orcs-oss/orcs-code
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add NVIDIA NIM and MiniMax provider support (#552)

Browse Source 
* feat: add NVIDIA NIM and MiniMax provider support

- Add nvidia-nim and minimax to --provider CLI flag
- Add model discovery for NVIDIA NIM (160+ models) and MiniMax
- Update /model picker to show provider-specific models
- Fix provider detection in startup banner
- Update .env.example with new provider options

Supported providers:
- NVIDIA NIM: https://integrate.api.nvidia.com/v1
- MiniMax: https://api.minimax.io/v1

* fix: resolve conflict in StartupScreen (keep NVIDIA/MiniMax + add Codex detection)

* fix: resolve providerProfile conflict (add imports from main, keep NVIDIA/MiniMax)

* fix: revert providerSecrets to match main (NVIDIA/MiniMax handled elsewhere)

* fix: add context window entries for NVIDIA NIM and new MiniMax models

* fix: use GLM-5 as NVIDIA NIM default and MiniMax-M2.5 for consistency

* fix: address remaining review items - add GLM/Kimi context entries, max output tokens, fix .env.example, revert to Nemotron default

* fix: filter NVIDIA NIM picker to chat/instruct models only, set provider-specific API keys from saved profiles

* chore: add more NVIDIA NIM context window entries for popular models

* fix: address remaining non-blocking items - fix base model, clear provider API keys on profile switch
This commit is contained in:
ArkhAngelLifeJiggy
2026-04-15 13:26:13 +01:00
committed by GitHub
parent 6b2121da12
commit 51191d6132
15 changed files with 628 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
src/utils/model/configs.ts
View File

@@ -37,6 +37,8 @@ export const CLAUDE_3_7_SONNET_CONFIG = {
gemini: 'gemini-2.0-flash',
github: 'github:copilot',
codex: 'gpt-5.4',
'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
minimax: 'MiniMax-M2.5',
} as const satisfies ModelConfig
export const CLAUDE_3_5_V2_SONNET_CONFIG = {
@@ -48,6 +50,8 @@ export const CLAUDE_3_5_V2_SONNET_CONFIG = {
gemini: 'gemini-2.0-flash',
github: 'github:copilot',
codex: 'gpt-5.4',
'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
minimax: 'MiniMax-M2.5',
} as const satisfies ModelConfig
export const CLAUDE_3_5_HAIKU_CONFIG = {
@@ -59,6 +63,8 @@ export const CLAUDE_3_5_HAIKU_CONFIG = {
gemini: 'gemini-2.0-flash-lite',
github: 'github:copilot',
codex: 'gpt-5.4',
'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
minimax: 'MiniMax-M2.5',
} as const satisfies ModelConfig
export const CLAUDE_HAIKU_4_5_CONFIG = {
@@ -70,6 +76,8 @@ export const CLAUDE_HAIKU_4_5_CONFIG = {
gemini: 'gemini-2.0-flash-lite',
github: 'github:copilot',
codex: 'gpt-5.4',
'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
minimax: 'MiniMax-M2.5',
} as const satisfies ModelConfig
export const CLAUDE_SONNET_4_CONFIG = {
@@ -81,6 +89,8 @@ export const CLAUDE_SONNET_4_CONFIG = {
gemini: 'gemini-2.0-flash',
github: 'github:copilot',
codex: 'gpt-5.4',
'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
minimax: 'MiniMax-M2.5',
} as const satisfies ModelConfig
export const CLAUDE_SONNET_4_5_CONFIG = {
@@ -92,6 +102,8 @@ export const CLAUDE_SONNET_4_5_CONFIG = {
gemini: 'gemini-2.0-flash',
github: 'github:copilot',
codex: 'gpt-5.4',
'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
minimax: 'MiniMax-M2.5',
} as const satisfies ModelConfig
export const CLAUDE_OPUS_4_CONFIG = {
@@ -103,6 +115,8 @@ export const CLAUDE_OPUS_4_CONFIG = {
gemini: 'gemini-2.5-pro-preview-03-25',
github: 'github:copilot',
codex: 'gpt-5.4',
'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
minimax: 'MiniMax-M2.5',
} as const satisfies ModelConfig
export const CLAUDE_OPUS_4_1_CONFIG = {
@@ -114,6 +128,8 @@ export const CLAUDE_OPUS_4_1_CONFIG = {
gemini: 'gemini-2.5-pro-preview-03-25',
github: 'github:copilot',
codex: 'gpt-5.4',
'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
minimax: 'MiniMax-M2.5',
} as const satisfies ModelConfig
export const CLAUDE_OPUS_4_5_CONFIG = {
@@ -125,6 +141,8 @@ export const CLAUDE_OPUS_4_5_CONFIG = {
gemini: 'gemini-2.5-pro-preview-03-25',
github: 'github:copilot',
codex: 'gpt-5.4',
'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
minimax: 'MiniMax-M2.5',
} as const satisfies ModelConfig
export const CLAUDE_OPUS_4_6_CONFIG = {
@@ -136,6 +154,8 @@ export const CLAUDE_OPUS_4_6_CONFIG = {
gemini: 'gemini-2.5-pro-preview-03-25',
github: 'github:copilot',
codex: 'gpt-5.4',
'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
minimax: 'MiniMax-M2.5',
} as const satisfies ModelConfig
export const CLAUDE_SONNET_4_6_CONFIG = {
@@ -147,6 +167,8 @@ export const CLAUDE_SONNET_4_6_CONFIG = {
gemini: 'gemini-2.0-flash',
github: 'github:copilot',
codex: 'gpt-5.4',
'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
minimax: 'MiniMax-M2.5',
} as const satisfies ModelConfig
// @[MODEL LAUNCH]: Register the new config here.
@@ -181,4 +203,4 @@ export const CANONICAL_ID_TO_KEY: Record<CanonicalModelId, ModelKey> =
(Object.entries(ALL_MODEL_CONFIGS) as [ModelKey, ModelConfig][]).map(
([key, cfg]) => [cfg.firstParty, key],
),
) as Record<CanonicalModelId, ModelKey>
) as Record<CanonicalModelId, ModelKey>