Ettore Di Giacinto 8dab1e74ba test(e2e): give the cloud-proxy models a window that fits the chat tools ...

A chat reports the window of its model. The cloud-proxy test models set
no context_size, so they got the 4096 default and the prompt did not fit.
Three saved-agent specs saw no request reach the upstream.

Assisted-by: Claude:claude-sonnet-5-5 go

2026-11-04 06:59:46 +00:00

..

addons

feat(addons): ask the Authority on every host operation call

2026-11-03 21:33:36 +00:00

e2e

test(e2e): give the cloud-proxy models a window that fits the chat tools

2026-11-04 06:59:46 +00:00

e2e-aio

Revert "chore(tests): Avoid network, sleep and more during tests" (#11601)

2026-08-19 16:39:39 +02:00

e2e-backends

feat(realtime): LFM3-Audio speech-to-speech on llama.cpp, remove liquid-audio (#12958)

2026-10-29 22:06:41 +01:00

e2e-chats

feat(chats): server-side chats with steering, sub-agents and compaction (#12918)

2026-11-01 12:08:23 +01:00

e2e-platform

feat(chats): server-side chats with steering, sub-agents and compaction (#12918)

2026-11-01 12:08:23 +01:00

e2e-ui

test(e2e-ui): give the mock model a window that fits the chat tools

2026-11-04 02:24:07 +00:00

fixtures

feat(face-recognition): add insightface/onnx backend for 1:1 verify, 1:N identify, embedding, detection, analysis (#9480)

2026-04-22 21:55:41 +02:00

integration

feat(stores): Adds Qdrant vector store backend

2026-10-13 08:13:55 +00:00

studiobot

test(studiobot): guard the add-ons of the transport against a data race

2026-11-03 19:03:12 +00:00

test_fish_drama3_gallery.py

feat(gallery): add experimental Fish Drama 3 (#12789)

2026-10-20 15:33:15 +02:00

test_invariant_backend.py

fix: the trl backend's _do_training method directly ... in backend.py (#10422)

2026-06-21 17:40:29 +02:00