Improve Combo modal model sourcing for Chutes/Ollama passthrough providers#323
Open
kwanLeeFrmVi wants to merge 30 commits intodecolua:masterfrom
Open
Improve Combo modal model sourcing for Chutes/Ollama passthrough providers#323kwanLeeFrmVi wants to merge 30 commits intodecolua:masterfrom
kwanLeeFrmVi wants to merge 30 commits intodecolua:masterfrom
Conversation
…t authentication - Add vertex and vertex-partner providers for Gemini and partner models (Claude, Llama, Mistral, GLM-5) - Implement VertexExecutor with google-auth-library for OAuth token minting - Support Service Account JSON credentials with automatic token caching - Add region and modelFamily configuration via providerSpecificData - Include provider logos and model definitions for both Vertex variants
…Gemini 3.1 Pro Preview models.
…dding new 3.x preview models
…o stop retry loop
… Mistral with DeepSeek and Qwen.
kwanLeeFrmVi
force-pushed
the
fix/Combo-model-picker
branch
2 times, most recently
from
8d4f6d5 to
4456fca
Compare
feat: Add Google Cloud Vertex AI provider support
…tner) Co-authored-by: Quan <quanle96@outlook.com> PR: decolua#298 Thanks to @kwanLeeFrmVi for the original implementation. Here is a summary of changes made during review integration: - Replaced google-auth-library with jose (already a project dependency) for SA JSON -> OAuth2 Bearer token minting (RS256 JWT assertion flow) - Moved auth logic (parseSaJson, refreshVertexToken, token cache) from executor into open-sse/services/tokenRefresh.js to match project pattern - Fixed executor to use proxyAwareFetch instead of raw fetch (proxy support) - Simplified buildUrl: use global aiplatform.googleapis.com endpoint for both vertex (Gemini) and vertex-partner; removed region/modelFamily fields - Added auto-detection of GCP project_id from raw API key via probe request (vertex-partner only, cached per key) - Added vertex/vertex-partner cases to /api/providers/validate/route.js - Updated model lists based on live testing: - vertex: gemini-3.1-pro-preview, gemini-3.1-flash-lite-preview, gemini-3-flash-preview, gemini-2.5-flash (removed gemini-2.5-pro: 404) - vertex-partner: deepseek-v3.2, qwen3-next-80b (instruct+thinking), glm-5 (removed Mistral/Llama: not enabled in test project) - gemini provider: added gemini-3.1-pro-preview, gemini-3.1-flash-lite-preview - Removed bun.lock (project uses npm/package-lock.json) - Removed region and modelFamily UI fields (global endpoint, auto-detect) - Kiro token auto-refresh on AccessDeniedException (from commit 2) Made-with: Cursor
…r better error handling
…lua#315) * feat: add modelId fallback for provider validation - If /models endpoint unavailable, validate via /chat/completions - Add optional Model ID input in EditCompatibleNodeModal - Improves compatibility with providers lacking /models endpoint * feat: improve provider validation with modelId fallback - Add Model ID input for chat/completions fallback validation - Reorder UI: API Key → Model ID → Check button + Badge - Display detailed BE error messages in FE - Add status-specific error handling (401/403/400/404/5xx) - Add unit tests for error message helpers - Add vitest devDependency
- Fix alias resolution for providers (chutes, vertex, etc.) by mapping their short IDs in open-sse/config/providerModels.js so modal lookups use the correct “ch/…” prefixes. - Overhaul ModelSelectModal passthrough logic to prioritize connection-specific enabledModels (with cleaned display names), merge user aliases, and fall back to static models so Chutes/Ollama selections mirror the Provider settings UI. - Refresh Chutes’ static fallback list to the latest TEE-focused models for a meaningful default set.
- Add isCustom flag to passthrough provider models in ModelSelectModal - Ensures enabled models from connections are properly identified as custom models - Prevents filtering issues when selecting models from passthrough providers
…viders - Add gemini-3.1-pro-preview to Gemini CLI model list - Add optional projectId parameter to refreshGoogleToken function - Add Project ID input field in Edit Connection modal for Gemini CLI - Store projectId in providerSpecificData for Gemini connections - Pass projectId through token refresh and credential retrieval flows - Fix indentation in refreshCodexToken function
- Add x-request-source: local header to Gemini CLI executor and provider models endpoint - Increase model test timeout from 15s to 30s for better reliability
kwanLeeFrmVi
force-pushed
the
fix/Combo-model-picker
branch
from
5c73cdd to
7c96272
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
PROVIDER_ID_TO_ALIASso API-key providers like Chutes, Vertex, Deepgram, etc. resolve to their short aliases (ch,vx,dg, …). This ensures/api/modelsand the Combo modal use consistentalias/modelidentifiers.passthroughModelsproviders:providerSpecificData.enabledModelsfrom the active connection, matching what the Provider detail page exposes.modelAliases.All merged with deduping and cleaned display names (strip lab prefixes such as
moonshotai/).Testing
bun dev, navigate to Dashboard → Combos.