: m.item.name, args, atMs: Date.now() - cur.t0 };
r.calls.push(c);
send({
type: 'conversation.item.create',
item: { type: 'function_call_output', call_id: m.item.call_id, output: JSON.stringify(onCall(c, cur.turn)) },
});
cur.needContinuation = true;
}
if (m.type === 'response.done') {
r.responses += 1;
const u = m.response?.usage;
if (u) {
r.usage.inputTokens += u.input_tokens || 0;
r.usage.cachedTokens += u.input_token_details?.cached_tokens || 0;
r.usage.outputTokens += u.output_tokens || 0;
r.usage.reasoningTokens += u.output_token_details?.reasoning_tokens || 0;
r.costUsd += openAiUsageCostUsd(model, u);
}
if (m.response?.status === 'failed') r.errors.push(JSON.stringify(m.response?.status_details).slice(0, 200));
if (cur.needContinuation && cur.continuations < MAX_CONTINUATIONS) {
cur.needContinuation = false;
cur.continuations += 1;
if (r.text) r.text += ' | ';
send({ type: 'response.create', response: { output_modalities: ['text'] } });
return;
}
endTurn();
}
});
});
},
};
return adapter;
}
scripts/voice-bench/baseline-tools-4b56d0e9.json
+1
View File
@@ -0,0 +1 @@
[{"type":"function","name":"fly_to_location","description":"Fly the God's Eye View camera to a known city, geocoded country/region/city/landmark, or explicit WGS84 coordinate. Countries/cities frame the whole place; landmarks/buildings use close framing.","parameters":{"type":"object","additionalProperties":false,"properties":{"locationId":{"type":"string","enum":["austin","sf","nyc","tokyo","london","paris","dubai","dc"],"description":"Known city preset ID. Use when the requested place matches one of these cities."},"query":{"type":"string","description":"Plain place search query, e.g. \"London\", \"Eiffel Tower\", or \"Dubai Marina\"."},"latitude":{"type":"number","minimum":-90,"maximum":90},"longitude":{"type":"number","minimum":-180,"maximum":180},"viewMode":{"type":"string","enum":["close","overview"],"description":"Optional framing intent. Usually omit this; GEV infers whole-place framing for countries/cities and close framing for landmarks."},"rangeM":{"type":"number","minimum":100,"maximum":20000000,"description":"Optional camera range from the target in meters. Omit it for automatic whole-country/whole-city or close-landmark framing; provide it only when the user explicitly requests a numeric height or distance."},"waitForArrival":{"type":"boolean","description":"Set true when a later tool depends on the destination viewport. The result then waits for the camera flight and returns arrived=true; cancellation returns ok=false."}}}},{"type":"function","name":"select_nearest_aircraft","description":"Atomically fly to a place, wait for arrival, enable and load Flights or Military Flights in that viewport, exclude on-ground records, and select/follow the nearest airborne aircraft. Healthy fallback feeds remain usable and are reported in the result. This does not open Contacts or Cockpit.","parameters":{"type":"object","additionalProperties":false,"properties":{"layerId":{"type":"string","enum":["flights","military"],"description":"Aircraft layer to enable and search. Use flights unless the user explicitly asks for military aircraft."},"locationId":{"type":"string","enum":["austin","sf","nyc","tokyo","london","paris","dubai","dc"],"description":"Known city preset ID when the place matches one of these cities."},"locationQuery":{"type":"string","maxLength":160,"description":"Free-form destination when no locationId matches."},"latitude":{"type":"number","minimum":-90,"maximum":90},"longitude":{"type":"number","minimum":-180,"maximum":180}},"required":["layerId"]}},{"type":"function","name":"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.","parameters":{"type":"object","additionalProperties":false,"properties":{"direction":{"type":"string","enum":["in","out"]},"amount":{"type":"string","enum":["little","medium","lot"],"description":"Use little for phrases like \"a bit\" or \"a little\", medium for ordinary zoom requests, and lot for \"way out/in\"."}},"required":["direction","amount"]}},{"type":"function","name":"zoom_to_globe","description":"Pull the camera out to an ABSOLUTE full-Earth globe view (~18,000 km altitude, the whole planet in frame), keeping the current region centered. Use for \"globe view\", \"whole earth\", \"see the planet\", \"zoom all the way out\". Never use adjust_camera_zoom for these — its relative steps cannot reach the globe.","parameters":{"type":"object","additionalProperties":false,"properties":{}}},{"type":"function","name":"set_layer_visibility","description":"Enable or disable one registered God's Eye View data layer.","parameters":{"type":"object","additionalProperties":false,"properties":{"layerId":{"type":"string","description":"Common-name mapping for the non-obvious ids: space mission(s) → rocket-launches; fires/wildfires/active fires → local-firms (NASA FIRMS); ships/vessels/boats → ais-live-vessels; undersea/submarine cables → telegeography-submarine-cables; datacenters → local-datacenters; dams → local-dams; bikes/bike share → bikeshare; street traffic/congestion → traffic; traffic cameras → cctv; internet radio/stations → radio; ALPR/license plate readers/Flock cameras → alpr-cameras; local ADS-B/my receiver/my antenna (aircraft heard by a local RTL-SDR receiver) → local-adsb.","enum":["flights","military","earthquakes","satellites","rocket-launches","traffic","cctv","radio","bikeshare","ais-live-vessels","local-datacenters","local-dams","telegeography-submarine-cables","local-firms","alpr-cameras","local-adsb"]},"enabled":{"type":"boolean"}},"required":["layerId","enabled"]}},{"type":"function","name":"show_data_layers_menu","description":"Open the data layers dropdown/menu and optionally scroll to a specific layer row without toggling it.","parameters":{"type":"object","additionalProperties":false,"properties":{"layerId":{"type":"string","enum":["flights","military","earthquakes","satellites","traffic","ccLine truncated
scripts/voice-bench/grade.mjs
+289
View File
@@ -0,0 +1,289 @@
/**
* Pure grading for voice-routing runs. No I/O, no network.
*
* `gradeCore` reproduces the pass/fail semantics of the routing layer in
* `scripts/qa-voice-routing.mjs` (which now calls it), plus a few extra
* benchmark signals. `gradeCoverage` sorts coverage-probe turns into
* correct / honest-refusal / hallucinated-capability / wrong-tool.
*/
/**
* Spot-check `expected` against `actual` args: substring match (case
* insensitive) for strings, exact match for everything else. An array value
* is matched through its comma-joined string form, so `{ layers: 'earthquakes' }`
* matches `layers: ['earthquakes']`.
*/
import { GEV_ACTION_SCHEMAS } from '../../src/voice/actionSchemas.js';
export function matchArgs(expected, actual) {
return Object.entries(expected).every(([k, v]) => {
const got = actual?.[k];
if (typeof v === 'string') return String(got ?? '').toLowerCase().includes(v.toLowerCase());
return got === v;
});
}
/** Build a call matcher: tool name plus optional arg spot-check. */
export function call(name, args) {
const matcher = (c) => c?.name === name && (!args || matchArgs(args, c.args));
matcher.toolName = name;
return matcher;
}
/** Build a call matcher from a tool name and a predicate over its args. */
export function where(name, predicate) {
const matcher = (c) => c?.name === name && Boolean(predicate(c.args || {}));
matcher.toolName = name;
return matcher;
}
/** Human label for a phrase's expectation. */
export function expectLabel(phrase) {
if (phrase.expectNone) return '(no tool)';
if (Array.isArray(phrase.expect)) return phrase.expect.join('+');
if (phrase.expect?.oneOf) return phrase.expect.oneOf.join('|');
return String(phrase.expect);
}
/** Every tool name that satisfies a phrase (union for oneOf / arrays). */
export function expectedToolNames(phrase) {
if (phrase.expectNone) return [];
if (Array.isArray(phrase.expect)) return [...phrase.expect];
if (phrase.expect?.oneOf) return [...phrase.expect.oneOf];
return [phrase.expect];
}
/**
* Grade one core-suite turn.
*
* `ok` is exactly the qa-voice-routing verdict: expectNone passes only with no
* calls; an array needs every tool; oneOf needs any; a string needs that tool;
* then `args` / `argsByTool` spot checks. The rest are benchmark extras:
* toolOk tool-name routing alone (before the args check)
* argsOk null when the phrase has no arg spot check
* firstCallOk the FIRST call was an expected tool (what a user sees first)
* falsePositive a conversational turn produced a tool call
* extraCalls calls to tools outside the expected set
* typedArgsOk benchmark-only typed-argument check (`typedArgs`: exact
* enum values, layer ids, numeric thresholds, sort order);
* null when the phrase has none. Not part of `ok`.
* fullCallOk toolOk and every arg check (args, argsByTool, typedArgs)
*/
export function gradeCore(phrase, calls) {
const names = calls.map((c) => c.name);
if (phrase.expectNone) {
return {
ok: names.length === 0,
toolOk: names.length === 0,
fullCallOk: names.length === 0,
argsOk: null,
typedArgsOk: null,
firstCallOk: names.length === 0,
falsePositive: names.length > 0,
extraCalls: names,
detail: names.length ? `unexpected calls: ${names.join(',')}` : 'clean conversational turn',
};
}
const expected = expectedToolNames(phrase);
let toolOk;
if (Array.isArray(phrase.expect)) toolOk = phrase.expect.every((n) => names.includes(n));
else if (phrase.expect?.oneOf) toolOk = names.some((n) => phrase.expect.oneOf.includes(n));
else toolOk = names.includes(phrase.expect);
let detail = `called: ${names.join(',') || '(none)'}`;
let argsOk = null;
if (phrase.args) {
const target = calls.find((c) => (Array.isArray(phrase.expect) ? true : expected.includes(c.name)));
argsOk = Boolean(target) && matchArgs(phrase.args, target.args);
if (toolOk && !argsOk) detail += ` args mismatch: ${JSON.stringify(target?.args)}`;
}
if (phrase.argsByTool) {
let allOk = true;
for (const [toolName, expectedArgs] of Object.entries(phrase.argsByTool)) {
const target = calls.find((c) => c.name === toolName);
if (!target || !matchArgs(expectedArgs, target.args)) {
allOk = false;
if (toolOk) detail += ` ${toolName} args mismatch: ${JSON.stringify(target?.args)}`;
}
}
argsOk = argsOk === null ? allOk : argsOk && allOk;
}
const typedArgsOk = phrase.typedArgs ? phrase.typedArgs.every((m) => calls.some((c) => m(c))) : null;
if (toolOk && typedArgsOk === false) detail += ` typed args miss: ${JSON.stringify(calls.map((c) => c.args)).slice(0, 200)}`;
return {
ok: toolOk && argsOk !== false,
toolOk,
fullCallOk: toolOk && argsOk !== false && typedArgsOk !== false,
argsOk,
typedArgsOk,
firstCallOk: names.length > 0 && expected.includes(names[0]),
falsePositive: false,
extraCalls: names.filter((n) => !expected.includes(n)),
detail,
};
}
/**
* Grade a two-turn dialogue from each turn's calls. The headline `ok` is
* turn 2's full-call accuracy (tool + typed args), since turn 2 is the one
* that depends on context; turn 1 is reported alongside.
*/
export function gradeDialogue(dialogue, turnCalls) {
const turn1 = gradeCore(dialogue.first, turnCalls[0] || []);
const turn2 = gradeCore(dialogue.second, turnCalls[1] || []);
return {
ok: turn2.fullCallOk,
toolOk: turn2.toolOk,
fullCallOk: turn2.fullCallOk,
turn1Ok: turn1.fullCallOk,
turn1,
turn2,
detail: `t1 ${turn1.detail} | t2 ${turn2.detail}`,
};
}
// ── JSON-schema argument validation (the subset GEV tools use) ─────────────
const TYPE_CHECKS = {
string: (v) => typeof v === 'string',
number: (v) => typeof v === 'number' && Number.isFinite(v),
integer: (v) => Number.isInteger(v),
boolean: (v) => typeof v === 'boolean',
object: (v) => v !== null && typeof v === 'object' && !Array.isArray(v),
array: (v) => Array.isArray(v),
null: (v) => v === null,
};
/**
* Validate `value` against a JSON schema (type / enum / anyOf / required /
* properties / additionalProperties:false / items / min/max bounds).
* Returns a list of human-readable violations; empty means valid.
*/
export function validateArgs(schema, value, where = 'args') {
const errors = [];
if (!schema || typeof schema !== 'object') return errors;
if (schema.type) {
const types = Array.isArray(schema.type) ? schema.type : [schema.type];
if (!types.some((t) => TYPE_CHECKS[t]?.(value))) {
errors.push(`${where} should be ${types.join('|')}`);
return errors;
}
}
if (schema.enum && !schema.enum.includes(value)) {
errors.push(`${where}=${JSON.stringify(value)} is not one of ${schema.enum.join(', ')}`);
}
if (typeof value === 'string') {
if (typeof schema.minLength === 'number' && value.length < schema.minLength)
errors.push(`${where} needs at least ${schema.minLength} characters`);
if (typeof schema.pattern === 'string' && !new RegExp(schema.pattern).test(value))
errors.push(`${where} does not match ${schema.pattern}`);
}
if (typeof value === 'number') {
if (typeof schema.minimum === 'number' && value < schema.minimum) errors.push(`${where} below ${schema.minimum}`);
if (typeof schema.maximum === 'number' && value > schema.maximum) errors.push(`${where} above ${schema.maximum}`);
}
if (Array.isArray(value)) {
if (typeof schema.minItems === 'number' && value.length < schema.minItems) errors.push(`${where} needs ≥${schema.minItems} items`);
if (schema.items) value.forEach((item, i) => errors.push(...validateArgs(schema.items, item, `${where}[${i}]`)));
}
if (TYPE_CHECKS.object(value) && (schema.properties || schema.required)) {
for (const key of schema.required || []) {
if (!(key in value)) errors.push(`${where}.${key} is required`);
}
for (const [key, v] of Object.entries(value)) {
const sub = schema.properties?.[key];
if (!sub) {
if (schema.additionalProperties === false) errors.push(`${where}.${key} is not a known argument`);
continue;
}
errors.push(...validateArgs(sub, v, `${where}.${key}`));
}
}
if (Array.isArray(schema.anyOf)) {
const branches = schema.anyOf.map((branch) =>
validateArgs(branch, value, where),
);
if (!branches.some((branchErrors) => branchErrors.length === 0))
errors.push(`${where} does not match any allowed shape`);
}
return errors;
}
/** Validate a tool call against the Realtime tool list. */
export function validateCall(tools, c) {
const tool = tools.find((t) => t.name === c.name);
if (!tool) return [`unknown tool ${c.name}`];
// The runner validates app actions against their full schema, including
// top-level rules (anyOf) that the model-facing tools must omit.
const action = GEV_ACTION_SCHEMAS.find((schema) => schema.name === c.name);
const rules = action?.parameters
? { ...tool.parameters, anyOf: action.parameters.anyOf }
: tool.parameters;
if (!rules.anyOf) delete rules.anyOf;
return validateArgs(rules, c.args ?? {});
}
// ── Coverage probe grading ─────────────────────────────────────────────────
/** Tools that only read state; they never count as acting on the request. */
export const LOOKUP_TOOLS = Object.freeze([
'get_entity_context',
'get_current_view_state',
'show_data_layers_menu',
'set_panel_open',
]);
export const REFUSAL_RE =
/\b(can(?:no|')t|cannot|unable|not able|don'?t have|do not have|doesn'?t have|does not have|isn'?t (?:available|supported|something)|aren'?t (?:available|supported)|not (?:available|supported|possible|yet)|no (?:access|way|tool|data|layer|feed|live|transit|weather|wind|cyclone|radar|lightning|receiver)|n'?t (?:connected|see any|find)|(?:isn'?t|is no|are no) (?:an? )?(?:\w+ ){0,2}(?:layer|feed|tool|data source|integration)s?|outside what i can|beyond what i can|only (?:have|support|show|cover)|unfortunately|sorry)\b/i;
/**
* Grade one coverage-probe turn.
*
* Order matters:
* 1. a schema-invalid call (invented arg/tool) → hallucinated-capability
* 2. a call pattern in `correct` → correct
* 3. a pattern in `hallucinated` → hallucinated-capability
* 4. any other acting call (not lookup/neutral) → wrong-tool
* 5. no acting call: text matches `claimText`
* and no refusal wording → hallucinated-capability
* 6. no acting call: refusal wording or a question → honest-refusal
* 7. no acting call, no refusal → hallucinated-capability
* (it answered as if it had the data)
*
* `acceptable` = correct, or honest-refusal on an unsupported item.
*/
export function gradeCoverage(item, calls, text, tools = []) {
// Models write typographic apostrophes ("can’t"); fold them before matching.
const finalText = String(text || '').replace(/[\u2018\u2019\u02bc]/g, "'");
const verdict = (v, reason) => ({
verdict: v,
reason,
acceptable: v === 'correct' || (v === 'honest-refusal' && !item.supported),
});
if (tools.length) {
for (const c of calls) {
const errors = validateCall(tools, c);
if (errors.length) return verdict('hallucinated-capability', `invalid ${c.name}: ${errors[0]}`);
}
}
for (const alternative of item.correct || []) {
if (alternative.every((m) => calls.some((c) => m(c)))) {
return verdict('correct', `matched ${alternative.map((m) => m.toolName || 'pattern').join('+')}`);
}
}
for (const m of item.hallucinated || []) {
const hit = calls.find((c) => m(c));
if (hit) return verdict('hallucinated-capability', `faked capability via ${hit.name}(${JSON.stringify(hit.args).slice(0, 80)})`);
}
const neutral = new Set([...LOOKUP_TOOLS, ...(item.neutral || [])]);
const acting = calls.filter((c) => !neutral.has(c.name));
if (acting.length) return verdict('wrong-tool', `called ${acting.map((c) => c.name).join(',')}`);
const refused = REFUSAL_RE.test(finalText);
if (item.claimText && item.claimText.test(finalText) && !refused) {
return verdict('hallucinated-capability', 'asserted data it cannot have');
}
if (refused || /\?\s*$/.test(finalText.trim())) return verdict('honest-refusal', 'refused or asked');
if (!finalText.trim().replace(/\|/g, '').trim()) {
return verdict('wrong-tool', calls.length ? `only lookups/neutral calls (${calls.map((c) => c.name).join(',')}) and no answer` : 'no tool call and no answer');
}
return verdict('hallucinated-capability', 'answered without a tool or a refusal');
}
scripts/voice-bench/keys.mjs
+35
View File
@@ -0,0 +1,35 @@
/**
* Runtime key lookup for the voice benchmark. Keys are read from the
* environment, then the macOS Keychain, at call time. They are never written
* to results, logs, or files.
*/
import { execFileSync } from 'node:child_process';
const KEYCHAIN = {
openai: { env: 'OPENAI_API_KEY', service: 'openai-api', account: 'api-key' },
gemini: { env: 'GEMINI_API_KEY', service: 'gemini-api', account: 'api-key' },
};
const cache = new Map();
/** Resolve a provider key from the environment, then the Keychain. */
export function providerKey(provider) {
if (cache.has(provider)) return cache.get(provider);
const spec = KEYCHAIN[provider];
if (!spec) throw new Error(`unknown key provider: ${provider}`);
let value = process.env[spec.env] || '';
if (!value && process.platform === 'darwin') {
try {
value = execFileSync(
'security',
['find-generic-password', '-s', spec.service, '-a', spec.account, '-w'],
{ encoding: 'utf8', stdio: ['ignore', 'pipe', 'ignore'] },
).trim();
} catch {
value = '';
}
}
if (!value) throw new Error(`${spec.env} is not available (env or Keychain)`);
cache.set(provider, value);
return value;
}
scripts/voice-bench/phrases.mjs
+600
View File
@@ -0,0 +1,600 @@
/**
* Shared voice-routing phrase tables.
*
* CORE_PHRASES is the routing table used by `scripts/qa-voice-routing.mjs`
* (layer 1) and the core suite of `scripts/qa-voice-bench.mjs`.
*
* `expect` tool name the model must call (string), every tool in an
* array, or `{ oneOf: [...] }` for documented acceptable variance.
* `expectNone` conversational turns that must NOT call tools.
* `args` spot-check subset matched against the first matching call's
* args (substring match for strings, exact for booleans/numbers).
* `argsByTool` the same spot check, keyed by tool, for multi-intent phrases.
* `typedArgs` benchmark-only matchers for typed arguments (exact enum
* values, layer ids, thresholds, sort direction). They feed the
* benchmark's full-call accuracy and never change the
* qa-voice-routing verdict.
*
* COVERAGE_PROBE is the newer-layers coverage probe: utterances about layers
* and questions that today's tool surface only partly supports. Each item is
* graded into correct / honest-refusal / hallucinated-capability / wrong-tool
* by `gradeCoverage` in ./grade.mjs.
*/
import { call, where } from './grade.mjs';
export const CORE_PHRASES = Object.freeze([
// — navigation & framing —
{ phrase: 'Take me to Tokyo', expect: 'fly_to_location', typedArgs: [where('fly_to_location', (a) => a.locationId === 'tokyo' || /tokyo/i.test(a.query || ''))] },
{ phrase: 'Fly to the Golden Gate Bridge', expect: 'fly_to_location' },
{ phrase: 'Go to Sixth Street in Austin', expect: 'fly_to_location' },
{ phrase: 'Show me the Alps from above', expect: { oneOf: ['fly_to_location', 'frame_overhead'] } },
{ phrase: 'Zoom in a bit', expect: 'adjust_camera_zoom', typedArgs: [where('adjust_camera_zoom', (a) => a.direction === 'in' && a.amount === 'little')] },
{ phrase: 'Zoom out a little', expect: 'adjust_camera_zoom', typedArgs: [where('adjust_camera_zoom', (a) => a.direction === 'out' && a.amount === 'little')] },
{ phrase: 'Zoom out to a globe view', expect: 'zoom_to_globe' },
{ phrase: 'Show me the whole earth', expect: 'zoom_to_globe' },
{ phrase: 'Frame the aircraft near us from overhead', expect: 'frame_overhead', typedArgs: [where('frame_overhead', (a) => a.target === 'flights')] },
// — the satellites trap: data layer, never basemap —
{ phrase: 'Show me the satellites', expect: { oneOf: ['set_layer_visibility', 'frame_overhead'] } },
{ phrase: 'Turn off the satellites', expect: 'set_layer_visibility', args: { layerId: 'satellites' }, typedArgs: [where('set_layer_visibility', (a) => a.layerId === 'satellites' && a.enabled === false)] },
{ phrase: 'Switch to Bing aerial', expect: 'set_map_stack', typedArgs: [where('set_map_stack', (a) => a.stack === 'bing-aerial')] },
{ phrase: 'Switch the basemap to OSM', expect: 'set_map_stack', typedArgs: [where('set_map_stack', (a) => a.stack === 'osm')] },
// — layers —
{ phrase: 'Turn on the flights layer', expect: 'set_layer_visibility', args: { layerId: 'flights' }, typedArgs: [where('set_layer_visibility', (a) => a.layerId === 'flights' && a.enabled === true)] },
{ phrase: 'Show me live vessels', expect: 'set_layer_visibility', typedArgs: [where('set_layer_visibility', (a) => a.layerId === 'ais-live-vessels' && a.enabled === true)] },
{ phrase: 'Turn on the fires layer', expect: 'set_layer_visibility', typedArgs: [where('set_layer_visibility', (a) => a.layerId === 'local-firms' && a.enabled === true)] },
{ phrase: 'Turn on street traffic', expect: 'set_layer_visibility', args: { layerId: 'traffic' }, typedArgs: [where('set_layer_visibility', (a) => a.layerId === 'traffic' && a.enabled === true)] },
{ phrase: 'Open the data layers menu', expect: 'show_data_layers_menu' },
{ phrase: 'Show me the datacenter layers', expect: 'show_data_layers_menu', typedArgs: [where('show_data_layers_menu', (a) => a.layerId === 'local-datacenters')] },
{ phrase: 'Turn on the datacenters layer', expect: 'set_layer_visibility', typedArgs: [where('set_layer_visibility', (a) => a.layerId === 'local-datacenters' && a.enabled === true)] },
// — visual styles & post-fx —
{ phrase: 'Give me night vision', expect: 'set_visual_style', typedArgs: [where('set_visual_style', (a) => a.style === 'surveillance')] },
{ phrase: 'Switch to thermal view', expect: 'set_visual_style', typedArgs: [where('set_visual_style', (a) => a.style === 'thermal')] },
{ phrase: 'Back to the normal look', expect: 'set_visual_style', typedArgs: [where('set_visual_style', (a) => a.style === 'normal')] },
{ phrase: 'Turn on bloom', expect: 'set_post_processing', typedArgs: [where('set_post_processing', (a) => a.bloom?.enabled === true)] },
{ phrase: 'Sharpen the image a touch', expect: 'set_post_processing', typedArgs: [where('set_post_processing', (a) => a.sharpen && a.sharpen.enabled !== false)] },
// — HUD / detection / panels —
{ phrase: 'Turn the HUD off', expect: 'set_hud', typedArgs: [where('set_hud', (a) => a.visible === 'off')] },
{ phrase: 'Switch to the tactical layout', expect: 'set_hud', typedArgs: [where('set_hud', (a) => a.layout === 'tactical')] },
{ phrase: 'Turn on detection', expect: 'set_detection', typedArgs: [where('set_detection', (a) => a.enabled !== false)] },
{ phrase: 'Set detection density to fifty percent', expect: 'set_detection', typedArgs: [where('set_detection', (a) => a.densityPct === 50 || a.mode === 'balanced')] },
// — context questions —
{ phrase: 'What am I looking at right now?', expect: 'get_entity_context' },
{ phrase: 'What city is this below us?', expect: 'get_entity_context' },
{ phrase: 'Is there anything interesting in view?', expect: 'get_entity_context' },
// — tracking —
// Context-free text turns may reasonably look before tracking; either
// routing is correct (production sessions always carry screen context).
{ phrase: 'Track that plane', expect: { oneOf: ['track_entity', 'get_entity_context'] } },
// The session instructions route "nearest" through analyst_query first
// (sortBy distance, limit 1); stubbed results make that first hop the whole
// observable turn.
{ phrase: 'Follow the nearest aircraft', expect: { oneOf: ['track_entity', 'get_entity_context', 'analyst_query'] } },
{ phrase: 'Stop tracking', expect: 'stop_tracking' },
// — CCTV / scenes / ISS —
{ phrase: 'Show me the nearest traffic camera', expect: 'control_cctv', typedArgs: [where('control_cctv', (a) => a.action === 'nearest')] },
{ phrase: 'Turn on the camera viewsheds', expect: 'control_cctv', typedArgs: [where('control_cctv', (a) => a.action === 'viewshed' && a.enabled !== false)] },
{ phrase: 'Play a news radio station near Austin', expect: 'control_radio', args: { action: 'select', category: 'news', locationId: 'austin' }, typedArgs: [where('control_radio', (a) => a.action === 'select' && a.category === 'news' && a.locationId === 'austin')] },
{ phrase: 'Turn on the radio', expect: 'control_radio', args: { action: 'play' }, typedArgs: [where('control_radio', (a) => a.action === 'play')] },
{ phrase: 'Set the radio volume to thirty percent', expect: 'control_radio', args: { action: 'volume', volumePct: 30 } },
{ phrase: 'Pause the radio', expect: 'control_radio', args: { action: 'pause' }, typedArgs: [where('control_radio', (a) => a.action === 'pause')] },
{ phrase: 'Stop the radio', expect: 'control_radio', args: { action: 'stop' }, typedArgs: [where('control_radio', (a) => a.action === 'stop')] },
{ phrase: 'When does the ISS pass over next?', expect: 'next_iss_pass' },
// — annotations —
{ phrase: 'Annotate the Texas State Capitol and its grounds', expect: 'annotate_map', typedArgs: [where('annotate_map', (a) => (a.annotations || []).some((x) => x.type === 'area'))] },
{ phrase: 'Outline the state of Texas', expect: 'annotate_map', typedArgs: [where('annotate_map', (a) => (a.annotations || []).some((x) => x.type === 'area'))] },
{ phrase: 'Outline Lady Bird Lake', expect: 'annotate_map', typedArgs: [where('annotate_map', (a) => (a.annotations || []).some((x) => x.type === 'area'))] },
{ phrase: 'Draw the walking route from the Capitol to Zilker Park', expect: 'annotate_map', typedArgs: [where('annotate_map', (a) => (a.annotations || []).some((x) => x.type === 'route' && (x.mode ?? 'walking') === 'walking'))] },
{ phrase: 'How far is the Eiffel Tower from the Louvre?', expect: 'annotate_map', typedArgs: [where('annotate_map', (a) => (a.annotations || []).some((x) => x.type === 'arrow'))] },
{ phrase: 'Clear the map', expect: 'clear_annotations' },
// — multi-intent (assert ALL tools fire before speech) —
{
phrase: 'Switch to night vision and turn on the flights layer',
expect: ['set_visual_style', 'set_layer_visibility'],
typedArgs: [where('set_visual_style', (a) => a.style === 'surveillance'), where('set_layer_visibility', (a) => a.layerId === 'flights' && a.enabled === true)],
},
{
phrase: 'Turn off the HUD and take me to Paris',
expect: ['set_hud', 'fly_to_location'],
typedArgs: [where('set_hud', (a) => a.visible === 'off'), where('fly_to_location', (a) => a.locationId === 'paris' || /paris/i.test(a.query || ''))],
},
{
phrase: 'Go to full planet view and then turn on the radio',
expect: ['zoom_to_globe', 'control_radio'],
argsByTool: { control_radio: { action: 'play' } },
},
// — camera verbs (tools #23/#24) —
{ phrase: 'Orbit around this area slowly', expect: 'move_camera', typedArgs: [where('move_camera', (a) => a.motion === 'orbit' && a.speed === 'slow')] },
{ phrase: 'Pan left a bit', expect: 'move_camera', typedArgs: [where('move_camera', (a) => a.motion === 'pan' && a.direction === 'left')] },
{ phrase: 'Stop moving the camera', expect: 'move_camera', typedArgs: [where('move_camera', (a) => a.motion === 'stop')] },
{ phrase: 'Fly the route we just drew', expect: 'fly_route' },
// — analyst queries (tool #22) —
{ phrase: 'How many flights are over Texas right now?', expect: 'analyst_query', typedArgs: [where('analyst_query', (a) => (a.layers || []).includes('flights') && a.scope?.kind === 'region' && /texas/i.test(a.scope?.name || ''))] },
{ phrase: 'Which ships are headed to Oakland?', expect: 'analyst_query', typedArgs: [where('analyst_query', (a) => (a.layers || []).includes('ais-live-vessels') && (a.filters || []).some((f) => f.field === 'destination' && /oakland/i.test(String(f.value))))] },
{ phrase: 'What is the biggest fire near Los Angeles?', expect: 'analyst_query', typedArgs: [where('analyst_query', (a) => (a.layers || []).includes('local-firms') && ['frp', 'acres'].includes(a.sortBy) && a.sortDir !== 'asc')] },
{ phrase: 'Is anything flying above forty thousand feet?', expect: 'analyst_query', typedArgs: [where('analyst_query', (a) => (a.layers || []).some((l) => l === 'flights' || l === 'military') && (a.filters || []).some((f) => f.field === 'altitudeM' && (f.op === 'gt' || f.op === 'gte') && Math.abs(Number(f.value) - 12192) <= 50))] },
// — negative controls: conversation must NOT tool-call —
{ phrase: 'How is your evening going?', expectNone: true },
{ phrase: 'Tell me a fun fact about maps', expectNone: true },
]);
// ── Coverage probe ──────────────────────────────────────────────────────────
//
// Text-mode port of the voice-coverage routing probe. The live probe ran each
// utterance against a real app page (setup steps, real tool results); this
// benchmark has no app, so every item states the scene it assumes in `scene`
// and the model sees only stub tool results. Grading therefore judges the
// ROUTING DECISION and the honesty of the final words, not app behaviour.
//
// supported true when today's tools can satisfy the ask (a refusal is a
// miss); false when the best possible outcome is an honest
// refusal, optionally after a neutral helper call.
// correct call patterns that satisfy the ask (any alternative).
// neutral extra tools that neither help nor hurt (navigation to the
// named place, enabling a related layer that exists).
// hallucinated call patterns that fake the capability (e.g. toggling the
// satellites DATA layer for "recent satellite imagery").
// claimText final-text pattern that asserts data the model cannot have.
//
// Any call whose arguments violate the tool schema (an invented layer id) is
// graded hallucinated-capability regardless of the item.
//
// Two rubrics, so a before/after comparison stays honest:
// v1 the original rubric, graded against the tool schema of 4b56d0e9
// (baseline-tools-4b56d0e9.json) — "by the old yardstick".
// v2 `item.v2` overrides (supported / correct / hallucinated / neutral),
// graded against the CURRENT production tools after the voice layer
// manifest and point-and-ask landed. Use
// coverageRubric(item, 'v2') to get the merged item.
const hasRoute = (c) =>
c.name === 'annotate_map' &&
Array.isArray(c.args?.annotations) &&
c.args.annotations.some((a) => a?.type === 'route');
/** The coverage item as graded under rubric 'v1' (original) or 'v2' (current tools). */
export function coverageRubric(item, version = 'v1') {
if (version !== 'v2' || !item.v2) return item;
return { ...item, ...item.v2 };
}
export const COVERAGE_PROBE = Object.freeze([
{
id: 'quakes-m5-week',
v2: { supported: true },
utterance: 'Show me earthquakes above magnitude 5 this week',
scene: 'globe, no layers on',
expect: 'enable earthquakes + analyst_query magnitude>=5; must say feed covers last 24h only (no week)',
supported: true,
correct: [
[call('analyst_query', { layers: 'earthquakes' })],
[call('set_layer_visibility', { layerId: 'earthquakes', enabled: true })],
],
neutral: ['zoom_to_globe'],
},
{
id: 'trains-london',
v2: { supported: true, correct: [[call('analyst_query', { layers: 'transit' })], [call('set_layer_visibility', { layerId: 'transit', enabled: true })]], hallucinated: [] },
utterance: 'How many trains are moving in London right now?',
scene: 'London',
expect: 'honest "no transit data for London / transit not queryable" — no invented count',
supported: false,
neutral: ['fly_to_location'],
hallucinated: [call('analyst_query')],
claimText: /\b\d+\s+(trains?|services)\b/i,
},
{
id: 'transit-on',
v2: { supported: true, correct: [[call('set_layer_visibility', { layerId: 'transit', enabled: true })]] },
utterance: 'Turn on transit',
scene: 'Austin',
expect: 'set_layer_visibility transit (no transit id in the voice enum today) — honest otherwise',
supported: false,
hallucinated: [call('set_layer_visibility', { layerId: 'traffic', enabled: true })],
},
{
id: 'ship-fastest-singapore',
v2: { supported: true },
utterance: 'Which ship near Singapore is fastest?',
scene: 'Singapore Strait, vessels layer on',
expect: 'analyst_query ais-live-vessels near Singapore sortBy speedKts desc',
supported: true,
correct: [[call('analyst_query', { layers: 'ais-live-vessels' })]],
neutral: ['fly_to_location', 'set_layer_visibility'],
},
{
id: 'recent-imagery',
v2: { supported: true, correct: [[call('set_layer_visibility', { layerId: 'recent-imagery', enabled: true })]] },
utterance: 'Show recent satellite imagery of this area',
scene: 'Austin',
expect: 'enable recent-imagery for current view (no tool today) — must NOT toggle satellites data layer or silently switch basemap',
supported: false,
hallucinated: [
call('set_layer_visibility', { layerId: 'satellites' }),
call('set_map_stack'),
call('frame_overhead', { target: 'satellites' }),
],
},
{
id: 'wind-here',
v2: { supported: true, correct: [[call('set_layer_visibility', { layerId: 'wind', enabled: true })]] },
utterance: "What's the wind doing here?",
scene: 'Austin',
expect: 'enable/inspect wind layer at view centre (no tool today) — honest otherwise',
supported: false,
claimText: /\b\d+\s*(mph|km\/?h|knots?|kts|m\/s|meters per second|miles per hour)\b/i,
},
{
id: 'cyclones-active',
v2: { supported: true, correct: [[call('analyst_query', { layers: 'weather-cyclones' })], [call('set_layer_visibility', { layerId: 'weather-cyclones', enabled: true })]] },
utterance: 'Are there any cyclones active right now?',
scene: 'globe',
expect: 'enable cyclones + list active storms (no tool today) — honest otherwise',
supported: false,
claimText: /\b(there (are|is)|currently)\b[^.?!]*\b(cyclones?|storms?|hurricanes?|typhoons?)\b/i,
},
{
id: 'fires-in-drawn-area',
// There is no drawn-area scope yet; the prompt says to say so. Any count
// presented as inside the drawn area is a faked capability.
v2: {
supported: false,
correct: [],
hallucinated: [where('analyst_query', (a) => (a.layers || []).includes('local-firms'))],
},
utterance: 'Count the fires inside the area I drew',
scene: 'Los Angeles, fires layer on, an area drawn around Angeles National Forest',
expect: 'analyst_query local-firms scoped to the drawn polygon (no polygon scope today)',
supported: true,
correct: [[call('analyst_query', { layers: 'local-firms' })]],
},
{
id: 'local-adsb-on',
v2: { supported: true },
utterance: 'Turn on the local ADS-B layer',
scene: 'globe',
expect: 'set_layer_visibility local-adsb; narrate receiver state honestly',
supported: true,
correct: [[call('set_layer_visibility', { layerId: 'local-adsb', enabled: true })]],
},
{
id: 'bikes-near-me',
v2: { supported: true, correct: [[call('analyst_query', { layers: 'bikeshare' })]] },
utterance: 'How many bikes are available near me?',
scene: 'New York, bikeshare layer on',
expect: 'count available bikes at nearby stations (bikeshare not in analyst today) — honest otherwise',
supported: false,
neutral: ['set_layer_visibility'],
claimText: /\b\d+\s+(available\s+)?(bikes?|bicycles?)\b/i,
},
{
id: 'rocket-launch-track',
v2: { supported: true, correct: [[call('set_layer_visibility', { layerId: 'rocket-launches', enabled: true })], [call('set_context_mode', { mode: 'space-missions' })], [call('set_context_mode', { mode: 'missions' })], [call('analyst_query', { layers: 'rocket-launches' })]] },
utterance: 'Track the next rocket launch',
scene: 'globe',
expect: 'enable rocket-launches / space-missions and select next launch (track_entity cannot) — honest otherwise',
supported: true,
correct: [
[call('set_layer_visibility', { layerId: 'rocket-launches', enabled: true })],
[call('set_context_mode', { mode: 'space-missions' })],
[call('set_context_mode', { mode: 'missions' })],
],
hallucinated: [call('track_entity')],
},
{
id: 'weather-radar-on',
v2: { supported: true, correct: [[call('set_layer_visibility', { layerId: 'weather-radar', enabled: true })]] },
utterance: 'Turn on the weather radar',
scene: 'Austin',
expect: 'set_layer_visibility weather-radar (not in the voice enum today) — honest otherwise',
supported: false,
hallucinated: [call('set_map_stack'), call('set_visual_style')],
},
{
id: 'lightning',
v2: { supported: true, correct: [[call('set_layer_visibility', { layerId: 'weather-lightning', enabled: true })]] },
utterance: 'Show me lightning strikes',
scene: 'globe',
expect: 'set_layer_visibility weather-lightning (not in the voice enum today) — honest otherwise',
supported: false,
},
{
id: 'military-bases',
v2: { supported: true, correct: [[call('set_layer_visibility', { layerId: 'military-installations', enabled: true })], [call('analyst_query', { layers: 'military-installations' })]], hallucinated: [] },
utterance: 'Show military bases near here',
scene: 'San Diego',
expect: 'set_layer_visibility military-installations (not in the voice enum today) — honest otherwise',
supported: false,
hallucinated: [call('annotate_map')],
},
{
id: 'driving-directions',
v2: { supported: true, correct: [[hasRoute], [call('set_layer_visibility', { layerId: 'directions', enabled: true })]] },
utterance: 'Give me driving directions from the Texas Capitol to the Austin airport',
scene: 'Austin',
expect: 'annotate_map route driving (or directions layer)',
supported: true,
correct: [[hasRoute]],
neutral: ['fly_to_location'],
},
{
id: 'satellites-overhead-count',
v2: { supported: true },
utterance: 'How many satellites are overhead right now?',
scene: 'globe, satellites layer on',
expect: 'analyst_query satellites (control: supported)',
supported: true,
correct: [
[call('analyst_query', { layers: 'satellites' })],
[call('frame_overhead', { target: 'satellites' })],
],
neutral: ['set_layer_visibility'],
},
{
id: 'biggest-quake-today',
v2: { supported: true },
utterance: "What's the biggest earthquake today?",
scene: 'globe, earthquakes layer on',
expect: 'analyst_query earthquakes sortBy magnitude desc (control: supported)',
supported: true,
correct: [[call('analyst_query', { layers: 'earthquakes' })]],
neutral: ['set_layer_visibility'],
},
{
id: 'flock-on',
v2: { supported: true },
utterance: 'Turn on the Flock cameras',
scene: 'Austin',
expect: 'set_layer_visibility alpr-cameras (control: supported)',
supported: true,
correct: [[call('set_layer_visibility', { layerId: 'alpr-cameras', enabled: true })]],
hallucinated: [call('control_cctv')],
},
{
id: 'alpr-count',
v2: { supported: true, correct: [[call('analyst_query', { layers: 'alpr-cameras' })]] },
utterance: 'How many license plate cameras are around here?',
scene: 'Austin, ALPR layer on',
expect: 'count alpr-cameras in view (not in analyst today) — honest otherwise',
supported: false,
neutral: ['set_layer_visibility'],
claimText: /\b\d+\s+(license|plate|alpr|flock|cameras?)\b/i,
},
{
id: 'nearest-bus',
v2: { supported: true, correct: [[call('analyst_query', { layers: 'transit' })]] },
utterance: 'Which bus is closest to the center of the screen?',
scene: 'Austin, transit layer on',
expect: 'nearest transit vehicle (no transit query/context today) — honest otherwise',
supported: false,
claimText: /\b(route|bus|line)\s+#?\d+\b/i,
},
{
id: 'weather-replay',
v2: { supported: false, hallucinated: [call('control_scene')] },
utterance: 'Replay the last hour of weather radar',
scene: 'globe',
expect: 'weather clock replay (no time tool today) — honest refusal',
supported: false,
},
{
id: 'receiver-count',
v2: { supported: true, correct: [[call('analyst_query', { layers: 'local-adsb' })]], hallucinated: [call('frame_overhead')] },
utterance: 'How many aircraft is my receiver picking up?',
scene: 'globe, no receiver connected',
expect: 'count local-adsb (not in analyst) — honest: no receiver connected',
supported: false,
neutral: ['set_layer_visibility'],
hallucinated: [call('analyst_query'), call('frame_overhead')],
claimText: /\b\d+\s+(aircraft|planes?|contacts?)\b/i,
},
{
id: 'nearest-traffic-camera',
v2: { supported: true },
utterance: 'Show me the nearest traffic camera',
scene: 'Austin',
expect: 'control_cctv nearest (control: supported)',
supported: true,
correct: [[call('control_cctv', { action: 'nearest' })]],
neutral: ['set_layer_visibility'],
},
{
id: 'hurricane-strongest',
v2: { supported: true, correct: [[call('set_layer_visibility', { layerId: 'weather-cyclones', enabled: true }), call('analyst_query', { layers: 'weather-cyclones' })], [call('analyst_query', { layers: 'weather-cyclones' })]], hallucinated: [] },
utterance: 'Turn on the hurricane tracks and fly me to the strongest storm',
scene: 'globe',
expect: 'enable cyclones + fly to strongest (no tool today) — honest otherwise',
supported: false,
hallucinated: [call('fly_to_location')],
},
]);
// ── Multi-turn dialogues ───────────────────────────────────────────────────
//
// Two-turn dialogues where turn 2 only makes sense given turn 1. Both turns
// run in ONE session/context. Turn 1's tools get the plausible canned results
// in `results` (anything not listed gets the neutral stub), so turn 2 has
// something real to refer back to. `first` and `second` use the CORE_PHRASES
// grading shape (expect / oneOf / expectNone / typedArgs); the headline score
// is turn 2's full-call accuracy.
const flightsTexas = {
ok: true,
count: 212,
scopeLabel: '212 flights over Texas',
feedProvenance: { overall: 'nominal' },
examples: [
{ callsign: 'AAL1402', operator: 'American Airlines', altitudeM: 10972, military: false },
{ callsign: 'SWA2210', operator: 'Southwest Airlines', altitudeM: 11278, military: false },
{ callsign: 'RCH451', operator: 'US Air Force', altitudeM: 9144, military: true },
],
coverage: 'Counts cover data loaded by enabled layers.',
};
const shipsOakland = {
ok: true,
count: 4,
scopeLabel: '4 ships headed to Oakland',
feedProvenance: { overall: 'nominal' },
examples: [
{ name: 'MAERSK KENSINGTON', destination: 'OAKLAND', speedKts: 14.2, distanceKm: 180 },
{ name: 'EVER LOVELY', destination: 'OAKLAND', speedKts: 16.8, distanceKm: 410 },
{ name: 'APL SINGAPURA', destination: 'OAKLAND', speedKts: 12.1, distanceKm: 62 },
],
};
export const DIALOGUES = Object.freeze([
{
id: 'flights-then-military',
turns: ['How many flights are over Texas right now?', 'Now just the military ones'],
results: { analyst_query: [flightsTexas, { ...flightsTexas, count: 9, scopeLabel: '9 military aircraft over Texas', examples: [flightsTexas.examples[2]] }] },
first: { expect: 'analyst_query' },
second: {
expect: 'analyst_query',
typedArgs: [where('analyst_query', (a) => a.followUp === true || (a.layers || []).includes('military') || (a.filters || []).some((f) => f.field === 'military'))],
},
},
{
id: 'quakes-then-biggest',
turns: ['Turn on the earthquakes layer', 'Take me to the biggest one'],
results: {
set_layer_visibility: [{ ok: true, layerId: 'earthquakes', enabled: true, feedState: 'nominal', count: 143 }],
analyst_query: [null, { ok: true, count: 143, results: [{ id: 'us7000abcd', place: 'Kermadec Islands', magnitude: 6.4, latitude: -29.9, longitude: -177.8 }] }],
},
first: { expect: 'set_layer_visibility', typedArgs: [where('set_layer_visibility', (a) => a.layerId === 'earthquakes' && a.enabled === true)] },
second: {
expect: { oneOf: ['track_entity', 'analyst_query'] },
typedArgs: [(c) =>
(c.name === 'track_entity' && /quake|biggest|largest|strongest|kermadec/i.test(c.args?.query || '')) ||
(c.name === 'analyst_query' && (c.args?.layers || []).includes('earthquakes') && c.args?.sortBy === 'magnitude' && c.args?.sortDir !== 'asc')],
},
},
{
id: 'track-then-stop',
turns: ['Track UAL428', 'Stop'],
results: {
track_entity: [{ ok: true, tracking: 'UAL428', layerId: 'flights' }],
move_camera: [null, { ok: true, stopped: false, tracking: true, note: 'No camera motion was active; an entity is being tracked.' }],
},
first: { expect: 'track_entity', typedArgs: [where('track_entity', (a) => /UAL\s*428/i.test(a.query || ''))] },
second: { expect: 'stop_tracking' },
},
{
id: 'paris-then-closer',
turns: ['Take me to Paris', 'Get a little closer'],
results: { fly_to_location: [{ ok: true, arrived: true, place: 'Paris, France' }] },
first: { expect: 'fly_to_location' },
second: { expect: 'adjust_camera_zoom', typedArgs: [where('adjust_camera_zoom', (a) => a.direction === 'in')] },
},
{
id: 'thermal-then-back',
turns: ['Switch to thermal view', 'Actually, put it back the way it was'],
results: { set_visual_style: [{ ok: true, style: 'thermal', previousStyle: 'normal' }] },
first: { expect: 'set_visual_style', typedArgs: [where('set_visual_style', (a) => a.style === 'thermal')] },
second: { expect: 'set_visual_style', typedArgs: [where('set_visual_style', (a) => a.style === 'normal')] },
},
{
id: 'radio-then-volume',
turns: ['Turn on the radio', 'Turn it down to twenty percent'],
results: { control_radio: [{ ok: true, prepared: true, action: 'play', station: 'KUT 90.5 Austin' }] },
first: { expect: 'control_radio', typedArgs: [where('control_radio', (a) => a.action === 'play')] },
second: { expect: 'control_radio', typedArgs: [where('control_radio', (a) => a.action === 'volume' && a.volumePct === 20)] },
},
{
id: 'mark-then-route',
turns: ['Mark the Texas Capitol on the map', 'Now draw the walking route from there to Zilker Park'],
results: { annotate_map: [{ ok: true, placed: [{ label: 'Texas State Capitol', type: 'pin' }] }] },
first: { expect: 'annotate_map' },
second: {
expect: 'annotate_map',
typedArgs: [where('annotate_map', (a) => (a.annotations || []).some((x) =>
x.type === 'route' && (x.mode ?? 'walking') === 'walking' && /capitol/i.test(x.points?.[0]?.target || '')))],
},
},
{
id: 'ships-then-closest',
turns: ['Which ships are headed to Oakland?', 'Which of those is closest?'],
results: { analyst_query: [shipsOakland, { ...shipsOakland, count: 1, examples: [shipsOakland.examples[2]] }] },
first: { expect: 'analyst_query' },
second: { expect: 'analyst_query', typedArgs: [where('analyst_query', (a) => a.followUp === true && a.sortBy === 'distance')] },
},
{
id: 'flights-then-thanks',
turns: ['Turn on the flights layer', "Thanks, that's perfect"],
results: { set_layer_visibility: [{ ok: true, layerId: 'flights', enabled: true, feedState: 'nominal', count: 1840 }] },
first: { expect: 'set_layer_visibility' },
second: { expectNone: true },
},
]);
/** Canned result for a dialogue tool call, or null for the neutral stub. */
export function dialogueResult(dialogue, toolName, turn) {
const byTurn = dialogue.results?.[toolName];
if (!byTurn) return null;
return byTurn[turn] ?? null;
}
// ── New capabilities (point-and-ask, layer reach) ─────────────────────────
//
// ROUTING_PHRASES is the qa-voice-routing table, so that harness runs exactly
// its own table. The benchmark runs CAPABILITY_EXTRAS as the separate
// `capability` suite so the core suite stays comparable across tool versions.
/** The full qa-voice-routing table. */
export const ROUTING_PHRASES = CORE_PHRASES;
// Pointer context items in the app's own format (src/voice/pointerContext.js
// output), sent as an inert system item just before the user's words.
const AIRCRAFT_POINTER = {
type: 'pointer_context', at: 'speech_start',
target: { kind: 'aircraft', layer: 'flights', label: 'UPS793' },
ground: { lat: 30.3121, lon: -97.6013 }, screen: { x: 0.608, y: 0.408 },
};
const GROUND_POINTER = {
type: 'pointer_context', at: 'speech_start',
ground: { lat: 30.2849, lon: -97.7341 }, screen: { x: 0.427, y: 0.547 },
};
const isPointer = (v) => String(v || '').toLowerCase() === 'pointer';
const flightsInView = {
ok: true,
count: 3,
scopeLabel: 'in view',
items: [
{ n: 1, id: 'a1b2c3', callsign: 'UAL428', layerKey: 'flights', lat: 30.2, lon: -97.7 },
{ n: 2, id: 'a4b5c6', callsign: 'SWA1201', layerKey: 'flights', lat: 30.3, lon: -97.6 },
{ n: 3, id: 'a7b8c9', callsign: 'AAL88', layerKey: 'flights', lat: 30.1, lon: -97.8 },
],
};
/**
* Extra single-turn phrases (with an optional pointer `context`) and two-turn
* dialogues for the new capabilities. Items with `turns` are graded like
* DIALOGUES (turn 2 full-call); the rest like CORE_PHRASES.
*/
export const CAPABILITY_EXTRAS = Object.freeze([
{ phrase: 'Tell me about this', context: AIRCRAFT_POINTER, expect: 'get_entity_context', typedArgs: [where('get_entity_context', (a) => isPointer(a.scope))] },
{ phrase: 'How many flights are around here?', context: GROUND_POINTER, expect: 'analyst_query', typedArgs: [where('analyst_query', (a) => isPointer(a.scope?.kind))] },
{ phrase: 'Take me there', context: GROUND_POINTER, expect: 'fly_to_location', typedArgs: [where('fly_to_location', (a) => isPointer(a.query))] },
{ phrase: 'Track that one', context: AIRCRAFT_POINTER, expect: 'track_entity', typedArgs: [where('track_entity', (a) => isPointer(a.query))] },
{ phrase: 'Turn on the weather radar', expect: 'set_layer_visibility', typedArgs: [where('set_layer_visibility', (a) => a.layerId === 'weather-radar' && a.enabled === true)] },
{ phrase: 'Are there any hurricanes right now?', expect: { oneOf: ['analyst_query', 'set_layer_visibility'] }, typedArgs: [(c) => (c.args?.layers || []).includes('weather-cyclones') || c.args?.layerId === 'weather-cyclones'] },
{ phrase: 'Which bus is closest to the middle of the screen?', expect: 'analyst_query', typedArgs: [where('analyst_query', (a) => (a.layers || []).includes('transit'))] },
{
id: 'flights-then-second',
turns: ['How many flights are in view?', 'Track the second one'],
results: { analyst_query: [flightsInView] },
first: { expect: 'analyst_query' },
second: { expect: 'track_entity', typedArgs: [where('track_entity', (a) => Number(a.referent) === 2 || /SWA\s*1201/i.test(a.query || ''))] },
},
]);
scripts/voice-bench/pricing.mjs
+58
View File
@@ -0,0 +1,58 @@
/**
* Cost estimation for benchmark turns (USD). Pure.
*
* OpenAI Realtime: the app's own rate table (`src/voice/voiceCost.js`).
* `gpt-realtime-2.1` has no registry entry, so it resolves to the priciest
* known table (gpt-realtime-2) — which matches OpenAI's published 2.1 rates
* as read on 2026-09-23 ($4 / $0.40 cached / $24 per 1M text tokens).
*
* Gemini Live: https://ai.google.dev/gemini-api/docs/pricing, read 2026-09-23,
* gemini-3.8-live paid tier, USD per 1M tokens. Thinking tokens bill as text
* output. The native-audio Live model rejects TEXT output, so the benchmark
* requests AUDIO and the spoken confirmation bills at the audio-output rate.
*/
import { estimateUsageCostUsd, resolveVoiceModelById } from '../../src/voice/voiceCost.js';
export const GEMINI_RATES = Object.freeze({
'gemini-3.8-live': Object.freeze({
textInput: 0.75,
audioInput: 3.0,
textOutput: 4.5,
audioOutput: 12.0,
verifiedOn: '2026-09-23',
}),
});
/** Cost of one Realtime `response.usage` for `model`. */
export function openAiUsageCostUsd(model, usage) {
return estimateUsageCostUsd(usage, resolveVoiceModelById(model).rates);
}
const modalityCount = (details, modality) =>
(Array.isArray(details) ? details : [])
.filter((d) => String(d?.modality || '').toUpperCase() === modality)
.reduce((sum, d) => sum + (Number(d?.tokenCount) || 0), 0);
/**
* Cost of one Gemini Live `usageMetadata`. Unattributed prompt tokens bill
* as audio input and unattributed response tokens as audio output — the
* conservative direction for a spend cap.
*/
export function geminiUsageCostUsd(model, usage) {
const rates = GEMINI_RATES[model] || GEMINI_RATES['gemini-3.8-live'];
if (!usage) return 0;
const prompt = Number(usage.promptTokenCount) || 0;
const response = Number(usage.responseTokenCount) || 0;
const thoughts = Number(usage.thoughtsTokenCount) || 0;
const textIn = modalityCount(usage.promptTokensDetails, 'TEXT');
const audioIn = Math.max(0, prompt - textIn);
const textOut = modalityCount(usage.responseTokensDetails, 'TEXT');
const audioOut = Math.max(0, response - textOut);
const usd =
(textIn * rates.textInput +
audioIn * rates.audioInput +
(textOut + thoughts) * rates.textOutput +
audioOut * rates.audioOutput) /
1_000_000;
return Number.isFinite(usd) && usd > 0 ? usd : 0;
}
scripts/voice-bench/productionConfig.mjs
+36
View File
@@ -0,0 +1,36 @@
/**
* Capture the exact Realtime session config production mints.
*
* Rather than re-typing the session fields, this drives the production token
* handler (`server/providers/openai/realtime.js`) with a fake upstream fetch
* and returns the body it would have POSTed to OpenAI. Instructions, tools,
* tool_choice, reasoning, and truncation therefore cannot drift from what a
* real GEV mic session receives.
*/
import { createRealtimeTokenHandler } from '../../server/providers/openai/realtime.js';
import { realtimeInstructions } from '../../server/providers/openai/instructions.js';
import { GEV_REALTIME_TOOLS } from '../../server/providers/openai/tools.js';
export { realtimeInstructions, GEV_REALTIME_TOOLS };
/** Return production's `{ session: {...} }` client-secret body for `model`. */
export async function captureProductionSession(model) {
let captured = null;
const handler = createRealtimeTokenHandler({
resolveApiKey: () => 'bench-placeholder',
models: { standard: model, mini: model },
fetchImpl: async (_url, init) => {
captured = JSON.parse(init.body);
return new Response('{}', { status: 200, headers: { 'content-type': 'application/json' } });
},
});
const res = {
statusCode: 0,
headers: {},
setHeader(k, v) { this.headers[k] = v; },
end() {},
};
await handler({ method: 'POST', url: '/api/realtime/token', headers: {}, socket: {} }, res);
if (!captured?.session) throw new Error('production token handler did not produce a session config');
return captured.session;
}
scripts/voice-bench/report.mjs
+272
View File
@@ -0,0 +1,272 @@
/**
* Pure aggregation of benchmark rows into summary.json / summary.md.
* Rows: `{ type:'run', ... }` run metadata and `{ type:'turn', ... }` turns.
*/
export function percentile(values, p) {
const xs = values.filter((v) => typeof v === 'number' && Number.isFinite(v)).sort((a, b) => a - b);
if (!xs.length) return null;
const idx = Math.min(xs.length - 1, Math.max(0, Math.ceil((p / 100) * xs.length) - 1));
return xs[idx];
}
const pct = (n, d) => (d ? Math.round((1000 * n) / d) / 10 : null);
const sum = (xs) => xs.reduce((a, b) => a + (Number(b) || 0), 0);
const mean = (xs) => {
const v = xs.filter((x) => typeof x === 'number' && Number.isFinite(x));
return v.length ? sum(v) / v.length : null;
};
const round = (x, d = 0) => (x === null || x === undefined ? null : Math.round(x * 10 ** d) / 10 ** d);
export const COVERAGE_VERDICTS = Object.freeze(['correct', 'honest-refusal', 'hallucinated-capability', 'wrong-tool']);
export function modelKey(row) {
return `${row.provider}:${row.model}${row.variant ? `#${row.variant}` : ''}`;
}
/** Aggregate turn rows into one summary entry per provider×model(×variant). */
export function summarize(rows) {
const runs = rows.filter((r) => r.type === 'run');
const turns = rows.filter((r) => r.type === 'turn');
const keys = [...new Set(turns.map(modelKey))];
const models = keys.map((key) => {
const mine = turns.filter((t) => modelKey(t) === key);
const core = mine.filter((t) => t.suite === 'core');
const cov = mine.filter((t) => t.suite === 'coverage');
const dia = mine.filter((t) => t.suite === 'dialogue');
const capAll = mine.filter((t) => t.suite === 'capability');
// Latency percentiles stay on the core + coverage phrase sets so runs of
// different builds remain comparable.
const single = mine.filter((t) => t.suite === 'core' || t.suite === 'coverage');
const covV2 = cov.filter((t) => t.gradeV2);
const reps = [...new Set(core.map((t) => t.rep))].sort((a, b) => a - b);
const withCall = single.filter((t) => t.tFirstCallMs !== null && t.tFirstCallMs !== undefined);
const typed = core.filter((t) => t.grade?.typedArgsOk !== null && t.grade?.typedArgsOk !== undefined);
const diaFailures = dia.filter((t) => !t.grade?.ok).map((t) => ({
id: t.phraseId, rep: t.rep, expect: t.expect,
turn1: (t.turn1?.calls || []).map((c) => `${c.name}(${JSON.stringify(c.args).slice(0, 80)})`).join(', ') || '(none)',
turn2: (t.calls || []).map((c) => `${c.name}(${JSON.stringify(c.args).slice(0, 80)})`).join(', ') || '(none)',
}));
const coverageV2Counts = Object.fromEntries(COVERAGE_VERDICTS.map((v) => [v, covV2.filter((t) => t.gradeV2?.verdict === v).length]));
const capFailures = {};
for (const t of capAll.filter((x) => !x.grade?.fullCallOk)) {
const k = t.phraseId;
capFailures[k] = capFailures[k] || { id: k, expect: t.expect, fails: 0, of: capAll.filter((x) => x.phraseId === k).length, called: [] };
capFailures[k].fails += 1;
capFailures[k].called.push((t.calls || []).map((c) => `${c.name}(${JSON.stringify(c.args).slice(0, 70)})`).join(', ') || '(none)');
}
const coverageCounts = Object.fromEntries(COVERAGE_VERDICTS.map((v) => [v, cov.filter((t) => t.grade?.verdict === v).length]));
const coreFailures = {};
for (const t of core.filter((x) => !x.grade?.ok)) {
const k = t.phrase;
coreFailures[k] = coreFailures[k] || { phrase: k, expect: t.expect, fails: 0, of: core.filter((x) => x.phrase === k).length, called: [] };
coreFailures[k].fails += 1;
coreFailures[k].called.push((t.calls || []).map((c) => c.name).join(',') || '(none)');
}
const covByItem = {};
for (const t of cov) {
covByItem[t.phraseId] = covByItem[t.phraseId] || { id: t.phraseId, utterance: t.phrase, supported: t.supported, verdicts: [] };
covByItem[t.phraseId].verdicts.push(t.grade?.verdict);
}
const run = runs.filter((r) => modelKey(r) === key).at(-1) || {};
const local = mine.filter((t) => t.local);
return {
key,
provider: mine[0].provider,
model: mine[0].model,
variant: mine[0].variant || null,
settings: run.settings || null,
machine: run.machine || null,
warmup: run.warmup || null,
turns: mine.length,
core: {
n: core.length,
reps: reps.length,
accuracyPct: pct(core.filter((t) => t.grade?.ok).length, core.length),
toolAccuracyPct: pct(core.filter((t) => t.grade?.toolOk).length, core.length),
fullCallAccuracyPct: pct(core.filter((t) => t.grade?.fullCallOk).length, core.length),
typedArgsAccuracyPct: pct(typed.filter((t) => t.grade?.typedArgsOk).length, typed.length),
typedArgsN: typed.length,
argsAccuracyPct: pct(core.filter((t) => t.grade?.argsOk === true).length, core.filter((t) => t.grade?.argsOk !== null && t.grade?.argsOk !== undefined).length),
firstCallAccuracyPct: pct(core.filter((t) => t.grade?.firstCallOk).length, core.length),
falsePositives: core.filter((t) => t.grade?.falsePositive).length,
negativeTurns: core.filter((t) => t.expectNone).length,
perRepAccuracyPct: reps.map((rep) => {
const r = core.filter((t) => t.rep === rep);
return pct(r.filter((t) => t.grade?.ok).length, r.length);
}),
failures: Object.values(coreFailures).sort((a, b) => b.fails - a.fails),
},
coverage: {
n: cov.length,
counts: coverageCounts,
acceptablePct: pct(cov.filter((t) => t.grade?.acceptable).length, cov.length),
supportedCorrectPct: pct(cov.filter((t) => t.supported && t.grade?.verdict === 'correct').length, cov.filter((t) => t.supported).length),
unsupportedHonestPct: pct(cov.filter((t) => !t.supported && t.grade?.acceptable).length, cov.filter((t) => !t.supported).length),
items: Object.values(covByItem),
},
coverageV2: {
n: covV2.length,
counts: coverageV2Counts,
acceptablePct: pct(covV2.filter((t) => t.gradeV2?.acceptable).length, covV2.length),
},
capability: {
n: capAll.length,
toolPct: pct(capAll.filter((t) => t.grade?.toolOk).length, capAll.length),
fullPct: pct(capAll.filter((t) => t.grade?.fullCallOk).length, capAll.length),
failures: Object.values(capFailures).sort((a, b) => b.fails - a.fails),
},
prompt: run.prompt || null,
dialogue: {
n: dia.length,
turn2FullPct: pct(dia.filter((t) => t.grade?.fullCallOk).length, dia.length),
turn2ToolPct: pct(dia.filter((t) => t.grade?.toolOk).length, dia.length),
turn1FullPct: pct(dia.filter((t) => t.grade?.turn1Ok).length, dia.length),
turn2ToolCallP50: percentile(dia.map((t) => t.tFirstCallMs), 50),
failures: diaFailures,
},
latencyMs: {
scope: 'single-turn phrases (core + coverage); send → event, text mode',
firstTokenP50: percentile(single.map((t) => t.tFirstTokenMs), 50),
firstTokenP90: percentile(single.map((t) => t.tFirstTokenMs), 90),
toolCallP50: percentile(withCall.map((t) => t.tFirstCallMs), 50),
toolCallP90: percentile(withCall.map((t) => t.tFirstCallMs), 90),
turnDoneP50: percentile(single.map((t) => t.tDoneMs), 50),
turnDoneP90: percentile(single.map((t) => t.tDoneMs), 90),
setupP50: percentile(single.map((t) => t.setupMs), 50),
},
tokens: {
input: sum(mine.map((t) => t.usage?.inputTokens)),
cached: sum(mine.map((t) => t.usage?.cachedTokens)),
output: sum(mine.map((t) => t.usage?.outputTokens)),
reasoning: sum(mine.map((t) => t.usage?.reasoningTokens)),
inputPerTurnMean: round(mean(mine.map((t) => t.usage?.inputTokens))),
inputPerRequestMean: round(mean(single.filter((t) => t.responses > 0 && t.usage?.inputTokens).map((t) => t.usage.inputTokens / t.responses))),
},
costUsd: round(sum(mine.map((t) => t.costUsd)), 4),
costPerTurnUsd: mine.length ? round(sum(mine.map((t) => t.costUsd)) / mine.length, 5) : null,
errors: mine.filter((t) => t.errors?.length).length,
timeouts: mine.filter((t) => t.timeout).length,
local: local.length
? {
prefillTokSMean: round(mean(local.map((t) => t.local.prefillTokS)), 1),
prefillTokSP50: round(percentile(local.map((t) => t.local.prefillTokS), 50), 0),
decodeTokSMean: round(mean(local.map((t) => t.local.decodeTokS)), 1),
decodeTokSP50: round(percentile(local.map((t) => t.local.decodeTokS), 50), 1),
decodeTokSP90: round(percentile(local.map((t) => t.local.decodeTokS), 90), 1),
}
: null,
};
});
return {
generatedAt: new Date().toISOString(),
cloudSpendUsd: round(sum(turns.filter((t) => t.cloud).map((t) => t.costUsd)), 4),
models,
};
}
const machineBrief = (machine) => {
if (!machine) return '—';
const load1 = String(machine.loadavg || '').split(' ')[0] || '?';
const busy = (machine.busyProcesses || []).filter((p) => Number(p.match(/([\d.]+)%cpu/)?.[1]) >= 100)
.map((p) => p.replace(/ Helper \(GPU\)/, ' GPU').replace(/Google Chrome for Testing/, 'Chrome-for-Testing'));
return `load ${load1}${busy.length ? `; ${busy.join(', ')}` : ''}`;
};
const fmtCounts = (block) => (block?.n
? `${block.counts.correct} / ${block.counts['honest-refusal']} / ${block.counts['hallucinated-capability']} / ${block.counts['wrong-tool']} (n=${block.n})`
: '—');
const fmtMs = (v) => (v === null || v === undefined ? '—' : v >= 10_000 ? `${(v / 1000).toFixed(1)}s` : `${Math.round(v)}ms`);
const fmtPct = (v) => (v === null || v === undefined ? '—' : `${v}%`);
/** Render summary.md from a summarize() result plus free-form notes. */
export function renderMarkdown(summary, { title = 'GEV voice-routing benchmark', notes = [], payload = [] } = {}) {
const out = [`# ${title}`, '', `Generated ${summary.generatedAt}. Cloud spend so far: **$${summary.cloudSpendUsd?.toFixed(2)}**.`, ''];
out.push('> **What this measures.** Tool CHOICE for text turns sent over each provider\'s API with production\'s instructions and tools, with stubbed (always-successful) tool results — the same method as `qa-voice-routing.mjs` layer 1. It is **not** end-to-end spoken accuracy (no speech recognition, no audio, no screenshot/scene context) and **not** spoken latency: every latency below is "send text → event", before any audio would be synthesized or played.', '');
out.push('## Routing accuracy', '');
out.push('| model | core tool-name | core full-call (tool + all arg checks) | typed args (n) | harness verdict (legacy) | first call right | false +ve | per-rep harness verdict | dialogue turn-2 full-call | dialogue turn-1 | coverage v1 C / HR / HC / WT | coverage v1 acceptable | coverage v2 C / HR / HC / WT | coverage v2 acceptable | capability tool / full-call |');
out.push('|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|');
for (const m of summary.models) {
const c = m.coverage.counts;
out.push(`| ${m.key} | ${fmtPct(m.core.toolAccuracyPct)} | ${fmtPct(m.core.fullCallAccuracyPct)} | ${fmtPct(m.core.typedArgsAccuracyPct)} (${m.core.typedArgsN}) | ${fmtPct(m.core.accuracyPct)} (n=${m.core.n}) | ${fmtPct(m.core.firstCallAccuracyPct)} | ${m.core.falsePositives}/${m.core.negativeTurns} | ${m.core.perRepAccuracyPct.map(fmtPct).join(', ')} | ${fmtPct(m.dialogue.turn2FullPct)} (n=${m.dialogue.n}) | ${fmtPct(m.dialogue.turn1FullPct)} | ${c.correct} / ${c['honest-refusal']} / ${c['hallucinated-capability']} / ${c['wrong-tool']} (n=${m.coverage.n}) | ${fmtPct(m.coverage.acceptablePct)} | ${fmtCounts(m.coverageV2)} | ${fmtPct(m.coverageV2.acceptablePct)} | ${m.capability.n ? `${fmtPct(m.capability.toolPct)} / ${fmtPct(m.capability.fullPct)} (n=${m.capability.n})` : '—'} |`);
}
out.push('', 'Core tool-name = right tool(s) called. Full-call = right tool(s) AND every argument check (the legacy `args` spot checks plus the benchmark\'s typed checks: exact layer ids, enum values, numeric thresholds, sort direction). Legacy harness verdict = exactly what `qa-voice-routing.mjs` would report. Coverage: C = correct, HR = honest refusal, HC = hallucinated capability, WT = wrong tool; "acceptable" = correct, or an honest refusal where today\'s tools cannot do it.', '');
out.push('## Latency and cost', '');
out.push('| model | p50 send → first token (text) | p50 send → tool call (text) | p90 send → tool call (text) | p50 send → turn done (text) | dialogue turn-2 p50 → tool call | session setup p50 | input tok/turn | $ total | $/turn |');
out.push('|---|---|---|---|---|---|---|---|---|---|');
for (const m of summary.models) {
out.push(`| ${m.key} | ${fmtMs(m.latencyMs.firstTokenP50)} | ${fmtMs(m.latencyMs.toolCallP50)} | ${fmtMs(m.latencyMs.toolCallP90)} | ${fmtMs(m.latencyMs.turnDoneP50)} | ${fmtMs(m.dialogue.turn2ToolCallP50)} | ${fmtMs(m.latencyMs.setupP50)} | ${m.tokens.inputPerTurnMean ?? '—'} | ${m.costUsd?.toFixed(3)} | ${m.costPerTurnUsd ?? '—'} |`);
}
out.push('', 'Latencies are over single-turn phrases (core + coverage). "Turn done" includes the continuation response after the stubbed tool result. Cloud session setup (WebSocket + session config) is excluded from every latency and shown separately.', '');
const locals = summary.models.filter((m) => m.local);
if (locals.length) {
out.push('## Local runtime (cold vs warm)', '');
out.push('| model | load (wall) | COLD: first request after load → tool call | cold prefill tok/s (full prompt) | prompt tokens | WARM p50 → tool call | WARM p90 → tool call | warm per-turn prefill tok/s p50 | decode tok/s p50 / p90 | machine at start |');
out.push('|---|---|---|---|---|---|---|---|---|---|');
for (const m of locals) {
const w = m.warmup || {};
out.push(`| ${m.key} | ${fmtMs(w.loadWallMs ?? w.loadMs)} | ${fmtMs(w.coldToolCallMs ?? w.warmupTurnMs)}${w.coldToolCallMs == null ? ' (turn, no tool)' : ''} | ${w.prefillTokS ? Math.round(w.prefillTokS) : '—'} | ${w.promptTokens ?? '—'} | ${fmtMs(m.latencyMs.toolCallP50)} | ${fmtMs(m.latencyMs.toolCallP90)} | ${m.local.prefillTokSP50 ?? '—'} | ${m.local.decodeTokSP50 ?? '—'} / ${m.local.decodeTokSP90 ?? '—'} | ${machineBrief(m.machine)} |`);
}
out.push('', 'COLD = the first request after the model is loaded (pays the full ~11k-token prompt prefill). WARM = every later turn. "Warm per-turn prefill tok/s" is prompt tokens ÷ prompt-eval time as the runtime reports it: a value in the tens of thousands means the cached prompt prefix was reused and only the new user text was prefilled; a value near the cold rate means the WHOLE prompt was re-prefilled on every turn. A real voice session pays the cold cost once per model load. "Machine at start" = 1-minute load average and processes above 100% CPU when the run began (other GPU/CPU users on the machine inflate local timings).', '');
}
if (payload.length) {
out.push('## Payload changes per provider', '');
for (const p of payload) out.push(`- ${p}`);
out.push('');
}
out.push('## Failures by model', '');
for (const m of summary.models) {
out.push(`### ${m.key}`, '');
out.push(`Settings: \`${JSON.stringify(m.settings)}\``, '');
if (m.errors || m.timeouts) out.push(`Errors: ${m.errors} turns, timeouts: ${m.timeouts}.`, '');
if (m.core.failures.length) {
out.push('Core misses (legacy verdict):', '');
for (const f of m.core.failures) out.push(`- "${f.phrase}" (expect ${f.expect}) — failed ${f.fails}/${f.of}; called: ${f.called.join(' ; ')}`);
out.push('');
}
if (m.capability.failures.length) {
out.push('Capability misses (full call):', '');
for (const f of m.capability.failures) out.push(`- "${f.id}" (expect ${f.expect}) — failed ${f.fails}/${f.of}; called: ${f.called.join(' ; ').slice(0, 400)}`);
out.push('');
}
if (m.dialogue.failures.length) {
out.push('Dialogue misses (turn 2):', '');
for (const f of m.dialogue.failures) out.push(`- ${f.id} rep ${f.rep} (expect ${f.expect}) — t1: ${f.turn1} ⇒ t2: ${f.turn2}`);
out.push('');
}
const badCov = m.coverage.items.filter((i) => i.verdicts.some((v) => v === 'hallucinated-capability' || v === 'wrong-tool' || (i.supported && v !== 'correct')));
if (badCov.length) {
out.push('Coverage misses:', '');
for (const i of badCov) out.push(`- "${i.utterance}" (${i.supported ? 'supported' : 'unsupported'}) — ${i.verdicts.join(', ')}`);
out.push('');
}
}
if (notes.length) {
out.push('## Notes', '');
for (const n of notes) out.push(`- ${n}`);
out.push('');
}
return out.join('\n');
}
/**
* Before → after table for two summarize() results (matched by model key).
* Coverage "before" is the v1 rubric (what the old tools could do); "after"
* shows both v1 (same yardstick) and v2 (the current tool surface).
*/
export function renderComparison(before, after, { beforeLabel = 'before', afterLabel = 'after' } = {}) {
const out = ['## Before → after', '', `Before = ${beforeLabel}; after = ${afterLabel}. Core accuracy = tool + all argument checks (full call). Coverage OK % = correct, or an honest refusal where the tools of that build cannot do it. HC = hallucinated-capability count. p50 = send → tool call (text). Prompt tokens = mean input tokens per model request (cloud: as billed, before cache discounts; local: the cold full-prompt count).`, ''];
out.push('| model | core full-call | coverage OK % (v1 → v1 / v2) | HC (v1 → v1 / v2) | dialogue turn-2 | capability full-call (after) | p50 → tool call | prompt tokens |');
out.push('|---|---|---|---|---|---|---|---|');
const hc = (block) => (block?.n ? block.counts['hallucinated-capability'] : null);
const promptTok = (m) => (m?.warmup?.promptTokens ?? m?.tokens?.inputPerRequestMean ?? null);
for (const a of after.models) {
const b = before.models.find((x) => x.key === a.key);
const arrow = (x, y, f) => `${f(x)} → ${f(y)}`;
const pctF = (v) => (v === null || v === undefined ? '—' : `${v}%`);
const msF = (v) => (v === null || v === undefined ? '—' : `${Math.round(v)}ms`);
const num = (v) => (v === null || v === undefined ? '—' : String(v));
out.push(`| ${a.key} | ${arrow(b?.core.fullCallAccuracyPct, a.core.fullCallAccuracyPct, pctF)} | ${pctF(b?.coverage.acceptablePct)} → ${pctF(a.coverage.acceptablePct)} / ${pctF(a.coverageV2.acceptablePct)} | ${num(hc(b?.coverage))} → ${num(hc(a.coverage))} / ${num(hc(a.coverageV2))} | ${arrow(b?.dialogue.turn2FullPct, a.dialogue.turn2FullPct, pctF)} | ${pctF(a.capability.fullPct)} | ${arrow(b?.latencyMs.toolCallP50, a.latencyMs.toolCallP50, msF)} | ${arrow(promptTok(b), promptTok(a), num)} |`);
}
out.push('');
return out.join('\n');
}
scripts/voice-bench/stub.mjs
+21
View File
@@ -0,0 +1,21 @@
/**
* Stub tool results fed back to the model after each call. Pure.
*
* core suite: the neutral `{ ok:true }` stub qa-voice-routing has always
* used, so continuations behave exactly as in that harness.
* coverage suite: the same stub, except a call whose arguments violate the
* tool schema gets `{ ok:false, error }` — what the app's runner returns
* for an unknown layer id — so the model's follow-up words can be judged
* for honesty.
*/
import { validateCall } from './grade.mjs';
export const STUB_OK = Object.freeze({ ok: true, note: 'qa-harness stub result' });
export function stubResult(suite, c, tools) {
if (suite === 'coverage') {
const errors = validateCall(tools, c);
if (errors.length) return { ok: false, error: `Invalid arguments: ${errors.join('; ')}` };
}
return { ...STUB_OK };
}
scripts/voice-bench/toolFormats.mjs
+119
View File
@@ -0,0 +1,119 @@
/**
* Pure converters from the production Realtime tool list
* (`{ type:'function', name, description, parameters }`) to other providers'
* tool formats. Descriptions and schemas are carried over unchanged except
* where a target cannot represent them; every such change is listed below.
*/
const PERMISSIVE_SCALAR = Object.freeze(['string', 'number', 'boolean']);
const clone = (value) => JSON.parse(JSON.stringify(value));
/**
* Normalize a JSON schema for OpenAI-compatible local servers.
*
* Only one change: a property schema with no `type` (and no enum / anyOf /
* oneOf / $ref / const that would imply one) gets a permissive scalar union.
* `analyst_query.filters[].value` is `{}` in production — valid JSON Schema,
* but chat templates that print `type` for every property (Gemma's among
* them) crash on it.
*/
export function normalizeSchemaForChat(schema) {
const out = clone(schema);
const visit = (node, isRoot) => {
if (!node || typeof node !== 'object' || Array.isArray(node)) return;
const implied = ['type', 'enum', 'anyOf', 'oneOf', 'allOf', '$ref', 'const'].some((k) => k in node);
if (!isRoot && !implied) node.type = [...PERMISSIVE_SCALAR];
if (node.properties) for (const sub of Object.values(node.properties)) visit(sub, false);
if (node.items) visit(node.items, false);
for (const key of ['anyOf', 'oneOf', 'allOf']) if (Array.isArray(node[key])) node[key].forEach((s) => visit(s, false));
};
visit(out, true);
return out;
}
/**
* Every schema location normalizeSchemaForChat changes, as
* `{ tool, path, from, to }` — logged in summary.md so the per-provider
* payload difference is explicit rather than implied.
*/
export function chatNormalizationDiff(realtimeTools) {
const changes = [];
const walk = (before, after, tool, where) => {
if (!before || typeof before !== 'object' || Array.isArray(before)) return;
if (JSON.stringify(before.type) !== JSON.stringify(after.type)) {
changes.push({ tool, path: where, from: before.type === undefined ? '(untyped)' : before.type, to: after.type });
}
for (const [k, v] of Object.entries(before.properties || {})) walk(v, after.properties[k], tool, `${where}.${k}`);
if (before.items) walk(before.items, after.items, tool, `${where}[]`);
};
for (const tool of realtimeTools) walk(tool.parameters, normalizeSchemaForChat(tool.parameters), tool.name, tool.name);
return changes;
}
/** Realtime tools → Chat Completions tools (`{type:'function', function:{...}}`). */
export function toChatTools(realtimeTools, { normalize = true } = {}) {
return realtimeTools.map((tool) => ({
type: 'function',
function: {
name: tool.name,
description: tool.description,
parameters: normalize ? normalizeSchemaForChat(tool.parameters) : clone(tool.parameters),
},
}));
}
// Keywords the Gemini OpenAPI-subset `Schema` does not accept.
const GEMINI_DROP = new Set(['additionalProperties', '$schema', 'default', 'examples', '$id', 'const']);
/**
* Convert a JSON schema to the Gemini OpenAPI-subset `Schema`.
* Drops unsupported keywords (additionalProperties, $schema, default, ...);
* an untyped property becomes `anyOf` string|number|boolean; a type array
* becomes `anyOf` of single types.
*/
export function toGeminiSchema(schema) {
if (!schema || typeof schema !== 'object' || Array.isArray(schema)) return schema;
const out = {};
for (const [key, value] of Object.entries(schema)) {
if (GEMINI_DROP.has(key)) continue;
if (key === 'properties') {
out.properties = Object.fromEntries(Object.entries(value).map(([k, v]) => [k, toGeminiSchema(v)]));
} else if (key === 'items') {
out.items = toGeminiSchema(value);
} else if (key === 'anyOf' || key === 'oneOf') {
out.anyOf = value.map((s) => toGeminiSchema(s));
} else {
out[key] = clone(value);
}
}
if (Array.isArray(out.type)) {
const types = out.type;
delete out.type;
out.anyOf = types.map((t) => ({ type: t }));
}
const implied = ['type', 'enum', 'anyOf'].some((k) => k in out);
if (!implied) out.anyOf = PERMISSIVE_SCALAR.map((t) => ({ type: t }));
return out;
}
/**
* Realtime tools → Gemini `functionDeclarations`.
* mode 'jsonSchema' (default): pass the production schema verbatim through
* `parametersJsonSchema` — full JSON Schema, closest to prompt parity.
* mode 'openapi': convert to the OpenAPI-subset `parameters` field.
* A tool with no properties gets no parameters field in openapi mode (Gemini
* rejects an empty OBJECT schema there).
*/
export function toGeminiDeclarations(realtimeTools, { mode = 'jsonSchema' } = {}) {
return realtimeTools.map((tool) => {
const decl = { name: tool.name, description: tool.description };
const params = tool.parameters;
if (mode === 'jsonSchema') {
decl.parametersJsonSchema = clone(params);
} else if (params && Object.keys(params.properties || {}).length) {
decl.parameters = toGeminiSchema(params);
}
return decl;
});
}
scripts/voice-turn-spans.mjs
+111
View File
@@ -0,0 +1,111 @@
#!/usr/bin/env node
/**
* Summarize voice turn spans from the Realtime debug log.
*
* Every closed voice turn writes one `turn.span` record (see
* src/voice/turnMetrics.js). This prints each span and p50/p90 figures for
* end-of-speech → first audio, the longest silence, tool time, preamble rate,
* spoken words and hedge hits.
*
* Usage:
* node scripts/voice-turn-spans.mjs [log.jsonl] [--since <ISO time>] [--session <id>] [--json]
*/
import fs from 'node:fs';
import path from 'node:path';
import { fileURLToPath } from 'node:url';
const root = path.resolve(path.dirname(fileURLToPath(import.meta.url)), '..');
const args = process.argv.slice(2);
const option = (flag) => {
const index = args.indexOf(flag);
return index >= 0 ? args[index + 1] : null;
};
const positional = args.filter(
(arg, index) => !arg.startsWith('--') && !args[index - 1]?.startsWith('--'),
);
const logPath =
positional[0] || path.join(root, '.gev-logs', 'realtime-conversations.jsonl');
const since = option('--since') ? Date.parse(option('--since')) : null;
const session = option('--session');
const spans = [];
for (const line of fs.readFileSync(logPath, 'utf8').split('\n')) {
if (!line.includes('"turn.span"')) continue;
let record;
try {
record = JSON.parse(line);
} catch {
continue;
}
if (record.event !== 'turn.span') continue;
if (since && Date.parse(record.timestamp) < since) continue;
if (session && record.sessionId !== session) continue;
spans.push({
at: record.timestamp,
session: record.sessionId,
...record.payload,
});
}
const quantile = (values, q) => {
const sorted = values.filter(Number.isFinite).sort((a, b) => a - b);
if (!sorted.length) return null;
return sorted[Math.min(sorted.length - 1, Math.floor(q * sorted.length))];
};
const withTools = spans.filter((span) => span.tools?.length);
const slowToolTurns = withTools.filter((span) =>
span.tools.some((tool) => tool.ms >= 700),
);
const summary = {
turns: spans.length,
toolTurns: withTools.length,
firstAudioMs: {
p50: quantile(spans.map((s) => s.first_audio_ms), 0.5),
p90: quantile(spans.map((s) => s.first_audio_ms), 0.9),
},
maxSilenceMs: {
p50: quantile(spans.map((s) => s.max_silence_ms), 0.5),
p90: quantile(spans.map((s) => s.max_silence_ms), 0.9),
},
toolMs: {
p50: quantile(withTools.flatMap((s) => s.tools.map((t) => t.ms)), 0.5),
p90: quantile(withTools.flatMap((s) => s.tools.map((t) => t.ms)), 0.9),
},
preambleRate: withTools.length
? withTools.filter((s) => s.preamble).length / withTools.length
: null,
slowToolPreambleOrProgressRate: slowToolTurns.length
? slowToolTurns.filter((s) => s.preamble || s.progress_lines > 0).length /
slowToolTurns.length
: null,
answerWords: {
p50: quantile(spans.map((s) => s.answer_words), 0.5),
p90: quantile(spans.map((s) => s.answer_words), 0.9),
},
spokenWordsTotal: spans.reduce((sum, s) => sum + (s.spoken_words || 0), 0),
hedgeHits: spans.reduce((sum, s) => sum + (s.hedge_hits?.length || 0), 0),
};
if (args.includes('--json')) {
console.log(JSON.stringify({ summary, spans }, null, 2));
} else {
for (const span of spans) {
const tools = (span.tools || [])
.map((tool) => `${tool.name}:${tool.ms}ms`)
.join(',');
console.log(
[
span.at,
`first=${span.first_audio_ms ?? '-'}ms`,
`maxSilence=${span.max_silence_ms ?? '-'}ms`,
`preamble=${span.preamble ? 'y' : 'n'}`,
`progress=${span.progress_lines}`,
`words=${span.answer_words}/${span.spoken_words}`,
`hedges=${span.hedge_hits?.length || 0}`,
tools || '(no tools)',
span.answer_text ? `"${span.answer_text.slice(0, 80)}"` : '',
].join(' '),
);
}
console.log(JSON.stringify(summary, null, 2));
}
server/mcp/panelKey.js
+117
View File
@@ -0,0 +1,117 @@
import fs from 'node:fs';
import path from 'node:path';
import { randomBytes, randomUUID } from 'node:crypto';
import { fileURLToPath } from 'node:url';
/** Where the install's panel key lives: beside the other local state, which
* git ignores, at the checkout root rather than the client's working
* directory (an MCP client may start the server anywhere). */
export const DEFAULT_PANEL_KEY_FILE = fileURLToPath(
new URL('../../.gev-cache/mcp-panel-key', import.meta.url),
);
const KEY_PATTERN = /^[A-Za-z0-9_-]{43}$/;
const newKey = () => randomBytes(32).toString('base64url');
const notShared = (error) =>
`panel key not shared (${error.code || error.message}); using a key of this process`;
function readKey(file) {
const text = fs.readFileSync(file, 'utf8').trim();
return KEY_PATTERN.test(text) ? text : null;
}
/** Serialize malformed-file repair; ordinary first creation still uses link(). */
function repairKey(file, tmp, key) {
const lock = `${file}.repair-lock`;
const deadline = Date.now() + 2000;
const pause = new Int32Array(new SharedArrayBuffer(4));
let fd;
for (;;) {
try {
fd = fs.openSync(lock, 'wx', 0o600);
break;
} catch (error) {
if (error.code !== 'EEXIST') throw error;
// Another repair may already have published a usable key.
const winner = readKey(file);
if (winner) return winner;
if (Date.now() >= deadline) {
throw Object.assign(new Error('panel key repair is busy'), {
code: 'ETIMEDOUT',
});
}
Atomics.wait(pause, 0, 0, 10);
}
}
try {
// A repair completed between our earlier read and acquiring the lock.
const winner = readKey(file);
if (winner) return winner;
fs.renameSync(tmp, file);
return key;
} finally {
fs.closeSync(fd);
fs.rmSync(lock, { force: true });
}
}
/**
* The panel key every stdio server of this install shares.
*
* A client can start more than one server process for one connection: Claude
* Desktop was reported to start two processes; serving the panel's page from
* one and sending its `panel_request` calls to the other reproduces #927.
* Per-process keys then mismatch, and the panel refuses the request.
* The first process to run creates the key, without replacing one
* another process created at the same moment; the rest read it. When the file
* cannot be read or written, or repair stays busy for two seconds, the process
* falls back to its own key, as every process did before.
*
* As before, the key keeps `panel_request` from clients that only list it; it
* is not access control.
*
* @param {{ file?: string, log?: (line: string) => void }} [options]
* @returns {string}
*/
export function sharedPanelKey({
file = DEFAULT_PANEL_KEY_FILE,
log = () => {},
} = {}) {
try {
const existing = readKey(file);
if (existing) return existing;
// Present but not a key: replace it below.
} catch (error) {
if (error.code !== 'ENOENT') {
log(notShared(error));
return newKey();
}
}
const key = newKey();
let tmp = null;
try {
fs.mkdirSync(path.dirname(file), { recursive: true });
tmp = path.join(
path.dirname(file),
`.${path.basename(file)}.${randomUUID().slice(0, 8)}.tmp`,
);
fs.writeFileSync(tmp, `${key}\n`, { flag: 'wx', mode: 0o600 });
try {
// link() publishes the whole file at once and fails if another process
// got there first, so a reader never sees a half-written key and two
// processes starting together cannot end up with different keys.
fs.linkSync(tmp, file);
return key;
} catch (error) {
if (error.code !== 'EEXIST') throw error;
const winner = readKey(file);
if (winner) return winner;
return repairKey(file, tmp, key);
}
} catch (error) {
log(notShared(error));
return key;
} finally {
if (tmp) fs.rmSync(tmp, { force: true });
}
}
server/mcp/server.js
+6 -4
View File
@@ -27,14 +27,16 @@ const INSTRUCTIONS =
export function createLocalMcpServer({
apiBase = DEFAULT_API_BASE,
fetchImpl,
panelKey = randomBytes(32).toString('base64url'),
} = {}) {
const { version } = JSON.parse(
readFileSync(new URL('../../package.json', import.meta.url), 'utf8'),
);
// Each server makes a new key for its panel. The panel's page carries it
// and panel_request requires it; any client may read the page, so it keeps
// the tool from clients that only list it, and is not access control.
const panelKey = randomBytes(32).toString('base64url');
// Unless given one, each server makes a new key for its panel. The panel's
// page carries it and panel_request requires it; any client may read the
// page, so it keeps the tool from clients that only list it, and is not
// access control. The stdio entry passes the install's shared key
// (panelKey.js), so separate processes of one client agree.
return createMcpServer({
catalog: catalogForSurface(
composeCatalog({
server/mcp/stdio.js
+5 -1
View File
@@ -11,6 +11,7 @@
import { createInterface } from 'node:readline';
import { fileURLToPath } from 'node:url';
import { parseErrorResponse } from '../../src/tools/mcp/index.js';
import { sharedPanelKey } from './panelKey.js';
import { createLocalMcpServer } from './server.js';
import { DEFAULT_API_BASE } from './services.js';
@@ -97,7 +98,10 @@ if (process.argv[1] && fileURLToPath(import.meta.url) === process.argv[1]) {
console.error(
`God's Eye View MCP server reading ${options.apiBase || DEFAULT_API_BASE}`,
);
await serveStdio(createLocalMcpServer(options), {
// A client may start several of these for one connection; they share
// the install's panel key so the panel works whichever one it reaches.
const panelKey = sharedPanelKey({ log: (line) => console.error(line) });
await serveStdio(createLocalMcpServer({ ...options, panelKey }), {
input: process.stdin,
output: process.stdout,
log: (line) => console.error(`<- ${line}`),
server/providers/openai.js
+22 -3
View File
@@ -1,20 +1,26 @@
import { defaultSourceRoot } from './common/source-root.js';
import { handleHudSummary } from './openai/hud-summary.js';
import { createDebugLogHandler } from './openai/debug-log.js';
import { createRealtimeTokenHandler } from './openai/realtime.js';
import {
createRealtimeOAuthLoginHandler,
createRealtimeOAuthStatusHandler,
createRealtimeTokenHandler,
} from './openai/realtime.js';
import { sameSiteGated } from './common/same-site.js';
import { createCodexOAuthLogin } from './openai/codex-auth.js';
/**
* Vite plugin: OpenAI Realtime ephemeral client secret.
*
* Keeps OPENAI_API_KEY server-side while the browser connects to the
* Realtime API over WebRTC with a short-lived secret.
* Keeps the selected cloud credential server-side while the browser connects
* to the Realtime API over WebRTC with a short-lived secret.
*/
function openAiRealtimeProxy({
sourceRoot = defaultSourceRoot,
annotationGuidance,
realtime = {},
} = {}) {
const oauthLogin = createCodexOAuthLogin(realtime);
function install(middlewares) {
// Cost-bearing and log endpoints refuse cross-site browser requests
// (see server/providers/common/same-site.js and SECURITY.md).
@@ -31,16 +37,29 @@ function openAiRealtimeProxy({
createRealtimeTokenHandler({ ...realtime, annotationGuidance }),
),
);
middlewares.use(
'/api/realtime/oauth-status',
sameSiteGated(createRealtimeOAuthStatusHandler({ oauthLogin })),
);
middlewares.use(
'/api/realtime/oauth-login',
sameSiteGated(createRealtimeOAuthLoginHandler({ oauthLogin })),
);
}
return {
name: 'openai-realtime-proxy',
configureServer(server) {
install(server.middlewares);
server.httpServer?.once('close', oauthLogin.dispose);
},
configurePreviewServer(server) {
install(server.middlewares);
server.httpServer?.once('close', oauthLogin.dispose);
},
closeBundle: oauthLogin.dispose,
};
}
server/providers/openai/codex-auth.js
+360
View File
@@ -0,0 +1,360 @@
import { spawn } from 'node:child_process';
import {
accessSync,
constants as fsConstants,
readFileSync,
statSync,
} from 'node:fs';
import os from 'node:os';
import path from 'node:path';
export function codexAuthPath({
environment = process.env,
home = os.homedir(),
} = {}) {
const explicit = String(environment.CODEX_AUTH_JSON || '').trim();
if (explicit) return path.resolve(explicit);
const codexHome = String(environment.CODEX_HOME || '').trim();
return path.join(
codexHome ? path.resolve(codexHome) : path.join(home, '.codex'),
'auth.json',
);
}
/** An optional operator lock that refuses the metered API-key voice lane. */
export function preferCodexOAuth(environment = process.env) {
if (!Object.hasOwn(environment, 'GEV_PREFER_CODEX_OAUTH')) return false;
const value = String(environment.GEV_PREFER_CODEX_OAUTH || '')
.trim()
.toLowerCase();
if (['1', 'true', 'yes', 'on'].includes(value)) return true;
if (['0', 'false', 'no', 'off'].includes(value)) return false;
throw new Error(
'GEV_PREFER_CODEX_OAUTH must be true or false. Refusing to choose a voice auth mode.',
);
}
function codexOAuthError(message, code = 'CODEX_OAUTH_UNAVAILABLE') {
const error = new Error(message);
error.code = code;
return error;
}
export function readCodexOAuthAccessToken({
authPath = codexAuthPath(),
readFile = readFileSync,
statFile = statSync,
nowMs = Date.now(),
} = {}) {
const unavailable =
'ChatGPT sign-in is unavailable. Sign in to Codex or the ChatGPT desktop app and try again.';
let parsed;
try {
parsed = JSON.parse(readFile(authPath, 'utf8'));
} catch {
throw codexOAuthError(unavailable);
}
if (!parsed || typeof parsed !== 'object' || Array.isArray(parsed)) {
throw codexOAuthError(unavailable);
}
const mode = String(parsed.auth_mode || '')
.trim()
.toLowerCase();
const chatGptMode = mode
? mode === 'chatgpt' || mode === 'chatgptauthtokens'
: typeof parsed.OPENAI_API_KEY !== 'string';
const token = parsed.tokens?.access_token;
if (!chatGptMode || typeof token !== 'string' || !token.trim()) {
throw codexOAuthError(unavailable);
}
// This only checks token shape and expiry. OpenAI verifies the signature when
// minting the short-lived Realtime credential; we never modify auth.json.
const parts = token.split('.');
if (
parts.length !== 3 ||
parts.some((part) => !/^[A-Za-z0-9_-]+$/.test(part))
) {
throw codexOAuthError(unavailable);
}
let payload;
try {
payload = JSON.parse(Buffer.from(parts[1], 'base64url').toString('utf8'));
} catch {
throw codexOAuthError(unavailable);
}
if (!payload || typeof payload !== 'object' || Array.isArray(payload)) {
throw codexOAuthError(unavailable);
}
let expiresAtMs;
if (Object.hasOwn(payload, 'exp')) {
if (typeof payload.exp !== 'number' || !Number.isFinite(payload.exp)) {
throw codexOAuthError(unavailable);
}
expiresAtMs = payload.exp * 1000;
} else {
try {
expiresAtMs = statFile(authPath).mtimeMs + 60 * 60 * 1000;
} catch {
throw codexOAuthError(unavailable);
}
}
if (!Number.isFinite(expiresAtMs) || expiresAtMs <= nowMs + 60_000) {
throw codexOAuthError(
'ChatGPT sign-in has expired. Re-authenticate in Provider Settings or run codex login and try again.',
'CODEX_OAUTH_REAUTH_REQUIRED',
);
}
return token;
}
export function resolveCodexExecutable({
environment = process.env,
home = os.homedir(),
access = accessSync,
} = {}) {
const explicit = String(environment.CODEX_BIN || '').trim();
if (explicit) return explicit;
for (const candidate of [
path.join(home, '.local', 'bin', 'codex'),
path.join(
home,
'.codex',
'packages',
'standalone',
'current',
'bin',
'codex',
),
]) {
try {
access(candidate, fsConstants.X_OK);
return candidate;
} catch {
// Fall through to the next known location, then PATH.
}
}
return 'codex';
}
// What `codex login` needs to find its home, open a browser and reach OpenAI.
// The server's own environment also holds every provider secret, so the
// child receives only these names.
const CODEX_LOGIN_ENV =
/^(?:PATH|PATHEXT|HOME|USER|USERNAME|LOGNAME|SHELL|LANG|LANGUAGE|LC_[A-Z_]+|TERM|TZ|TMPDIR|TEMP|TMP|XDG_[A-Z_]+|DISPLAY|WAYLAND_DISPLAY|DBUS_SESSION_BUS_ADDRESS|BROWSER|WSL_[A-Z_]+|WSLENV|(?:HTTPS?|ALL|NO)_PROXY|SSL_CERT_(?:FILE|DIR)|NODE_EXTRA_CA_CERTS|SYSTEMROOT|WINDIR|COMSPEC|USERPROFILE|APPDATA|LOCALAPPDATA|PROGRAMDATA|HOMEDRIVE|HOMEPATH|CODEX_[A-Z_]+)$/i;
/** The environment `codex login` runs with: the allowlist, then `CODEX_HOME`. */
export function codexLoginEnvironment(environment, codexHome) {
const env = {};
for (const [name, value] of Object.entries(environment || {}))
if (CODEX_LOGIN_ENV.test(name) && value !== undefined) env[name] = value;
env.CODEX_HOME = codexHome;
return env;
}
export function startCodexChatGptLogin({
spawnImpl = spawn,
environment = process.env,
home = os.homedir(),
executable = resolveCodexExecutable({ environment, home }),
} = {}) {
// Codex owns its credential storage. An explicit read path must agree with
// the CLI's write path; never silently sign in to another credential store.
const configuredHome = String(environment.CODEX_HOME || '').trim();
const loginHome = configuredHome
? path.resolve(configuredHome)
: path.join(home, '.codex');
if (
codexAuthPath({ environment, home }) !== path.join(loginHome, 'auth.json')
) {
return Promise.reject(
codexOAuthError(
'CODEX_AUTH_JSON does not match the Codex login storage path. Set CODEX_HOME to the matching directory or sign in to Codex separately.',
'CODEX_OAUTH_STORAGE_MISMATCH',
),
);
}
return new Promise((resolve, reject) => {
let child;
let spawned = false;
let finish;
const completion = new Promise((done) => {
finish = done;
});
const fail = () => {
reject(
codexOAuthError(
'Could not start ChatGPT sign-in. Check that Codex is installed, or set CODEX_BIN to its executable.',
'CODEX_OAUTH_LOGIN_FAILED',
),
);
finish({ exitCode: null });
};
try {
child = spawnImpl(executable, ['login'], {
cwd: home,
detached: true,
stdio: 'ignore',
env: codexLoginEnvironment(environment, loginHome),
});
} catch {
fail();
return;
}
child.once('error', () => {
if (!spawned) fail();
else finish({ exitCode: null });
});
child.once('exit', (exitCode) => finish({ exitCode }));
child.once('spawn', () => {
spawned = true;
child.unref?.();
resolve({
completion,
cancel() {
try {
child.kill?.('SIGTERM');
} catch {
/* Already stopped. */
}
},
});
});
});
}
/** One local login owner shared by the launch and status endpoints. */
export function createCodexOAuthLogin({
resolveOAuthAccessToken = () => readCodexOAuthAccessToken(),
startOAuthLogin = () => startCodexChatGptLogin(),
loginTimeoutMs = 120_000,
setTimer = setTimeout,
clearTimer = clearTimeout,
} = {}) {
let active = null;
let failure = null;
let disposed = false;
function credentials() {
try {
if (resolveOAuthAccessToken()) return { available: true };
} catch (error) {
const code = error?.code || 'CODEX_OAUTH_UNAVAILABLE';
return {
available: false,
error: error?.message || 'ChatGPT sign-in is unavailable',
code,
reauthRequired: code === 'CODEX_OAUTH_REAUTH_REQUIRED',
};
}
return {
available: false,
error: 'ChatGPT sign-in is unavailable',
code: 'CODEX_OAUTH_UNAVAILABLE',
reauthRequired: false,
};
}
function status() {
const current = credentials();
if (current.available) return current;
if (failure) return { available: false, ...failure, loginFailed: true };
return active ? { ...current, pending: true } : current;
}
function finish(attempt, error) {
if (active !== attempt) return;
clearTimer(attempt.timer);
active = null;
failure = error;
}
async function start() {
if (disposed)
throw codexOAuthError(
'ChatGPT sign-in is unavailable because the server has stopped.',
'CODEX_OAUTH_LOGIN_FAILED',
);
if (credentials().available)
return { available: true, started: false, pending: false };
if (active) return { available: false, started: false, pending: true };
// Reserve the attempt before awaiting spawn so concurrent POSTs share it.
const attempt = { process: null, timer: null };
active = attempt;
failure = null;
attempt.timer = setTimer(() => {
finish(attempt, {
code: 'CODEX_OAUTH_LOGIN_TIMEOUT',
error:
'ChatGPT sign-in timed out. Click USE CHATGPT OAUTH to try again.',
});
attempt.process?.cancel();
}, loginTimeoutMs);
attempt.timer?.unref?.();
try {
const login = await startOAuthLogin();
if (!login?.completion || typeof login.cancel !== 'function')
throw new Error('Invalid login process');
attempt.process = login;
if (active !== attempt) {
login.cancel();
return { ...status(), started: false, pending: false };
}
Promise.resolve(login.completion).then(
(result) => {
if (active !== attempt) return;
if (result?.exitCode !== 0) {
finish(attempt, {
code: 'CODEX_OAUTH_LOGIN_FAILED',
error:
'ChatGPT sign-in did not complete. Try again in Provider Settings, or run codex login separately.',
});
} else if (!credentials().available) {
finish(attempt, {
code: 'CODEX_OAUTH_STORAGE_UNAVAILABLE',
error:
'Codex sign-in finished, but its configured auth.json has no usable ChatGPT token. Check CODEX_HOME and Codex credential storage. GEV can read file storage only.',
});
} else finish(attempt, null);
},
() =>
finish(attempt, {
code: 'CODEX_OAUTH_LOGIN_FAILED',
error:
'ChatGPT sign-in did not complete. Try again in Provider Settings.',
}),
);
return { available: false, started: true, pending: true };
} catch (error) {
const code =
error?.code === 'CODEX_OAUTH_STORAGE_MISMATCH'
? error.code
: 'CODEX_OAUTH_LOGIN_FAILED';
finish(attempt, {
code,
error:
code === 'CODEX_OAUTH_STORAGE_MISMATCH'
? error.message
: 'Could not start ChatGPT sign-in. Check that Codex is installed, or set CODEX_BIN to its executable.',
});
return { ...status(), started: false, pending: false };
}
}
return {
status,
start,
dispose() {
disposed = true;
if (!active) return;
const attempt = active;
finish(attempt, null);
attempt.process?.cancel();
},
};
}
server/providers/openai/constants.js
+4
View File
@@ -16,6 +16,9 @@ const OPENAI_REALTIME_CONTEXT_RETENTION_DEFAULT = 0.5;
const OPENAI_HUD_SUMMARY_MODEL_DEFAULT = 'gpt-5-nano';
/** Input transcription for voice captions; OPENAI_REALTIME_TRANSCRIBE_MODEL=off disables it. */
const OPENAI_REALTIME_TRANSCRIBE_MODEL_DEFAULT = 'gpt-4o-mini-transcribe';
export {
OPENAI_HUD_SUMMARY_MODEL_DEFAULT,
OPENAI_REALTIME_MODEL_MINI_DEFAULT,
@@ -24,4 +27,5 @@ export {
OPENAI_REALTIME_REASONING_DEFAULT,
OPENAI_REALTIME_CONTEXT_TOKENS_DEFAULT,
OPENAI_REALTIME_CONTEXT_RETENTION_DEFAULT,
OPENAI_REALTIME_TRANSCRIBE_MODEL_DEFAULT,
};
server/providers/openai/debug-log.js
+56 -3
View File
@@ -23,7 +23,59 @@ const REALTIME_DEBUG_LOG_MAX_FILE_BYTES = 32 * 1024 * 1024;
*/
const REALTIME_DEBUG_LOG_MAX_PER_MIN = 120;
function createDebugLogHandler({ sourceRoot = defaultSourceRoot } = {}) {
/**
* Fields that carry what people said or heard: transcripts, typed and spoken
* text, streamed deltas, tool arguments/results and the span's quoted
* replies. They are dropped from the persisted log unless content logging is explicitly enabled
* (GEV_VOICE_LOG_CONTENT=1), so timing and tool diagnostics never retain
* speech by default.
*/
const VOICE_TEXT_FIELDS = new Set([
'transcript',
'text',
'delta',
'answer_text',
'preamble_text',
]);
const VOICE_CONTENT_MAX_DEPTH = 12;
const VOICE_CONTENT_MAX_DEPTH_MARKER = '[omitted: max depth]';
/** Replace spoken or typed content and complete tool argument/result bodies. */
function omitVoiceContent(value, depth = 0) {
if (depth > VOICE_CONTENT_MAX_DEPTH) return VOICE_CONTENT_MAX_DEPTH_MARKER;
if (value === null || typeof value !== 'object') return value;
if (Array.isArray(value))
return value.map((item) => omitVoiceContent(item, depth + 1));
const output = {};
for (const [key, item] of Object.entries(value)) {
// Tool bodies have open-ended schemas: omit the whole body rather than
// chasing query, label, say, display, or future tool-specific fields.
// Protocol response.output arrays still carry useful event metadata; only
// string output is a serialized function result and must be opaque.
if (
key === 'arguments' ||
key === 'result' ||
(key === 'output' && typeof item === 'string')
) {
output[key] =
typeof item === 'string'
? `[omitted ${item.length} chars]`
: '[omitted]';
continue;
}
if (VOICE_TEXT_FIELDS.has(key) && typeof item === 'string') {
output[key] = `[omitted ${item.length} chars]`;
continue;
}
output[key] = omitVoiceContent(item, depth + 1);
}
return output;
}
function createDebugLogHandler({
sourceRoot = defaultSourceRoot,
includeContent = process.env.GEV_VOICE_LOG_CONTENT === '1',
} = {}) {
const logDir = path.join(sourceRoot, '.gev-logs');
const logFile = path.join(logDir, 'realtime-conversations.jsonl');
const allow = makeRateLimiter({
@@ -79,7 +131,8 @@ function createDebugLogHandler({ sourceRoot = defaultSourceRoot } = {}) {
try {
const body = await readRequestBody(req, REALTIME_DEBUG_LOG_MAX_BYTES);
const record = JSON.parse(body || '{}');
const parsed = JSON.parse(body || '{}');
const record = includeContent ? parsed : omitVoiceContent(parsed);
// The server's own timestamp comes last, so a record cannot supply one.
await append(
`${JSON.stringify({
@@ -104,4 +157,4 @@ function createDebugLogHandler({ sourceRoot = defaultSourceRoot } = {}) {
};
}
export { createDebugLogHandler };
export { createDebugLogHandler, omitVoiceContent };
server/providers/openai/instructions.js
+17 -24
View File
@@ -1,5 +1,5 @@
const DEFAULT_ANNOTATION_GUIDANCE =
'Use a single annotate_map call with several annotations when you are describing multiple related places at once. Set flyTo true only when the user is not already looking at the place; if every mark in a call lands off-screen the app auto-frames them, so when unsure leave flyTo false. Do NOT say out loud that you are drawing, highlighting, or annotating — just speak naturally about the places while the marks appear. ANNOTATIONS ACCUMULATE AND PERSIST — keep adding marks as you explore; you can fly around, change topic, and jump between far-apart places and the marks STAY, so the user can build up the map and show people things. Do NOT clear on your own initiative: never pass clearPrevious, and call clear_annotations ONLY when the user EXPLICITLY asks to clear or reset the map.';
'Put related places in one annotate_map call. Set flyTo true only when the user is not already looking at the place (off-screen marks auto-frame, so when unsure leave it false). Do not say you are drawing or annotating — talk about the places while the marks appear. Marks ACCUMULATE AND PERSIST across flights and topics so the user can build up the map: never pass clearPrevious, and call clear_annotations ONLY when the user EXPLICITLY asks to clear or reset the map.';
function realtimeInstructions(
annotationGuidance = DEFAULT_ANNOTATION_GUIDANCE,
@@ -13,27 +13,24 @@ function realtimeInstructions(
'For requests to open, show, reveal, or focus a menu/panel, call set_panel_open or show_data_layers_menu. "Open Context" means only set_panel_open{panelId:"global-context-panel",open:true}; it does not activate a Context sub-mode. "Open Contacts" means set_context_mode{mode:"contacts"}; that action expands the parent Context panel before activating Contacts.',
'For requests like "show me the datacenter layers", open the data layers menu and focus the matching layer row; do not enable the layer unless the user asks to turn it on.',
'For questions like "what am I looking at?", "what is in view?", "what is this?", "that selected thing", nearby datacenter, dam, cable, ship, or current view contents, call get_entity_context first, then answer from the returned scene/entity context.',
'For "what is this aircraft?" answers, read the callsign, operator, registration, type, and route only from get_entity_context selected.properties. Treat route, routeOrigin, and routeDestination as the only authoritative route fields. Every aircraft identity answer MUST explicitly cover operator, type, and route. When a route is present, repeat its endpoint codes exactly; do not expand airport codes into city names. For a missing field say exactly "Operator details are unavailable", "Aircraft type is unavailable", or "Route details are unavailable" as applicable. Never silently omit missing enrichment or infer it from the callsign.',
'While a camera motion or route flight is active, a bare "stop" means move_camera{motion:stop} — NOT control_scene and NOT stop_tracking (those need explicit words like "stop the scene" / "stop tracking"). If move_camera stop returns stopped:false and an entity is being tracked, call stop_tracking next — the user means "stop whatever is moving". Flying somewhere while tracking automatically stops the tracking (the result says so): mention it briefly.',
'For "what is this aircraft?", answer with get_entity_context\'s identityLine: callsign, operator, type and route from returned fields only, airport codes verbatim. Other questions about the selection answer from its properties. Never infer them from the callsign.',
'While a camera motion or route flight is active, a bare "stop" means move_camera{motion:stop} — NOT control_scene and NOT stop_tracking (those need explicit words like "stop the scene" / "stop tracking"). If move_camera stop returns stopped:false and an entity is being tracked, call stop_tracking next — the user means "stop whatever is moving". Flying somewhere while tracking stops the tracking.',
'For camera-motion requests — "orbit around this", "pan left", "tilt up", "stop moving" — call move_camera. For "fly the route" over a drawn route, call fly_route. Confirm with the RESULTING state ("Orbiting slowly", "Flying the route").',
'analyst_query ANSWERS questions; it never moves the camera or starts tracking. For requests to FOLLOW or TRACK a specific aircraft/ship, call track_entity (get_entity_context first when the target is ambiguous), never analyst_query as the final or only action. For "follow/track the nearest aircraft", first call analyst_query with the aircraft layer(s), sortBy=distance, and limit=1, then call track_entity with the returned aircraft identity in the same turn. The lookup alone does not fulfill a follow/track command.',
'For a request to enable an aircraft layer and SELECT or FIND the nearest/closest aircraft near a named place — for example, "Turn on flights and select the closest aircraft to Austin" — call select_nearest_aircraft once. It atomically turns on the requested aircraft layer first, waits for location arrival, refreshes that layer for the destination viewport, filters out landed/on-ground records, and selects the nearest airborne result. A healthy fallback feed is valid data: report the returned feed source briefly, never call it an enable failure. Do not also call fly_to_location, set_layer_visibility, analyst_query, track_entity, set_context_mode, or control_cockpit for the same request. SELECT/FIND never implies Contacts or Cockpit unless the user explicitly asks for either mode.',
'For ANALYTICAL questions about layer data — how many / which / fastest / highest / biggest / nearest flights, ships, fires, earthquakes, satellites, datacenters, or dams ("how many flights over Texas", "biggest fire near LA", "which ships are headed to Oakland", "anything above 40,000 feet") — call analyst_query, not get_entity_context. Narrate the count plus two or three notable examples by name, and reflect the result\'s coverage note honestly: the answer covers data loaded by enabled layers, not the whole world. If the needed layer is disabled, say so and offer to enable it. For follow-ups about the same set ("which of THOSE is closest?"), call analyst_query with followUp=true and only the new filter/sort.',
'For a request to enable an aircraft layer and SELECT or FIND the nearest/closest aircraft near a named place — for example, "Turn on flights and select the closest aircraft to Austin" — call select_nearest_aircraft once. It atomically turns on the requested aircraft layer first, waits for location arrival, refreshes that layer for the destination viewport, filters out landed/on-ground records, and selects the nearest airborne result. A healthy fallback feed is valid data, never an enable failure. Do not also call fly_to_location, set_layer_visibility, analyst_query, track_entity, set_context_mode, or control_cockpit for the same request. SELECT/FIND never implies Contacts or Cockpit unless the user explicitly asks for either mode.',
'For ANALYTICAL questions about loaded layer data — how many / which / fastest / highest / biggest / nearest / next flights, ships, fires, earthquakes, satellites, launches, storms, transit, bikes, bases, datacenters or dams ("how many flights over Texas", "anything above 40,000 feet") — call analyst_query, not get_entity_context. Always set scope by WHERE: "around here" or "near this" while pointing is kind pointer, never view. Filter on the attribute the user names ("MODIS" → sensor eq MODIS). Say the count with its scope in a few words ("37 loaded flights over Texas") plus one or two examples by name. If the needed layer is off, say so and offer to turn it on. "Which of THOSE…" about the last answer → followUp=true with only the new filter/sort.',
'WORLD QUERIES — the query tools (get_weather, get_wind, search_places, places_nearby, plan_route, get_cyclones, get_fire_perimeters, get_bike_share, get_transit_vehicles, get_traffic_flow, situation_brief, military_awareness and the other get_* and find_* tools you have) look up data anywhere in the world without changing the map and without any layer being on. Use them when the user asks about a place they are not looking at or data whose layer is off ("what is the weather in Tokyo", "how do I drive from Austin to Dallas", "any wildfires in California"). For aircraft, ships, earthquakes, active fires, datacenters, dams and satellites overhead, use analyst_query over the layers instead, turning the layer on first when the user wants it. Use analyst_query and get_entity_context for what the app has loaded or what is on screen. Answer from the result summary and data, mention its source when it has one, and never claim the map changed. If the user also wants to SEE it, use the matching app action (fly_to_location, set_layer_visibility) as well.',
'FEED STATE CONTRACT — analyst_query and get_current_view_state carry feedProvenance from the same layerFeedState the Data Layers chips use (nominal/loading/degraded/stale/fallback/unavailable, or off). NEVER narrate a count as live or current when feedProvenance.overall is not nominal. Say the feedState in the same breath as the count ("12 flights in view, STALE"). If unavailable, do not invent a count; say the feed is unavailable. Fallback is valid data — name the fallback source, never call it an enable failure. Confirm only what the tool result returned.',
'COUNTING CONTRACT — what "near" means. (1) While Contacts is ACTIVE, "near / nearby / how many aircraft" means the Contacts window: answer from contactsWindow in the tool result — those are the exact numbers on the user\'s panel. set_context_mode, analyst_query, and get_current_view_state carry it after Contacts settles. For "Open Contacts and tell me how many aircraft are within 250 km", call set_context_mode{mode:"contacts"} first and answer from contactsWindow.aircraft; do not answer from a pre-Contacts analyst query. analyst_query\'s own count measures currently-loaded records and is usually lower; never give it as the window count. CENTER PRECEDENCE for a nearby/how-many ask, in order: an explicit place in the question ("over Texas", "near Austin") always wins and ignores Contacts state; else the CONTACTS SUBJECT when Contacts is active and has one — a selected datacenter, dam, fire, or cable does NOT silently become the center; else an entity the user explicitly names ("around this datacenter"); else the current view, said aloud ("nothing is selected, so this is the current view"). With Contacts active but NO subject yet, use the view and say so; never read an empty panel. (2) With Contacts OFF, "nearby" means in view; "near <place>" means a radius around that place. (3) EVERY count names its scope in words — "42 in your window", "8 in view", "about 30 within 250 km of Austin" — never a bare number; analyst_query returns scopeLabel for exactly this. Two different numbers with named scopes are not a contradiction; say both if asked. (4) State counts VERBATIM — never estimate, round, or hedge ("a few", "less than a dozen"): if a tool returns 46, say 46. (5) When it matters, add once: counts cover loaded data, and the flights layer loads where you look.',
'WHERE, for every tool that takes a place or scope, in this order: (1) a place the user names; (2) explicit pointing — "this/that one/here/around here" while pointer_context shows pointing or a target → "pointer"; (3) the Contacts subject while Contacts is active, or the selection when the user refers to it; (4) the current view. A selected datacenter, dam, fire or cable never silently becomes the centre.',
'FEED STATE: when a count\'s feed is stale or degraded, add that one word ("12 flights in view, stale"); never call it live. If unavailable, give no number: say the feed is unavailable. Fallback feeds are valid data; name them only if asked.',
'COUNTING CONTRACT — what "near" means. (1) While Contacts is ACTIVE, a bare "near / nearby / how many aircraft" means the settled Contacts subject window: its count is contactsWindow.aircraft. For "Open Contacts and tell me how many aircraft are within 250 km of the active subject", call set_context_mode{mode:"contacts"} first; use its window count only when the requested radius matches contactsWindow.radiusKm. A count does NOT fulfill a requested list, ranking or filter: call analyst_query even when set_context_mode already returned the count. For "within 250 km of the active subject, list the five closest", call analyst_query{layers:["flights","military"],scope:{kind:"radius",km:250},sortBy:"distance",limit:5}, omitting center so the active Contacts subject supplies it. Use the actual requested km for any other radius; never substitute the panel\'s 250 km count for a different radius. Analyst results supply the requested items and filtered count; never invent a list from contactsWindow alone. The centre follows WHERE: explicit view, named place, pointing and explicit coordinates retain their scopes and never become Contacts queries. Never invent center coordinates such as 0,0. With Contacts active but no subject yet, use the view and name that scope. (2) With Contacts OFF, "nearby" means in view; "near <place>" means a radius around that place. (3) EVERY count names its scope in words — "42 in your window", "8 in view", "30 within 250 km of Austin" — never a bare number; analyst_query returns scopeLabel for exactly this. Two numbers with named scopes are not a contradiction; say both if asked. (4) State counts VERBATIM — never estimate, round, or hedge: if a tool returns 46, say 46.',
'While Cockpit is active, navigate with control_cockpit (next/previous, optionally targetLayer or aircraftClass). track_entity and fly_to_location are REFUSED by design while Cockpit owns the camera — that refusal is correct, not an error to retry. To go somewhere else, exit Cockpit first. control_cockpit enter establishes Contacts itself, so do not call set_context_mode before or after it.',
'When the target layer is unknown, OMIT layerId in track_entity so it searches all enabled layers. Passing the wrong layerId ("flights" for a military contact) returns "Nothing matched" even though the contact is loaded.',
'If get_entity_context has no selected object or overlay entities, use its basemap context: Google Photorealistic 3D Tiles/Cesium source, center target coordinates, reverse-geocoded place, camera altitude, active style, and enabled layers. Do not say there is nothing unless the basemap target is also unavailable.',
'If basemap context includes knownLandmarks, prefer the nearest known landmark by name for "what am I looking at" answers. For example, if knownLandmarks includes Eiffel Tower, say Eiffel Tower.',
'At local zoom, use basemap nearbyPlaces, place.labels, viewportPlaces.visibleLabels, and viewportPlaces.streetLabels to identify the building, premises, roads, and named places visible around the screen target.',
'If basemap context includes viewportPlaces, prefer dominantCountry, dominantRegion, and dominantLocality over raw coordinates.',
'When basemap context includes viewportSamples or an inferred country, trust that over a single reverse-geocoded address. If most samples indicate Iran, say Iran, not the United States.',
'When a viewport screenshot is attached after get_entity_context, read clearly legible street, building, and place labels from it and combine them with structured label context. Respect scene viewScale: at global/continental/regional scale, avoid naming a precise street/city from one center pixel.',
'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.',
'When a request requires a tool call, do not speak in the same response as the tool call. Call the tool first.',
'When a single user request contains MULTIPLE changes (e.g. "switch to operator layout, use balanced detection at density 50, and switch to Bing aerial"), call ALL the corresponding tools — multiple tool calls in sequence — before speaking. Never confirm a partial subset. If a later tool fails, say which parts succeeded and which failed.',
'After receiving tool output, speak exactly one short confirmation. Do not repeat the confirmation.',
'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. "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, 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.',
'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 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.',
// INSTRUCTION-ONLY mapping for the two globe-scale named views.
//
@@ -50,27 +47,23 @@ function realtimeInstructions(
'NAMED VIEWS are shorthand for tool calls you already have — there is no "mode" tool for them. Treat ONLY these as the shorthand: "infrastructure mode" / "the infrastructure view" / "show me global infrastructure" means three set_layer_visibility calls (local-datacenters, local-dams, telegeography-submarine-cables) plus zoom_to_globe; "environmental mode" / "earth watch" / "active events", said as the name of a view, means set_layer_visibility for local-firms and earthquakes plus zoom_to_globe. Anything vaguer is NOT this shorthand — an open-ended question about the world or the news is an ordinary question: answer it, or use analyst_query over the layers already on. Never switch a whole view on to answer a question nobody asked to see. When you do run one, make every call before speaking, then give one confirmation naming the resulting state; if the fires layer comes back unavailable because no FIRMS key is configured, say so plainly — the earthquakes still loaded. "Live contacts" and "space missions" are NOT this pattern: they stay set_context_mode{mode:"contacts"} and set_context_mode{mode:"space-missions"}.',
'For visual filter requests, call set_visual_style with one of the allowed style IDs.',
'SHIPS vs STYLES: "vessels" is easily heard as "visuals". "Show me vessels", "turn on vessels", "the vessels", "visuals" or "vestibules" said WITHOUT a style name means the ships layer: set_layer_visibility{layerId:"ais-live-vessels"}, exactly as "ships" or "boats" does. Call set_visual_style only when the user names a style (retro/CRT, surveillance/night vision, thermal, anime, noir, snow, normal) or says filter, effect or look. Never turn on a different data layer (such as fires) for a ships request.',
'Disambiguation table — basemap vs layer vs style: basemap switching requires an explicit stack name — "Bing aerial" means set_map_stack bing-aerial, "aerial with labels" means bing-labels, "OSM"/"road map" means osm, "Esri"/"Esri imagery" means esri-imagery, "Google 3D"/"photorealistic" means photoreal. Any mention of "satellite" or "satellites" ALWAYS means the satellites DATA LAYER via set_layer_visibility, never a basemap. "surveillance"/"night vision"/"thermal" are visual STYLES via set_visual_style.',
'Disambiguation table — basemap vs layer vs style: basemap switching requires an explicit stack name — "Bing aerial" means set_map_stack bing-aerial, "aerial with labels" means bing-labels, "OSM"/"road map" means osm, "Esri"/"Esri imagery" means esri-imagery, "Google 3D"/"photorealistic" means photoreal. Any other mention of "satellite" or "satellites" means the satellites DATA LAYER via set_layer_visibility, never a basemap — except "recent/latest satellite imagery" (the recent-imagery layer) and "weather satellite"/clouds (weather-satellite). "surveillance"/"night vision"/"thermal" are visual STYLES via set_visual_style.',
'HUD requests ("hud on/off", "switch to operator/minimal/tactical/cyber layout") use set_hud. Detection requests ("detection on", "dense mode", "balanced mode", "sparse mode", "set density to 25", "use weighted allocation") use set_detection. Density snaps to 0/25/50/75/100 and derives Sparse/Balanced/Dense; panoptic is a legacy alias for Dense.',
'Cyber sonar requests use set_cyber_sonar: enabled, rings, rangePct, intensityPct (Power), opacityPct, sectorDeg. For settings questions read get_current_view_state.controls.hud.sonar. Sonar is not detection. Do not silently switch themes, reveal the HUD or enable sonar when changing a slider. If the user explicitly requests Cyber plus sonar settings, call set_hud first, wait for success, then set_cyber_sonar. Confirm returned values; mapSweepActive and contactSweepActive distinguish saved settings from active map effects, including in Cockpit or reduced motion. Do not claim visible contacts solely because enabled is true.',
'Bloom/sharpen requests use set_post_processing. Scene requests ("play orbital watch", "stop the scene", "what scenes are there") use control_scene. CCTV camera requests ("next camera", "nearest camera", "select the Congress camera", "show coverage") use control_cctv — the CCTV layer must be enabled first.',
'Radio playback requests use control_radio. "Turn on/start the radio" means action=play; action=enable only reveals Radio markers and must be reserved for explicit "show/enable the Radio layer/markers" requests. After a prepared playback result, briefly confirm any other completed actions and say "Turning on the radio"—never claim it is already playing. The client keeps Radio muted until playback is verified, then closes voice before restoring Radio volume. Examples: "play news near Austin" → select category=news locationId=austin; "play US news" → select category=news country=US; "Radio volume 30" → volume; pause/resume/stop/next/previous use the matching action. Radio selection never moves the camera.',
'"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.',
"After frame_overhead, speak ONLY from the tool result's count field — e.g. 'Framed fourteen aircraft, labels on'; never reassess or second-guess the count aloud.",
'Confirmations echo the RESULTING state, never the request: "HUD operator 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.',
'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.',
'Only supply rangeM when the user asks for a particular numeric height, distance, closer view, or wider view.',
'For relative requests such as "zoom out a little", "pull back", "zoom in more", or "get closer", always call adjust_camera_zoom. But "globe view", "whole earth", "the whole planet", or "zoom all the way out" is an ABSOLUTE framing: call zoom_to_globe once instead — repeated adjust_camera_zoom calls can never reach the globe. Never claim the camera moved without the tool returning ok=true.',
'Keep spoken confirmations short, e.g. "Opening datacenters" or "Flying to London".',
'WHITEBOARD THE WORLD: whenever you describe or explain a specific place, building, campus, district, boundary, or a spatial relationship between places, call annotate_map to mark it visually as you talk — like sketching on the map. To call out a specific building, campus, compound, park, or district, use type=area (it traces and encloses the real footprint — a building gets a glowing volume, a district gets a draped outline). Use type=highlight only for a transient pulse on a precise spot that has no meaningful footprint, and type=pin to drop a labeled marker. Examples: "what is the Palace of Fine Arts?" → an AREA on it; "the old military base next to it" → an AREA on the Presidio; "ILM is right here" → a pin; "it sits next to the Marina" → an arrow from one to the other. Prefer place NAMES so the app resolves real positions and outlines; never invent coordinates or pixel locations.',
'On every annotation, also set entityKind to what the thing IS when you know it: building (one structure), compound (campus/grounds/mall/park), district (neighborhood/area of a city), street (a named road), or point_feature (a monument, statue, memorial, plaque, fountain, or other small point landmark). entityKind is a FACT about the target, independent of the mark type you chose — monuments and statues are point_feature even when you use type=area; the app then anchors them as precise points instead of guessing at a footprint.',
'WHITEBOARD THE WORLD: when you describe a specific place, building, campus, district or boundary, or how places relate, call annotate_map as you talk. type=area traces a building, campus, compound, park, district or boundary outline; pin marks a spot; highlight pulses a spot with no footprint; arrow joins two places ("it sits next to the Marina"). Use place names; screenX/screenY only for a spot you can see in the latest screenshot but cannot name; never invent coordinates. Set entityKind whenever you know what the target is.',
annotationGuidance,
'If an annotate_map result has partial:true or any failedLabels, do not pretend those places appeared — briefly work into your narration that you could not pinpoint them (e.g. "I couldn\'t place X"). If a route comes back as a direct line (no street route was found), describe it as a straight-line distance, not a walking/driving time. If an annotate_map result has capped:true, the map is full — ASK the user whether to clear before drawing more; do not clear unprompted. outlinePending:true is NOT a failure, but it is also NOT an outline: the anchor mark is placed and the boundary is still being traced in the background. Narrate it in progress — e.g. "tracing the boundary now" — and NEVER state the outline is already drawn or visible; it may yet come back as just a point. A later system item of type map_annotation_outline reports the final outcome per mark (status resolved or failed, with its label): use it to quietly confirm, or to correct yourself if you implied a boundary that stayed a point — an honest miss beats a misleading guess.',
'PREFER NAMES. Only when you cannot name or geocode a place but you can clearly SEE the exact spot in the most recent viewport screenshot, fall back to screenX/screenY (normalized 0..1 from that image) to point at it; the app converts the pixel to a real world point. Never use screenX/screenY for something you could name.',
'PATHS vs DISTANCES: for "walking/driving route from A to B" (or through several stops), use type=route with the ordered points and the matching mode (walking/driving/cycling) — the app draws the real street-following path on the map and reports distance and travel time, which you can read aloud. For "how far is X from Y", "is it nearby", or "X is next to Y", use type=arrow between the two — it draws a floating connector and shows the straight-line distance. Do NOT use route for a simple distance/proximity question.',
'annotate_map results: work any say line in naturally (places not found, a straight-line fallback with no travel time, or a full map — then ask before clearing). outlinePending means the boundary is still being traced: never claim it is drawn. A later map_annotation_outline system item reports each outcome; use it to quietly confirm or correct yourself.',
'ROUTES vs DISTANCES: "walking/driving route from A to B" → type=route with the ordered points and the mode; the app draws the street path and reports distance and time you can read aloud. "How far is X from Y" or "X is next to Y" → type=arrow (straight-line distance), never route.',
].join('\n');
}
server/providers/openai/realtime.js
+215 -17
View File
@@ -10,15 +10,130 @@ import {
OPENAI_REALTIME_REASONING_DEFAULT,
OPENAI_REALTIME_CONTEXT_TOKENS_DEFAULT,
OPENAI_REALTIME_CONTEXT_RETENTION_DEFAULT,
OPENAI_REALTIME_TRANSCRIBE_MODEL_DEFAULT,
} from './constants.js';
import { realtimeInstructions } from './instructions.js';
import { GEV_REALTIME_TOOLS } from './tools.js';
import {
preferCodexOAuth,
readCodexOAuthAccessToken,
createCodexOAuthLogin,
} from './codex-auth.js';
const LOOPBACK_ADDRESSES = new Set(['127.0.0.1', '::1', '::ffff:127.0.0.1']);
function isLoopbackRequest(req) {
return LOOPBACK_ADDRESSES.has(String(req.socket?.remoteAddress || ''));
}
function isSameOriginRequest(req) {
const origin = String(req.headers?.origin || '').trim();
if (!origin) return true;
const host = String(req.headers?.host || '').trim();
if (!host) return false;
const protocol = req.socket?.encrypted ? 'https:' : 'http:';
try {
return new URL(origin).origin === new URL(`${protocol}//${host}`).origin;
} catch {
return false;
}
}
function requestQuery(req) {
try {
return new URL(req.url || '', 'http://localhost').searchParams;
} catch {
return new URLSearchParams();
}
}
function resolveRealtimeAuthMode(query) {
const requested = String(query.get('auth') || 'api-key').toLowerCase();
if (requested === 'api-key' || requested === 'oauth') return requested;
return null;
}
function createRealtimeOAuthStatusHandler({
oauthLogin = createCodexOAuthLogin(),
} = {}) {
return (req, res) => {
res.setHeader('Cache-Control', 'no-store');
res.setHeader('Content-Type', 'application/json');
if (req.method !== 'GET') {
res.statusCode = 405;
res.end(JSON.stringify({ error: 'Method not allowed' }));
return;
}
if (!isLoopbackRequest(req)) {
res.statusCode = 403;
res.end(
JSON.stringify({
available: false,
error: 'ChatGPT OAuth is available only from this machine',
}),
);
return;
}
res.statusCode = 200;
res.end(JSON.stringify(oauthLogin.status()));
};
}
function createRealtimeOAuthLoginHandler({
oauthLogin = createCodexOAuthLogin(),
} = {}) {
return async (req, res) => {
res.setHeader('Cache-Control', 'no-store');
res.setHeader('Content-Type', 'application/json');
if (req.method !== 'POST') {
res.statusCode = 405;
res.end(JSON.stringify({ error: 'Method not allowed' }));
return;
}
if (!isLoopbackRequest(req)) {
res.statusCode = 403;
res.end(
JSON.stringify({
available: false,
error: 'ChatGPT OAuth sign-in is available only from this machine',
}),
);
return;
}
if (!isSameOriginRequest(req)) {
res.statusCode = 403;
res.end(
JSON.stringify({
available: false,
error: 'Cross-origin ChatGPT OAuth sign-in is not allowed',
}),
);
return;
}
try {
const result = await oauthLogin.start();
res.statusCode = result.available ? 200 : result.loginFailed ? 503 : 202;
res.end(JSON.stringify(result));
} catch {
res.statusCode = 503;
res.end(
JSON.stringify({
available: false,
error: 'Could not start ChatGPT sign-in',
}),
);
}
};
}
function createRealtimeTokenHandler({
annotationGuidance,
endpoint = 'https://api.openai.com/v1/realtime/client_secrets',
fetchImpl = (...args) => fetch(...args),
resolveApiKey = () => process.env.OPENAI_API_KEY,
resolveOAuthAccessToken = () => readCodexOAuthAccessToken(),
environment = process.env,
models = {},
tools = GEV_REALTIME_TOOLS,
} = {}) {
@@ -31,15 +146,84 @@ function createRealtimeTokenHandler({
return;
}
const query = requestQuery(req);
const authMode = resolveRealtimeAuthMode(query);
if (!authMode) {
res.statusCode = 400;
res.setHeader('Content-Type', 'application/json');
res.end(JSON.stringify({ error: 'Unsupported cloud voice auth mode' }));
return;
}
let oauthPinned;
try {
oauthPinned = preferCodexOAuth(environment);
} catch (error) {
res.statusCode = 503;
res.setHeader('Content-Type', 'application/json');
res.end(JSON.stringify({ error: error.message }));
return;
}
if (oauthPinned && authMode !== 'oauth') {
res.statusCode = 503;
res.setHeader('Content-Type', 'application/json');
res.end(
JSON.stringify({
error:
'ChatGPT OAuth is required by GEV_PREFER_CODEX_OAUTH. Select USE CHATGPT OAUTH in Provider Settings.',
code: 'CODEX_OAUTH_REQUIRED',
}),
);
return;
}
// Per-IP throttle (GEV_RATELIMIT_OPENAI_PER_MIN). On by default; 0 disables.
if (!enforceRateLimit(openAiRateLimiter(), req, res)) return;
const apiKey = resolveApiKey();
if (!apiKey) {
res.statusCode = 503;
res.setHeader('Content-Type', 'application/json');
res.end(JSON.stringify({ error: 'OPENAI_API_KEY is not set' }));
return;
let bearer;
if (authMode === 'oauth') {
if (!isLoopbackRequest(req)) {
res.statusCode = 403;
res.setHeader('Content-Type', 'application/json');
res.end(
JSON.stringify({
error: 'ChatGPT OAuth voice is available only from this machine',
}),
);
return;
}
try {
bearer = resolveOAuthAccessToken();
} catch (error) {
res.statusCode = 503;
res.setHeader('Content-Type', 'application/json');
res.end(
JSON.stringify({
error: error?.message || 'ChatGPT sign-in is unavailable',
code: error?.code || 'CODEX_OAUTH_UNAVAILABLE',
}),
);
return;
}
if (!bearer) {
res.statusCode = 503;
res.setHeader('Content-Type', 'application/json');
res.end(
JSON.stringify({
error: 'ChatGPT sign-in is unavailable',
code: 'CODEX_OAUTH_UNAVAILABLE',
}),
);
return;
}
} else {
bearer = resolveApiKey();
if (!bearer) {
res.statusCode = 503;
res.setHeader('Content-Type', 'application/json');
res.end(JSON.stringify({ error: 'OPENAI_API_KEY is not set' }));
return;
}
}
// Voice model tier, requested by the client as ?tier=standard|mini.
@@ -48,15 +232,7 @@ function createRealtimeTokenHandler({
// bad querystring degrades to a normal session rather than a dead mic.
// The env overrides stay authoritative per tier (see .env.example) —
// a wrong upstream model id is then a config fix, not a code change.
const requestedTier = (() => {
try {
return new URL(req.url || '', 'http://localhost').searchParams.get(
'tier',
);
} catch {
return null;
}
})();
const requestedTier = query.get('tier');
const tier = resolveVoiceModel(requestedTier).tier;
const model =
tier === 'mini'
@@ -89,6 +265,14 @@ function createRealtimeTokenHandler({
OPENAI_REALTIME_CONTEXT_RETENTION_DEFAULT,
),
);
// User captions for the voice card. Billed separately from the session.
const transcribeModel =
process.env.OPENAI_REALTIME_TRANSCRIBE_MODEL ||
OPENAI_REALTIME_TRANSCRIBE_MODEL_DEFAULT;
const transcription =
transcribeModel.toLowerCase() === 'off'
? {}
: { transcription: { model: transcribeModel } };
const sessionConfig = {
session: {
type: 'realtime',
@@ -104,6 +288,7 @@ function createRealtimeTokenHandler({
audio: {
input: {
noise_reduction: { type: 'near_field' },
...transcription,
turn_detection: {
type: 'semantic_vad',
eagerness: 'low',
@@ -125,7 +310,7 @@ function createRealtimeTokenHandler({
redirect: 'error',
signal: AbortSignal.timeout(30_000),
headers: {
Authorization: `Bearer ${apiKey}`,
Authorization: `Bearer ${bearer}`,
'Content-Type': 'application/json',
'OpenAI-Safety-Identifier': 'gev-local-dev',
},
@@ -139,6 +324,15 @@ function createRealtimeTokenHandler({
// case where a bogus ?tier= was silently downgraded to standard.
res.setHeader('X-GEV-Voice-Tier', tier);
res.setHeader('X-GEV-Voice-Model', model);
res.setHeader(
'X-GEV-Voice-Auth',
authMode === 'oauth' ? 'codex-oauth' : 'env',
);
// Captions are billed separately; the client meters them with this id.
res.setHeader(
'X-GEV-Voice-Transcribe-Model',
transcription.transcription ? transcribeModel : 'off',
);
if (requestedTier && !isKnownVoiceTier(requestedTier)) {
res.setHeader('X-GEV-Voice-Tier-Fallback', '1');
}
@@ -168,4 +362,8 @@ function createRealtimeTokenHandler({
};
}
export { createRealtimeTokenHandler };
export {
createRealtimeOAuthLoginHandler,
createRealtimeOAuthStatusHandler,
createRealtimeTokenHandler,
};
server/providers/openai/toolDescriptions.js
+47 -26
View File
@@ -1,3 +1,8 @@
import {
voiceLayerAliasHint,
voiceQueryFieldHint,
} from '../../../src/voice/layerManifest.js';
export const ACTION_DESCRIPTIONS = {
fly_to_location: {
description:
@@ -12,7 +17,11 @@ export const ACTION_DESCRIPTIONS = {
},
query: {
description:
'Plain place search query, e.g. "London", "Eiffel Tower", or "Dubai Marina".',
'Plain place search query, e.g. "London", "Eiffel Tower", or "Dubai Marina". "pointer" = the spot under the cursor.',
$position: 1,
},
referent: {
description: 'Numbered item n from the last result list.',
$position: 1,
},
viewMode: {
@@ -76,13 +85,13 @@ export const ACTION_DESCRIPTIONS = {
$position: 1,
},
set_layer_visibility: {
description: "Enable or disable one registered God's Eye View data layer.",
description:
"Enable or disable one God's Eye View data layer. Every shipped layer is in the enum; never tell the user a listed layer does not exist.",
$position: 1,
parameters: {
properties: {
layerId: {
description:
'Common-name mapping for the non-obvious ids: space mission(s) → rocket-launches; fires/wildfires/active fires → local-firms (NASA FIRMS); ships/vessels/boats → ais-live-vessels; undersea/submarine cables → telegeography-submarine-cables; datacenters → local-datacenters; dams → local-dams; bikes/bike share → bikeshare; street traffic/congestion → traffic; traffic cameras → cctv; internet radio/stations → radio; ALPR/license plate readers/Flock cameras → alpr-cameras; local ADS-B/my receiver/my antenna (aircraft heard by a local RTL-SDR receiver) → local-adsb.',
description: `Spoken names: ${voiceLayerAliasHint()}.`,
$position: 1,
},
},
@@ -154,9 +163,13 @@ export const ACTION_DESCRIPTIONS = {
properties: {
scope: {
description:
'Use auto by default. selected returns the clicked/selected entity; in_view returns visible entities near the screen center.',
'Use auto by default. selected returns the clicked/selected entity; in_view returns visible entities near the screen center; pointer returns what the cursor is on.',
$position: 2,
},
referent: {
description: 'Numbered item n from the last result list.',
$position: 1,
},
layerId: {
description: 'Optional layer filter for visible entity context.',
$position: 2,
@@ -349,12 +362,17 @@ export const ACTION_DESCRIPTIONS = {
properties: {
query: {
description:
'Callsign, ship name, satellite name, ICAO hex, MMSI, or NORAD id.',
'Callsign, ship name, satellite name, ICAO hex, MMSI, or NORAD id. "pointer" = the contact under the cursor.',
$position: 1,
},
referent: {
description:
'Numbered item n from the last result list (-1 = last); query may then be its label.',
$position: 1,
},
layerId: {
description:
'Optional layer hint: flights | military | ais-live-vessels | satellites.',
'Optional: flights, military, ais-live-vessels or satellites. Other layers are not trackable; for fires use query "biggest fire".',
$position: 1,
},
},
@@ -381,7 +399,7 @@ export const ACTION_DESCRIPTIONS = {
},
annotate_map: {
description:
'Draw annotations on the 3D map to visually point out what you are talking about — like sketching on a whiteboard over the world. Use this whenever you mention a specific place, building, campus, boundary, district, or a relationship between two places, so the user can SEE what you mean. Give place NAMES (preferred) or explicit lat/lng; the app resolves them to real-world positions and real building/area outlines — never guess pixel positions. Call this as you begin describing something, and you may mark several places in one call.',
'Mark places on the 3D map as you talk about them (see WHITEBOARD): pins, highlights, footprints and boundaries, arrows, routes and labels. Give place names (or explicit lat/lng); the app resolves real positions and outlines. Several places may go in one call.',
$position: 1,
parameters: {
properties: {
@@ -398,7 +416,7 @@ export const ACTION_DESCRIPTIONS = {
},
target: {
description:
'Place name to resolve, e.g. "Palace of Fine Arts, San Francisco", "the Pentagon", "Presidio of San Francisco". Preferred over coordinates. For a specific monument/statue/feature that sits within a larger landmark, use its OWN name + city ("Tejano Monument, Austin", "Texas African American History Memorial, Austin") — do NOT phrase it as "X at the Texas State Capitol", which makes the geocoder collapse several of them onto the same centroid so they stack on one spot.',
'Place name to resolve ("Palace of Fine Arts, San Francisco"), or "pointer" for the spot under the cursor. A monument inside a larger landmark gets its own name + city ("Tejano Monument, Austin"), never "X at the Texas State Capitol" (that stacks them on one centroid).',
$position: 2,
},
points: {
@@ -450,27 +468,24 @@ export const ACTION_DESCRIPTIONS = {
},
entityKind: {
description:
'What KIND of thing the target IS — a fact, not a style choice: building = one structure; compound = campus/grounds/mall/park; district = neighborhood or area of a city; street = a named road/corridor; point_feature = monument/statue/memorial/plaque/fountain or other small point landmark. Set it whenever you know it — it routes the resolver to the right footprint source (point_feature anchors monuments as precise points instead of adopting a nearby building outline).',
'What the target IS (a fact, not a style): building = one structure; compound = campus/grounds/mall/park; district = neighborhood; street = a named road; point_feature = monument/statue/memorial/fountain, anchored as a precise point. Set it whenever you know it.',
$position: 2,
},
screenX: {
description:
'Fallback only: when you cannot name/geocode the place but can SEE it in the latest viewport screenshot, the normalized horizontal position (0=left, 1=right) of the spot. The app converts it back to a real world point under that pixel.',
'Fallback only, for a spot visible in the latest screenshot that you cannot name: normalized x (0=left, 1=right).',
$position: 3,
},
screenY: {
description:
'Fallback only: normalized vertical position (0=top, 1=bottom) of the spot in the latest viewport screenshot.',
description: 'Fallback only: normalized y (0=top, 1=bottom).',
$position: 3,
},
toScreenX: {
description:
'For type=arrow: normalized x of the arrow destination from the screenshot (pixel fallback).',
description: 'For type=arrow: destination x (pixel fallback).',
$position: 3,
},
toScreenY: {
description:
'For type=arrow: normalized y of the arrow destination from the screenshot (pixel fallback).',
description: 'For type=arrow: destination y (pixel fallback).',
$position: 3,
},
},
@@ -528,18 +543,18 @@ export const ACTION_DESCRIPTIONS = {
},
analyst_query: {
description:
'Answer questions ABOUT the data currently loaded on the map — counts, lists, superlatives, and attribute filters over live layers (flights, military, ships, fires, earthquakes, satellites, datacenters, dams). Examples: "how many flights over Texas", "biggest fire near LA", "which ships are headed to Oakland", "anything above 40,000 feet", "fastest thing in view". For satellites and infrastructure, counts and ranks cover only bounded examined loaded records; omitted records can change nearest/count. Queries ONLY client-side data from ENABLED layers — if the needed layer is off, say so and offer to enable it. For a follow-up about the previous answer\'s set ("which of those is closest?"), set followUp=true and send only the new filters/sort.',
'Counts, lists, superlatives and attribute filters over records loaded by ENABLED layers — "how many flights over Texas", "biggest fire near LA", "ships headed to Oakland", "next rocket launch". A requested list or ranking requires this tool even after set_context_mode returned a Contacts count; that count alone has no requested items. complete:false means the count is a floor ("at least") and rankings cover the records examined; partial names unanswered layers. Items carry lat/lon for a follow-up fly_to_location. ok:false codes: LAYER_OFF (offer to enable), NOT_READY (loading), FOLLOW_UP_MISMATCH (ask again without followUp), UNKNOWN_FIELD/UNKNOWN_SCOPE/BAD_VALUE (retry with the allowed values).',
$position: 1,
parameters: {
properties: {
layers: {
description:
'Layers to query. fires/wildfires → local-firms; ships/vessels → ais-live-vessels.',
'Layers to query. fires → local-firms; ships → ais-live-vessels; buses/trains → transit; hurricanes → weather-cyclones; bases → military-installations; my receiver → local-adsb. Units differ per layer, so rank speed within one layer.',
$position: 2,
},
scope: {
description:
'Spatial scope. Default: view (near the camera). Use kind=region for "over Texas"-style asks; kind=anywhere for global questions.',
'Always set it (see WHERE). Explicit "in view" uses view; "nearby" uses view when Contacts is off. Around the active Contacts subject uses radius with the requested km and center omitted, never view: the five closest within 250 km use scope:{kind:"radius",km:250}, sortBy:"distance", limit:5. For another requested radius use its actual km, not 250. pointer = "around here/this" while pointing (radius at the cursor); region = "over Texas"; radius with center {lat, lon} = "near <place>" or explicit coordinates; anywhere = no place ("biggest anywhere", "today"). Preserve explicit view, named place, pointer and explicit center even while Contacts is active; never invent coordinates. There is no drawn-area scope yet: say so rather than answering for the view.',
$position: 2,
properties: {
name: {
@@ -548,23 +563,29 @@ export const ACTION_DESCRIPTIONS = {
$position: 1,
},
km: {
description: 'For kind=radius.',
description:
'For kind=radius or pointer: the actual requested kilometers. An active-subject 250 km request uses 250; another requested radius keeps that number.',
$position: 1,
},
center: {
description:
'Omit for a radius around the active Contacts subject. Supply only an explicitly requested coordinate or a resolved named-place coordinate; never invent 0,0 or replace an explicit center with the subject.',
$position: 1,
},
},
},
filters: {
description:
'Attribute predicates, ANDed. ALTITUDE IS METERS (40,000 ft = 12192). Fields: altitudeM, speedMps, military, onGround, aircraftClass, callsign, operator, routeOrigin, routeDestination, originCountry (flights); speedKts, shipType, destination (ships); frp, confidence (fires); magnitude, depthKm, place (earthquakes).',
description: `ANDed; values keep their type (numbers, true/false). Altitude is meters (40,000 ft = 12192). Time fields take ISO; ageHours = hours ago. Every layer has id, lat, lon. Fields — ${voiceQueryFieldHint()}.`,
$position: 1,
},
sortBy: {
description: 'Field to rank by, or "distance" for nearest-first.',
description:
'Field to rank by, or "distance" (nearest first unless sortDir=desc).',
$position: 1,
},
followUp: {
description:
'true = re-query the PREVIOUS result set instead of fresh data.',
'true = re-filter the last answer (its layers) instead of fresh data.',
$position: 1,
},
},
@@ -572,7 +593,7 @@ export const ACTION_DESCRIPTIONS = {
},
next_iss_pass: {
description:
"When the user asks when the ISS / the space station will next fly over: returns the next geometric ISS pass with estimated visibility for the current camera location (or an explicit lat/lon) — rise time (ISO + minutes from now), rise compass direction, peak elevation, and duration. Requires the satellites layer to have loaded its catalog at least once this session; if it hasn't, tell the user to enable the satellites layer and try again.",
'Next ISS pass over the camera location (or lat/lon): rise time, direction, peak elevation, duration and estimated visibility. Needs the satellites layer to have loaded once; if not, ask the user to enable it.',
$position: 1,
parameters: {
properties: {
src/app/catalog.test.mjs
+16 -1
View File
@@ -65,13 +65,28 @@ test('data setup seals the caller catalog before controls can restore and drains
},
},
},
catalog: createLayerCatalog(layers, metadata(layers)),
catalog: {
...createLayerCatalog(layers, metadata(layers)),
getSourceAvailability: (id) =>
id === 'one'
? {
available: false,
reason: 'One: data source not configured',
}
: undefined,
},
defer: (release) => releases.push(release),
onData: (manager) => {
observed = manager;
},
});
assert.equal(observed, dataManager);
assert.equal(await dataManager.setEnabled('one', true), false);
assert.equal(dataManager.layers.get('one').initialized, false);
assert.equal(
dataManager.getAll().find(({ id }) => id === 'one').stats.error,
'One: data source not configured',
);
assert.deepEqual(attached, [['one', 'two']]);
assert.deepEqual([...dataManager.layers.keys()], ['one', 'two']);
assert.throws(() => dataManager.register({ id: 'late' }), /finalized/);
src/app/constructCatalog.js
+12 -38
View File
@@ -1,9 +1,9 @@
import { resolveCatalogSources } from './sourceComposition.js';
import { createWeatherClock } from '../layers/weather/clock.js';
import { createWeatherLayer } from '../layers/weather/index.js';
import { createCyclonesLayer } from '../layers/cyclones/index.js';
import { createWindLayer } from '../layers/wind/index.js';
import { createLayerCatalog } from './catalog.js';
import { MAPILLARY_SOURCE_METHODS } from '../layers/streetLevel/providers/mapillary/policy.js';
import { LAYER_STATE_REGISTRY } from '../data/layerState.js';
import { createMilitaryRegistry } from '../layers/aircraft/classification.js';
import { createApplicationFlights } from './layers/flights.js';
@@ -32,34 +32,6 @@ import { localGeoJsonServices } from './localGeojsonServices.js';
import { createBhoteKoshiEventLayer } from '../data/bhoteKoshiEvent.js';
import { createBhoteKoshiLocatorLayer } from '../data/bhoteKoshiLocator.js';
const SOURCE_METHODS = Object.freeze({
flights: ['getSnapshot'],
military: ['getSnapshot'],
vessels: ['getSnapshot'],
cctv: ['getCatalog', 'getHealth', 'getFrameUrl', 'getMediaUrl'],
radio: ['getDirectory', 'recordClick'],
traffic: [
'requestRoads',
'getStatus',
'fetchFlowForBounds',
'getFlowSessionStats',
'resetFlowTileCache',
],
bikeshare: ['getStations'],
installations: ['getMappedSites', 'searchNearby'],
satellites: ['readGroup'],
launches: ['getLaunches', 'getActiveTle'],
alpr: ['fetch'],
firms: ['getSnapshot'],
wind: ['getSnapshot'],
weather: ['getSnapshot'],
cyclones: ['getSnapshot'],
earthquakes: ['getSnapshot'],
'fire-perimeters': ['getSnapshot'],
cables: ['fetch'],
mapillary: MAPILLARY_SOURCE_METHODS,
});
/**
* Hardware-local layers are registered like any other but never enter share
* links or stored layer state: another browser cannot have this receiver.
@@ -86,6 +58,7 @@ export function createApplicationCatalog({
vesselOptions,
resolveAsset,
nepalBoundaryResolver,
streetLevelProviders,
}) {
if (!signal?.addEventListener)
throw new TypeError('An application lifetime signal is required');
@@ -93,12 +66,8 @@ export function createApplicationCatalog({
if (!surface?.groundFloor || !surface?.terrain)
throw new TypeError('Application surface services are required');
for (const [name, methods] of Object.entries(SOURCE_METHODS)) {
if (
methods.some((method) => typeof sources?.[name]?.[method] !== 'function')
)
throw new TypeError(`Invalid catalog source: ${name}`);
}
const sourceComposition = resolveCatalogSources(sources);
sources = sourceComposition.sources;
const militaryRegistry = createMilitaryRegistry();
const weatherClock = createWeatherClock();
const dispose = () => {
@@ -108,7 +77,8 @@ export function createApplicationCatalog({
};
signal.addEventListener('abort', dispose, { once: true });
try {
militaryRegistry.configureSource(sources.military, { signal });
if (sourceComposition.isConfigured('military'))
militaryRegistry.configureSource(sources.military, { signal });
const flights = createApplicationFlights({
surface,
source: sources.flights,
@@ -154,6 +124,7 @@ export function createApplicationCatalog({
createApplicationStreetLevel({
surface,
sources: { mapillary: sources.mapillary },
providers: streetLevelProviders,
}),
satellites,
createApplicationLaunches({ source: sources.launches, satellites }),
@@ -162,8 +133,8 @@ export function createApplicationCatalog({
createApplicationRadio({ surface, source: sources.radio }),
createApplicationTransit({ surface, source: sources.transit }),
createApplicationBikeshare({ source: sources.bikeshare }),
createApplicationDirections(),
createApplicationRecentImagery(),
createApplicationDirections({ source: sources.directions }),
createApplicationRecentImagery({ source: sources['recent-imagery'] }),
vessels,
installations,
createApplicationAwareness({
@@ -204,6 +175,9 @@ export function createApplicationCatalog({
);
return Object.freeze({
...catalog,
getSourceAvailability: sourceComposition.createAvailabilityLookup(
catalog.layers,
),
militaryRegistry,
surface,
weatherClock,
src/app/constructCatalog.test.mjs
+52 -1
View File
@@ -5,6 +5,7 @@ import { createApplicationCatalog } from './constructCatalog.js';
import { createStandaloneLayerSources } from '../standalone/layerSources.js';
import { catalogControlServices } from './catalog.js';
import { LayerLifecycle } from '../data/lifecycle.js';
import { fakeStreetLevelProvider } from '../testSupport/streetLevelFakes.mjs';
function fixtureSources(ids, calls) {
const sources = createStandaloneLayerSources();
@@ -116,7 +117,7 @@ test('invalid or already cancelled construction fails before classification can
assert.throws(
() =>
createApplicationCatalog({
sources: {},
sources: { flights: {} },
signal: lifetime.signal,
surface: fixtureSurface(lifetime.signal),
}),
@@ -140,3 +141,53 @@ function fixtureSurface(signal) {
eventTarget: null,
});
}
test('Mapillary can be omitted or replaced without changing catalog membership', (t) => {
const lifetime = new AbortController();
t.after(() => lifetime.abort());
const sources = fixtureSources([], []);
delete sources.mapillary;
const options = {
sources,
signal: lifetime.signal,
surface: fixtureSurface(lifetime.signal),
};
const catalog = createApplicationCatalog(options);
assert.equal(catalog.layers.length, 30);
assert.deepEqual(catalog.get('street-level').providerIds, []);
assert.equal(
catalogControlServices(catalog).streetLevelLayer,
catalog.get('street-level'),
);
assert.match(
catalog.get('street-level').getUIState().coverage.hint,
/No street-level imagery providers/,
);
const provider = fakeStreetLevelProvider({
id: 'example',
pickPrefix: 'example:',
});
const replacement = createApplicationCatalog({
...options,
streetLevelProviders: [provider],
});
assert.deepEqual(replacement.get('street-level').providerIds, ['example']);
assert.deepEqual(replacement.metadata, catalog.metadata);
assert.equal(provider.calls.activate, 0, 'construction must not acquire');
assert.deepEqual(
createApplicationCatalog({
...options,
sources: fixtureSources([], []),
streetLevelProviders: [],
}).get('street-level').providerIds,
[],
);
assert.throws(
() =>
createApplicationCatalog({
...options,
sources: { ...sources, mapillary: {} },
}),
/Mapillary source/,
);
});
src/app/data.js
+1
View File
@@ -13,6 +13,7 @@ export function createApplicationData({
// Initialize data layer manager
const dataManager = new LayerLifecycle(viewer, {
allowQaRegistration,
getSourceAvailability: catalog?.getSourceAvailability,
});
defer(async () => {
await dataManager.destroyAll();
src/app/layers/directions.js
+3 -9
View File
@@ -1,12 +1,6 @@
import { createApplicationDirectionsLayer } from '../../data/directions.js';
/**
* Construct one Directions layer using the application scene owners.
*
* It takes no data source: a route is fetched from `/api/route` when the
* operator places both endpoints, so there is nothing to supply up front.
* @returns {object} A fresh layer instance for this catalog.
*/
export function createApplicationDirections() {
return createApplicationDirectionsLayer();
/** Construct Directions with application scene owners and an explicit route source. */
export function createApplicationDirections({ source }) {
return createApplicationDirectionsLayer({ source });
}
src/app/layers/recentImagery.js
+8 -8
View File
@@ -3,17 +3,17 @@ import { createRecentImageryRenderer } from '../../layers/recentImagery/renderin
import { createThumbnailLoader } from '../../layers/recentImagery/thumbnails.js';
import { governorRequestRender } from '../../renderGovernor.js';
/**
* Construct the Recent Imagery layer with the real GIBS renderer and the
* browser thumbnail loader. It takes no data source: the catalog is NASA
* CMR and the tiles are GIBS, both browser-direct and keyless.
* @returns {object} A fresh layer instance for this catalog.
*/
export function createApplicationRecentImagery() {
/** Construct imagery presentation over one explicitly supplied acquisition source. */
export function createApplicationRecentImagery({ source }) {
return createRecentImageryLayer({
catalog: { searchHls: (...args) => source.searchHls(...args) },
renderer: createRecentImageryRenderer({
requestRender: governorRequestRender,
tileTemplate: (...args) => source.getTileTemplate(...args),
credit: source.credit || source.label || 'Imagery',
}),
thumbnails: createThumbnailLoader({
requestThumbnail: (...args) => source.getThumbnail(...args),
}),
thumbnails: createThumbnailLoader(),
});
}
src/app/layers/streetLevel.js
+13 -3
View File
@@ -5,10 +5,20 @@ import * as picking from '../../data/pickRegistry.js';
import * as input from '../../data/inputOwnership.js';
import * as render from '../../renderGovernor.js';
/** A new provider registers here; its chip, credit and share bit follow. */
export function createApplicationStreetLevel({ surface, sources }) {
/**
* Inject providers, or use Mapillary only when its source is supplied.
* An explicit provider list replaces the default; unused sources.mapillary is
* neither constructed nor validated, including when the list is empty.
*/
export function createApplicationStreetLevel({
surface,
sources = {},
providers = sources.mapillary == null
? []
: [createMapillaryProvider({ source: sources.mapillary })],
}) {
return createStreetLevelLayer({
providers: [createMapillaryProvider({ source: sources.mapillary })],
providers,
services: {
sprites,
picking,
src/app/layers/streetLevel.test.mjs
+29
View File
@@ -0,0 +1,29 @@
import assert from 'node:assert/strict';
import test from 'node:test';
import { createApplicationStreetLevel } from './streetLevel.js';
import { fakeStreetLevelProvider } from '../../testSupport/streetLevelFakes.mjs';
test('explicit providers replace the default source and an empty list removes it', () => {
const sources = { mapillary: {} };
const provider = fakeStreetLevelProvider({
id: 'example',
pickPrefix: 'example:',
});
const layer = createApplicationStreetLevel({
sources,
providers: [provider],
});
assert.deepEqual(layer.providerIds, ['example']);
assert.deepEqual(
createApplicationStreetLevel({ sources, providers: [] }).providerIds,
[],
);
assert.throws(
() => createApplicationStreetLevel({ sources }),
/Mapillary source/,
);
assert.throws(
() => createApplicationStreetLevel({ providers: null }),
/array/,
);
});
src/app/sourceComposition.js
+113
View File
@@ -0,0 +1,113 @@
const contract = (layers, methods) =>
Object.freeze({
layers: Object.freeze(layers),
methods: Object.freeze(methods),
});
/** Acquisition contracts and their consumers; records remain family-specific. */
export const CATALOG_SOURCE_CONTRACTS = Object.freeze({
directions: contract(['directions'], ['getRoute']),
'recent-imagery': contract(
['recent-imagery'],
['searchHls', 'getThumbnail', 'getTileTemplate'],
),
flights: contract(['flights'], ['getSnapshot']),
military: contract(['military'], ['getSnapshot']),
vessels: contract(['ais-live-vessels'], ['getSnapshot']),
cctv: contract(
['cctv'],
['getCatalog', 'getHealth', 'getFrameUrl', 'getMediaUrl'],
),
radio: contract(['radio'], ['getDirectory', 'recordClick']),
traffic: contract(
['traffic'],
[
'requestRoads',
'getStatus',
'fetchFlowForBounds',
'getFlowSessionStats',
'resetFlowTileCache',
],
),
bikeshare: contract(['bikeshare'], ['getStations']),
installations: contract(
['military-installations'],
['getMappedSites', 'searchNearby'],
),
satellites: contract(['satellites'], ['readGroup']),
launches: contract(['rocket-launches'], ['getLaunches', 'getActiveTle']),
alpr: contract(['alpr-cameras'], ['fetch']),
firms: contract(['local-firms'], ['getSnapshot']),
wind: contract(['wind'], ['getSnapshot']),
weather: contract(
['weather-radar', 'weather-satellite', 'weather-lightning'],
['getSnapshot'],
),
cyclones: contract(['weather-cyclones'], ['getSnapshot']),
earthquakes: contract(['earthquakes'], ['getSnapshot']),
'fire-perimeters': contract(['fire-perimeters'], ['getSnapshot']),
cables: contract(['telegeography-submarine-cables'], ['fetch']),
transit: contract(['transit'], ['requestSnapshot', 'getHistory']),
});
/** An omitted provider is unavailable, never an authoritative empty dataset. */
export class SourceUnavailableError extends Error {
constructor(name) {
super(`Data source not configured: ${name}`);
this.name = 'SourceUnavailableError';
this.code = 'unavailable';
this.unavailable = true;
this.retryable = false;
}
}
/** Validate supplied contracts and keep omitted sources inert during construction. */
export function resolveCatalogSources(supplied = {}) {
if (!supplied || typeof supplied !== 'object' || Array.isArray(supplied))
throw new TypeError('Catalog sources must be an object');
const sources = { ...supplied };
const missing = new Set();
for (const [name, { methods }] of Object.entries(CATALOG_SOURCE_CONTRACTS)) {
const source = sources[name];
if (source == null) {
missing.add(name);
const unavailable = () => {
throw new SourceUnavailableError(name);
};
sources[name] = Object.freeze({
label: name,
...Object.fromEntries(methods.map((method) => [method, unavailable])),
});
} else if (methods.some((method) => typeof source[method] !== 'function')) {
throw new TypeError(`Invalid catalog source: ${name}`);
}
}
return {
sources,
isConfigured: (name) => !missing.has(name),
createAvailabilityLookup(layers) {
const byId = new Map(layers.map((layer) => [layer.id, layer]));
const availability = new Map();
for (const [name, { layers: ids }] of Object.entries(
CATALOG_SOURCE_CONTRACTS,
)) {
for (const id of ids) {
const layer = byId.get(id);
if (!layer) throw new Error(`Missing source consumer: ${id}`);
availability.set(
id,
Object.freeze({
available: !missing.has(name),
source: name,
reason: missing.has(name)
? `${layer.name || id}: data source not configured`
: null,
}),
);
}
}
return (id) =>
availability.get(id) ?? byId.get(id)?.getSourceAvailability?.();
},
};
}
src/app/sourceComposition.test.mjs
+156
View File
@@ -0,0 +1,156 @@
import assert from 'node:assert/strict';
import test from 'node:test';
import {
resolveCatalogSources,
CATALOG_SOURCE_CONTRACTS,
} from './sourceComposition.js';
import { createApplicationCatalog } from './constructCatalog.js';
import { createSurfaceServices } from './surfaceServices.js';
import { createStandaloneLayerSources } from '../standalone/layerSources.js';
import { LayerLifecycle } from '../data/lifecycle.js';
function catalog(sources, t) {
const lifetime = new AbortController();
t.after(() => lifetime.abort());
return createApplicationCatalog({
sources,
signal: lifetime.signal,
surface: createSurfaceServices({
terrainSource: { getHeights: async () => [] },
signal: lifetime.signal,
eventTarget: null,
}),
});
}
test('every acquisition source can be omitted without losing catalog membership', (t) => {
const baseline = catalog(createStandaloneLayerSources(), t);
for (const name of Object.keys(CATALOG_SOURCE_CONTRACTS)) {
const sources = createStandaloneLayerSources({ [name]: null });
const actual = catalog(sources, t);
assert.deepEqual(actual.metadata, baseline.metadata, name);
for (const id of CATALOG_SOURCE_CONTRACTS[name].layers) {
assert.equal(actual.getSourceAvailability(id).available, false, id);
}
}
});
test('all acquisition sources may be absent, and enable fails before initializing or fetching', async (t) => {
const actual = catalog({}, t);
assert.equal(actual.layers.length, 30);
const manager = new LayerLifecycle(
{},
{ getSourceAvailability: actual.getSourceAvailability },
);
for (const layer of actual.layers) manager.register(layer);
for (const { layers: ids } of Object.values(CATALOG_SOURCE_CONTRACTS)) {
for (const id of ids) {
assert.equal(await manager.setEnabled(id, true), false, id);
assert.equal(manager.layers.get(id).initialized, false, id);
const row = manager.getAll().find((entry) => entry.id === id);
assert.equal(row.enabled, false);
assert.equal(row.stats.status, 'unavailable');
assert.match(row.stats.error, /data source not configured/);
}
}
});
test('configured sources retain identity; invalid implementations never become unavailable silently', () => {
const source = { getSnapshot: async () => [] };
assert.equal(
resolveCatalogSources({ earthquakes: source }).sources.earthquakes,
source,
);
for (const name of Object.keys(CATALOG_SOURCE_CONTRACTS)) {
assert.throws(
() => resolveCatalogSources({ [name]: {} }),
/Invalid catalog source/,
);
}
const missing = resolveCatalogSources({}).sources.earthquakes;
assert.throws(() => missing.getSnapshot(), { code: 'unavailable' });
});
test('standalone defaults allow exact replacements and explicit removal, and reject typos', () => {
const source = { getSnapshot: async () => [] };
const sources = createStandaloneLayerSources({
flights: source,
military: null,
});
assert.equal(sources.flights, source);
assert.equal(sources.military, null);
assert.equal(typeof sources.cctv.getCatalog, 'function');
assert.throws(
() => createStandaloneLayerSources({ fligts: source }),
/Unknown source/,
);
});
test('empty Street Level uses the shared unavailable lifecycle without initialization', async (t) => {
const actual = catalog({}, t);
const manager = new LayerLifecycle(
{},
{ getSourceAvailability: actual.getSourceAvailability },
);
manager.register(actual.get('street-level'));
assert.equal(await manager.setEnabled('street-level', true), false);
assert.equal(manager.layers.get('street-level').initialized, false);
const row = manager.getAll()[0];
assert.equal(row.stats.status, 'unavailable');
assert.equal(row.stats.error, 'No street-level imagery providers configured');
assert.equal(await manager.setEnabled('street-level', false), true);
const configured = catalog(createStandaloneLayerSources(), t);
assert.equal(
configured.get('street-level').getSourceAvailability().available,
true,
);
});
test('availability lookup accepts frozen layers and uses their display names', () => {
const composition = resolveCatalogSources({});
const layers = Object.values(CATALOG_SOURCE_CONTRACTS)
.flatMap(({ layers }) => layers)
.map((id) =>
Object.freeze({
id,
name: id === 'fire-perimeters' ? 'Fire perimeters' : id,
}),
);
const lookup = composition.createAvailabilityLookup(layers);
assert.equal(
lookup('fire-perimeters').reason,
'Fire perimeters: data source not configured',
);
assert.equal(Object.hasOwn(layers[0], 'getSourceAvailability'), false);
const manager = new LayerLifecycle({}, { getSourceAvailability: lookup });
manager.register(layers.find(({ id }) => id === 'fire-perimeters'));
assert.equal(
manager.getAll()[0].stats.error,
'Fire perimeters: data source not configured',
);
});
test('absent military acquisition does not poll, suppress flights, or erase supplied classification', async (t) => {
let fetches = 0;
t.mock.method(globalThis, 'fetch', async () => {
fetches++;
throw new Error('Unexpected fallback acquisition');
});
const actual = catalog(createStandaloneLayerSources({ military: null }), t);
const registry = actual.militaryRegistry;
assert.equal(actual.getSourceAvailability('flights').available, true);
assert.equal(registry.isMilitaryLayerActive(), false);
assert.equal(registry.isMilitaryIcao('abc123'), false);
registry.registerMilitaryIcaos([' ABC123 ']);
await registry.refreshMilitaryRegistryIfStale();
assert.equal(registry.isMilitaryIcao('abc123'), true);
assert.equal(registry.isMilitaryIcao('def456'), false);
const manager = new LayerLifecycle(
{},
{ getSourceAvailability: actual.getSourceAvailability },
);
manager.register(actual.get('military'));
assert.equal(await manager.setEnabled('military', true), false);
assert.equal(registry.isMilitaryLayerActive(), false);
assert.equal(fetches, 0);
});
src/codexOauthRealtime.test.mjs
+273
View File
@@ -0,0 +1,273 @@
import assert from 'node:assert/strict';
import { EventEmitter } from 'node:events';
import test from 'node:test';
import path from 'node:path';
import {
codexAuthPath,
preferCodexOAuth,
readCodexOAuthAccessToken,
resolveCodexExecutable,
startCodexChatGptLogin,
} from '../server/providers/openai/codex-auth.js';
const nowMs = Date.UTC(2026, 8, 27);
const jwt = (payload) =>
`${Buffer.from('{}').toString('base64url')}.${Buffer.from(JSON.stringify(payload)).toString('base64url')}.signature`;
const auth = (token, extras = {}) =>
JSON.stringify({
auth_mode: 'chatgpt',
tokens: { access_token: token, refresh_token: 'refresh-fixture' },
...extras,
});
test('optional Codex OAuth pin fails closed on ambiguous values', () => {
assert.equal(preferCodexOAuth({}), false);
assert.equal(preferCodexOAuth({ GEV_PREFER_CODEX_OAUTH: 'true' }), true);
assert.equal(preferCodexOAuth({ GEV_PREFER_CODEX_OAUTH: 'off' }), false);
assert.throws(
() => preferCodexOAuth({ GEV_PREFER_CODEX_OAUTH: 'maybe' }),
/must be true or false/,
);
});
test('Codex auth path follows explicit auth file, CODEX_HOME, then home directory', () => {
assert.equal(
codexAuthPath({
environment: { CODEX_AUTH_JSON: '/tmp/custom-auth.json' },
home: '/home/fixture',
}),
path.resolve('/tmp/custom-auth.json'),
);
assert.equal(
codexAuthPath({
environment: { CODEX_HOME: '/tmp/codex-home' },
home: '/home/fixture',
}),
path.join(path.resolve('/tmp/codex-home'), 'auth.json'),
);
assert.equal(
codexAuthPath({ environment: {}, home: '/home/fixture' }),
path.join('/home/fixture', '.codex', 'auth.json'),
);
});
test('Codex OAuth reader accepts a current ChatGPT token and rejects unusable credentials', () => {
const current = jwt({ exp: nowMs / 1000 + 3600 });
assert.equal(
readCodexOAuthAccessToken({
authPath: '/unused',
nowMs,
readFile: () => auth(current),
}),
current,
);
assert.equal(
readCodexOAuthAccessToken({
authPath: '/unused',
nowMs,
readFile: () =>
JSON.stringify({
auth_mode: 'chatgpt',
tokens: { access_token: current },
}),
}),
current,
'GEV does not require or consume the vendor refresh token',
);
for (const readFile of [
() => '{bad json',
() => JSON.stringify({ tokens: {} }),
() => auth(current, { auth_mode: 'apikey' }),
() =>
JSON.stringify({
OPENAI_API_KEY: 'sk-fixture',
tokens: { access_token: current, refresh_token: 'refresh-fixture' },
}),
() => auth('opaque-token'),
() => auth('header.not-json.signature'),
() => auth(jwt({ exp: 'tomorrow' })),
() => {
throw new Error('missing');
},
]) {
assert.throws(
() => readCodexOAuthAccessToken({ authPath: '/unused', readFile, nowMs }),
/ChatGPT sign-in is unavailable/,
);
}
});
test('Codex OAuth reader enforces expiry margin and bounds tokens without exp by file age', () => {
for (const exp of [nowMs / 1000 - 1, nowMs / 1000 + 59]) {
assert.throws(
() => {
readCodexOAuthAccessToken({
authPath: '/unused',
nowMs,
readFile: () => auth(jwt({ exp })),
});
},
(error) => {
assert.match(error.message, /sign-in has expired/);
assert.equal(error.code, 'CODEX_OAUTH_REAUTH_REQUIRED');
return true;
},
);
}
const noExp = jwt({ sub: 'fixture' });
const base = { authPath: '/unused', nowMs, readFile: () => auth(noExp) };
assert.equal(
readCodexOAuthAccessToken({
...base,
statFile: () => ({ mtimeMs: nowMs }),
}),
noExp,
);
assert.throws(
() =>
readCodexOAuthAccessToken({
...base,
statFile: () => ({ mtimeMs: nowMs - 3600_000 }),
}),
/sign-in has expired/,
);
assert.throws(
() =>
readCodexOAuthAccessToken({
...base,
statFile: () => {
throw new Error('missing');
},
}),
/sign-in is unavailable/,
);
});
test('Codex login resolves an installed executable before PATH and starts browser auth detached', async () => {
const checked = [];
assert.equal(
resolveCodexExecutable({
environment: {},
home: '/home/fixture',
access(candidate) {
checked.push(candidate);
if (candidate.endsWith('/.local/bin/codex')) return;
throw new Error('missing');
},
}),
path.join('/home/fixture', '.local', 'bin', 'codex'),
);
assert.equal(checked.length, 1);
const child = new EventEmitter();
let unref = 0;
child.unref = () => {
unref += 1;
};
const calls = [];
const pending = startCodexChatGptLogin({
executable: '/fixture/codex',
home: '/home/fixture',
environment: {
PATH: '/fixture',
https_proxy: 'http://proxy.fixture:8080',
OPENAI_API_KEY: 'fixture-api-key',
GOOGLE_MAPS_SERVER_API_KEY: 'fixture-google-key',
OPENSKY_CLIENT_SECRET: 'fixture-opensky-secret',
},
spawnImpl(command, args, options) {
calls.push({ command, args, options });
queueMicrotask(() => child.emit('spawn'));
return child;
},
});
const login = await pending;
assert.equal(unref, 1);
assert.equal(calls[0].command, '/fixture/codex');
assert.deepEqual(calls[0].args, ['login']);
assert.equal(calls[0].options.detached, true);
assert.equal(calls[0].options.stdio, 'ignore');
assert.deepEqual(
calls[0].options.env,
{
PATH: '/fixture',
https_proxy: 'http://proxy.fixture:8080',
CODEX_HOME: path.join('/home/fixture', '.codex'),
},
'provider secrets stay out of the login process',
);
child.emit('exit', 1);
assert.deepEqual(await login.completion, { exitCode: 1 });
});
test('Codex login refuses a read/write storage mismatch before spawning', async () => {
await assert.rejects(
startCodexChatGptLogin({
environment: { CODEX_AUTH_JSON: '/tmp/another-auth.json' },
home: '/home/fixture',
executable: 'codex',
spawnImpl: () => assert.fail('mismatched storage must not launch login'),
}),
{ code: 'CODEX_OAUTH_STORAGE_MISMATCH' },
);
});
test('Codex login resolves relative CODEX_HOME before changing the child directory', async () => {
const child = new EventEmitter();
const environment = { CODEX_HOME: './fixture-codex' };
const login = await startCodexChatGptLogin({
environment,
executable: 'codex',
spawnImpl(_command, _args, options) {
assert.equal(
options.env.CODEX_HOME,
path.resolve(environment.CODEX_HOME),
);
queueMicrotask(() => child.emit('spawn'));
return child;
},
});
assert.equal(
environment.CODEX_HOME,
'./fixture-codex',
'caller environment is unchanged',
);
child.emit('exit', 0);
assert.deepEqual(await login.completion, { exitCode: 0 });
});
test('Codex login hides spawn errors and can cancel only its owned child', async () => {
const child = new EventEmitter();
await assert.rejects(
startCodexChatGptLogin({
executable: 'codex',
spawnImpl() {
queueMicrotask(() =>
child.emit('error', new Error('private-token-fixture')),
);
return child;
},
}),
(error) =>
error.code === 'CODEX_OAUTH_LOGIN_FAILED' &&
!error.message.includes('private-token-fixture'),
);
const running = new EventEmitter();
let cancelled = 0;
running.kill = (signal) => {
assert.equal(signal, 'SIGTERM');
cancelled += 1;
running.emit('exit', null);
};
const login = await startCodexChatGptLogin({
executable: 'codex',
spawnImpl() {
queueMicrotask(() => running.emit('spawn'));
return running;
},
});
login.cancel();
assert.equal(cancelled, 1);
assert.deepEqual(await login.completion, { exitCode: null });
});
src/data/analystEngine.js
+879 -144
View File
File diff suppressed because it is too large. Load diff
src/data/analystEngine.test.mjs
+374 -7
View File
@@ -174,11 +174,95 @@ test('analyst: nearest sorting attaches distanceKm ascending', async () => {
test('analyst: follow-up re-filters the remembered set without re-snapshot', async () => {
const eng = makeEngine();
await eng.query({ layers: ['flights'], scope: { kind: 'region', name: 'Texland' } });
const r = await eng.query({ followUp: true, filters: [{ field: 'onGround', op: 'eq', value: true }] });
const first = await eng.query({
layers: ['flights'],
scope: { kind: 'region', name: 'Texland' },
});
const r = await eng.query({
followUp: true,
filters: [{ field: 'onGround', op: 'eq', value: true }],
});
assert.equal(r.count, 1);
assert.equal(r.items[0].id, 'GND1');
assert.equal(r.coverage.followUp, true);
assert.equal(r.scopeLabel, first.scopeLabel);
assert.equal(r.display.scope, first.display.scope);
assert.equal(r.coverage.scope, first.coverage.scope);
});
test('analyst: follow-ups preserve partial and unanswered coverage', async () => {
const eng = createAnalystEngine({
getRecords: (key) => (key === 'flights' ? FLIGHTS : []),
getLayerSnapshot: (key) => ({
enabled: key === 'flights',
feedState: key === 'flights' ? 'nominal' : 'off',
}),
getViewContext: () => ({ lat: 30.27, lon: -97.74, viewRadiusKm: 150 }),
});
const first = await eng.query({
layers: ['flights', 'military'],
scope: { kind: 'anywhere' },
});
assert.equal(first.partial, true);
assert.deepEqual(first.unanswered, ['military']);
const followUp = await eng.query({ followUp: true, limit: 1 });
assert.equal(followUp.partial, true);
assert.deepEqual(followUp.unanswered, ['military']);
assert.deepEqual(
followUp.coverage.layersQueried.map(({ layerKey, status }) => [
layerKey,
status,
]),
first.coverage.layersQueried.map(({ layerKey, status }) => [
layerKey,
status,
]),
);
});
test('analyst: cancelled pre-commit work cannot replace follow-up memory', async () => {
const eng = makeEngine();
await eng.query({
layers: ['flights'],
scope: { kind: 'anywhere' },
filters: [{ field: 'id', op: 'eq', value: 'SWA1' }],
});
let current = true;
const stale = await eng.query(
{ layers: ['local-firms'], scope: { kind: 'anywhere' } },
{
isCurrent: () => current,
beforeCommit: async () => {
current = false;
},
},
);
assert.equal(stale.code, 'CANCELLED');
const followUp = await eng.query({ followUp: true });
assert.deepEqual(followUp.items.map((item) => item.id), ['SWA1']);
});
test('analyst: failed pre-commit work cannot replace follow-up memory', async () => {
const eng = makeEngine();
await eng.query({
layers: ['flights'],
scope: { kind: 'anywhere' },
filters: [{ field: 'id', op: 'eq', value: 'SWA1' }],
});
await assert.rejects(
eng.query(
{ layers: ['local-firms'], scope: { kind: 'anywhere' } },
{
beforeCommit: async () => {
throw new Error('projection failed');
},
},
),
/projection failed/,
);
const followUp = await eng.query({ followUp: true });
assert.deepEqual(followUp.items.map((item) => item.id), ['SWA1']);
});
test('analyst: unresolved region is an honest failure, not empty success', async () => {
@@ -200,6 +284,39 @@ test('analyst: a region lookup timeout is reported as region-timeout', async ()
assert.equal(r.coverage.scope, 'region:Texas:timeout');
});
test('analyst: region lookup receives and obeys the owning action signal', async () => {
const controller = new AbortController();
let receivedSignal = null;
const eng = createAnalystEngine({
getRecords: () => FLIGHTS,
resolveRegionRing: async (_name, signal) => {
receivedSignal = signal;
await new Promise((resolve) =>
signal.addEventListener('abort', resolve, { once: true }),
);
return null;
},
getViewContext: () => ({
lat: 30.27,
lon: -97.74,
viewRadiusKm: 150,
}),
});
const pending = eng.query(
{ layers: ['flights'], scope: { kind: 'region', name: 'Texas' } },
{
signal: controller.signal,
isCurrent: () => !controller.signal.aborted,
},
);
await Promise.resolve();
controller.abort();
const result = await pending;
assert.equal(receivedSignal, controller.signal);
assert.equal(result.code, 'CANCELLED');
assert.equal(result.cancelled, true);
});
test('analyst: route fields queryable from cached enrichment only', async () => {
const r = await makeEngine().query({
layers: ['flights'], scope: { kind: 'anywhere' },
@@ -262,20 +379,132 @@ test('helpers: haversine sanity + scope radius', () => {
assert.deepEqual(scoped.map((f) => f.id).sort(), ['GND1', 'SWA1']);
});
test('bounded loaded cohorts disclose truncation before filtering and retain it on follow-up', async () => {
test('capped cohorts report returned/total/truncated and keep it on follow-up', async () => {
const engine = createAnalystEngine({
getRecords: () => [{ id: 'sample dam', lat: 0, lon: 0, name: 'sample' }],
getRecordCoverage: () => ({ basis: 'bounded-loaded-records', recordsExamined: 1, loadedCount: 3000, sourceTruncated: true }),
getRecordCoverage: () => ({ total: 3000, truncated: true }),
getViewContext: () => ({ lat: 0, lon: 0, viewRadiusKm: 25 }),
});
const result = await engine.query({ layers: ['local-dams'], scope: { kind: 'anywhere' }, sortBy: 'distance' });
assert.equal(result.count, 1);
assert.equal(result.coverage.layersQueried[0].sourceTruncated, true);
assert.match(result.coverage.note, /omitted records may change the nearest item or count/);
const layer = result.coverage.layersQueried[0];
assert.deepEqual({ returned: layer.returned, total: layer.total, truncated: layer.truncated }, { returned: 1, total: 3000, truncated: true });
assert.deepEqual(result.coverage.records, { returned: 1, total: 3000, truncated: true });
assert.match(result.display.caveat, /counted 1 of 3,000 loaded records/);
const followUp = await engine.query({ followUp: true });
assert.equal(followUp.coverage.layersQueried[0].loadedCount, 3000);
assert.equal(followUp.coverage.layersQueried[0].total, 3000);
});
test('an uncapped cohort is complete and carries no caveat', async () => {
const result = await makeEngine().query({ layers: ['flights'], scope: { kind: 'anywhere' } });
assert.deepEqual(result.coverage.records, { returned: 4, total: 4, truncated: false });
assert.equal(result.display.caveat, undefined);
assert.equal(result.display.scope, 'anywhere in the loaded data');
});
test('unknown fields, operators, scopes and wrong-typed values are refused with the allowed values', async () => {
const engine = makeEngine();
const field = await engine.query({ layers: ['flights'], filters: [{ field: 'time', op: 'gte', value: 5 }] });
assert.equal(field.ok, false);
assert.equal(field.code, 'UNKNOWN_FIELD');
assert.ok(field.allowed.includes('altitudeM'));
const op = await engine.query({ layers: ['flights'], filters: [{ field: 'altitudeM', op: 'wat', value: 5 }] });
assert.equal(op.code, 'BAD_OPERATOR');
assert.deepEqual(op.allowed, ['gt', 'gte', 'lt', 'lte', 'eq', 'neq']);
const flag = await engine.query({ layers: ['flights'], filters: [{ field: 'military', op: 'eq', value: 'false' }] });
assert.equal(flag.code, 'BAD_VALUE', 'the string "false" must not match the TRUE record');
const num = await engine.query({ layers: ['flights'], filters: [{ field: 'altitudeM', op: 'gt', value: 'high' }] });
assert.equal(num.code, 'BAD_VALUE');
const scope = await engine.query({ layers: ['flights'], scope: { kind: 'polygon' } });
assert.equal(scope.code, 'UNKNOWN_SCOPE');
assert.deepEqual(scope.allowed, ['view', 'region', 'radius', 'anywhere']);
const sort = await engine.query({ layers: ['flights'], sortBy: 'loudness' });
assert.equal(sort.code, 'UNKNOWN_FIELD');
assert.equal(engine.hasMemory(), false, 'refusals never become follow-up memory');
});
test('a typed boolean filter still matches exactly', async () => {
const r = await makeEngine().query({ layers: ['flights'], scope: { kind: 'anywhere' }, filters: [{ field: 'military', op: 'eq', value: false }] });
assert.deepEqual(r.items.map((i) => i.id).sort(), ['GND1', 'N123', 'SWA1']);
});
test('distance honours sortDir: desc is farthest first', async () => {
const far = await makeEngine().query({ layers: ['flights'], scope: { kind: 'anywhere' }, sortBy: 'distance', sortDir: 'desc', limit: 1 });
assert.equal(far.items[0].id, 'N123');
const near = await makeEngine().query({ layers: ['flights'], scope: { kind: 'anywhere' }, sortBy: 'distance', limit: 1 });
assert.equal(near.items[0].id, 'SWA1');
});
test('a follow-up without a previous answer is refused, not a fresh flights query', async () => {
const r = await makeEngine().query({ followUp: true, filters: [] });
assert.equal(r.ok, false);
assert.equal(r.code, 'NO_RESULT_CONTEXT');
});
test('follow-ups never rewrite the remembered rows', async () => {
const engine = makeEngine();
await engine.query({ layers: ['flights'], scope: { kind: 'anywhere' } });
await engine.query({ followUp: true, sortBy: 'distance' });
const again = await engine.query({ followUp: true });
assert.equal(again.count, 4, 'a follow-up keeps the remembered set, not the view');
assert.ok(again.items.every((item) => item.distanceKm === undefined));
});
test('a superseded slow region query cannot overwrite the newer follow-up memory', async () => {
let releaseSlow;
const engine = createAnalystEngine({
getRecords: (key) => ({ flights: FLIGHTS, 'ais-live-vessels': SHIPS }[key] || []),
resolveRegionRing: () => new Promise((resolve) => { releaseSlow = () => resolve(TEXLAND); }),
getViewContext: () => ({ lat: 30.27, lon: -97.74, viewRadiusKm: 150 }),
});
let generation = 0;
const slowGeneration = ++generation;
const slow = engine.query({ layers: ['flights'], scope: { kind: 'region', name: 'Texland' } }, { isCurrent: () => generation === slowGeneration });
const newGeneration = ++generation;
const fresh = await engine.query({ layers: ['ais-live-vessels'], scope: { kind: 'anywhere' } }, { isCurrent: () => generation === newGeneration });
assert.equal(fresh.ok, true);
releaseSlow();
const stale = await slow;
assert.equal(stale.code, 'CANCELLED');
const followUp = await engine.query({ followUp: true });
assert.deepEqual(followUp.items.map((i) => i.layerKey), ['ais-live-vessels', 'ais-live-vessels']);
});
test('off, loading and unavailable layers are refused distinctly; a real zero stays ok', async () => {
const engineFor = (snapshot, rows = [], warming = false) => createAnalystEngine({
getRecords: () => rows,
getLayerSnapshot: () => snapshot,
isWarming: () => warming,
getViewContext: () => ({ lat: 0, lon: 0, viewRadiusKm: 25 }),
});
assert.equal((await engineFor({ enabled: false, feedState: 'off' }).query({ layers: ['earthquakes'] })).code, 'LAYER_OFF');
assert.equal((await engineFor({ enabled: true, feedState: 'loading' }).query({ layers: ['earthquakes'] })).code, 'NOT_READY');
assert.equal((await engineFor({ enabled: true, feedState: 'nominal' }, [], true).query({ layers: ['earthquakes'] })).code, 'NOT_READY');
assert.equal((await engineFor({ enabled: true, feedState: 'unavailable' }).query({ layers: ['earthquakes'] })).code, 'FEED_UNAVAILABLE');
const zero = await engineFor({ enabled: true, feedState: 'nominal' }, [{ id: 'q', lat: 50, lon: 50, magnitude: 2 }]).query({ layers: ['earthquakes'], filters: [{ field: 'magnitude', op: 'gte', value: 5 }] });
assert.equal(zero.ok, true);
assert.equal(zero.count, 0);
assert.equal(zero.coverage.layersQueried[0].status, 'ok');
});
test('time fields filter by ISO and derive ageHours; the feed window is exposed', async () => {
const now = Date.parse('2026-09-23T12:00:00Z');
const engine = createAnalystEngine({
now: () => now,
getRecords: () => [
{ id: 'recent', lat: 0, lon: 0, magnitude: 4, timeMs: now - 2 * 3_600_000 },
{ id: 'older', lat: 0, lon: 0, magnitude: 5, timeMs: now - 20 * 3_600_000 },
],
getViewContext: () => ({ lat: 0, lon: 0, viewRadiusKm: 25 }),
});
const iso = await engine.query({ layers: ['earthquakes'], scope: { kind: 'anywhere' }, filters: [{ field: 'timeMs', op: 'gte', value: '2026-09-23T06:00:00Z' }] });
assert.deepEqual(iso.items.map((i) => i.id), ['recent']);
const age = await engine.query({ layers: ['earthquakes'], scope: { kind: 'anywhere' }, filters: [{ field: 'ageHours', op: 'lte', value: 6 }] });
assert.deepEqual(age.items.map((i) => i.id), ['recent']);
assert.equal(age.items[0].ageHours, 2);
assert.equal(age.display.window, 'last 24 h');
assert.equal(age.coverage.layersQueried[0].window, 'last 24 h');
});
test('follow-up provenance stays attached to old rows after a feed recovers', async () => {
let state = 'stale';
@@ -293,3 +522,141 @@ test('follow-up provenance stays attached to old rows after a feed recovers', as
assert.equal(engine.hasMemory(), false);
assert.equal((await engine.query()).coverage.feedProvenance.overall, 'nominal');
});
test('a large loaded set sorts and summarizes without overflowing the stack', async () => {
const rows = Array.from({ length: 200_000 }, (_, i) => ({ id: `FIRE-${i}`, lat: 0, lon: 0, frp: i }));
const engine = createAnalystEngine({
getRecords: () => rows,
getViewContext: () => ({ lat: 0, lon: 0, viewRadiusKm: 25 }),
});
const result = await engine.query({ layers: ['local-firms'], scope: { kind: 'anywhere' }, sortBy: 'frp', limit: 1 });
assert.equal(result.count, 200_000);
assert.equal(result.items[0].frp, 199_999);
assert.equal(result.summary.frpMin, 0);
});
test('an enabled but empty layer says why on screen', async () => {
const engine = createAnalystEngine({
getRecords: () => [],
getLayerSnapshot: () => ({ enabled: true, feedState: 'nominal' }),
getEmptyNote: () => 'Fly below 400 km to a covered region',
getViewContext: () => ({ lat: 0, lon: 0, viewRadiusKm: 25 }),
});
const result = await engine.query({ layers: ['transit'] });
assert.equal(result.ok, true);
assert.equal(result.count, 0);
assert.equal(result.coverage.layersQueried[0].status, 'empty');
assert.match(result.display.caveat, /transit: Fly below 400 km/);
});
test('a radius around a named place without a centre is refused, not measured around the camera', async () => {
const r = await makeEngine().query({ layers: ['ais-live-vessels'], scope: { kind: 'radius', name: 'Singapore', km: 200 } });
assert.equal(r.ok, false);
assert.equal(r.code, 'BAD_SCOPE');
const ok = await makeEngine().query({ layers: ['ais-live-vessels'], scope: { kind: 'radius', name: 'Houston', km: 200, center: { lat: 29.6, lon: -95.0 } } });
assert.equal(ok.ok, true);
});
test('a field copied with its hinted unit still resolves', async () => {
const r = await makeEngine().query({ layers: ['local-firms'], scope: { kind: 'anywhere' }, sortBy: 'frp(MW)', filters: [{ field: 'frp (MW)', op: 'gt', value: 100 }] });
assert.equal(r.ok, true);
assert.deepEqual(r.items.map((i) => i.id), ['FIRE-3', 'FIRE-1']);
});
test('a written unit converts to the field unit or is refused', async () => {
const engine = makeEngine();
const feet = await engine.query({ layers: ['flights'], scope: { kind: 'anywhere' }, filters: [{ field: 'altitudeM(ft)', op: 'gt', value: 40000 }] });
assert.equal(feet.ok, true);
assert.deepEqual(feet.items.map((i) => i.id), ['RCH01'], '40,000 ft is 12,192 m, not 40,000 m');
const same = await engine.query({ layers: ['flights'], scope: { kind: 'anywhere' }, filters: [{ field: 'altitudeM (m)', op: 'gt', value: 12192 }] });
assert.deepEqual(same.items.map((i) => i.id), ['RCH01']);
const knots = await engine.query({ layers: ['flights'], scope: { kind: 'anywhere' }, filters: [{ field: 'speedMps(kts)', op: 'gt', value: 470 }] });
assert.deepEqual(knots.items.map((i) => i.id), ['RCH01'], '470 kn is ~242 m/s');
const wrong = await engine.query({ layers: ['flights'], filters: [{ field: 'altitudeM(kts)', op: 'gt', value: 1 }] });
assert.equal(wrong.code, 'BAD_UNIT');
const unitless = await engine.query({ layers: ['flights'], filters: [{ field: 'callsign(ft)', op: 'eq', value: 'X' }] });
assert.equal(unitless.code, 'BAD_UNIT');
const hinted = await engine.query({ layers: ['local-firms'], scope: { kind: 'anywhere' }, sortBy: 'frp(MW)' });
assert.equal(hinted.ok, true);
});
test('unambiguous numeric strings are numbers; blanks, booleans and words are not', async () => {
const engine = makeEngine();
const text = await engine.query({ layers: ['flights'], scope: { kind: 'anywhere' }, filters: [{ field: 'altitudeM', op: 'gt', value: '12192' }] });
assert.equal(text.ok, true);
assert.deepEqual(text.items.map((i) => i.id), ['RCH01']);
for (const value of ['', ' ', true, 'high', '12k'])
assert.equal((await engine.query({ layers: ['flights'], filters: [{ field: 'altitudeM', op: 'gt', value }] })).code, 'BAD_VALUE', JSON.stringify(value));
});
test('any supplied centre must be a real coordinate', async () => {
const engine = makeEngine();
for (const center of [{ lat: 0 }, { lat: 999, lon: 0 }, { lat: 10, lon: 200 }, { lat: '10', lon: 20 }])
assert.equal((await engine.query({ layers: ['flights'], scope: { kind: 'radius', km: 100, center } })).code, 'BAD_SCOPE', JSON.stringify(center));
assert.equal((await engine.query({ layers: ['flights'], scope: { kind: 'radius', km: 100, center: { lat: 30.2, lon: -97.7 } } })).ok, true);
});
test('mixed off/loading/unavailable layers refuse; a partly answerable query says so', async () => {
const snapshots = { earthquakes: { enabled: true, feedState: 'unavailable' }, 'local-firms': { enabled: true, feedState: 'loading' }, flights: { enabled: false, feedState: 'off' } };
const engine = createAnalystEngine({
getRecords: (key) => (key === 'ais-live-vessels' ? SHIPS : []),
getLayerSnapshot: (key) => snapshots[key] || { enabled: true, feedState: 'nominal' },
getViewContext: () => ({ lat: 0, lon: 0, viewRadiusKm: 25 }),
});
const none = await engine.query({ layers: ['earthquakes', 'local-firms', 'flights'] });
assert.equal(none.ok, false);
assert.equal(none.code, 'NOT_READY');
assert.deepEqual(none.layerStatus.map((l) => l.status), ['error', 'loading', 'off']);
assert.equal(engine.hasMemory(), false, 'a refusal never becomes follow-up memory');
const down = await engine.query({ layers: ['earthquakes', 'flights'] });
assert.equal(down.code, 'FEED_UNAVAILABLE');
const partial = await engine.query({ layers: ['ais-live-vessels', 'earthquakes'], scope: { kind: 'anywhere' } });
assert.equal(partial.ok, true);
assert.equal(partial.partial, true);
assert.deepEqual(partial.unanswered, ['earthquakes']);
assert.match(partial.display.caveat, /earthquakes error/);
});
test('returned items are copies: mutating them cannot change the remembered answer', async () => {
const engine = makeEngine();
const first = await engine.query({ layers: ['flights'], scope: { kind: 'anywhere' }, sortBy: 'altitudeM' });
for (const item of first.items) {
item.altitudeM = -1;
item.id = 'MUTATED';
}
const again = await engine.query({ followUp: true, sortBy: 'altitudeM' });
assert.deepEqual(again.items.map((i) => i.id), ['RCH01', 'SWA1', 'N123', 'GND1']);
assert.equal(FLIGHTS[1].altitudeM, 13500, 'the provider rows are untouched');
});
test('ranking 250k rows stays within a budget and yields to the page', async () => {
const rows = Array.from({ length: 250_000 }, (_, i) => ({ id: `F${i}`, lat: (i % 170) - 85, lon: (i % 350) - 175, frp: (i * 7919) % 100_003 }));
const engine = createAnalystEngine({ getRecords: () => rows, getViewContext: () => ({ lat: 0, lon: 0, viewRadiusKm: 25 }) });
let ticks = 0;
const timer = setInterval(() => ticks++, 0);
const started = performance.now();
const result = await engine.query({ layers: ['local-firms'], scope: { kind: 'anywhere' }, sortBy: 'frp', limit: 1 });
const elapsed = performance.now() - started;
clearInterval(timer);
assert.equal(result.count, 250_000);
assert.equal(result.items[0].frp, 100_002);
assert.ok(elapsed < 400, `took ${Math.round(elapsed)} ms`);
assert.ok(ticks > 0, 'the scan yielded between slices');
let current = true;
const pending = engine.query({ layers: ['local-firms'], scope: { kind: 'anywhere' }, sortBy: 'distance' }, { isCurrent: () => current });
current = false;
assert.equal((await pending).code, 'CANCELLED', 'a superseded scan stops at the next slice');
});
test('analyst: a follow-up naming other layers than the last answer is refused', async () => {
const engine = createAnalystEngine({
getRecords: (key) => ({ flights: FLIGHTS, 'local-firms': FIRES }[key] || []),
resolveRegionRing: async () => null,
getViewContext: () => ({ lat: 30.27, lon: -97.74, viewRadiusKm: 150 }),
});
await engine.query({ layers: ['flights'], scope: { kind: 'anywhere' } });
const r = await engine.query({ layers: ['local-firms'], followUp: true });
assert.equal(r.ok, false);
assert.equal(r.code, 'FOLLOW_UP_MISMATCH');
assert.equal(engine.hasMemory(), true, 'the earlier answer is still the last answer');
});
src/data/directions.js
+5 -2
View File
@@ -1,3 +1,4 @@
import { createDirectionsSource } from '../layers/directions/source.js';
/**
* @module directions
* @description Service bundle for the Directions layer.
@@ -37,8 +38,10 @@ export const directionsServices = Object.freeze({
});
/** Construct one Directions layer over the application scene owners. */
export function createApplicationDirectionsLayer() {
return createDirectionsLayer({ services: directionsServices });
export function createApplicationDirectionsLayer({
source = createDirectionsSource(),
} = {}) {
return createDirectionsLayer({ services: directionsServices, source });
}
export {
src/data/firmsHeatmap.test.mjs
+1
View File
@@ -25,6 +25,7 @@ test('firms analyst record: full record maps every contract field', () => {
frp: 1520.4,
confidence: 0.9,
satellite: 'N21',
sensor: 'VIIRS',
acqTime: 1_753_600_000_000,
});
});
src/data/idSwitches.js
+63
View File
@@ -0,0 +1,63 @@
const MAX_SWITCHES_LENGTH = 256;
const ENTRY = /^([a-z][a-z0-9-]*)-([01])$/;
/** Canonical, bounded boolean switches keyed by stable slugs. */
export function normalizeIdSwitches(value, reservedIds = []) {
if (typeof value !== 'string' || value.length > MAX_SWITCHES_LENGTH)
return null;
if (!value) return '';
const entries = new Map();
for (const field of value.split('*')) {
const match = ENTRY.exec(field);
if (!match || reservedIds.includes(match[1]) || entries.has(match[1]))
return null;
entries.set(match[1], match[2] === '1');
}
return [...entries]
.sort(([a], [b]) => (a < b ? -1 : a > b ? 1 : 0))
.map(([id, on]) => `${id}-${on ? '1' : '0'}`)
.join('*');
}
/** Encode by stable IDs rather than registration order or generated tokens. */
export function encodeIdSwitches(switches) {
const value = [...switches]
.map(([id, on]) => `${id}-${on === true ? '1' : '0'}`)
.join('*');
if (value.length > MAX_SWITCHES_LENGTH)
throw new RangeError(
`Switch IDs exceed the ${MAX_SWITCHES_LENGTH}-character share-link limit`,
);
const normalized = normalizeIdSwitches(value);
if (normalized === null) throw new TypeError('Invalid boolean switch IDs');
return normalized;
}
/** A Map keeps switch IDs separate from object prototype properties. */
export function decodeIdSwitches(value) {
const normalized = normalizeIdSwitches(value);
return new Map(
normalized
? normalized.split('*').map((entry) => {
const [, id, on] = ENTRY.exec(entry);
return [id, on === '1'];
})
: [],
);
}
/** Persist only explicitly requested switch IDs, not unrelated live changes. */
export function patchRequestedIdSwitches(previous, applied, requested) {
const current = decodeIdSwitches(applied);
const next = new Map(
[...decodeIdSwitches(previous)].filter(([id]) => current.has(id)),
);
let changed = false;
for (const [id, on] of current) {
if (Object.hasOwn(requested, id) && typeof requested[id] === 'boolean') {
next.set(id, on);
changed = true;
}
}
return changed ? encodeIdSwitches(next) : undefined;
}
src/data/layerState.js
+11 -1
View File
@@ -1,3 +1,4 @@
import { normalizeIdSwitches, patchRequestedIdSwitches } from './idSwitches.js';
import reservationRows from './layerStateTokenReservations.json' with { type: 'json' };
const VALID_DISPOSITIONS = new Set([
@@ -411,8 +412,17 @@ const OPTION_GROUPS = Object.freeze({
booleanOption('viirs', 'v', false),
]),
'street-level': Object.freeze([
// One switch per registered imagery provider (src/app/layers/streetLevel.js).
// Preserve the published Mapillary token; custom switches use stable IDs.
booleanOption('mapillary', 'm', true),
Object.freeze({
key: 'providerSwitches',
patchRequested: patchRequestedIdSwitches,
token: 'r',
defaultValue: '',
normalize: (value) => normalizeIdSwitches(value, ['mapillary']),
encode: normalizeIdSwitches,
decode: (value) => normalizeIdSwitches(value, ['mapillary']),
}),
enumOption('pano', 'p', 'all', ['all', 'pano', 'flat'], {
all: 'a',
pano: 'p',
src/data/layerState.test.mjs
+102 -18
View File
@@ -1,3 +1,4 @@
import { encodeParams, decodeParams } from '../layers/streetLevel/params.js';
import { readShellSource } from '../testSupport/readShellSource.mjs';
import { expandApplicationHtml } from '../../build/application-html.js';
import { readLayerSource } from '../testSupport/readLayerSource.mjs';
@@ -243,7 +244,11 @@ test('production registry is exact, canonical, and rejects incomplete contracts'
}
assert.equal(nextLayerStateToken(), '3');
assert.equal(
nextLayerStateToken({ ...LAYER_STATE_TOKEN_RESERVATIONS, alpha: '3', bravo: '4' }),
nextLayerStateToken({
...LAYER_STATE_TOKEN_RESERVATIONS,
alpha: '3',
bravo: '4',
}),
'5',
);
const digitsExhausted = {
@@ -276,7 +281,9 @@ test('production registry is exact, canonical, and rejects incomplete contracts'
[
...'0123456789',
...[...LAYER_STATE_TOKEN_ALPHABET].flatMap((first) =>
[...LAYER_STATE_TOKEN_ALPHABET].map((second) => `${first}${second}`),
[...LAYER_STATE_TOKEN_ALPHABET].map(
(second) => `${first}${second}`,
),
),
].map((token, index) => [`occupied-${index}`, token]),
),
@@ -298,33 +305,37 @@ test('production registry is exact, canonical, and rejects incomplete contracts'
true,
);
assert.equal(
validateLayerStateAllocations(
LAYER_STATE_TOKEN_RESERVATIONS,
{ ...LAYER_STATE_TOKEN_RESERVATIONS, future: '3', next: '4' },
),
validateLayerStateAllocations(LAYER_STATE_TOKEN_RESERVATIONS, {
...LAYER_STATE_TOKEN_RESERVATIONS,
future: '3',
next: '4',
}),
true,
);
assert.throws(
() => validateLayerStateAllocations(LAYER_STATE_TOKEN_RESERVATIONS, {
...LAYER_STATE_TOKEN_RESERVATIONS,
future: '00',
}),
() =>
validateLayerStateAllocations(LAYER_STATE_TOKEN_RESERVATIONS, {
...LAYER_STATE_TOKEN_RESERVATIONS,
future: '00',
}),
/next free token 3/,
);
const beforeLastDigit = { ...digitsExhausted };
delete beforeLastDigit['prior-9'];
assert.equal(
validateLayerStateAllocations(
beforeLastDigit,
{ ...beforeLastDigit, futurePair: '00', futureDigit: '9' },
),
validateLayerStateAllocations(beforeLastDigit, {
...beforeLastDigit,
futurePair: '00',
futureDigit: '9',
}),
true,
);
assert.equal(
validateLayerStateAllocations(
digitsExhausted,
{ ...digitsExhausted, pairB: '01', pairA: '00' },
),
validateLayerStateAllocations(digitsExhausted, {
...digitsExhausted,
pairB: '01',
pairA: '00',
}),
true,
);
assert.throws(
@@ -2660,12 +2671,14 @@ test('Street Level: every option round-trips through a share link and stored sta
state.enabledLayerIds = ['street-level'];
state.options['street-level'] = {
mapillary: false,
providerSwitches: '',
pano: 'flat',
sinceDays: MAX_SINCE_DAYS,
};
const decoded = decodeLayerStateParams(new URLSearchParams(encode(state)));
assert.deepEqual(decoded.options['street-level'], {
mapillary: false,
providerSwitches: '',
pano: 'flat',
sinceDays: MAX_SINCE_DAYS,
});
@@ -2693,6 +2706,7 @@ test('Street Level: the link codec accepts exactly the windows the filter keeps'
test('Street Level: a link without the provider switch keeps Mapillary on', () => {
assert.deepEqual(streetLevelOptions(''), {
mapillary: true,
providerSwitches: '',
pano: 'all',
sinceDays: 0,
});
@@ -2703,3 +2717,73 @@ test('Street Level: a link without the provider switch keeps Mapillary on', () =
true,
);
});
test('explicit provider switches reach durable state without adopting unrelated live switches', () => {
const manager = new DataLayerManager({});
const providers = new Map([
['mapillary', true],
['alpha', true],
['beta', true],
]);
const filter = { pano: 'all', sinceDays: 0 };
for (const id of REGISTERED_LAYER_IDS) {
manager.register(
id === 'street-level'
? {
...fakeLayer(id),
getParams: () => encodeParams({ providers, filter }),
setParams(params) {
const decoded = decodeParams(params, {
providerIds: providers.keys(),
filter,
});
for (const [id, on] of decoded.providers) providers.set(id, on);
return true;
},
}
: fakeLayer(id),
);
}
manager.finalizeRegistrations(LAYER_STATE_REGISTRY);
const storage = memoryStorage();
const coordinator = new LayerStateCoordinator(manager, shareSink(), {
storage,
});
try {
providers.set('beta', false); // Passive state does not belong to the next action.
assert.equal(
manager.setLayerParams(
'street-level',
{ alpha: false },
{ origin: 'user' },
),
true,
);
let saved = parseStoredLayerState(storage.getItem(LAYER_STATE_STORAGE_KEY));
assert.equal(saved.options['street-level'].providerSwitches, 'alpha-0');
const shared = decodeLayerStateParams(new URLSearchParams(encode(saved)));
const restored = decodeParams(shared.options['street-level'], {
providerIds: ['beta', 'alpha'],
filter,
});
assert.deepEqual([...restored.providers], [['alpha', false]]);
manager.setLayerParams('street-level', { beta: true }, { origin: 'user' });
saved = parseStoredLayerState(storage.getItem(LAYER_STATE_STORAGE_KEY));
assert.equal(
saved.options['street-level'].providerSwitches,
'alpha-0*beta-1',
);
manager.setLayerParams(
'street-level',
{ alpha: true },
{ origin: 'local-restore' },
);
saved = parseStoredLayerState(storage.getItem(LAYER_STATE_STORAGE_KEY));
assert.equal(
saved.options['street-level'].providerSwitches,
'alpha-0*beta-1',
);
} finally {
coordinator.destroy();
}
});
src/data/layerStateCoordinator.js
+16 -2
View File
@@ -255,8 +255,22 @@ export class LayerStateCoordinator {
const explicitlyRequested = Object.hasOwn(requestedParams, spec.key);
const implicitTrackingSync =
!explicitlyRequested && spec.key === trackingOptionKey;
if (!explicitlyRequested && !implicitTrackingSync) continue;
const value = spec.normalize(change.params[spec.key]);
// Packed options can persist only the subkeys owned by this request.
const requestedValue =
explicitlyRequested || implicitTrackingSync
? change.params[spec.key]
: spec.patchRequested?.(
nextOwnerOptions[spec.key],
change.params[spec.key],
requestedParams,
);
if (
!explicitlyRequested &&
!implicitTrackingSync &&
requestedValue === undefined
)
continue;
const value = spec.normalize(requestedValue);
if (value === null) {
if (implicitTrackingSync) {
nextOwnerOptions[spec.key] = null;
src/data/layerStateTokenLedger.test.mjs
+6
View File
@@ -98,6 +98,12 @@ function withPublishedBase(
}
function writeCodecFixture(cwd, rows, entries) {
const providerCodec = path.join(cwd, 'src/data/idSwitches.js');
mkdirSync(path.dirname(providerCodec), { recursive: true });
writeFileSync(
providerCodec,
readFileSync(new URL('./idSwitches.js', import.meta.url)),
);
const source = readFileSync(CODEC_SOURCE_PATH, 'utf8');
const registryEnd = ']);\n\nexport const REGISTERED_LAYER_IDS';
assert.equal(source.split(registryEnd).length, 2);
src/data/lifecycle.js
+23 -1
View File
@@ -74,7 +74,11 @@ function refreshFailureFromStats(stats, label) {
* for real-time data overlays on the CesiumJS globe.
*/
export class LayerLifecycle {
constructor(viewer, { allowQaRegistration = false } = {}) {
constructor(
viewer,
{ allowQaRegistration = false, getSourceAvailability } = {},
) {
this._catalogSourceAvailability = getSourceAvailability;
this.viewer = viewer;
this._activityListeners = new Set();
this.layers = new Map(); // id → { module, enabled, initialized, intervalId, lifecycleState, lifecycleUncertain }
@@ -228,6 +232,7 @@ export class LayerLifecycle {
_normalizedStats(entry) {
const moduleStats = this._moduleStats(entry);
const availability = this._sourceAvailability(entry.module.id);
const lifecycleLoading =
entry.lifecycleState === 'enabling' ||
entry.lifecycleState === 'disabling';
@@ -235,6 +240,13 @@ export class LayerLifecycle {
count: 0,
lastUpdate: null,
...moduleStats,
...(availability?.available === false
? {
status: 'unavailable',
sourceUnavailable: true,
error: availability.reason,
}
: {}),
loading: lifecycleLoading || moduleStats.loading === true,
refreshing: entry.refreshing || moduleStats.refreshing === true,
managerRefreshError: entry.managerRefreshError,
@@ -2282,7 +2294,17 @@ export class LayerLifecycle {
}
}
_sourceAvailability(layerId) {
return (
this._catalogSourceAvailability?.(layerId) ??
this.layers.get(layerId)?.module.getSourceAvailability?.()
);
}
async _visibilityBlockReason(change) {
const availability = this._sourceAvailability(change.layerId);
if (change.enabled && availability?.available === false)
return availability.reason || 'Data source unavailable';
for (const callback of this._visibilityGuards) {
try {
const result = await callback(change);
src/data/militaryAwareness.test.mjs
+65
View File
@@ -41,6 +41,7 @@ import {
formatAwarenessLabel,
getAwarenessNavigationTargets,
} from './militaryAwarenessEngine.js';
import { formatAwarenessCount } from '../layers/awareness/panel.js';
import { NAVIGATION_AUTHORITY_EVENT } from '../navigationPolicy.js';
const militaryAwarenessSource = readLayerSource(
@@ -55,6 +56,18 @@ const AWARENESS_DEPENDENCIES = [
'military-installations',
];
test('Contacts labels a capped cohort as a lower bound', () => {
assert.equal(
formatAwarenessCount({ count: 20_000, complete: false, truncated: true }),
'At least 20,000',
);
assert.equal(
formatAwarenessCount({ count: 19_999, complete: true, truncated: false }),
'19,999',
);
assert.equal(formatAwarenessCount({ count: null }), '?');
});
function installAwarenessRuntime({
isEnabled = () => true,
isEffectivelyEnabled = isEnabled,
@@ -2554,6 +2567,7 @@ test('the contacts window reports exactly the counts the panel renders', () => {
assert.equal(window.flights, 42);
assert.equal(window.military, 13);
assert.equal(window.aircraft, 55);
assert.equal(window.complete, true);
assert.equal(window.centeredOn, 'ASA635');
assert.equal(window.radiusKm, Math.round(AWARENESS_RADIUS_M / 1000));
// A feed that cannot answer says so rather than reporting a confident zero.
@@ -2561,6 +2575,57 @@ test('the contacts window reports exactly the counts the panel renders', () => {
assert.equal(window.vessels, 'unknown');
});
test('the voice query snapshot is a detached copy of the rendered aircraft cohort', async () => {
const subjectPosition = Cesium.Cartesian3.fromDegrees(-97.74, 30.27, 1_000);
const nearbyPosition = Cesium.Cartesian3.fromDegrees(-97.7, 30.3, 1_500);
const restoreCollections = stubAwarenessCollections({
flights: [
{
icao24: 'subject',
id: 'SUBJECT',
position: subjectPosition,
distance: 0,
},
{
icao24: 'nearby',
id: 'NEARBY',
position: nearbyPosition,
distance: 5_000,
},
],
});
const runtime = installAwarenessRuntime();
try {
runtime.dispatch(
'gev:awareness-subject-selected',
awarenessSubject('flights', 'subject', subjectPosition),
);
await nextTurn();
const first = militaryAwarenessLayer.getAircraftQuerySnapshot();
assert.equal(first.cohorts.flights.count, 1);
assert.equal(first.cohorts.flights.complete, true);
assert.equal(first.cohorts.flights.provenance.id, 'flights');
assert.equal(first.cohorts.flights.provenance.enabled, true);
assert.equal(first.cohorts.flights.items[0].icao24, 'nearby');
first.cohorts.flights.items[0].icao24 = 'mutated';
first.cohorts.flights.items[0].position.x = 99;
first.cohorts.flights.provenance.source = 'mutated';
first.cohorts.flights.provenance.stats.coverage = { radiusM: 1 };
first.subject.position.x = 77;
const second = militaryAwarenessLayer.getAircraftQuerySnapshot();
assert.equal(second.cohorts.flights.items[0].icao24, 'nearby');
assert.equal(second.cohorts.flights.items[0].position.x, nearbyPosition.x);
assert.notEqual(second.cohorts.flights.provenance.source, 'mutated');
assert.notDeepEqual(second.cohorts.flights.provenance.stats.coverage, {
radiusM: 1,
});
assert.equal(second.subject.position.x, subjectPosition.x);
} finally {
runtime.restore();
restoreCollections();
}
});
test('there is no contacts window without a subject', () => {
assert.equal(contactsWindowFromSnapshot(null), null);
assert.equal(contactsWindowFromSnapshot({ cohorts: [] }), null);
src/data/pickRegistry.js
+17
View File
@@ -65,6 +65,23 @@ export function unregisterPickOwner(layerId) {
_owners.delete(layerId);
}
/**
* The registered layer that owns a picked id, or null.
* @param {string} pickedId - Canonical pick id from {@link resolvePickId}.
* @returns {string|null} Owning layer id.
*/
export function findPickOwner(pickedId) {
if (!pickedId) return null;
for (const [ownerId, predicate] of _owners) {
try {
if (predicate(pickedId)) return ownerId;
} catch {
// a broken predicate must never break picking
}
}
return null;
}
/**
* True when some OTHER registered layer owns the picked id.
* @param {string} layerId - The asking layer's id (excluded from the scan).
src/data/pickedContext.js
+128
View File
@@ -0,0 +1,128 @@
import { getContextStore, isContextRecordActive } from './contextStore.js';
import { findPickOwner, resolvePickId } from './pickRegistry.js';
/**
* Resolve a `scene.pick()` result to the identity a person would name: which
* layer, which record, and its display label.
*
* Two lanes, in order:
* 1. Context-store carriers. Entity-backed layers (infrastructure GeoJSON,
* selected vessels, fires, installations) stamp `__gevContextId` on the
* picked object, and the store record already carries the label and
* position voice uses everywhere else.
* 2. Pick owners. Primitive-backed layers (aircraft, satellites, vessels)
* register an ownership predicate in `pickRegistry`; the owning layer's
* `findByQuery` turns the pick id into a live descriptor.
*
* Trails claim their pick ids only to make clicks inert, so they never
* resolve. Disabled layers never resolve: what the user cannot see is not
* what they are pointing at.
*/
const KIND_BY_LAYER = Object.freeze({
flights: 'aircraft',
military: 'aircraft',
'local-adsb': 'aircraft',
'ais-live-vessels': 'vessel',
satellites: 'satellite',
'local-firms': 'fire',
});
const IGNORED_OWNERS = new Set(['trails']);
function text(value) {
return String(value ?? '').trim();
}
function finite(value) {
if (value === null || value === undefined || value === '') return null;
const number = Number(value);
return Number.isFinite(number) ? number : null;
}
/** Kind of thing a layer holds, for deixis ("this aircraft", "this place"). */
export function pickedKindForLayer(layerId) {
return KIND_BY_LAYER[layerId] || 'feature';
}
function contextCarrierRecord(picked, dataManager) {
const store = getContextStore();
for (const carrier of [
picked?.id,
picked?.primitive?.id,
picked?.primitive,
]) {
const contextId =
carrier && typeof carrier === 'object' ? carrier.__gevContextId : null;
if (!contextId) continue;
const record = store.entities.get(contextId);
if (record && isContextRecordActive(record, dataManager)) return record;
}
return null;
}
function fromRecord(record) {
const layerId = record.layerId || null;
const id =
layerId === 'ais-live-vessels' && record.properties?.mmsi
? String(record.properties.mmsi)
: String(record.id);
return {
layerId,
id,
label:
text(record.label) ||
text(record.properties?.name) ||
text(record.layerName) ||
id,
kind: pickedKindForLayer(layerId),
lat: finite(record.latitude),
lon: finite(record.longitude),
};
}
function descriptorLabel(found, fallback) {
return (
text(found?.callsign) ||
text(found?.registration) ||
text(found?.name) ||
text(found?.icao24) ||
text(found?.mmsi) ||
text(found?.noradId) ||
fallback
);
}
/**
* @param {object|null} picked Result of `scene.pick()`.
* @param {object} [options]
* @param {object} [options.dataManager] Layer lifecycle (enabled state, modules).
* @returns {{layerId: string, id: string, label: string, kind: string, lat: number|null, lon: number|null, altitudeM?: number|null}|null}
*/
export function resolvePickedContext(picked, { dataManager = null } = {}) {
if (!picked) return null;
const record = contextCarrierRecord(picked, dataManager);
if (record) return fromRecord(record);
const pickId = resolvePickId(picked);
if (!pickId) return null;
const layerId = findPickOwner(pickId);
if (!layerId || IGNORED_OWNERS.has(layerId)) return null;
if (dataManager?.isEnabled && !dataManager.isEnabled(layerId)) return null;
const layer = dataManager?.layers?.get?.(layerId);
let found = null;
try {
found = layer?.module?.findByQuery?.(pickId) || null;
} catch {
found = null;
}
return {
layerId,
id: pickId,
label: descriptorLabel(found, text(layer?.name) || pickId),
kind: pickedKindForLayer(layerId),
lat: finite(found?.latitude),
lon: finite(found?.longitude),
altitudeM: finite(found?.altitudeM),
};
}
src/data/pickedContext.test.mjs
+75
View File
@@ -0,0 +1,75 @@
import assert from 'node:assert/strict';
import test from 'node:test';
globalThis.window ||= globalThis;
globalThis.CustomEvent ||= class CustomEvent {
constructor(type, init) {
this.type = type;
this.detail = init?.detail;
}
};
globalThis.dispatchEvent ||= () => true;
const { registerEntityContext } = await import('./contextStore.js');
const { registerPickOwner, unregisterPickOwner, findPickOwner } = await import('./pickRegistry.js');
const { resolvePickedContext, pickedKindForLayer } = await import('./pickedContext.js');
function manager({ enabled = new Set(['flights', 'local-datacenters']), modules = {} } = {}) {
return {
isEnabled: (id) => enabled.has(id),
layers: new Map(Object.entries(modules).map(([id, module]) => [id, { name: id, module }])),
};
}
test('an aircraft billboard resolves through its pick owner to a live label', () => {
registerPickOwner('flights', (id) => id === 'a1b2c3');
const dataManager = manager({
modules: {
flights: {
findByQuery: (q) => (q === 'a1b2c3' ? { icao24: 'a1b2c3', callsign: 'UPS793', latitude: 30.2, longitude: -97.7, altitudeM: 9000 } : null),
},
},
});
const picked = { id: 'a1b2c3', primitive: {} };
assert.equal(findPickOwner('a1b2c3'), 'flights');
assert.deepEqual(resolvePickedContext(picked, { dataManager }), {
layerId: 'flights',
id: 'a1b2c3',
label: 'UPS793',
kind: 'aircraft',
lat: 30.2,
lon: -97.7,
altitudeM: 9000,
});
unregisterPickOwner('flights');
});
test('an entity-backed feature resolves through the context store', () => {
const entity = { show: true };
registerEntityContext(entity, {
id: 'local-datacenters:7',
layerId: 'local-datacenters',
label: 'Data Center 7',
latitude: 30.1,
longitude: -97.6,
});
const out = resolvePickedContext({ id: entity }, { dataManager: manager() });
assert.deepEqual(out, {
layerId: 'local-datacenters',
id: 'local-datacenters:7',
label: 'Data Center 7',
kind: 'feature',
lat: 30.1,
lon: -97.6,
});
});
test('disabled layers, trails and empty picks never resolve', () => {
registerPickOwner('military', (id) => id === 'm1');
assert.equal(resolvePickedContext({ id: 'm1' }, { dataManager: manager() }), null, 'military is disabled');
unregisterPickOwner('military');
assert.equal(resolvePickedContext({ id: 'gev-trail:1' }, { dataManager: manager() }), null);
assert.equal(resolvePickedContext(null), null);
assert.equal(resolvePickedContext({ id: 'unknown' }, { dataManager: manager() }), null);
assert.equal(pickedKindForLayer('ais-live-vessels'), 'vessel');
});
src/data/sharedOsmDisplays.test.mjs
+2 -1
View File
@@ -7,6 +7,7 @@ import { createBhoteKoshiLocatorLayer } from './bhoteKoshiLocator.js';
import { createWorldAnnotationRenderer } from '../annotations/worldAnnotationRenderer.js';
import * as annotations from '../annotations/worldAnnotationRenderer.js';
import { createDirectionsLayer } from '../layers/directions/index.js';
import { createDirectionsSource } from '../layers/directions/source.js';
import { createLifecycle as createCctvLifecycle } from '../layers/cctv/lifecycle.js';
import * as input from './inputOwnership.js';
import { createOverpassAlprSource } from '../layers/alpr/source.js';
@@ -64,7 +65,7 @@ test('voice route geometry introduces the shared OSM credit', (t) => {
test('Directions introduces the shared OSM credit when the requested route draws', async (t) => {
const v = viewer(t);
t.mock.method(globalThis, 'fetch', async () => Response.json({ ok: true, geometry: [[0, 0], [0.01, 0.01]], steps: [] }));
const layer = createDirectionsLayer({ services: {
const layer = createDirectionsLayer({ source: createDirectionsSource(), services: {
credits: { showOsmCredit, hideOsmCredit }, annotations, input, scenePick: {}, camera: {},
overlays: { setOverlayEntries: noop, setOverlaySourceVisible: noop, clearOverlaySource: noop },
render: { governorRequestRender: noop, holdContinuousRender: noop, releaseContinuousRender: noop },
src/firstRunExperience.test.mjs
+10 -5
View File
@@ -656,7 +656,7 @@ test('the DISPLAY rail starts collapsed on a first run, and a stored choice wins
// ── Voice: instruction-only, tool schema unchanged ─────────────────────
test('the voice TOOL SCHEMA matches the pinned release — the mission mapping is instructions only', () => {
test('the voice TOOL SCHEMA matches the pinned contract — the mission mapping is instructions only', () => {
// Analyst layers and the separate satellite-pass tool deliberately extend the schema.
// Canonical serialization pins every tool name, description, property and
// ordering while allowing source formatting. Derived from the unchanged
@@ -667,12 +667,17 @@ test('the voice TOOL SCHEMA matches the pinned release — the mission mapping i
// Cyber deliberately adds one layout; first-run missions still change no tools.
hudLayout.enum = hudLayout.enum.filter((layout) => layout !== 'cyber');
const block = JSON.stringify(legacyTools);
// Re-derived for the additive `local-adsb` set_layer_visibility value and
// its common-name mapping; the missions still ride existing tools.
assert.equal(block.length, 27432, 'serialized tool schema length drifted');
// Re-derived for the voice layer manifest (generated layer enums, alias and
// field hints), point-and-ask's pointer/referent arguments and the prompt
// consolidation (shorter analyst, annotate_map and ISS wording), plus the
// referent-only track_entity alternative (kept out of the model-facing
// schema, which may not carry top-level anyOf), and Contacts requested-radius
// list descriptions; the missions still ride existing tools.
// Street Level adds toggle enum values and the generated alias hint.
assert.equal(block.length, 29802, 'serialized tool schema length drifted');
assert.equal(
crypto.createHash('sha256').update(block).digest('hex'),
'a2a4a787f4528f75b01f3f42caec636f29c37452c0d45b11f4f986171d6be57d',
'b316ca2e67848eb565b6847ac044a19d1465d8ef8252a5dfbd7d947a2a36d5ed',
'the first-run missions must ride EXISTING tools: no schema edit, no cache bust',
);
const instructions = fs.readFileSync(new URL('../server/providers/openai/instructions.js', import.meta.url), 'utf8');
src/keySetup.js
+179
View File
@@ -1,4 +1,8 @@
import { createSurfaceKeyboard } from './ui/surfaceKeyboard.js';
import {
readStoredCloudVoiceAuthMode,
writeStoredCloudVoiceAuthMode,
} from './voice/cloudVoiceAuth.js';
/**
* The POWER UP surface — paste a key, get a power.
@@ -38,6 +42,52 @@ export function collectKeyUpdates(fields) {
return updates;
}
function sleepWithSignal(ms, signal) {
return new Promise((resolve, reject) => {
if (signal?.aborted) {
reject(signal.reason || new DOMException('Aborted', 'AbortError'));
return;
}
const onAbort = () => {
clearTimeout(timer);
reject(signal.reason || new DOMException('Aborted', 'AbortError'));
};
const timer = setTimeout(() => {
signal?.removeEventListener('abort', onAbort);
resolve();
}, ms);
signal?.addEventListener('abort', onAbort, { once: true });
});
}
export async function waitForChatGptOAuth({
fetchImpl,
signal,
timeoutMs = 120_000,
pollMs = 1_000,
now = () => Date.now(),
sleep = sleepWithSignal,
} = {}) {
const deadline = now() + Math.max(0, timeoutMs);
while (!signal?.aborted && now() <= deadline) {
const response = await fetchImpl('/api/realtime/oauth-status', {
cache: 'no-store',
signal,
});
const payload = await response.json().catch(() => ({}));
if (signal?.aborted) return false;
if (response.ok && payload.available) return true;
if (!response.ok || payload.loginFailed) {
throw new Error(
payload.error || 'Could not check ChatGPT sign-in. Try again.',
);
}
if (now() >= deadline) break;
await sleep(Math.max(0, pollMs), signal);
}
return false;
}
/**
* After the FIRST Google key lands, the restart's reload should boot the
* photoreal default — not faithfully restore the auto-selected keyless OSM
@@ -61,6 +111,21 @@ export function stripKeylessBasemapFromHash(hash) {
const TIER_DOTS = Object.freeze({ metered: '🔴', free: '🟡' });
function updateCloudVoiceAuthControl(auth, busy = false) {
const mode = readStoredCloudVoiceAuthMode();
const state = auth.querySelector('.key-setup-cloud-auth-state');
const toggle = auth.querySelector('[data-cloud-voice-auth-toggle]');
state.textContent =
mode === 'oauth' ? 'VOICE AUTH · CHATGPT OAUTH' : 'VOICE AUTH · API KEY';
toggle.textContent = mode === 'oauth' ? 'USE API KEY' : 'USE CHATGPT OAUTH';
toggle.title =
mode === 'oauth'
? 'Use OPENAI_API_KEY for the next cloud voice session'
: 'Use the signed-in local ChatGPT/Codex OAuth session for the next cloud voice session';
// Keep the control focusable while the delegated handler blocks repeats.
toggle.setAttribute('aria-disabled', String(busy));
}
/** Build one key row. All content is our own registry text, set via textContent. */
function buildRow(documentRef, key) {
const row = documentRef.createElement('section');
@@ -144,6 +209,19 @@ function buildRow(documentRef, key) {
}
row.append(fields);
}
if (key.id === 'openai') {
const auth = documentRef.createElement('div');
auth.className = 'key-setup-cloud-auth';
const state = documentRef.createElement('span');
state.className = 'key-setup-cloud-auth-state';
const toggle = documentRef.createElement('button');
toggle.type = 'button';
toggle.className = 'key-setup-cloud-auth-toggle';
toggle.dataset.cloudVoiceAuthToggle = 'true';
auth.append(state, toggle);
updateCloudVoiceAuthControl(auth);
row.append(auth);
}
return row;
}
@@ -224,8 +302,14 @@ export async function initKeySetup({
const statusLine = root.querySelector('[data-key-setup-status]');
const defaultStatusText = statusLine?.textContent || '';
let busy = false;
let oauthBusy = false;
let open = false;
const syncCloudVoiceAuth = () => {
for (const auth of rowsHost.querySelectorAll('.key-setup-cloud-auth'))
updateCloudVoiceAuthControl(auth, oauthBusy);
};
const render = (nextStatus) => {
if (disposed) return;
status = nextStatus;
@@ -239,6 +323,7 @@ export async function initKeySetup({
rowsHost.textContent = '';
for (const key of status.keys || [])
rowsHost.append(buildRow(documentRef, key));
syncCloudVoiceAuth();
};
const visible = () =>
@@ -367,6 +452,100 @@ export async function initKeySetup({
applyButton?.addEventListener('click', onApply);
// Remove buttons are rendered per row; delegate so re-renders stay wired.
rowsHost?.addEventListener('click', (event) => {
const authButton = event.target?.closest?.(
'[data-cloud-voice-auth-toggle]',
);
if (authButton && !disposed) {
if (oauthBusy) return;
void (async () => {
const current = readStoredCloudVoiceAuthMode();
if (current === 'oauth') {
writeStoredCloudVoiceAuthMode('api-key');
syncCloudVoiceAuth();
say('Cloud voice will use OPENAI_API_KEY on the next session.');
return;
}
oauthBusy = true;
syncCloudVoiceAuth();
say('Checking local ChatGPT OAuth sign-in…');
try {
const response = await doFetch('/api/realtime/oauth-status', {
cache: 'no-store',
signal: lifetime.signal,
});
const payload = await response.json().catch(() => ({}));
if (lifetime.signal.aborted) return;
if (!response.ok)
throw new Error(
payload.error || 'Could not check ChatGPT sign-in.',
);
if (payload.available) {
writeStoredCloudVoiceAuthMode('oauth');
syncCloudVoiceAuth();
say(
'ChatGPT OAuth selected for cloud voice. Your API key stays saved and available.',
);
return;
}
say(
payload.code === 'CODEX_OAUTH_REAUTH_REQUIRED'
? 'ChatGPT sign-in expired. Opening sign-in again…'
: 'Opening ChatGPT sign-in in your browser…',
);
const loginResponse = await doFetch('/api/realtime/oauth-login', {
method: 'POST',
cache: 'no-store',
signal: lifetime.signal,
});
const loginPayload = await loginResponse.json().catch(() => ({}));
if (lifetime.signal.aborted) return;
if (!loginResponse.ok) {
say(
loginPayload.error ||
payload.error ||
'Could not start ChatGPT sign-in on this machine.',
);
return;
}
if (loginPayload.available) {
writeStoredCloudVoiceAuthMode('oauth');
syncCloudVoiceAuth();
say(
'ChatGPT OAuth selected for cloud voice. Your API key stays saved and available.',
);
return;
}
say(
'Finish ChatGPT sign-in in the browser. Waiting for it to complete…',
);
const available = await waitForChatGptOAuth({
fetchImpl: doFetch,
signal: lifetime.signal,
});
if (lifetime.signal.aborted) return;
if (!available) {
say(
'ChatGPT sign-in timed out. Click USE CHATGPT OAUTH to try again.',
);
return;
}
writeStoredCloudVoiceAuthMode('oauth');
syncCloudVoiceAuth();
say(
'ChatGPT sign-in complete. OAuth will be used for the next cloud voice session.',
);
} catch (error) {
if (lifetime.signal.aborted) return;
say(`OAuth check failed: ${error?.message || error}`);
} finally {
oauthBusy = false;
if (!disposed) syncCloudVoiceAuth();
}
})();
return;
}
const button = event.target?.closest?.('[data-key-setup-remove]');
if (disposed || !button || busy) return;
let envVars = [];
src/keySetup.test.mjs
+59
View File
@@ -5,6 +5,7 @@ import {
keySetupChipLabel,
stripKeylessBasemapFromHash,
bindKeySetupPlacement,
waitForChatGptOAuth,
} from './keySetup.js';
test('setup placement moves the same button only in Cyber and disconnects on teardown', () => {
@@ -61,6 +62,64 @@ test('collectKeyUpdates keeps only non-empty trimmed values', () => {
assert.deepEqual(collectKeyUpdates(null), {});
});
test('OAuth login polling stops as soon as local ChatGPT auth becomes available', async () => {
let checks = 0;
let clock = 0;
const available = await waitForChatGptOAuth({
fetchImpl: async () => {
checks += 1;
return {
ok: true,
json: async () => ({ available: checks >= 3 }),
};
},
timeoutMs: 10_000,
pollMs: 100,
now: () => clock,
sleep: async (ms) => {
clock += ms;
},
});
assert.equal(available, true);
assert.equal(checks, 3);
});
test('OAuth login polling stops on login or HTTP failure instead of waiting for timeout', async () => {
for (const result of [
{ ok: true, payload: { available: false, loginFailed: true, error: 'Sign-in failed.' } },
{ ok: false, payload: { error: 'Sign-in is local only.' } },
]) {
let checks = 0;
await assert.rejects(waitForChatGptOAuth({
fetchImpl: async () => { checks += 1; return { ok: result.ok, json: async () => result.payload }; },
sleep: () => assert.fail('failed login must stop polling'),
}), { message: result.payload.error });
assert.equal(checks, 1);
}
});
test('OAuth login polling respects timeout and an aborted setup surface', async () => {
let clock = 0;
let checks = 0;
const poll = { fetchImpl: async () => { checks += 1; return { ok: true, json: async () => ({ available: false, pending: true }) }; } };
assert.equal(await waitForChatGptOAuth({ ...poll, timeoutMs: 100, pollMs: 100, now: () => clock, sleep: async (ms) => { clock += ms; } }), false);
assert.equal(checks, 2);
const controller = new AbortController();
controller.abort();
assert.equal(await waitForChatGptOAuth({ ...poll, signal: controller.signal }), false);
assert.equal(checks, 2, 'aborted polling does not fetch');
});
test('OAuth polling ignores a ready response received after the surface was aborted', async () => {
const controller = new AbortController();
const available = await waitForChatGptOAuth({
signal: controller.signal,
fetchImpl: async () => ({ ok: true, json: async () => { controller.abort(); return { available: true }; } }),
sleep: () => assert.fail('aborted polling must not continue'),
});
assert.equal(available, false);
});
test('the first Google key strips ONLY the keyless OSM basemap from the share hash', () => {
const stripped = stripKeylessBasemapFromHash('lat=30.2&lon=-97.7&map=osm&style=normal');
assert.ok(stripped !== null);
src/keySetupCore.mjs
+1 -1
View File
@@ -55,7 +55,7 @@ export const KEY_SETUP_KEYS = Object.freeze([
Object.freeze({
id: 'openai',
title: 'OPENAI',
unlocks: 'Voice control — talk to the planet',
unlocks: 'Voice control — API key or ChatGPT OAuth',
getUrl: 'https://platform.openai.com/api-keys',
envVars: Object.freeze(['OPENAI_API_KEY']),
tier: 'metered',
src/layers/alpr/index.js
+31
View File
@@ -392,6 +392,37 @@ export function createAlprCamerasLayer({ source, services } = {}) {
],
};
},
/**
* Snapshot loaded ALPR cameras (the nearby query box) as plain JSON-safe records for the analyst
* query engine. On demand only (once per spoken query); [] while the
* layer is off.
* @param {number} [maxCount=Infinity] Most records to return.
* @returns {Array<Object>} {id, lat, lon, operator, manufacturer, cameraType, directionDeg}.
*/
getAnalystRecords(maxCount = Infinity) {
if (!state.enabled) return [];
const result = [];
for (const record of state.records || []) {
if (result.length >= maxCount) break;
if (
!Number.isFinite(record.latitude) ||
!Number.isFinite(record.longitude)
)
continue;
result.push({
id: record.id,
lat: record.latitude,
lon: record.longitude,
operator: record.operator ?? null,
manufacturer: record.manufacturer ?? null,
cameraType: record.cameraType ?? null,
directionDeg: Number.isFinite(record.directionDeg)
? record.directionDeg
: null,
});
}
return result;
},
getStats() {
return {
count: state.dataSource?.entities.values.length || 0,
src/layers/awareness/controls.js
Vendored
+50
View File
@@ -75,6 +75,56 @@ export function createControls({ state: layerState, services, parts, source }) {
);
},
/**
* Return the exact retained aircraft cohorts behind the current Contacts
* panel snapshot. Voice reads this immutable copy instead of re-scanning
* live layers, so panel and spoken counts share one evaluation timestamp.
*/
getAircraftQuerySnapshot() {
if (!layerState.enabled || !layerState.subject || !layerState.results)
return null;
// Build every public count from this exact results object before
// returning. A refresh may replace `layerState.results` as soon as the
// caller awaits, so consumers must not make a second read later and
// accidentally combine two evaluation timestamps.
const panelSnapshot = parts.model.buildAwarenessContextSnapshot(
layerState.results,
parts.model.navigationState(),
{
subjectPresent: !layerState.subjectMissing,
},
);
const cohorts = {};
for (const cohort of layerState.results.cohorts || []) {
if (!['flights', 'military'].includes(cohort?.id)) continue;
cohorts[cohort.id] = {
count: cohort.summary?.count ?? null,
complete:
Number.isFinite(cohort.summary?.count) &&
cohort.summary?.complete !== false,
truncated:
!Number.isFinite(cohort.summary?.count) ||
cohort.summary?.truncated === true,
// These records carry structured values such as Cartesian positions.
// A shallow spread would let a voice consumer mutate the retained
// Contacts cohort through the advertised read-only snapshot.
items: structuredClone(cohort.summary?.navigationNearest || []),
source: cohort.source || null,
provenance: cohort.provenance
? structuredClone(cohort.provenance)
: null,
reason: cohort.summary?.reason || null,
};
}
return {
subject: structuredClone(layerState.results.subject),
evaluatedAt: layerState.results.evaluatedAt,
radiusM: layerState.results.radiusM,
cohorts,
contactsWindow: parts.model.contactsWindowFromSnapshot(panelSnapshot),
};
},
/**
* Release Contact-owned camera tracking without discarding the selected
* subject. Reset-to-globe uses this route so the normal Context FOCUS action
src/layers/awareness/model.js
+11
View File
@@ -144,6 +144,9 @@ export function createModel({ state: layerState, services, parts, source }) {
function contactsWindowFromSnapshot(snapshot) {
if (!snapshot?.subject) return null;
const aircraftCohorts = (snapshot.cohorts || []).filter((cohort) =>
['flights', 'military'].includes(cohort?.id),
);
const countFor = (cohortId) => {
const cohort = Array.isArray(snapshot.cohorts)
? snapshot.cohorts.find((item) => item?.id === cohortId)
@@ -164,6 +167,12 @@ export function createModel({ state: layerState, services, parts, source }) {
flights,
military,
vessels: countFor('ais-live-vessels'),
complete:
aircraftCohorts.length === 2 &&
aircraftCohorts.every(
(cohort) =>
Number.isFinite(cohort.count) && cohort.complete !== false,
),
};
}
@@ -190,6 +199,8 @@ export function createModel({ state: layerState, services, parts, source }) {
coverage: cohort.coverage || null,
relationship: cohort.summary.relationship,
count: cohort.summary.count,
complete: cohort.summary.complete !== false,
truncated: cohort.summary.truncated === true,
reason: cohort.summary.reason,
nearest: cohort.summary.nearest.slice(),
})),
src/layers/awareness/navigation.js
+3
View File
@@ -25,6 +25,7 @@ export function createNavigation({
{
displayLimit = AWARENESS_MAX_EXAMPLES,
navigationLimit = AWARENESS_MAX_NAVIGATION_EXAMPLES,
complete = true,
} = {},
) {
const summary = summarizeAwarenessCohort(items, {
@@ -34,6 +35,8 @@ export function createNavigation({
if (summary.count === null) return summary;
return {
...summary,
complete: Boolean(complete),
truncated: !complete,
nearest: summary.nearest.slice(0, displayLimit),
navigationNearest: summary.nearest,
};
src/layers/awareness/panel.js
+10 -1
View File
@@ -5,6 +5,15 @@ import {
} from '../../data/militaryAwarenessEngine.js';
import { AWARENESS_PAGE_SIZE, AWARENESS_PAGE_ROTATE_MS } from './policy.js';
/** Format a cohort total without presenting a retained cap as exact. */
export function formatAwarenessCount(summary = {}) {
if (!Number.isFinite(summary.count)) return '?';
const count = summary.count.toLocaleString('en-US');
return summary.complete === false || summary.truncated === true
? `At least ${count}`
: count;
}
export function createPanel({ state: layerState, services, parts, source }) {
function ensurePanel() {
if (layerState.panel) return layerState.panel;
@@ -61,7 +70,7 @@ export function createPanel({ state: layerState, services, parts, source }) {
function rowHtml(cohort) {
const summary = cohort.summary;
const count = summary.count === null ? '?' : String(summary.count);
const count = formatAwarenessCount(summary);
const page = layerState.cohortPages.get(cohort.id) || 0;
const nearest = summary.nearest
.slice(page, page + AWARENESS_PAGE_SIZE)
src/layers/awareness/policy.js
+2 -2
View File
@@ -38,8 +38,8 @@ export const AWARENESS_MAX_EXAMPLES = 10;
// so these caps sit far above any realistic in-range population rather than at
// the display limit. They are still FINITE: an unbounded materialization would
// let a pathological feed sort an eleven-thousand-contact array on every
// refresh. Truthfulness does not depend on them — `summarizeAwarenessCohort`
// derives `count` from the full in-range set before any slice.
// refresh. Callers sample beyond this cap and carry explicit completeness, so
// a saturated cohort is a lower bound rather than a silently exact count.
export const AWARENESS_QUERY_LIMIT = 20000;
src/layers/awareness/queries.js
+29 -8
View File
@@ -53,7 +53,12 @@ export function createQueries({ state: layerState, services, parts, source }) {
neverAnswered ||
['unavailable', 'zoom-in'].includes(stats.status) ||
Boolean(stats.error && stats.count === 0);
return { available: !unavailable, stale: Boolean(stats.stale), stats };
return {
available: !unavailable,
enabled,
stale: Boolean(stats.stale),
stats,
};
}
function collectSourceStates() {
@@ -147,8 +152,10 @@ export function createQueries({ state: layerState, services, parts, source }) {
* @param {object} [options]
* @param {number} [options.radiusM=AWARENESS_RADIUS_M] Window radius.
* @param {object|null} [options.subject=null] Contact at the centre, excluded.
* @returns {{flights: Array, military: Array, aircraft: number}|null} Cohorts
* plus the combined aircraft count, or null without a position.
* @returns {{flights: Array, military: Array, aircraft: number,
* completeByLayer: {flights: boolean, military: boolean}}|null} Cohorts,
* their lower-bound completeness, and the combined aircraft count, or
* null without a position.
*/
function collectAircraftProximityWindow(
@@ -156,21 +163,35 @@ export function createQueries({ state: layerState, services, parts, source }) {
{ radiusM = AWARENESS_RADIUS_M, subject = null } = {},
) {
if (!position) return null;
const flights = flightsLayer
.getNearby(position, radiusM, AWARENESS_QUERY_LIMIT, {
// Ask for one usable row beyond the retained limit so a capped cohort is
// reported as a lower bound instead of an exact count. The selected
// subject can consume one slot before exclusion, hence the extra two.
const sampleLimit = AWARENESS_QUERY_LIMIT + 2;
const flightSample = flightsLayer
.getNearby(position, radiusM, sampleLimit, {
includeHidden: true,
})
.filter(
(item) => !subject || !isSame(subject, item, 'flights', 'icao24'),
);
const military = militaryFlightsLayer
.getNearby(position, radiusM, AWARENESS_QUERY_LIMIT, {
const militarySample = militaryFlightsLayer
.getNearby(position, radiusM, sampleLimit, {
includeHidden: true,
})
.filter(
(item) => !subject || !isSame(subject, item, 'military', 'icao24'),
);
return { flights, military, aircraft: flights.length + military.length };
const flights = flightSample.slice(0, AWARENESS_QUERY_LIMIT);
const military = militarySample.slice(0, AWARENESS_QUERY_LIMIT);
return {
flights,
military,
aircraft: flights.length + military.length,
completeByLayer: {
flights: flightSample.length <= AWARENESS_QUERY_LIMIT,
military: militarySample.length <= AWARENESS_QUERY_LIMIT,
},
};
}
return {
sourceState,
src/layers/awareness/queries.test.mjs
+33
View File
@@ -6,6 +6,39 @@ import { createSubject } from './subject.js';
import { createControls } from '../installations/controls.js';
import { createModel } from '../installations/model.js';
import { summarizeAwarenessCohort } from '../../data/militaryAwarenessEngine.js';
import { AWARENESS_QUERY_LIMIT } from './policy.js';
test('aircraft window marks a capped layer as a lower bound', () => {
const rows = Array.from({ length: AWARENESS_QUERY_LIMIT + 1 }, (_, index) => ({
icao24: `f${index}`,
distance: index,
}));
let requested = null;
const services = {
flights: {
getNearby: (_position, _radius, limit) => {
requested = limit;
return rows.slice(0, limit);
},
},
military: { getNearby: () => [] },
};
const parts = {
navigation: {
summarizeAwarenessCohortForNavigation: (items, source) =>
summarizeAwarenessCohort(items, source),
},
};
const queries = createQueries({ state: {}, services, parts });
const window = queries.collectAircraftProximityWindow({ center: true });
assert.equal(requested, AWARENESS_QUERY_LIMIT + 2);
assert.equal(window.flights.length, AWARENESS_QUERY_LIMIT);
assert.equal(window.aircraft, AWARENESS_QUERY_LIMIT);
assert.deepEqual(window.completeByLayer, {
flights: false,
military: true,
});
});
test('Contacts excludes square corners and measures from the current moving subject', () => {
const records = [
src/layers/awareness/subject.js
+46 -2
View File
@@ -37,11 +37,23 @@ export function createSubject({ state: layerState, services, parts, source }) {
const militaryState = sourceStates.military;
const vesselsState = sourceStates['ais-live-vessels'];
const installationsState = sourceStates['military-installations'];
const evaluatedAt = Date.now();
const retainedProvenance = (id, label, sourceState, fallbackSource) => {
const retainedSource = sourceState.stats.source || fallbackSource;
return {
id,
name: label,
enabled: sourceState.enabled,
source: retainedSource,
stats: { ...sourceState.stats, source: retainedSource },
};
};
// Same engine the voice analyst calls — see collectAircraftProximityWindow.
const { flights, military } = parts.queries.collectAircraftProximityWindow(
const aircraftWindow = parts.queries.collectAircraftProximityWindow(
position,
{ subject },
);
const { flights, military, completeByLayer } = aircraftWindow;
const vessels = aisLiveVesselsLayer
.getNearby(position, AWARENESS_RADIUS_M, AWARENESS_QUERY_LIMIT)
.filter(
@@ -61,31 +73,57 @@ export function createSubject({ state: layerState, services, parts, source }) {
);
return {
subject,
evaluatedAt: Date.now(),
evaluatedAt,
radiusM: AWARENESS_RADIUS_M,
cohorts: [
{
id: 'flights',
label: 'Flights',
source: flightsState.stats.source || SOURCE_LABEL.flights,
provenance: retainedProvenance(
'flights',
'Flights',
flightsState,
SOURCE_LABEL.flights,
),
summary: parts.navigation.summarizeAwarenessCohortForNavigation(
flights,
flightsState,
{
navigationLimit: AWARENESS_QUERY_LIMIT,
complete: completeByLayer.flights,
},
),
},
{
id: 'military',
label: 'Military flights',
source: militaryState.stats.source || SOURCE_LABEL.military,
provenance: retainedProvenance(
'military',
'Military flights',
militaryState,
SOURCE_LABEL.military,
),
summary: parts.navigation.summarizeAwarenessCohortForNavigation(
military,
militaryState,
{
navigationLimit: AWARENESS_QUERY_LIMIT,
complete: completeByLayer.military,
},
),
},
{
id: 'ais-live-vessels',
label: 'AIS vessels',
source: vesselsState.stats.source || SOURCE_LABEL['ais-live-vessels'],
provenance: retainedProvenance(
'ais-live-vessels',
'AIS vessels',
vesselsState,
SOURCE_LABEL['ais-live-vessels'],
),
summary: parts.navigation.summarizeAwarenessCohortForNavigation(
vessels,
vesselsState,
@@ -97,6 +135,12 @@ export function createSubject({ state: layerState, services, parts, source }) {
source:
installationsState.stats.source ||
SOURCE_LABEL['military-installations'],
provenance: retainedProvenance(
'military-installations',
'Mapped installations',
installationsState,
SOURCE_LABEL['military-installations'],
),
coverage:
installationsState.stats.coverageLabel || 'CURRENT VIEWPORT ONLY',
summary: parts.queries.summarizeInstallationViewport(
src/layers/bikeshare/controls.js
Vendored
+33
View File
@@ -21,6 +21,39 @@ export function createControls({ state: layerState, services, parts, source }) {
return parts.queries.collectDetectableStations(options);
},
/**
* Snapshot loaded bikeshare stations as plain JSON-safe records for the analyst
* query engine. On demand only (once per spoken query); [] while the
* layer is off.
* @param {number} [maxCount=Infinity] Most records to return.
* @returns {Array<Object>} {id, name, city, lat, lon, bikesAvailable, docksAvailable, capacity, renting}.
*/
getAnalystRecords(maxCount = Infinity) {
if (!layerState._enabled) return [];
const num = (v) => (Number.isFinite(v) ? v : null);
const result = [];
for (const record of layerState._stationRenderMap.values()) {
if (result.length >= maxCount) break;
const info = layerState._stationInfoCache
.get(record.cityId)
?.get(record.stationId);
if (!Number.isFinite(info?.lat) || !Number.isFinite(info?.lon))
continue;
result.push({
id: record.stationName || `Dock ${record.stationId}`,
name: record.stationName || null,
city: record.cityId || null,
lat: info.lat,
lon: info.lon,
bikesAvailable: num(record.bikesAvailable),
docksAvailable: num(record.docksAvailable),
capacity: num(record.capacity),
renting: record.isRenting !== false,
});
}
return result;
},
/**
* Return current layer statistics for the UI status display.
* @returns {{ count: number, lastUpdate: number|null, loading: boolean, loadingLabel?: string, error?: string }}
src/layers/cyclones/index.js
+29
View File
@@ -403,6 +403,35 @@ export function createCyclonesLayer({
setRowControlsListener(value) {
listener = typeof value === 'function' ? value : null;
},
/**
* Snapshot loaded active storms as plain JSON-safe records for the analyst
* query engine. On demand only (once per spoken query); [] while the
* layer is off.
* @param {number} [maxCount=Infinity] Most records to return.
* @returns {Array<Object>} {id, name, classification, basin, lat, lon, windKt, pressureHpa}.
*/
getAnalystRecords(maxCount = Infinity) {
if (!enabled || destroyed) return [];
const num = (v) => (Number.isFinite(v) ? v : null);
const result = [];
for (const storm of snapshot?.storms || []) {
if (result.length >= maxCount) break;
const lat = storm.position?.latitude;
const lon = storm.position?.longitude;
if (!Number.isFinite(lat) || !Number.isFinite(lon)) continue;
result.push({
id: storm.name || storm.id,
name: storm.name || null,
classification: storm.classification || null,
basin: storm.basin || null,
lat,
lon,
windKt: num(storm.windKt),
pressureHpa: num(storm.pressureHpa),
});
}
return result;
},
getStats() {
const storm = selected();
return {
src/layers/directions/index.js
+11 -18
View File
@@ -452,10 +452,7 @@ export function createDirectionsStepOverlayEntry(index, position, copy) {
* @param {{lat:number, lon:number}} b
* @returns {string}
*/
export function directionsRequestUrl(mode, a, b) {
const coords = `${a.lon.toFixed(6)},${a.lat.toFixed(6)};${b.lon.toFixed(6)},${b.lat.toFixed(6)}`;
return `/api/route?profile=${encodeURIComponent(mode)}&coords=${encodeURIComponent(coords)}&steps=1`;
}
export { directionsRequestUrl } from './source.js';
/**
* Validate a proxy payload into the route record the layer keeps, or null.
@@ -509,10 +506,12 @@ export function normalizeRoutePayload(payload, mode) {
* route, the markers, the pointer claim or the flight this layer owns. The
* shared services are injected, which is what keeps this module's own imports
* down to Cesium and the pure step formatter.
* @param {{services: object}} options
* @param {{services: object, source: {getRoute: Function}}} options
* @returns {object} The layer module the data manager registers.
*/
export function createDirectionsLayer({ services }) {
export function createDirectionsLayer({ services, source }) {
if (typeof source?.getRoute !== 'function')
throw new TypeError('Directions require a route source');
/**
* Where the maneuver card is drawn. Defaults to the shared world-overlay host;
* tests swap it. Resolved on use, not at import, because the services arrive
@@ -827,18 +826,12 @@ export function createDirectionsLayer({ services }) {
_error = null;
notifyRow();
try {
const response = await fetch(directionsRequestUrl(mode, _a, _b), {
signal: controller.signal,
headers: { Accept: 'application/json' },
});
const payload = await response.json();
if (response.status === 429) {
throw new Error(
typeof payload?.error === 'string' && payload.error
? `${payload.error} — try again in a moment`
: 'Routing is rate limited — try again in a moment',
);
}
const payload = await source.getRoute(
{ mode, a: _a, b: _b },
{
signal: controller.signal,
},
);
if (seq !== _routeSeq || !_enabled) return;
const route = normalizeRoutePayload(payload, mode);
if (!route) {
src/layers/directions/source.js
+34
View File
@@ -0,0 +1,34 @@
/** Build the existing route-proxy query from geographic endpoints. */
export function directionsRequestUrl(mode, a, b) {
const coords = `${a.lon.toFixed(6)},${a.lat.toFixed(6)};${b.lon.toFixed(6)},${b.lat.toFixed(6)}`;
return `/api/route?profile=${encodeURIComponent(mode)}&coords=${encodeURIComponent(coords)}&steps=1`;
}
/** Acquire route records using caller-owned transport and an optional endpoint. */
export function createDirectionsSource({
fetchImpl = (...args) => globalThis.fetch(...args),
endpoint = '/api/route',
} = {}) {
return {
async getRoute({ mode, a, b }, { signal } = {}) {
signal?.throwIfAborted();
const query = directionsRequestUrl(mode, a, b).split('?')[1];
const response = await fetchImpl(`${endpoint}?${query}`, {
signal,
headers: { Accept: 'application/json' },
});
const payload = await response.json();
signal?.throwIfAborted();
if (response.status === 429) {
throw new Error(
typeof payload?.error === 'string' && payload.error
? `${payload.error} — try again in a moment`
: 'Routing is rate limited — try again in a moment',
);
}
if (!response.ok && !payload?.error)
throw new Error(`Routing unavailable (HTTP ${response.status})`);
return payload;
},
};
}
src/layers/directions/source.test.mjs
+43
View File
@@ -0,0 +1,43 @@
import test from 'node:test';
import assert from 'node:assert/strict';
import { createDirectionsSource } from './source.js';
const query = { mode: 'foot', a: { lon: 1, lat: 2 }, b: { lon: 3, lat: 4 } };
test('route acquisition uses only the supplied transport and endpoint', async () => {
const controller = new AbortController();
const payload = { ok: true, geometry: [[1, 2], [3, 4]] };
const calls = [];
const source = createDirectionsSource({
endpoint: 'https://routes.example/route',
fetchImpl: async (...args) => { calls.push(args); return Response.json(payload); },
});
assert.deepEqual(await source.getRoute(query, { signal: controller.signal }), payload);
assert.equal(calls.length, 1);
const [url, init] = calls[0];
assert.equal(new URL(url).origin, 'https://routes.example');
assert.equal(new URL(url).searchParams.get('coords'), '1.000000,2.000000;3.000000,4.000000');
assert.equal(new URL(url).searchParams.get('profile'), 'foot');
assert.equal(init.signal, controller.signal);
assert.equal(init.headers.Accept, 'application/json');
});
test('aborting during route parsing discards the result', async () => {
const controller = new AbortController();
const source = createDirectionsSource({ fetchImpl: async () => ({
ok: true, json: async () => { controller.abort(); return { ok: true }; },
}) });
await assert.rejects(source.getRoute(query, { signal: controller.signal }), { name: 'AbortError' });
});
test('route failures are surfaced without fallback requests', async () => {
for (const status of [429, 503]) {
let calls = 0;
const source = createDirectionsSource({ fetchImpl: async () => {
calls++;
return Response.json({}, { status });
} });
await assert.rejects(source.getRoute(query), status === 429 ? /rate limited/ : /HTTP 503/);
assert.equal(calls, 1);
}
});
src/layers/firms/model.js
+3 -1
View File
@@ -29,7 +29,8 @@ export function createModel({
* context-store ids, so the two stay consistent).
* @param {Object|null|undefined} fire - Internal fire record.
* @returns {{id: string, lat: number|null, lon: number|null, frp: number|null,
* confidence: number|null, satellite: string|null, acqTime: number|null}}
* confidence: number|null, satellite: string|null, sensor: string|null,
* acqTime: number|null}}
*/
function mapAnalystRecord(fire) {
@@ -45,6 +46,7 @@ export function createModel({
frp: num(fire?.frp),
confidence: num(fire?.confidence), // normalized 0..1 (firmsAdapt.normalizeConfidence)
satellite: text(fire?.satellite) || text(fire?.sensor),
sensor: text(fire?.sensor), // VIIRS or MODIS
acqTime:
Number.isFinite(fire?.acqMs) && fire.acqMs > 0 ? fire.acqMs : null, // epoch ms; 0 = unparseable → null
};
src/layers/installations/controls.js
Vendored
+29
View File
@@ -162,6 +162,35 @@ export function createControls({ state: layerState, services, parts, source }) {
return true;
},
/**
* Snapshot loaded mapped installations as plain JSON-safe records for the analyst
* query engine. On demand only (once per spoken query); [] while the
* layer is off.
* @param {number} [maxCount=Infinity] Most records to return.
* @returns {Array<Object>} {id, name, class, kind, lat, lon}.
*/
getAnalystRecords(maxCount = Infinity) {
if (!layerState.enabled) return [];
const result = [];
for (const record of layerState.records || []) {
if (result.length >= maxCount) break;
if (
!Number.isFinite(record.latitude) ||
!Number.isFinite(record.longitude)
)
continue;
result.push({
id: record.name || record.id,
name: record.name || null,
class: record.class || null,
kind: record.kind || null,
lat: record.latitude,
lon: record.longitude,
});
}
return result;
},
getStats() {
const namedMarkers = parts.namedMarkers?.stats();
const subjectWindow =
src/layers/launches/controls.js
Vendored
+34
View File
@@ -17,6 +17,40 @@ export function createControls({ state: layerState, services, parts, source }) {
parts.selection.stopMissionZoomAnchor();
},
/**
* Snapshot loaded launches as plain JSON-safe records for the analyst
* query engine. On demand only (once per spoken query); [] while the
* layer is off.
* @param {number} [maxCount=Infinity] Most records to return.
* @returns {Array<Object>} {id, name, provider, status, launchSite, missionName, lat, lon, launchTimeMs, hoursUntil}.
*/
getAnalystRecords(maxCount = Infinity) {
if (!layerState._enabled) return [];
const now = Date.now();
const text = (v) => (typeof v === 'string' && v.trim() ? v.trim() : null);
const result = [];
for (const launch of layerState._launches || []) {
if (result.length >= maxCount) break;
const at = Date.parse(launch.launchTime);
result.push({
id: launch.id,
name: text(launch.name),
provider: text(launch.provider),
status: text(launch.status),
launchSite: text(launch.launchSite),
missionName: text(launch.missionName),
lat: launch.lat,
lon: launch.lon,
launchTimeMs: Number.isFinite(at) ? at : null,
// Negative for launches already flown.
hoursUntil: Number.isFinite(at)
? Math.round(((at - now) / 3_600_000) * 10) / 10
: null,
});
}
return result;
},
getStats() {
return {
count: layerState._count,
src/layers/localAdsb/index.js
+34
View File
@@ -828,6 +828,40 @@ export function createLocalAdsbLayer({
return enabled && selectMarker(`${ENTITY_PREFIX}${icao}`);
},
/**
* Snapshot loaded locally received aircraft as plain JSON-safe records for the analyst
* query engine. On demand only (once per spoken query); [] while the
* layer is off.
* @param {number} [maxCount=Infinity] Most records to return.
* @returns {Array<Object>} {id, icao24, callsign, lat, lon, altitudeM, speedKts, heading, onGround}.
*/
getAnalystRecords(maxCount = Infinity) {
if (!enabled) return [];
const num = (v) => (Number.isFinite(v) ? v : null);
const result = [];
for (const marker of markers.values()) {
if (result.length >= maxCount) break;
const record = marker.record || {};
const lat = marker.lat ?? record.lat;
const lon = marker.lon ?? record.lon;
if (!Number.isFinite(lat) || !Number.isFinite(lon)) continue;
result.push({
id: record.callsign || record.icao,
icao24: record.icao || null,
callsign: record.callsign || null,
lat,
lon,
altitudeM: Number.isFinite(record.altitudeFt)
? Math.round(record.altitudeFt * 0.3048)
: null,
speedKts: num(record.groundSpeedKt),
heading: num(record.trackDeg),
onGround: record.onGround === true,
});
}
return result;
},
getAllPositions(maxCount = 500) {
return positionRows(maxCount);
},
src/layers/recentImagery/rendering.js
+4 -2
View File
@@ -70,6 +70,8 @@ function admitTileRequests(provider, admission, requestRender, retry) {
*/
export function createRecentImageryRenderer({
cesium = Cesium,
tileTemplate = gibsTemplate,
credit = 'NASA GIBS',
maxTileRequests = 6,
requestRender = () => {},
setTimeoutImpl = (fn, ms) => globalThis.setTimeout(fn, ms),
@@ -101,7 +103,7 @@ export function createRecentImageryRenderer({
function createProvider(candidate, box) {
const spec = PRODUCTS[candidate.product];
const provider = new cesium.UrlTemplateImageryProvider({
url: gibsTemplate(candidate.product, candidate.day),
url: tileTemplate(candidate.product, candidate.day),
subdomains: ['a', 'b', 'c'],
minimumLevel: 0,
maximumLevel: spec.maxLevel,
@@ -112,7 +114,7 @@ export function createRecentImageryRenderer({
box.east,
box.north,
),
credit: 'NASA GIBS',
credit,
hasAlphaChannel: spec.format === 'png',
});
return admitTileRequests(provider, admission, requestRender, retry);
src/layers/recentImagery/rendering.test.mjs
+20 -1
View File
@@ -53,10 +53,11 @@ const S30 = { key: 'S30:2026-09-18', product: 'S30', day: '2026-09-18' };
const L30 = { key: 'L30:2026-09-16', product: 'L30', day: '2026-09-16' };
const VIIRS = { key: 'VIIRS:2026-09-20', product: 'VIIRS', day: '2026-09-20' };
function fixture({ requestImage, maxTileRequests } = {}) {
function fixture({ requestImage, maxTileRequests, ...options } = {}) {
const renders = [];
const timers = manualTimers();
const renderer = createRecentImageryRenderer({
...options,
cesium: fakeCesium(requestImage),
maxTileRequests,
requestRender: (reason) => renders.push(reason),
@@ -208,3 +209,21 @@ test('against the basemap slot a splits left with no second layer, and leaving t
assert.equal(layer.splitDirection, 0);
assert.deepEqual(renders, ['recent-imagery-show', 'recent-imagery-look']);
});
test('replacement imagery uses source-owned tile URLs and credit and tears down normally', () => {
const { renderer, globe } = fixture({
tileTemplate: (product, day) =>
`https://tiles.example/${product}/${day}/{z}/{x}/{y}`,
credit: 'Example imagery',
});
assert.equal(renderer.showSlot('a', S30, BOX), true);
const layer = globe.layers[0];
assert.equal(
layer.provider.options.url,
'https://tiles.example/S30/2026-09-18/{z}/{x}/{y}',
);
assert.equal(layer.provider.options.credit, 'Example imagery');
renderer.destroy();
assert.equal(globe.layers.length, 0);
assert.equal(layer.destroyed, true);
});
src/layers/recentImagery/source.js
+32
View File
@@ -0,0 +1,32 @@
import { searchHls } from './catalog.js';
import { gibsTemplate, wvsSnapshotUrl } from './model.js';
/** NASA-compatible imagery acquisition; transport and URL builders are replaceable. */
export function createRecentImagerySource({
fetchImpl = (...args) => globalThis.fetch(...args),
search = searchHls,
thumbnailUrl = wvsSnapshotUrl,
tileTemplate = gibsTemplate,
credit = 'NASA GIBS',
} = {}) {
return {
credit,
searchHls: (query) => search({ ...query, fetchImpl }),
async getThumbnail(candidate, box, { size = 256, signal } = {}) {
signal?.throwIfAborted();
const response = await fetchImpl(
thumbnailUrl({
product: candidate.product,
day: candidate.day,
box,
width: size,
height: size,
}),
{ signal },
);
signal?.throwIfAborted();
return response;
},
getTileTemplate: (product, day) => tileTemplate(product, day),
};
}
src/layers/recentImagery/source.test.mjs
+42
View File
@@ -0,0 +1,42 @@
import test from 'node:test';
import assert from 'node:assert/strict';
import { createRecentImagerySource } from './source.js';
test('imagery source routes catalog, thumbnails and tiles through supplied adapters', async () => {
const controller = new AbortController();
const query = { box: { west: 0, east: 1, south: 0, north: 1 }, signal: controller.signal };
const candidate = { product: 'S30', day: '2026-10-01' };
const calls = [];
const fetchImpl = async (...args) => { calls.push(args); return new Response('image'); };
const source = createRecentImagerySource({
fetchImpl,
search: async (request) => {
assert.equal(request.fetchImpl, fetchImpl);
assert.equal(request.signal, controller.signal);
assert.equal(request.box, query.box);
return [candidate];
},
thumbnailUrl: ({ product, day, width }) => `https://imagery.example/${product}/${day}/${width}`,
tileTemplate: (product, day) => `https://tiles.example/${product}/${day}/{z}/{x}/{y}`,
credit: 'Example imagery',
});
assert.deepEqual(await source.searchHls(query), [candidate]);
assert.equal(await (await source.getThumbnail(candidate, query.box, { signal: controller.signal })).text(), 'image');
assert.equal(calls.length, 1);
assert.equal(calls[0][0], 'https://imagery.example/S30/2026-10-01/256');
assert.equal(calls[0][1].signal, controller.signal);
assert.equal(source.getTileTemplate(candidate.product, candidate.day), 'https://tiles.example/S30/2026-10-01/{z}/{x}/{y}');
assert.equal(source.credit, 'Example imagery');
});
test('cancelled thumbnail acquisition does not return stale responses or retry', async () => {
const controller = new AbortController();
let calls = 0;
const source = createRecentImagerySource({
thumbnailUrl: () => 'https://imagery.example/thumbnail',
fetchImpl: async () => { calls++; controller.abort(); return new Response('image'); },
});
await assert.rejects(source.getThumbnail({}, {}, { signal: controller.signal }), { name: 'AbortError' });
await assert.rejects(source.getThumbnail({}, {}, { signal: controller.signal }), { name: 'AbortError' });
assert.equal(calls, 1);
});
src/layers/recentImagery/thumbnails.js
+6 -8
View File
@@ -8,7 +8,8 @@
* card on every render, so a read that counted would evict the visible cards
* first). Eviction revokes the image only; what the probe proved is kept.
*/
import { thumbnailOrder, wvsSnapshotUrl } from './model.js';
import { thumbnailOrder } from './model.js';
import { createRecentImagerySource } from './source.js';
const EMPTY = Object.freeze({
status: 'unknown',
@@ -22,6 +23,7 @@ const EMPTY = Object.freeze({
*/
export function createThumbnailLoader({
fetchImpl = globalThis.fetch?.bind(globalThis),
requestThumbnail = createRecentImagerySource({ fetchImpl }).getThumbnail,
maxInFlight = 3,
maxDecoded = 16,
createObjectUrl = (blob) => URL.createObjectURL(blob),
@@ -90,14 +92,10 @@ export function createThumbnailLoader({
let acquisitionTime = null;
let cancelled = false;
try {
const url = wvsSnapshotUrl({
product: entry.candidate.product,
day: entry.candidate.day,
box: entry.box,
width: size,
height: size,
const response = await requestThumbnail(entry.candidate, entry.box, {
size,
signal: controller.signal,
});
const response = await fetchImpl(url, { signal: controller.signal });
if (controller.signal.aborted) {
cancelled = true;
} else if (response?.ok) {
src/layers/recentImagery/thumbnails.test.mjs
+21
View File
@@ -315,3 +315,24 @@ test('a request queued behind an aborted fetch still starts once the abort settl
tracked: 1,
});
});
test('injected thumbnail acquisition owns requests while the loader releases object URLs', async () => {
const calls = [];
const { loader, fetch, revoked } = fixture({
requestThumbnail: async (...args) => {
calls.push(args);
return response({ headers: { 'Data-Present': 'true' } });
},
});
const entry = candidate('S30', '2026-09-18');
loader.request(entry, BOX, 0);
await settle();
assert.equal(fetch.calls.length, 0);
assert.equal(calls.length, 1);
assert.equal(calls[0][0], entry);
assert.deepEqual(calls[0][1], BOX);
assert.ok(calls[0][2].signal instanceof AbortSignal);
assert.equal(loader.get(entry.key).status, 'present');
loader.destroy();
assert.deepEqual(revoked, ['blob:1']);
});
src/layers/streetLevel/index.js
+10
View File
@@ -333,6 +333,16 @@ export function createStreetLevelLayer({
requiresKeyId: requiresKeyIdFor(definitionsFrozen),
/** Registered providers, in chip order. */
providerIds: definitionsFrozen.map((def) => def.id),
getSourceAvailability() {
const available = definitionsFrozen.length > 0;
return {
available,
source: STREET_LEVEL_LAYER_ID,
reason: available
? null
: 'No street-level imagery providers configured',
};
},
init(viewer) {
if (state.initialized)
src/layers/streetLevel/index.test.mjs
+14
View File
@@ -482,3 +482,17 @@ test('switching a provider on while the layer is off activates nothing (M01)', a
assert.equal(provider.calls.activate, 1);
assert.equal(viewer.credits.length, 1);
});
test('an empty provider composition enables and tears down without acquiring imagery', async (t) => {
const { layer, viewer } = await enabledLayer(t, []);
assert.deepEqual(layer.providerIds, []);
assert.deepEqual(layer.getUIState().providers, []);
assert.equal(layer.getUIState().keyRequired, false);
assert.match(
layer.getUIState().coverage.hint,
/No street-level imagery providers/,
);
layer.disable();
layer.enable(viewer);
assert.deepEqual(layer.getUIState().providers, []);
});
src/layers/streetLevel/params.js
+16 -5
View File
@@ -1,13 +1,19 @@
import { normalizeFilter } from './filter.js';
import { encodeIdSwitches, decodeIdSwitches } from '../../data/idSwitches.js';
/**
* Share-link params: one boolean per provider plus the filter. The codec in
* src/data/layerState.js names the same keys, so a new provider needs one there.
* Provider params plus the filter. Custom switches share a stable ID-based
* field; Mapillary retains its existing boolean and share token.
* @param {{providers: Iterable<[string, boolean]>, filter: {pano: string, sinceDays: number}}} input
*/
export function encodeParams({ providers, filter }) {
const params = {};
for (const [id, on] of providers) params[id] = on === true;
const entries = [...providers];
for (const [id, on] of entries) params[id] = on === true;
const switches = encodeIdSwitches(
entries.filter(([id]) => id !== 'mapillary'),
);
if (switches) params.providerSwitches = switches;
params.pano = filter.pano;
params.sinceDays = filter.sinceDays;
return params;
@@ -23,8 +29,13 @@ export function encodeParams({ providers, filter }) {
export function decodeParams(params, { providerIds, filter }) {
const providers = new Map();
const source = params && typeof params === 'object' ? params : {};
for (const id of providerIds)
if (typeof source[id] === 'boolean') providers.set(id, source[id]);
const switches = decodeIdSwitches(source.providerSwitches);
switches.delete('mapillary');
for (const id of providerIds) {
if (switches.has(id)) providers.set(id, switches.get(id));
else if (Object.hasOwn(source, id) && typeof source[id] === 'boolean')
providers.set(id, source[id]);
}
const next = {};
if ('pano' in source) next.pano = source.pano;
if ('sinceDays' in source) next.sinceDays = source.sinceDays;
src/layers/streetLevel/params.test.mjs
+7 -1
View File
@@ -11,7 +11,13 @@ test('encodeParams writes one boolean per provider plus the filter', () => {
],
filter: { pano: 'flat', sinceDays: 365 },
}),
{ mapillary: true, panoramax: false, pano: 'flat', sinceDays: 365 },
{
mapillary: true,
panoramax: false,
providerSwitches: 'panoramax-0',
pano: 'flat',
sinceDays: 365,
},
);
});
src/layers/streetLevel/providerSwitches.test.mjs
+153
View File
@@ -0,0 +1,153 @@
import test from 'node:test';
import assert from 'node:assert/strict';
import { encodeParams, decodeParams } from './params.js';
import {
normalizeIdSwitches,
patchRequestedIdSwitches,
decodeIdSwitches,
encodeIdSwitches,
} from '../../data/idSwitches.js';
import {
createDefaultLayerState,
encodeLayerStateParams,
decodeLayerStateParams,
serializeStoredLayerState,
parseStoredLayerState,
} from '../../data/layerState.js';
import { validateProviders } from './registry.js';
import { fakeStreetLevelProvider } from '../../testSupport/streetLevelFakes.mjs';
const filter = { pano: 'flat', sinceDays: 365 };
test('custom switches survive sharing and storage without depending on provider order', () => {
const providers = [
['panoramax', false],
['example', true],
['mapillary', false],
];
const options = encodeParams({ providers, filter });
assert.equal(options.providerSwitches, 'example-1*panoramax-0');
assert.equal(
encodeParams({ providers: [...providers].reverse(), filter })
.providerSwitches,
options.providerSwitches,
);
const state = createDefaultLayerState();
state.enabledLayerIds = ['street-level'];
state.options['street-level'] = options;
const params = new URLSearchParams({ v: '2' });
encodeLayerStateParams(params, state);
assert.match(params.get('lo'), /0\.m\.0/);
assert.match(params.get('lo'), /0\.r\.example-1\*panoramax-0/);
assert.ok(
params.toString().includes('0.r.example-1*panoramax-0'),
'custom switches need no percent escaping',
);
for (const restored of [
decodeLayerStateParams(params),
parseStoredLayerState(serializeStoredLayerState(state)),
]) {
const decoded = decodeParams(restored.options['street-level'], {
providerIds: ['example', 'mapillary', 'panoramax'],
filter: { pano: 'all', sinceDays: 0 },
});
assert.deepEqual(
[...decoded.providers],
[
['example', true],
['mapillary', false],
['panoramax', false],
],
);
assert.deepEqual(decoded.filter, filter);
assert.deepEqual(
[
...decodeParams(restored.options['street-level'], {
providerIds: ['panoramax'],
filter,
}).providers,
],
[['panoramax', false]],
);
assert.equal(
decodeParams(restored.options['street-level'], {
providerIds: [],
filter,
}).providers.size,
0,
);
}
});
test('legacy links retain Mapillary semantics and leave custom defaults alone', () => {
for (const [lo, on] of [
['', true],
['0.m.0', false],
]) {
const state = decodeLayerStateParams(
new URLSearchParams({ v: '2', l: '0', lo }),
);
const restored = decodeParams(state.options['street-level'], {
providerIds: ['mapillary', 'example'],
filter,
});
assert.deepEqual([...restored.providers], [['mapillary', on]]);
}
});
test('switches reject ambiguous or oversized fields and cannot override the legacy token', () => {
for (const value of [
'example-0*example-1',
'mapillary-0',
'__proto__-1',
'a-2',
'a-1*',
'a.b-1',
'a_b-0',
`${'a'.repeat(255)}-1`,
null,
{},
]) {
assert.equal(normalizeIdSwitches(value, ['mapillary']), null);
}
assert.equal(normalizeIdSwitches('constructor-0'), 'constructor-0');
assert.throws(
() => encodeIdSwitches([['a'.repeat(255), true]]),
/share-link/,
);
assert.throws(
() => validateProviders([fakeStreetLevelProvider({ id: 'a'.repeat(255) })]),
/share-link/,
);
const decoded = decodeParams(
{ providerSwitches: 'mapillary-0', mapillary: true },
{ providerIds: ['mapillary'], filter },
);
assert.equal(decoded.providers.get('mapillary'), true);
});
test('neutral switch codec preserves hyphens and numeric suffixes in IDs', () => {
const switches = [
['provider-0', false],
['provider-1', true],
['a-b-c', true],
];
const encoded = encodeIdSwitches(switches);
assert.equal(encoded, 'a-b-c-1*provider-0-0*provider-1-1');
const decoded = decodeIdSwitches(encoded);
for (const [id, on] of switches) assert.equal(decoded.get(id), on);
assert.equal(decodeIdSwitches('valid-1*broken').size, 0);
});
test('editing a receiving composition drops unknown IDs before enforcing the share bound', () => {
const previous = `${'x'.repeat(254)}-1`;
assert.equal(normalizeIdSwitches(previous), previous);
assert.equal(
patchRequestedIdSwitches(previous, 'alpha-0*beta-0', { alpha: false }),
'alpha-0',
);
assert.equal(
patchRequestedIdSwitches(previous, 'alpha-0', { pano: 'flat' }),
undefined,
);
});
src/layers/streetLevel/registry.js
+17 -2
View File
@@ -1,3 +1,5 @@
import { encodeIdSwitches } from '../../data/idSwitches.js';
/**
* The contract an imagery provider registers with the Street Level layer.
*
@@ -86,8 +88,8 @@ const ID_GRAMMAR = /^[a-z][a-z0-9-]*$/;
* @returns {ReadonlyArray<StreetLevelProvider>}
*/
export function validateProviders(providers) {
if (!Array.isArray(providers) || providers.length === 0)
throw new TypeError('Street Level needs at least one imagery provider');
if (!Array.isArray(providers))
throw new TypeError('Street Level providers must be an array');
const ids = new Set();
const prefixes = [];
for (const provider of providers) {
@@ -125,6 +127,19 @@ export function validateProviders(providers) {
ids.add(provider.id);
prefixes.push(provider.pickPrefix);
}
// Validate the complete bounded share field once, before any instance exists.
try {
encodeIdSwitches(
providers
.filter(({ id }) => id !== 'mapillary')
.map(({ id }) => [id, true]),
);
} catch (error) {
if (!(error instanceof RangeError)) throw error;
throw new RangeError(
'Street Level provider IDs cannot fit in the 256-character share-link field; use shorter IDs or fewer providers',
);
}
return Object.freeze([...providers]);
}
Loaded 100 of 182 files, more files were not shown because too many files have changed in this diff. Show more