adjust github mcp tools calls for payload size, timeout#20
Merged
gabemontero merged 1 commit intoredhat-ai-dev:mainfrom Jan 28, 2026
Merged
Conversation
gabemontero
force-pushed
the
fix-after-github-error
branch
2 times, most recently
from
de7b21c to
137e0b5
Compare
discovered during testing of the performance agent that the github add comment tool call was failing for the k8s top outpu. investigation confirmed that the output exceeded the max length for a github comment, so adding some truncating logic to adhere to the size limit also broke out failure processing for creating and issue from failure processing for adding comments; we should at least note the github issue creation, with an indicator if any of the comment failed finally, added a timeout to the comment tool calls, as failure/retry at the openai/LLS level lead to huge delays from the UI perspective (one instance or 1200 seconds).
gabemontero
force-pushed
the
fix-after-github-error
branch
from
137e0b5 to
a08f2b2
Compare
maysunfaisal
approved these changes
Jan 27, 2026
Contributor
|
@gabemontero lol I was two minutes slower. I just had some minor comments so I'll resolve them. No worries! |
Contributor
Author
oops sorry about that @thepetk |
Contributor
|
@gabemontero NP! I was only curious about this: just to see if removing all spaces is intended |
Contributor
Author
TBH @thepetk that bit was claude generate (just realized I forgot to add the claude assisted bit to the commit comment) .... I then went with testing to confirm/deny correctness WRT testing, this code rendered things "correctly" IMO from an end user point of view ... see gabemontero-appstudio-test-org/llama-stack-langgraph-test#54 .... at least one of those first two comments was at |
Contributor
Yeah.. tbh from the little I know/have experienced LLMs shouldn't have problems to work with a "joint" body. Pretty much that's the reason I consider it to be a minor point. From my side I'll try to test the updated template as a whole and if there's anything to change I'll open a follow up PR! |
thepetk
added a commit
that referenced
this pull request
Jan 29, 2026
* Update RAG metadata regeneration logic (#13) * Update logic for RAG Metadata caching Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Remove .git suffix from URL Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Add tests for RAG metadata regen Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Fix ruff linting err Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Address PR review and ty linter Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Update Llama Stack run config for openai to ollama Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Update Ollama Deployment to pull embedding model Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> --------- Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Create pull request template based on ai-lab-template (#16) * Add CI/CD for App, Llama Stack (#17) * Add CI/CD for App, Llama Stack Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Update .github/workflows/image.yaml Co-authored-by: Theofanis Petkos <thepetk@gmail.com> * Update .github/workflows/image.yaml Co-authored-by: Theofanis Petkos <thepetk@gmail.com> * Update .github/workflows/image.yaml Co-authored-by: Theofanis Petkos <thepetk@gmail.com> --------- Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> Co-authored-by: Theofanis Petkos <thepetk@gmail.com> * Fix workflow for space and image inspect (#19) Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * adjust github mcp tools calls for payload size, timeout (#20) discovered during testing of the performance agent that the github add comment tool call was failing for the k8s top outpu. investigation confirmed that the output exceeded the max length for a github comment, so adding some truncating logic to adhere to the size limit also broke out failure processing for creating and issue from failure processing for adding comments; we should at least note the github issue creation, with an indicator if any of the comment failed finally, added a timeout to the comment tool calls, as failure/retry at the openai/LLS level lead to huge delays from the UI perspective (one instance or 1200 seconds). * Consolidate GITHUB TOKENS - 1 (#18) Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Prepare for RHDH 1.9 --------- Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> Co-authored-by: Maysun Faisal <31771087+maysunfaisal@users.noreply.github.com> Co-authored-by: Gabe Montero <gmontero@redhat.com>
gabemontero
added a commit
that referenced
this pull request
Jan 30, 2026
* Update RAG metadata regeneration logic (#13) * Update logic for RAG Metadata caching Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Remove .git suffix from URL Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Add tests for RAG metadata regen Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Fix ruff linting err Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Address PR review and ty linter Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Update Llama Stack run config for openai to ollama Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Update Ollama Deployment to pull embedding model Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> --------- Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Create pull request template based on ai-lab-template (#16) * Add CI/CD for App, Llama Stack (#17) * Add CI/CD for App, Llama Stack Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Update .github/workflows/image.yaml Co-authored-by: Theofanis Petkos <thepetk@gmail.com> * Update .github/workflows/image.yaml Co-authored-by: Theofanis Petkos <thepetk@gmail.com> * Update .github/workflows/image.yaml Co-authored-by: Theofanis Petkos <thepetk@gmail.com> --------- Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> Co-authored-by: Theofanis Petkos <thepetk@gmail.com> * Fix workflow for space and image inspect (#19) Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * adjust github mcp tools calls for payload size, timeout (#20) discovered during testing of the performance agent that the github add comment tool call was failing for the k8s top outpu. investigation confirmed that the output exceeded the max length for a github comment, so adding some truncating logic to adhere to the size limit also broke out failure processing for creating and issue from failure processing for adding comments; we should at least note the github issue creation, with an indicator if any of the comment failed finally, added a timeout to the comment tool calls, as failure/retry at the openai/LLS level lead to huge delays from the UI perspective (one instance or 1200 seconds). * Consolidate GITHUB TOKENS - 1 (#18) Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Introduce gitops sync waves (#22) * Enforce Secrets Creation Acknowledgment (#24) * Fix Secret ACK checkbox Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * Default Checkbox to False, and enforce using enum Assisted-by: Claude Opus 4.5 Generated-by: Cursor Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> --------- Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> * UX & Ingestion Optimizations (#23) * Remove polling * Avoid concurrent ingestion * Update streamlit app * Add manual refresh * Add more comments * Update comment * Prepare for RHDH 1.9 --------- Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com> Co-authored-by: Maysun Faisal <31771087+maysunfaisal@users.noreply.github.com> Co-authored-by: Gabe Montero <gmontero@redhat.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?:
discovered during testing of the performance agent that the github add comment tool call was failing for the k8s top outpu.
investigation confirmed that the output exceeded the max length for a github comment, so adding some truncating logic to adhere to the size limit
also broke out failure processing for creating and issue from failure processing for adding comments; we should at least note the github issue creation, with an indicator if any of the comment failed
finally, added a timeout to the comment tool calls, as failure/retry at the openai/LLS level lead to huge delays from the UI perspective (one instance of 1200 seconds).
How to test changes / Special notes to the reviewer:
supply a prompt like
get me cpu and memory statistics for my openshift cluster