Jeffrey Quesnelle 5b82658b3c Merge pull request #90129 from rroverin/fix/nvidia-nim-tool-message-name-field ...

fix(providers): strip name/tool_name from NVIDIA NIM tool messages

2026-08-25 16:39:36 -04:00

..

__init__.py

feat: provider modules — ProviderProfile ABC, 33 providers, fetch_models, transport single-path

2026-05-05 13:40:01 -07:00

test_e2e_wiring.py

fix nvidia tool message schema

2026-08-19 18:10:53 +02:00

test_entry_point_discovery.py

fix: gate entry-point provider scan on plugins.enabled and skip register(ctx) targets

2026-08-13 11:11:53 -07:00

test_fetch_models_base_url.py

fix(providers): honor a custom base_url over models_url in fetch_models

2026-08-18 14:27:36 -07:00

test_meta_ai_profile.py

feat(providers): flip bundled meta-ai profile to the Responses wire

2026-08-17 12:58:51 -07:00

test_plugin_discovery.py

perf(providers): cache provider list snapshots

2026-08-03 17:16:34 +05:30

test_profile_wiring.py

test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s

2026-07-29 13:39:40 -07:00

test_provider_profiles.py

fix nvidia tool message schema

2026-08-19 18:10:53 +02:00

test_provider_registry.py

test: pin the hit-path copy guard on the provider snapshot cache

2026-08-03 17:16:34 +05:30

test_transport_parity.py

fix(nous): stop dropping "thinking off" on Portal models that can honor it

2026-08-19 22:14:56 -05:00