Commit Graph

11 Commits

Author SHA1 Message Date
Peter Steinberger
d4eb40248a fix: normalize gemini 3 pro preview config 2026-05-08 06:08:58 +01:00
rolandrscheel
aeac10f5ce fix(plugins): reuse workspace metadata for session model refs (#76655)
Fixes the session-list plugin metadata hot path by reusing the active workspace-scoped plugin metadata snapshot for manifest model-id normalization and setup CLI backend fallback. Also keeps model-pricing collection on its provided manifest registry and fixes the CI-only hoisted test mock failure.

Validated with targeted plugin/gateway/model-selection tests, CI-shaped gateway startup shard, Testbox `pnpm check:changed`, and green PR CI.

Thanks @rolandrscheel.
2026-05-03 15:58:14 +01:00
Peter Steinberger
8ce44b057f refactor: narrow internal agent exports 2026-05-01 08:46:50 +01:00
Agustin Rivera
9a0b43c47e feat(nvidia): add NVIDIA provider with onboarding flow (#71204)
* feat(nvidia): add NVIDIA provider with onboarding flow

Add the NVIDIA build.nvidia.com API as a bundled provider. Default model
is nvidia/nvidia/nemotron-3-super-120b-a12b: first segment is the provider
id, remaining "nvidia/nemotron-3-super-120b-a12b" is the literal upstream
model id (which happens to start with "nvidia/" because NVIDIA is also the
model maker).

Supporting core change: introduce a provider capability flag
nativeIdsIncludeProviderPrefix so providers whose native catalog ids
intentionally include their provider prefix (OpenRouter) opt into self-prefix
dedupe in modelKey, without hardcoding provider names in core. Providers
whose ids merely happen to start with their own name (NVIDIA) leave the flag
unset and get the full <provider>/<model-id> concatenation.

- extensions/nvidia/*: new plugin, catalog, onboarding, tests, docs
- extensions/openrouter/index.ts: declare nativeIdsIncludeProviderPrefix
- src/plugins/types.ts: add field to ProviderPlugin
- src/plugins/registry.ts: populate self-prefix set on registration
- src/agents/provider-self-prefix.ts: sync accessor used by modelKey
- src/agents/model-ref-shared.ts: modelKey consults the flag
- test updates for affected surfaces

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* refactor(model-picker): simplify literal-prefix display to label-only

* fix(model-picker): pass workspaceDir/env to allowlist literal-prefix resolution

* chore: untrack generated baseline JSON artifacts (gitignored)

* fix(nvidia): show literal model ref in picker and onboarding notes

* fix(nvidia): show hint whenever display label differs from stored config

* fix(nvidia): drop redundant hint from Keep current label

* fix(nvidia): restore literal double-prefix display labels

* fix(picker): handle literal-prefix fast path

* fix(picker): show literal keep label

* fix(docs): update nvidia provider docs

* fix(nvidia): update test helper imports

* fix(changelog): add nvidia provider entry

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-29 09:25:12 -07:00
Peter Steinberger
04e96c11ea fix(gateway): skip plugin pricing scans when disabled 2026-04-28 08:23:53 +01:00
Peter Steinberger
b74f35ee6f refactor(plugins): move provider routing metadata to manifests 2026-04-27 10:06:30 +01:00
sudhindrat
f92a8ae9f3 fix(model-ref): re-add nvidia/ prefix in normalizeStaticProviderModelId (#71552) (#71660)
* fix(model-ref): re-add nvidia/ prefix in normalizeStaticProviderModelId (#71552)

* fix(test): use nvidia-prefixed model fixture for double-prefix guard

---------

Co-authored-by: Sudhindra Tatti <sudhi@sudhindras-mini.lan>
2026-04-25 17:07:39 -04:00
Peter Steinberger
c3074bd513 refactor: dedupe path lowercase helpers 2026-04-07 15:53:50 +01:00
Peter Steinberger
3107faf571 Plugin SDK: split model id normalizers from heavy shared surface 2026-04-07 12:19:57 +08:00
Peter Steinberger
5ac07b8ef0 fix: normalize huggingface refs and discovery timeout 2026-04-05 09:18:17 +01:00
Peter Steinberger
41243529fb refactor(providers): centralize provider model policy 2026-04-04 06:16:48 +01:00