Skip to content

Commit 3129d52

Browse files
committed
ci: add required Azure config for pullfrog 0.1.58+
1 parent 59da055 commit 3129d52

1 file changed

Lines changed: 9 additions & 3 deletions

File tree

.github/workflows/pullfrog.yml

Lines changed: 9 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -37,9 +37,15 @@ jobs:
3737
env:
3838
# Review with GPT Sol via our Azure Foundry deployment instead of the
3939
# default Anthropic route. AZURE_API_KEY comes from the Pullfrog
40-
# dashboard; these two are set here so they stay readable in run logs
40+
# dashboard; the rest is set here so it stays readable in run logs
4141
# (dashboard-stored values get registered as GitHub Actions log masks).
42-
# The Azure deployment must be named exactly `gpt-5.6-sol`: the
43-
# @ai-sdk/azure provider uses the model id as the deployment name.
42+
# Since pullfrog 0.1.58 (first-class Azure support), the deployment
43+
# name and the model's token limits are required: a deployment name
44+
# carries no catalog metadata, so pullfrog cannot look them up, and
45+
# without them completions cap at 32000 tokens and auto-compaction
46+
# is disabled. Limits per models.dev azure/gpt-5.6-sol.
4447
AZURE_RESOURCE_NAME: pullfrog-resource
48+
AZURE_DEPLOYMENT: gpt-5.6-sol
49+
AZURE_CONTEXT: '1050000'
50+
AZURE_MAX_OUTPUT: '128000'
4551
PULLFROG_MODEL: azure/gpt-5.6-sol

0 commit comments

Comments
 (0)