phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 09:53:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat!: standardize base_url for inference

Browse source 
Completes #3732 by removing runtime URL transformations and requiring
users to provide full URLs in configuration. All providers now use
'base_url' consistently and respect the exact URL provided without
appending paths like /v1 or /openai/v1 at runtime.

Add unit test to enforce URL standardization across remote inference providers (verifies all use 'base_url' field with HttpUrl | None type)

BREAKING CHANGE: Users must update configs to include full URL paths
(e.g., http://localhost:11434/v1 instead of http://localhost:11434).

Signed-off-by: Charlie Doern <cdoern@redhat.com>
This commit is contained in:
Charlie Doern 2025-10-22 17:16:21 -04:00
parent 7093978754
commit 7a9c32f737
67 changed files with 282 additions and 227 deletions
Download patch file Download diff file Expand all files Collapse all files

6
tests/integration/suites.py
View file

@ -50,7 +50,7 @@ SETUP_DEFINITIONS: dict[str, Setup] = {
name="ollama",
description="Local Ollama provider with text + safety models",
env={
"OLLAMA_URL": "http://0.0.0.0:11434",
"OLLAMA_URL": "http://0.0.0.0:11434/v1",
"SAFETY_MODEL": "ollama/llama-guard3:1b",
},
defaults={
@ -64,7 +64,7 @@ SETUP_DEFINITIONS: dict[str, Setup] = {
name="ollama",
description="Local Ollama provider with a vision model",
env={
"OLLAMA_URL": "http://0.0.0.0:11434",
"OLLAMA_URL": "http://0.0.0.0:11434/v1",
},
defaults={
"vision_model": "ollama/llama3.2-vision:11b",
@ -75,7 +75,7 @@ SETUP_DEFINITIONS: dict[str, Setup] = {
name="ollama-postgres",
description="Server-mode tests with Postgres-backed persistence",
env={
"OLLAMA_URL": "http://0.0.0.0:11434",
"OLLAMA_URL": "http://0.0.0.0:11434/v1",
"SAFETY_MODEL": "ollama/llama-guard3:1b",
"POSTGRES_HOST": "127.0.0.1",
"POSTGRES_PORT": "5432",