You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 0ddad16
Browse filesBrowse the repository at this point in the historyBrowse files
test(live): answer the Current Debate prompt and pin Muse Spark 1.3 Contributor
The live journeys were never updated for Current Debate (#72): Actions was
out of minutes from 2026-09-27 to 2026-09-30, so the first real live-e2e run
was on 2026-10-01. Five journeys stopped at "Which debate is this for?" or,
in the Library, at a disabled Add Source button with no current debate. They
now answer the prompt the way the full-stack specs do, and the Library
journey starts a debate first.
The live gate's default model is now meta/muse-spark-1.3-contributor
($0.10/$0.20 per million tokens, against $0.15/$0.50 for GLM 5.3 Flash). It
supports every parameter the app sends. It is test-only and stays out of the
app catalog.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Live mode uses the same locked stack but skips pgTAP and the fake-provider specs. It runs `e2e/live/` on desktop Chromium against real OpenRouter, Jev, and Exa. Imported web pages are fetched live too. The fake provider becomes a recording proxy. It forwards every chat call to OpenRouter with the model pinned to `LIVE_MODEL` (default `z-ai/glm-5.3-flash`; CI reads the `LIVE_MODEL` repository variable), passes Jev decisions through unchanged, and refuses calls past `MAX_UPSTREAM_CALLS` (200). The default is inexpensive and broadly hosted, so requests can use OpenRouter's balanced provider routing instead of depending on one endpoint.
196
+
Live mode uses the same locked stack but skips pgTAP and the fake-provider specs. It runs `e2e/live/` on desktop Chromium against real OpenRouter, Jev, and Exa. Imported web pages are fetched live too. The fake provider becomes a recording proxy. It forwards every chat call to OpenRouter with the model pinned to `LIVE_MODEL` (default `meta/muse-spark-1.3-contributor`; CI reads the `LIVE_MODEL` repository variable, which is unset), passes Jev decisions through unchanged, and refuses calls past `MAX_UPSTREAM_CALLS` (200). The default is the cheapest model that supports every request parameter the app sends, including `response_format`and reasoning effort. It is test-only and not in the app catalog, so users cannot pick it. Meta is its only provider, so an outage there fails the gate instead of failing over.
197
197
198
198
The specs cover web-researched case generation, verified Factoids citations, Ask with web search, URL import, streamed Ask, Attack, Brainstorm, a judged sparring round, and Crossfire with live Jev signals. Outputs vary, so tests assert structure rather than text:
0 commit comments