Skip to content

chore(gitops): upgrade models to gemini-3.6-flash #35

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
dembrane-sam-bot wants to merge 1 commit into
base: main
Choose a base branch
from
Open

chore(gitops): upgrade models to gemini-3.6-flash #35

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 8 additions & 8 deletions helm/echo/values-echo-next.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
# for echo-next without touching prod/testing (which do not reference this file).
#
# Swaps all three LLM groups (multimodal pro, multimodal fast, text fast) to
# Gemini 3.5 Flash on Vertex, EU-resident.
# Gemini 3.6 Flash on Vertex, EU-resident.
#
# Gemini 3.x is only served on the GLOBAL Vertex hostname
# (aiplatform.googleapis.com), not the regional eu-aiplatform.googleapis.com
Expand All @@ -15,28 +15,28 @@
#
# The api_base hardcodes project + model because litellm appends ":generateContent"
# to it verbatim. This file is echo-next-only, so the dembrane-echo project is correct.
# The _2/_3 regional failovers stay disabled (3.5 Flash is global-host only).
# The _2/_3 regional failovers stay disabled (3.6 Flash is global-host only).
common:
env:
LLM__MULTI_MODAL_PRO__MODEL: "vertex_ai/gemini-3.5-flash"
LLM__MULTI_MODAL_PRO__MODEL: "vertex_ai/gemini-3.6-flash"
LLM__MULTI_MODAL_PRO__VERTEX_LOCATION: "eu"
LLM__MULTI_MODAL_PRO__API_BASE: "https://aiplatform.googleapis.com/v1/projects/dembrane-echo/locations/eu/publishers/google/models/gemini-3.5-flash"
LLM__MULTI_MODAL_PRO__API_BASE: "https://aiplatform.googleapis.com/v1/projects/dembrane-echo/locations/eu/publishers/google/models/gemini-3.6-flash"
LLM__MULTI_MODAL_PRO_2__MODEL: ""
LLM__MULTI_MODAL_PRO_2__VERTEX_LOCATION: ""
LLM__MULTI_MODAL_PRO_3__MODEL: ""
LLM__MULTI_MODAL_PRO_3__VERTEX_LOCATION: ""

LLM__MULTI_MODAL_FAST__MODEL: "vertex_ai/gemini-3.5-flash"
LLM__MULTI_MODAL_FAST__MODEL: "vertex_ai/gemini-3.6-flash"
LLM__MULTI_MODAL_FAST__VERTEX_LOCATION: "eu"
LLM__MULTI_MODAL_FAST__API_BASE: "https://aiplatform.googleapis.com/v1/projects/dembrane-echo/locations/eu/publishers/google/models/gemini-3.5-flash"
LLM__MULTI_MODAL_FAST__API_BASE: "https://aiplatform.googleapis.com/v1/projects/dembrane-echo/locations/eu/publishers/google/models/gemini-3.6-flash"
LLM__MULTI_MODAL_FAST_2__MODEL: ""
LLM__MULTI_MODAL_FAST_2__VERTEX_LOCATION: ""
LLM__MULTI_MODAL_FAST_3__MODEL: ""
LLM__MULTI_MODAL_FAST_3__VERTEX_LOCATION: ""

LLM__TEXT_FAST__MODEL: "vertex_ai/gemini-3.5-flash"
LLM__TEXT_FAST__MODEL: "vertex_ai/gemini-3.6-flash"
LLM__TEXT_FAST__VERTEX_LOCATION: "eu"
LLM__TEXT_FAST__API_BASE: "https://aiplatform.googleapis.com/v1/projects/dembrane-echo/locations/eu/publishers/google/models/gemini-3.5-flash"
LLM__TEXT_FAST__API_BASE: "https://aiplatform.googleapis.com/v1/projects/dembrane-echo/locations/eu/publishers/google/models/gemini-3.6-flash"
LLM__TEXT_FAST_2__MODEL: ""
LLM__TEXT_FAST_2__VERTEX_LOCATION: ""
LLM__TEXT_FAST_3__MODEL: ""
Expand Down
12 changes: 6 additions & 6 deletions helm/echo/values-extended-env.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,17 +13,17 @@
# 2026-06-08 (model swap + AssemblyAI webhook round-trip).
common:
env:
LLM__MULTI_MODAL_PRO__MODEL: "vertex_ai/gemini-3.5-flash"
LLM__MULTI_MODAL_PRO__MODEL: "vertex_ai/gemini-3.6-flash"
LLM__MULTI_MODAL_PRO__VERTEX_LOCATION: "eu"
LLM__MULTI_MODAL_PRO__API_BASE: "https://aiplatform.googleapis.com/v1/projects/dembrane-echo/locations/eu/publishers/google/models/gemini-3.5-flash"
LLM__MULTI_MODAL_PRO__API_BASE: "https://aiplatform.googleapis.com/v1/projects/dembrane-echo/locations/eu/publishers/google/models/gemini-3.6-flash"

LLM__MULTI_MODAL_FAST__MODEL: "vertex_ai/gemini-3.5-flash"
LLM__MULTI_MODAL_FAST__MODEL: "vertex_ai/gemini-3.6-flash"
LLM__MULTI_MODAL_FAST__VERTEX_LOCATION: "eu"
LLM__MULTI_MODAL_FAST__API_BASE: "https://aiplatform.googleapis.com/v1/projects/dembrane-echo/locations/eu/publishers/google/models/gemini-3.5-flash"
LLM__MULTI_MODAL_FAST__API_BASE: "https://aiplatform.googleapis.com/v1/projects/dembrane-echo/locations/eu/publishers/google/models/gemini-3.6-flash"

LLM__TEXT_FAST__MODEL: "vertex_ai/gemini-3.5-flash"
LLM__TEXT_FAST__MODEL: "vertex_ai/gemini-3.6-flash"
LLM__TEXT_FAST__VERTEX_LOCATION: "eu"
LLM__TEXT_FAST__API_BASE: "https://aiplatform.googleapis.com/v1/projects/dembrane-echo/locations/eu/publishers/google/models/gemini-3.5-flash"
LLM__TEXT_FAST__API_BASE: "https://aiplatform.googleapis.com/v1/projects/dembrane-echo/locations/eu/publishers/google/models/gemini-3.6-flash"

EMBEDDING_MODEL: "vertex_ai/text-embedding-004"
EMBEDDING_BASE_URL: "https://europe-west4-aiplatform.googleapis.com"
2 changes: 1 addition & 1 deletion helm/echo/values.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,7 +91,7 @@ agent:
memory: "1Gi"
env:
ECHO_API_URL: "http://echo-api:8000/api"
LLM_MODEL: "gemini-3.5-flash"
LLM_MODEL: "gemini-3.6-flash"
VERTEX_LOCATION: "eu"
# Gemini 3.x is global-host only; locations/eu stays in the request path.
VERTEX_API_ENDPOINT: "aiplatform.googleapis.com"
Expand Down