Skip to content

LCORE-1285: update llama stack to 0.5.0 #1112

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
jrobertboos wants to merge 6 commits into
base: main
Choose a base branch
from
Open

LCORE-1285: update llama stack to 0.5.0 #1112

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
2e001ab
Update dependencies to llama-stack version 0.5.0 and add llama-stack-…
jrobertboos Feb 6, 2026
5d62e33
Merge branch 'main' into lcore-1285
jrobertboos Feb 9, 2026
11e8a4a
Updated `test.containerfile` to rhoai-3.4
jrobertboos Feb 17, 2026
5ff72cd
Merge branch 'main' into lcore-1285
jrobertboos Mar 2, 2026
de20d7a
Update base image in test.containerfile to use upstream Red Hat UBI
jrobertboos Mar 3, 2026
60efb35
fixed type error
jrobertboos Mar 3, 2026
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
6 changes: 3 additions & 3 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,9 +28,9 @@ dependencies = [
# Used by authentication/k8s integration
"kubernetes>=30.1.0",
# Used to call Llama Stack APIs
"llama-stack==0.4.3",
"llama-stack-client==0.4.3",
"llama-stack-api==0.4.4",
"llama-stack==0.5.0",
"llama-stack-client==0.5.0",
"llama-stack-api==0.5.0",
# Used by Logger
"rich>=14.0.0",
# Used by JWK token auth handler
Expand Down
2 changes: 1 addition & 1 deletion src/constants.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

# Minimal and maximal supported Llama Stack version
MINIMAL_SUPPORTED_LLAMA_STACK_VERSION = "0.2.17"
MAXIMAL_SUPPORTED_LLAMA_STACK_VERSION = "0.4.3"
MAXIMAL_SUPPORTED_LLAMA_STACK_VERSION = "0.5.0"
Copy link
Contributor

@asimurka asimurka Mar 4, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

0.5.1 is already out


UNABLE_TO_PROCESS_RESPONSE = "Unable to process this request"

Expand Down
3 changes: 3 additions & 0 deletions src/utils/responses.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1079,6 +1079,9 @@ def _extract_text_from_content(

text_fragments: list[str] = []
for part in content:
if isinstance(part, str):
Copy link
Contributor

@asimurka asimurka Mar 4, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is not necessary. Function extracts text parts from OpenResponses input/output which is either plain string or sequence of response items i.e., never sequence of plain strings.

text_fragments.append(part.strip())
continue
Comment on lines +1082 to +1084
Copy link
Contributor

@coderabbitai coderabbitai bot Mar 3, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor

Avoid appending empty fragments from whitespace-only string parts.

Line 1083 appends part.strip() unconditionally. If part is whitespace-only, this adds "" and can create spacing artifacts in the final joined text.

Suggested fix 
-        if isinstance(part, str):
-            text_fragments.append(part.strip())
+        if isinstance(part, str):
+            stripped_part = part.strip()
+            if stripped_part:
+                text_fragments.append(stripped_part)
             continue
🤖 Prompt for AI Agents 
Verify each finding against the current code and only fix it if needed.

In `@src/utils/responses.py` around lines 1082 - 1084, The code currently appends
part.strip() to text_fragments unconditionally inside the branch that checks
isinstance(part, str); change this to only append when the stripped string is
non-empty to avoid inserting empty fragments from whitespace-only parts—update
the branch handling the variables part and text_fragments (where the if
isinstance(part, str): ... continue logic appears) so that you compute stripped
= part.strip() and append stripped only if stripped is truthy.

if part.type == "input_text":
input_text_part = cast(InputTextPart, part)
if input_text_part.text:
Expand Down
2 changes: 1 addition & 1 deletion tests/e2e/features/info.feature
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ Feature: Info tests
When I access REST API endpoint "info" using HTTP GET method
Then The status code of the response is 200
And The body of the response has proper name Lightspeed Core Service (LCS) and version 0.4.1
And The body of the response has llama-stack version 0.4.3
And The body of the response has llama-stack version 0.5.0

@skip-in-library-mode
Scenario: Check if info endpoint reports error when llama-stack connection is not working
Expand Down
98 changes: 86 additions & 12 deletions uv.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Loading