feat(models): host google gemini models#2122
Merged
waleedlatif1 merged 2 commits intostagingfrom Nov 26, 2025
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub. |
Contributor
Greptile OverviewGreptile SummaryThis PR extends the hosted model infrastructure to support Google Gemini models, following the same pattern established for OpenAI and Anthropic. Key Changes:
Implementation Quality: Confidence Score: 5/5
Important Files ChangedFile Analysis
Sequence DiagramsequenceDiagram
participant Client as Workflow Execution
participant Utils as providers/utils.ts
participant KeyRotation as lib/utils.ts
participant Env as lib/env.ts
participant Google as Google Gemini API
Client->>Utils: getApiKey('google', model, userKey)
Utils->>Utils: Check if hosted platform
alt isHosted && isGeminiModel
Utils->>KeyRotation: getRotatingApiKey('gemini')
KeyRotation->>Env: Check GEMINI_API_KEY_1
KeyRotation->>Env: Check GEMINI_API_KEY_2
KeyRotation->>Env: Check GEMINI_API_KEY_3
KeyRotation->>KeyRotation: Calculate keyIndex = currentMinute % keys.length
KeyRotation-->>Utils: Return rotated API key
Utils-->>Client: Return server API key
Client->>Google: Make request with rotated key
else User provided key
Utils-->>Client: Return user's API key
Client->>Google: Make request with user's key
end
|
This was referenced Nov 26, 2025
waleedlatif1
added a commit
that referenced
this pull request
Nov 29, 2025
…pylon, intercom, mailchimp, loading optimizations (#2132) * fix(memory-util): fixed unbounded array of gmail/outlook pollers causing high memory util, added missing db indexes/removed unused ones, auto-disable schedules/webhooks after 10 consecutive failures (#2115) * fix(memory-util): fixed unbounded array of gmail/outlook pollers causing high memory util, added missing db indexes/removed unused ones, auto-disable schedules/webhooks after 10 consecutive failures * ack PR comments * ack * improvement(teams-plan): seats increase simplification + not triggering checkout session (#2117) * improvement(teams-plan): seats increase simplification + not triggering checkout session * cleanup via helper * feat(tools): added sentry, incidentio, and posthog tools (#2116) * feat(tools): added sentry, incidentio, and posthog tools * update docs * fixed docs to use native fumadocs for llms.txt and copy markdown, fixed tool issues * cleanup * enhance error extractor, fixed posthog tools * docs enhancements, cleanup * added more incident io ops, remove zustand/shallow in favor of zustand/react/shallow * fix type errors * remove unnecessary comments * added vllm to docs * feat(i18n): update translations (#2120) * feat(i18n): update translations * fix build --------- Co-authored-by: waleedlatif1 <waleedlatif1@users.noreply.github.com> * improvement(workflow-execution): perf improvements to passing workflow state + decrypted env vars (#2119) * improvement(execution): load workflow state once instead of 2-3 times * decrypt only in get helper * remove comments * remove comments * feat(models): host google gemini models (#2122) * feat(models): host google gemini models * remove unused primary key * feat(i18n): update translations (#2123) Co-authored-by: waleedlatif1 <waleedlatif1@users.noreply.github.com> * feat(tools): added zendesk, pylon, intercom, & mailchimp (#2126) * feat(tools): added zendesk, pylon, intercom, & mailchimp * finish zendesk and pylon * updated docs * feat(i18n): update translations (#2129) * feat(i18n): update translations * fixed build --------- Co-authored-by: waleedlatif1 <waleedlatif1@users.noreply.github.com> * fix(permissions): add client-side permissions validation to prevent unauthorized actions, upgraded custom tool modal (#2130) * fix(permissions): add client-side permissions validation to prevent unauthorized actions, upgraded custom tool modal * fix failing test * fix test * cleanup * fix(custom-tools): add composite index on custom tool names & workspace id (#2131) --------- Co-authored-by: Vikhyath Mondreti <vikhyathvikku@gmail.com> Co-authored-by: waleedlatif1 <waleedlatif1@users.noreply.github.com>
DarkShark-RAz
pushed a commit
to DarkShark-RAz/sim
that referenced
this pull request
Nov 30, 2025
* feat(models): host google gemini models * remove unused primary key
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
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
host google gemini models, we already hosted anthropic and openai but now we host gemini too
Type of Change
Testing
Tested manually
Checklist