[FirebaseAILogic] Request official support timeline for Gemini 3.8 Live via Agent Platform
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 20/100
- Issue type
- Feature
- Clarity
- Needs clarification
- Activity status
- Active
- Tech stack
- firebase, ios, swift
- Domain
- backend-api-design
Research direction
Start with the linked Firebase Live API documentation and the referenced voice activity support pull request (#16889), then check the model lifecycle reference for the stated retirement date. The issue asks for official support status, timeline, and iOS SDK limitations; it does not identify a code change or tests that would define completion.
Written by the indexing model from the issue text.
Description
Description
The Firebase AI Logic documentation currently states that Gemini Live 3.x models are not supported when using the Agent Platform Gemini API.
However, Firebase Apple SDK has already introduced support for Gemini 3.x-specific Live API messages, including voice activity events (#16889).
I have also successfully connected to gemini-3.8-live using the Firebase Apple SDK.
Questions
- Is Gemini 3.8 Live support through Firebase AI Logic still under development, or is the documentation outdated?
- Is there an estimated timeline for official support?
- Are there any known limitations or compatibility issues when using this model with the current iOS SDK?
Why this matters
I maintain an iOS language-learning application that uses Gemini Live API for real-time voice conversations.
The existing gemini-live-2.5-flash-native-audio model is scheduled for retirement on December 13, 2026, according to Google Cloud's model lifecycle documentation.
We need a supported migration path before this deadline to avoid service disruption.
Any clarification or roadmap information would be greatly appreciated.
References
- Firebase Live API documentation: https://firebase.google.com/docs/ai-logic/live-api
- Voice activity support PR: https://github.com/firebase/firebase-ios-sdk/pull/16889
- Model lifecycle: https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions
API Proposal
No response
Firebase Product(s)
AI Logic
- Dominant language
- C++
- Stars
- 7k
- Forks
- 1.8k
- Avg merge
- 1d 1h
- Merged PRs (30d)
- 70
Getting set up
- No Dockerfile or Docker Compose file
- Has a pull request template
- Read the contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from firebase/firebase-ios-sdk
-
api: analytics
Difficulty 4/5 3-5 days Newbie friendliness 35/100
firebase/firebase-ios-sdk#17075 ·
Maintainers usually reply within 1 day
-
api: firestore
Difficulty 4/5 3-5 days Newbie friendliness 43/100
firebase/firebase-ios-sdk#17073 ·
Maintainers usually reply within 1 day
-
RTDB: `.info` listen `onComplete` runs off the repo queue, so `infoSyncTree` is mutated from two threads (crash in `FSyncTree applyOperationHelper`)Possibly taken @paulb777 claimed this 3 days ago. Open
firebase/firebase-ios-sdk#17069 · 1 comment · 1 assignee ·
Maintainers usually reply within 1 day
-
Firestore watch stream keeps an expired App Check token until the next Auth refresh (no-op App Check change listener in FirestoreClient)Possibly taken @dconeybe claimed this 5 days ago. Openapi: firestore
firebase/firebase-ios-sdk#17056 · 1 comment · 1 assignee ·
Maintainers usually reply within 1 day
-
api: crashlytics
Difficulty 4/5 3-5 days Newbie friendliness 35/100
firebase/firebase-ios-sdk#17046 ·
Maintainers usually reply within 1 day
All issues in firebase/firebase-ios-sdk
Similar issues
-
feat
Difficulty 2/5 1-3 hours Newbie friendliness 65/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
-
Issue-Docs Needs-Triage
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
microsoft/winget-cli#6692 ·
Maintainers usually reply within 2 days
-
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
stratum-mining/sv2-tp#167 ·
Maintainers usually reply within 1 day
-
better error message bug low priority semantics strings
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
Maintainers usually reply within 1 day