[2024b] RHOAIENG-18535: chore(deps): bump mysql-connector-python from 9.0.0 to 9.1.0 in Pipfiles #1228
Conversation
… 9.0.0 to 9.1.0 in Pipfiles
… 9.0.0 to 9.1.0 in Pipfiles
jiridanek
added
tide/merge-method-squash
WalkthroughThis change updates the versions of the Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant Pipfile/requirements.txt
participant Python Env
User->>Pipfile/requirements.txt: Specifies new versions (multidict 6.6.2, mysql-connector-python 9.1.0)
Pipfile/requirements.txt->>Python Env: Triggers installation with updated versions
Python Env-->>User: Installs packages with new constraints (Python >= 3.9 for mysql-connector-python)
Possibly related PRs
Suggested labels
Suggested reviewers
Poem
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: The full list of commands accepted by this bot can be found here.
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
|
@coderabbitai review |
✅ Actions performedReview triggered.
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (2)
runtimes/rocm-pytorch/ubi9-python-3.11/Pipfile (1)
38-38: Tiny nit – allow future patch versions?Pinning with
~=9.1.0restricts upgrades to the 9.1.* patch line only.
If you want to pick up 9.2.x automatically (as was previously allowed with~=9.0.0), use~=9.1instead.-mysql-connector-python = "~=9.1.0" +mysql-connector-python = "~=9.1"Otherwise, current pin is acceptable.
jupyter/tensorflow/ubi9-python-3.11/Pipfile (1)
32-33: Minor nit – keep spec width consistentEvery other DB connector uses three-part specs (
~=<major>.<minor>.<patch>).
For visual consistency, consider:-mysql-connector-python = "~=9.1.0" +mysql-connector-python = "~=9.1.0" # (no functional change, purely style)
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
⛔ Files ignored due to path filters (12)
jupyter/datascience/ubi9-python-3.11/Pipfile.lockis excluded by!**/*.lockjupyter/minimal/ubi9-python-3.11/Pipfile.lockis excluded by!**/*.lockjupyter/pytorch/ubi9-python-3.11/Pipfile.lockis excluded by!**/*.lockjupyter/rocm/pytorch/ubi9-python-3.11/Pipfile.lockis excluded by!**/*.lockjupyter/rocm/tensorflow/ubi9-python-3.11/Pipfile.lockis excluded by!**/*.lockjupyter/tensorflow/ubi9-python-3.11/Pipfile.lockis excluded by!**/*.lockjupyter/trustyai/ubi9-python-3.11/Pipfile.lockis excluded by!**/*.lockruntimes/datascience/ubi9-python-3.11/Pipfile.lockis excluded by!**/*.lockruntimes/pytorch/ubi9-python-3.11/Pipfile.lockis excluded by!**/*.lockruntimes/rocm-pytorch/ubi9-python-3.11/Pipfile.lockis excluded by!**/*.lockruntimes/rocm-tensorflow/ubi9-python-3.11/Pipfile.lockis excluded by!**/*.lockruntimes/tensorflow/ubi9-python-3.11/Pipfile.lockis excluded by!**/*.lock
📒 Files selected for processing (29)
jupyter/datascience/ubi9-python-3.11/Pipfile(1 hunks)jupyter/datascience/ubi9-python-3.11/requirements.txt(1 hunks)jupyter/minimal/ubi9-python-3.11/requirements.txt(1 hunks)jupyter/pytorch/ubi9-python-3.11/Pipfile(1 hunks)jupyter/pytorch/ubi9-python-3.11/requirements.txt(1 hunks)jupyter/rocm/pytorch/ubi9-python-3.11/Pipfile(1 hunks)jupyter/rocm/pytorch/ubi9-python-3.11/requirements.txt(1 hunks)jupyter/rocm/tensorflow/ubi9-python-3.11/Pipfile(1 hunks)jupyter/rocm/tensorflow/ubi9-python-3.11/requirements.txt(1 hunks)jupyter/tensorflow/ubi9-python-3.11/Pipfile(1 hunks)jupyter/tensorflow/ubi9-python-3.11/requirements.txt(1 hunks)jupyter/trustyai/ubi9-python-3.11/Pipfile(1 hunks)jupyter/trustyai/ubi9-python-3.11/requirements.txt(2 hunks)manifests/base/jupyter-datascience-notebook-imagestream.yaml(1 hunks)manifests/base/jupyter-pytorch-notebook-imagestream.yaml(1 hunks)manifests/base/jupyter-rocm-pytorch-notebook-imagestream.yaml(1 hunks)manifests/base/jupyter-rocm-tensorflow-notebook-imagestream.yaml(1 hunks)manifests/base/jupyter-tensorflow-notebook-imagestream.yaml(1 hunks)manifests/base/jupyter-trustyai-notebook-imagestream.yaml(1 hunks)runtimes/datascience/ubi9-python-3.11/Pipfile(1 hunks)runtimes/datascience/ubi9-python-3.11/requirements.txt(1 hunks)runtimes/pytorch/ubi9-python-3.11/Pipfile(1 hunks)runtimes/pytorch/ubi9-python-3.11/requirements.txt(1 hunks)runtimes/rocm-pytorch/ubi9-python-3.11/Pipfile(1 hunks)runtimes/rocm-pytorch/ubi9-python-3.11/requirements.txt(1 hunks)runtimes/rocm-tensorflow/ubi9-python-3.11/Pipfile(1 hunks)runtimes/rocm-tensorflow/ubi9-python-3.11/requirements.txt(1 hunks)runtimes/tensorflow/ubi9-python-3.11/Pipfile(1 hunks)runtimes/tensorflow/ubi9-python-3.11/requirements.txt(1 hunks)
🧰 Additional context used
🧠 Learnings (29)
📓 Common learnings
Learnt from: jiridanek
PR: opendatahub-io/notebooks#0
File: :0-0
Timestamp: 2025-06-30T19:44:57.619Z
Learning: In the opendatahub-io/notebooks repository, jiridanek effectively manages comprehensive PR reviews by tracking all feedback as follow-up GitHub issues rather than blocking merge of high-quality implementations. This demonstrates excellent project management practices for balancing current deliverables with future improvements.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#0
File: :0-0
Timestamp: 2025-06-20T11:51:59.716Z
Learning: This project follows the practice of associating PRs with Jira tickets from https://issues.redhat.com for traceability between requirements, release process, and product documentation. This is critical for enterprise software development compliance and cross-team coordination.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1127
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:20-20
Timestamp: 2025-06-27T07:49:01.198Z
Learning: jiridanek reviewed the transformers v4.50.0 release notes and assessed that the changes are minimal and unlikely to cause TrustyAI integration problems, indicating the actual changelog contained mostly bug fixes and minor additions rather than breaking changes.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1154
File: manifests/base/jupyter-tensorflow-notebook-imagestream.yaml:45-45
Timestamp: 2025-06-13T08:34:01.300Z
Learning: When updating dependency versions in `manifests/base/*-imagestream.yaml`, the project convention is to modify only the newest tag (e.g., "2025.1") and intentionally leave earlier tags (e.g., "2024.2") unchanged.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1154
File: manifests/base/jupyter-pytorch-notebook-imagestream.yaml:0-0
Timestamp: 2025-06-16T11:06:33.139Z
Learning: In the opendatahub-io/notebooks repository, N-1 versions of images in manifest files (like imagestream.yaml files) should not be updated regularly. The versions of packages like codeflare-sdk in N-1 images are frozen to what was released when the image was moved from N to N-1 version. N-1 images are only updated for security vulnerabilities of packages, not for regular version bumps. This is why the version of packages in N-1 images may be quite old compared to the latest N version.
runtimes/rocm-tensorflow/ubi9-python-3.11/Pipfile (7)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#0
File: :0-0
Timestamp: 2025-06-16T11:32:09.203Z
Learning: In the opendatahub-io/notebooks repository, there is a known issue with missing `runtimes/rocm/pytorch/ubi9-python-3.11/kustomize/base/kustomization.yaml` file that causes rocm runtime tests to fail with "no such file or directory" error. This is tracked in JIRA RHOAIENG-22044 and was intended to be fixed in PR #1015.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/datascience/ubi9-python-3.11/Pipfile:34-36
Timestamp: 2025-06-28T14:13:27.890Z
Learning: In the opendatahub-io/notebooks repository, the dependency pinning strategy follows a deliberate pattern: core `jupyterlab` package uses exact pinning (==) across all notebook images to ensure UI consistency, while JupyterLab extensions and all server components (jupyter-server, jupyter-server-proxy, jupyter-server-terminals) use compatible release (~=) pinning to allow automatic security updates and bug fixes while maintaining API compatibility.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1197
File: runtimes/minimal/ubi9-python-3.11/requirements.txt:395-405
Timestamp: 2025-06-26T15:28:35.416Z
Learning: psutil version 7.x is compatible with UBI9, CentOS Stream 9, and RHEL 9 platforms in the opendatahub-io/notebooks repository. The upgrade from psutil 5.x to 7.x has been validated for these environments.
manifests/base/jupyter-trustyai-notebook-imagestream.yaml (10)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1154
File: manifests/base/jupyter-pytorch-notebook-imagestream.yaml:0-0
Timestamp: 2025-06-16T11:06:33.139Z
Learning: In the opendatahub-io/notebooks repository, N-1 versions of images in manifest files (like imagestream.yaml files) should not be updated regularly. The versions of packages like codeflare-sdk in N-1 images are frozen to what was released when the image was moved from N to N-1 version. N-1 images are only updated for security vulnerabilities of packages, not for regular version bumps. This is why the version of packages in N-1 images may be quite old compared to the latest N version.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1154
File: manifests/base/jupyter-tensorflow-notebook-imagestream.yaml:45-45
Timestamp: 2025-06-13T08:34:01.300Z
Learning: When updating dependency versions in `manifests/base/*-imagestream.yaml`, the project convention is to modify only the newest tag (e.g., "2025.1") and intentionally leave earlier tags (e.g., "2024.2") unchanged.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/datascience/ubi9-python-3.11/Pipfile:34-36
Timestamp: 2025-06-28T14:13:27.890Z
Learning: In the opendatahub-io/notebooks repository, the dependency pinning strategy follows a deliberate pattern: core `jupyterlab` package uses exact pinning (==) across all notebook images to ensure UI consistency, while JupyterLab extensions and all server components (jupyter-server, jupyter-server-proxy, jupyter-server-terminals) use compatible release (~=) pinning to allow automatic security updates and bug fixes while maintaining API compatibility.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1127
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:20-20
Timestamp: 2025-06-27T07:49:01.198Z
Learning: jiridanek reviewed the transformers v4.50.0 release notes and assessed that the changes are minimal and unlikely to cause TrustyAI integration problems, indicating the actual changelog contained mostly bug fixes and minor additions rather than breaking changes.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#0
File: :0-0
Timestamp: 2025-06-26T16:19:31.295Z
Learning: In the opendatahub-io/notebooks repository, the Playwright Docker image version in `.github/workflows/build-notebooks-TEMPLATE.yaml` (format: `mcr.microsoft.com/playwright:v1.53.1-noble`) must always match the `@playwright/test` version specified in the `tests/browser/package.json` file. Both versions need to be updated together to maintain consistency between CI/CD pipeline and project dependencies.
manifests/base/jupyter-rocm-tensorflow-notebook-imagestream.yaml (6)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1154
File: manifests/base/jupyter-pytorch-notebook-imagestream.yaml:0-0
Timestamp: 2025-06-16T11:06:33.139Z
Learning: In the opendatahub-io/notebooks repository, N-1 versions of images in manifest files (like imagestream.yaml files) should not be updated regularly. The versions of packages like codeflare-sdk in N-1 images are frozen to what was released when the image was moved from N to N-1 version. N-1 images are only updated for security vulnerabilities of packages, not for regular version bumps. This is why the version of packages in N-1 images may be quite old compared to the latest N version.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#0
File: :0-0
Timestamp: 2025-06-16T11:32:09.203Z
Learning: In the opendatahub-io/notebooks repository, there is a known issue with missing `runtimes/rocm/pytorch/ubi9-python-3.11/kustomize/base/kustomization.yaml` file that causes rocm runtime tests to fail with "no such file or directory" error. This is tracked in JIRA RHOAIENG-22044 and was intended to be fixed in PR #1015.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1154
File: manifests/base/jupyter-tensorflow-notebook-imagestream.yaml:45-45
Timestamp: 2025-06-13T08:34:01.300Z
Learning: When updating dependency versions in `manifests/base/*-imagestream.yaml`, the project convention is to modify only the newest tag (e.g., "2025.1") and intentionally leave earlier tags (e.g., "2024.2") unchanged.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
jupyter/rocm/pytorch/ubi9-python-3.11/Pipfile (7)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#0
File: :0-0
Timestamp: 2025-06-16T11:32:09.203Z
Learning: In the opendatahub-io/notebooks repository, there is a known issue with missing `runtimes/rocm/pytorch/ubi9-python-3.11/kustomize/base/kustomization.yaml` file that causes rocm runtime tests to fail with "no such file or directory" error. This is tracked in JIRA RHOAIENG-22044 and was intended to be fixed in PR #1015.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/datascience/ubi9-python-3.11/Pipfile:34-36
Timestamp: 2025-06-28T14:13:27.890Z
Learning: In the opendatahub-io/notebooks repository, the dependency pinning strategy follows a deliberate pattern: core `jupyterlab` package uses exact pinning (==) across all notebook images to ensure UI consistency, while JupyterLab extensions and all server components (jupyter-server, jupyter-server-proxy, jupyter-server-terminals) use compatible release (~=) pinning to allow automatic security updates and bug fixes while maintaining API compatibility.
runtimes/rocm-pytorch/ubi9-python-3.11/Pipfile (8)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#0
File: :0-0
Timestamp: 2025-06-16T11:32:09.203Z
Learning: In the opendatahub-io/notebooks repository, there is a known issue with missing `runtimes/rocm/pytorch/ubi9-python-3.11/kustomize/base/kustomization.yaml` file that causes rocm runtime tests to fail with "no such file or directory" error. This is tracked in JIRA RHOAIENG-22044 and was intended to be fixed in PR #1015.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/datascience/ubi9-python-3.11/Pipfile:34-36
Timestamp: 2025-06-28T14:13:27.890Z
Learning: In the opendatahub-io/notebooks repository, the dependency pinning strategy follows a deliberate pattern: core `jupyterlab` package uses exact pinning (==) across all notebook images to ensure UI consistency, while JupyterLab extensions and all server components (jupyter-server, jupyter-server-proxy, jupyter-server-terminals) use compatible release (~=) pinning to allow automatic security updates and bug fixes while maintaining API compatibility.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1197
File: runtimes/minimal/ubi9-python-3.11/requirements.txt:395-405
Timestamp: 2025-06-26T15:28:35.416Z
Learning: psutil version 7.x is compatible with UBI9, CentOS Stream 9, and RHEL 9 platforms in the opendatahub-io/notebooks repository. The upgrade from psutil 5.x to 7.x has been validated for these environments.
manifests/base/jupyter-pytorch-notebook-imagestream.yaml (8)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1154
File: manifests/base/jupyter-pytorch-notebook-imagestream.yaml:0-0
Timestamp: 2025-06-16T11:06:33.139Z
Learning: In the opendatahub-io/notebooks repository, N-1 versions of images in manifest files (like imagestream.yaml files) should not be updated regularly. The versions of packages like codeflare-sdk in N-1 images are frozen to what was released when the image was moved from N to N-1 version. N-1 images are only updated for security vulnerabilities of packages, not for regular version bumps. This is why the version of packages in N-1 images may be quite old compared to the latest N version.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1154
File: manifests/base/jupyter-tensorflow-notebook-imagestream.yaml:45-45
Timestamp: 2025-06-13T08:34:01.300Z
Learning: When updating dependency versions in `manifests/base/*-imagestream.yaml`, the project convention is to modify only the newest tag (e.g., "2025.1") and intentionally leave earlier tags (e.g., "2024.2") unchanged.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/datascience/ubi9-python-3.11/Pipfile:34-36
Timestamp: 2025-06-28T14:13:27.890Z
Learning: In the opendatahub-io/notebooks repository, the dependency pinning strategy follows a deliberate pattern: core `jupyterlab` package uses exact pinning (==) across all notebook images to ensure UI consistency, while JupyterLab extensions and all server components (jupyter-server, jupyter-server-proxy, jupyter-server-terminals) use compatible release (~=) pinning to allow automatic security updates and bug fixes while maintaining API compatibility.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
manifests/base/jupyter-rocm-pytorch-notebook-imagestream.yaml (10)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1154
File: manifests/base/jupyter-pytorch-notebook-imagestream.yaml:0-0
Timestamp: 2025-06-16T11:06:33.139Z
Learning: In the opendatahub-io/notebooks repository, N-1 versions of images in manifest files (like imagestream.yaml files) should not be updated regularly. The versions of packages like codeflare-sdk in N-1 images are frozen to what was released when the image was moved from N to N-1 version. N-1 images are only updated for security vulnerabilities of packages, not for regular version bumps. This is why the version of packages in N-1 images may be quite old compared to the latest N version.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#0
File: :0-0
Timestamp: 2025-06-16T11:32:09.203Z
Learning: In the opendatahub-io/notebooks repository, there is a known issue with missing `runtimes/rocm/pytorch/ubi9-python-3.11/kustomize/base/kustomization.yaml` file that causes rocm runtime tests to fail with "no such file or directory" error. This is tracked in JIRA RHOAIENG-22044 and was intended to be fixed in PR #1015.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1154
File: manifests/base/jupyter-tensorflow-notebook-imagestream.yaml:45-45
Timestamp: 2025-06-13T08:34:01.300Z
Learning: When updating dependency versions in `manifests/base/*-imagestream.yaml`, the project convention is to modify only the newest tag (e.g., "2025.1") and intentionally leave earlier tags (e.g., "2024.2") unchanged.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/datascience/ubi9-python-3.11/Pipfile:34-36
Timestamp: 2025-06-28T14:13:27.890Z
Learning: In the opendatahub-io/notebooks repository, the dependency pinning strategy follows a deliberate pattern: core `jupyterlab` package uses exact pinning (==) across all notebook images to ensure UI consistency, while JupyterLab extensions and all server components (jupyter-server, jupyter-server-proxy, jupyter-server-terminals) use compatible release (~=) pinning to allow automatic security updates and bug fixes while maintaining API compatibility.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#0
File: :0-0
Timestamp: 2025-06-26T16:19:31.295Z
Learning: In the opendatahub-io/notebooks repository, the Playwright Docker image version in `.github/workflows/build-notebooks-TEMPLATE.yaml` (format: `mcr.microsoft.com/playwright:v1.53.1-noble`) must always match the `@playwright/test` version specified in the `tests/browser/package.json` file. Both versions need to be updated together to maintain consistency between CI/CD pipeline and project dependencies.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#0
File: :0-0
Timestamp: 2025-06-26T16:19:31.295Z
Learning: In the opendatahub-io/notebooks repository, the Playwright Docker image version in `.github/workflows/build-notebooks-TEMPLATE.yaml` (format: `mcr.microsoft.com/playwright:v1.53.1-noble`) must always match the `@playwright/test` version specified in the `tests/browser/package.json` file. Both versions need to be updated together to maintain consistency between CI/CD pipeline and project dependencies.
jupyter/tensorflow/ubi9-python-3.11/Pipfile (6)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/datascience/ubi9-python-3.11/Pipfile:34-36
Timestamp: 2025-06-28T14:13:27.890Z
Learning: In the opendatahub-io/notebooks repository, the dependency pinning strategy follows a deliberate pattern: core `jupyterlab` package uses exact pinning (==) across all notebook images to ensure UI consistency, while JupyterLab extensions and all server components (jupyter-server, jupyter-server-proxy, jupyter-server-terminals) use compatible release (~=) pinning to allow automatic security updates and bug fixes while maintaining API compatibility.
manifests/base/jupyter-tensorflow-notebook-imagestream.yaml (7)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1154
File: manifests/base/jupyter-pytorch-notebook-imagestream.yaml:0-0
Timestamp: 2025-06-16T11:06:33.139Z
Learning: In the opendatahub-io/notebooks repository, N-1 versions of images in manifest files (like imagestream.yaml files) should not be updated regularly. The versions of packages like codeflare-sdk in N-1 images are frozen to what was released when the image was moved from N to N-1 version. N-1 images are only updated for security vulnerabilities of packages, not for regular version bumps. This is why the version of packages in N-1 images may be quite old compared to the latest N version.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1154
File: manifests/base/jupyter-tensorflow-notebook-imagestream.yaml:45-45
Timestamp: 2025-06-13T08:34:01.300Z
Learning: When updating dependency versions in `manifests/base/*-imagestream.yaml`, the project convention is to modify only the newest tag (e.g., "2025.1") and intentionally leave earlier tags (e.g., "2024.2") unchanged.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/datascience/ubi9-python-3.11/Pipfile:34-36
Timestamp: 2025-06-28T14:13:27.890Z
Learning: In the opendatahub-io/notebooks repository, the dependency pinning strategy follows a deliberate pattern: core `jupyterlab` package uses exact pinning (==) across all notebook images to ensure UI consistency, while JupyterLab extensions and all server components (jupyter-server, jupyter-server-proxy, jupyter-server-terminals) use compatible release (~=) pinning to allow automatic security updates and bug fixes while maintaining API compatibility.
runtimes/tensorflow/ubi9-python-3.11/Pipfile (6)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/datascience/ubi9-python-3.11/Pipfile:34-36
Timestamp: 2025-06-28T14:13:27.890Z
Learning: In the opendatahub-io/notebooks repository, the dependency pinning strategy follows a deliberate pattern: core `jupyterlab` package uses exact pinning (==) across all notebook images to ensure UI consistency, while JupyterLab extensions and all server components (jupyter-server, jupyter-server-proxy, jupyter-server-terminals) use compatible release (~=) pinning to allow automatic security updates and bug fixes while maintaining API compatibility.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1197
File: runtimes/minimal/ubi9-python-3.11/requirements.txt:395-405
Timestamp: 2025-06-26T15:28:35.416Z
Learning: psutil version 7.x is compatible with UBI9, CentOS Stream 9, and RHEL 9 platforms in the opendatahub-io/notebooks repository. The upgrade from psutil 5.x to 7.x has been validated for these environments.
jupyter/datascience/ubi9-python-3.11/Pipfile (6)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/datascience/ubi9-python-3.11/Pipfile:34-36
Timestamp: 2025-06-28T14:13:27.890Z
Learning: In the opendatahub-io/notebooks repository, the dependency pinning strategy follows a deliberate pattern: core `jupyterlab` package uses exact pinning (==) across all notebook images to ensure UI consistency, while JupyterLab extensions and all server components (jupyter-server, jupyter-server-proxy, jupyter-server-terminals) use compatible release (~=) pinning to allow automatic security updates and bug fixes while maintaining API compatibility.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
runtimes/datascience/ubi9-python-3.11/Pipfile (7)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/datascience/ubi9-python-3.11/Pipfile:34-36
Timestamp: 2025-06-28T14:13:27.890Z
Learning: In the opendatahub-io/notebooks repository, the dependency pinning strategy follows a deliberate pattern: core `jupyterlab` package uses exact pinning (==) across all notebook images to ensure UI consistency, while JupyterLab extensions and all server components (jupyter-server, jupyter-server-proxy, jupyter-server-terminals) use compatible release (~=) pinning to allow automatic security updates and bug fixes while maintaining API compatibility.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1197
File: runtimes/minimal/ubi9-python-3.11/requirements.txt:395-405
Timestamp: 2025-06-26T15:28:35.416Z
Learning: psutil version 7.x is compatible with UBI9, CentOS Stream 9, and RHEL 9 platforms in the opendatahub-io/notebooks repository. The upgrade from psutil 5.x to 7.x has been validated for these environments.
manifests/base/jupyter-datascience-notebook-imagestream.yaml (7)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1154
File: manifests/base/jupyter-pytorch-notebook-imagestream.yaml:0-0
Timestamp: 2025-06-16T11:06:33.139Z
Learning: In the opendatahub-io/notebooks repository, N-1 versions of images in manifest files (like imagestream.yaml files) should not be updated regularly. The versions of packages like codeflare-sdk in N-1 images are frozen to what was released when the image was moved from N to N-1 version. N-1 images are only updated for security vulnerabilities of packages, not for regular version bumps. This is why the version of packages in N-1 images may be quite old compared to the latest N version.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1154
File: manifests/base/jupyter-tensorflow-notebook-imagestream.yaml:45-45
Timestamp: 2025-06-13T08:34:01.300Z
Learning: When updating dependency versions in `manifests/base/*-imagestream.yaml`, the project convention is to modify only the newest tag (e.g., "2025.1") and intentionally leave earlier tags (e.g., "2024.2") unchanged.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/datascience/ubi9-python-3.11/Pipfile:34-36
Timestamp: 2025-06-28T14:13:27.890Z
Learning: In the opendatahub-io/notebooks repository, the dependency pinning strategy follows a deliberate pattern: core `jupyterlab` package uses exact pinning (==) across all notebook images to ensure UI consistency, while JupyterLab extensions and all server components (jupyter-server, jupyter-server-proxy, jupyter-server-terminals) use compatible release (~=) pinning to allow automatic security updates and bug fixes while maintaining API compatibility.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
jupyter/pytorch/ubi9-python-3.11/Pipfile (6)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/datascience/ubi9-python-3.11/Pipfile:34-36
Timestamp: 2025-06-28T14:13:27.890Z
Learning: In the opendatahub-io/notebooks repository, the dependency pinning strategy follows a deliberate pattern: core `jupyterlab` package uses exact pinning (==) across all notebook images to ensure UI consistency, while JupyterLab extensions and all server components (jupyter-server, jupyter-server-proxy, jupyter-server-terminals) use compatible release (~=) pinning to allow automatic security updates and bug fixes while maintaining API compatibility.
runtimes/pytorch/ubi9-python-3.11/Pipfile (7)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/datascience/ubi9-python-3.11/Pipfile:34-36
Timestamp: 2025-06-28T14:13:27.890Z
Learning: In the opendatahub-io/notebooks repository, the dependency pinning strategy follows a deliberate pattern: core `jupyterlab` package uses exact pinning (==) across all notebook images to ensure UI consistency, while JupyterLab extensions and all server components (jupyter-server, jupyter-server-proxy, jupyter-server-terminals) use compatible release (~=) pinning to allow automatic security updates and bug fixes while maintaining API compatibility.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1197
File: runtimes/minimal/ubi9-python-3.11/requirements.txt:395-405
Timestamp: 2025-06-26T15:28:35.416Z
Learning: psutil version 7.x is compatible with UBI9, CentOS Stream 9, and RHEL 9 platforms in the opendatahub-io/notebooks repository. The upgrade from psutil 5.x to 7.x has been validated for these environments.
jupyter/rocm/tensorflow/ubi9-python-3.11/Pipfile (7)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#0
File: :0-0
Timestamp: 2025-06-16T11:32:09.203Z
Learning: In the opendatahub-io/notebooks repository, there is a known issue with missing `runtimes/rocm/pytorch/ubi9-python-3.11/kustomize/base/kustomization.yaml` file that causes rocm runtime tests to fail with "no such file or directory" error. This is tracked in JIRA RHOAIENG-22044 and was intended to be fixed in PR #1015.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/datascience/ubi9-python-3.11/Pipfile:34-36
Timestamp: 2025-06-28T14:13:27.890Z
Learning: In the opendatahub-io/notebooks repository, the dependency pinning strategy follows a deliberate pattern: core `jupyterlab` package uses exact pinning (==) across all notebook images to ensure UI consistency, while JupyterLab extensions and all server components (jupyter-server, jupyter-server-proxy, jupyter-server-terminals) use compatible release (~=) pinning to allow automatic security updates and bug fixes while maintaining API compatibility.
jupyter/minimal/ubi9-python-3.11/requirements.txt (5)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
jupyter/trustyai/ubi9-python-3.11/Pipfile (7)
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1218
File: jupyter/datascience/ubi9-python-3.11/Pipfile:34-36
Timestamp: 2025-06-28T14:13:27.890Z
Learning: In the opendatahub-io/notebooks repository, the dependency pinning strategy follows a deliberate pattern: core `jupyterlab` package uses exact pinning (==) across all notebook images to ensure UI consistency, while JupyterLab extensions and all server components (jupyter-server, jupyter-server-proxy, jupyter-server-terminals) use compatible release (~=) pinning to allow automatic security updates and bug fixes while maintaining API compatibility.
Learnt from: jiridanek
PR: opendatahub-io/notebooks#1127
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:20-20
Timestamp: 2025-06-27T07:49:01.198Z
Learning: jiridanek reviewed the transformers v4.50.0 release notes and assessed that the changes are minimal and unlikely to cause TrustyAI integration problems, indicating the actual changelog contained mostly bug fixes and minor additions rather than breaking changes.
jupyter/datascience/ubi9-python-3.11/requirements.txt (5)
undefined
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
</retrieved_learning>
jupyter/pytorch/ubi9-python-3.11/requirements.txt (5)
undefined
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
</retrieved_learning>
runtimes/rocm-pytorch/ubi9-python-3.11/requirements.txt (2)
undefined
<retrieved_learning>
Learnt from: jiridanek
PR: opendatahub-io/notebooks#0
File: :0-0
Timestamp: 2025-06-16T11:32:09.203Z
Learning: In the opendatahub-io/notebooks repository, there is a known issue with missing runtimes/rocm/pytorch/ubi9-python-3.11/kustomize/base/kustomization.yaml file that causes rocm runtime tests to fail with "no such file or directory" error. This is tracked in JIRA RHOAIENG-22044 and was intended to be fixed in PR #1015.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
</retrieved_learning>
jupyter/trustyai/ubi9-python-3.11/requirements.txt (6)
undefined
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1127
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:20-20
Timestamp: 2025-06-27T07:49:01.198Z
Learning: jiridanek reviewed the transformers v4.50.0 release notes and assessed that the changes are minimal and unlikely to cause TrustyAI integration problems, indicating the actual changelog contained mostly bug fixes and minor additions rather than breaking changes.
</retrieved_learning>
jupyter/rocm/tensorflow/ubi9-python-3.11/requirements.txt (6)
undefined
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: opendatahub-io/notebooks#0
File: :0-0
Timestamp: 2025-06-16T11:32:09.203Z
Learning: In the opendatahub-io/notebooks repository, there is a known issue with missing runtimes/rocm/pytorch/ubi9-python-3.11/kustomize/base/kustomization.yaml file that causes rocm runtime tests to fail with "no such file or directory" error. This is tracked in JIRA RHOAIENG-22044 and was intended to be fixed in PR #1015.
</retrieved_learning>
runtimes/rocm-tensorflow/ubi9-python-3.11/requirements.txt (2)
undefined
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: opendatahub-io/notebooks#0
File: :0-0
Timestamp: 2025-06-16T11:32:09.203Z
Learning: In the opendatahub-io/notebooks repository, there is a known issue with missing runtimes/rocm/pytorch/ubi9-python-3.11/kustomize/base/kustomization.yaml file that causes rocm runtime tests to fail with "no such file or directory" error. This is tracked in JIRA RHOAIENG-22044 and was intended to be fixed in PR #1015.
</retrieved_learning>
jupyter/tensorflow/ubi9-python-3.11/requirements.txt (5)
undefined
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: The jupyter-bokeh pinning to 3.0.5 in TrustyAI notebook image was not due to TrustyAI code compatibility issues, but because the trustyai package itself explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency, causing pip dependency resolution conflicts when trying to upgrade to jupyter-bokeh 4.x.
</retrieved_learning>
runtimes/pytorch/ubi9-python-3.11/requirements.txt (1)
undefined
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
</retrieved_learning>
runtimes/datascience/ubi9-python-3.11/requirements.txt (1)
undefined
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
</retrieved_learning>
jupyter/rocm/pytorch/ubi9-python-3.11/requirements.txt (5)
undefined
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: TrustyAI's jupyter-bokeh was pinned to 3.0.5 due to compatibility requirements with TrustyAI's visualization components, but the actual deployed version in requirements.txt shows 3.0.7, indicating incremental testing. The upgrade to 4.0.5 in this PR represents the completion of a gradual migration strategy from the 3.x series after confirming compatibility with Bokeh 3.7.3.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI explicitly declares jupyter-bokeh~=3.0.5 as a hard dependency in both their requirements.txt and pyproject.toml files, with no open issues tracking jupyter-bokeh 4.x compatibility. This creates an unresolvable pip dependency conflict when trying to upgrade jupyter-bokeh to 4.x in notebook images that include TrustyAI.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: opendatahub-io/notebooks#0
File: :0-0
Timestamp: 2025-06-16T11:32:09.203Z
Learning: In the opendatahub-io/notebooks repository, there is a known issue with missing runtimes/rocm/pytorch/ubi9-python-3.11/kustomize/base/kustomization.yaml file that causes rocm runtime tests to fail with "no such file or directory" error. This is tracked in JIRA RHOAIENG-22044 and was intended to be fixed in PR #1015.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:15:41.168Z
Learning: The jupyter-bokeh package was previously pinned to version 3.0.5 in the TrustyAI notebook image due to compatibility requirements with TrustyAI components, as indicated by the comment "Should be pinned down to this version in order to be compatible with trustyai" that was removed in this update.
</retrieved_learning>
<retrieved_learning>
Learnt from: jiridanek
PR: #1218
File: jupyter/trustyai/ubi9-python-3.11/Pipfile:49-49
Timestamp: 2025-06-28T14:21:09.429Z
Learning: TrustyAI 0.6.1 (latest version as of June 2025) has a hard dependency constraint on jupyter-bokeh~=3.0.5, preventing upgrades to jupyter-bokeh 4.x in notebook images that include TrustyAI. This requires either waiting for TrustyAI to update their dependency or excluding TrustyAI from jupyter-bokeh upgrades.
</retrieved_learning>
🔇 Additional comments (38)
runtimes/tensorflow/ubi9-python-3.11/Pipfile (1)
31-31: Lock-file is up to dateI ran a repository-wide search for any lingering
9.0.*references tomysql-connector-pythonand found none—your Pipfile.lock (and any requirements artifacts) already reflect~=9.1.0. No further action is needed.runtimes/rocm-tensorflow/ubi9-python-3.11/Pipfile (1)
30-30: Consistent bump acknowledged.The ROCm-TensorFlow image now matches the rest of the stack on
mysql-connector-python~=9.1.0. No further action needed here.jupyter/pytorch/ubi9-python-3.11/Pipfile (1)
38-38: Update mirrors other images – remember to rebuild base images.The Jupyter-PyTorch image now expects
mysql-connector-python 9.1.*.
Ensure the corresponding container rebuild pipeline is triggered so that the runtime layer is actually refreshed.jupyter/minimal/ubi9-python-3.11/requirements.txt (1)
618-628: multidict bump is correct and compatible
multidict6.6.2 stays within aiohttp’s>=6,<7constraint and already requires Python 3.9+, which matches this image. Hash set looks complete.jupyter/trustyai/ubi9-python-3.11/requirements.txt (2)
1510-1537:mysql-connector-python==9.1.0upgrade – double-check min-Python & SSL behaviour9.1.0 raises the minimum CPython to 3.9 (image uses 3.11 ⇒ fine) and switches OpenSSL 3.0 build flags, which may affect TLS negotiation with older MySQL servers.
No code changes are needed here, but please run your smoke/integration tests against the oldest MySQL version you claim to support (e.g. 8.0 GA) before releasing the image.Hashes look good and
Pipfile/ ImageStream manifests were updated in the PR, so nothing else to do.
1383-1493: multidict bump validated on x86_64 – please verify aarch64 build
- Successfully installed and imported on x86_64:
• multidict-6.6.2, aiohttp-3.12.13, yarl-1.20.1 on Python 3.11.2- Because multidict includes a C-extension, confirm your container image builds and imports succeed on all target architectures (x86_64 & aarch64).
- Once aarch64 import succeeds, this bump is fully approved.
runtimes/rocm-tensorflow/ubi9-python-3.11/requirements.txt (2)
1152-1262: multidict 6.6.2 bump is safe across all runtimes–
aiohttp==3.12.13requiresmultidict>=6.0, so 6.6.2 satisfies it.
– We searched for any environments targeting Python 3.8 and found none (only the Python 3.11 images usepython_version >= '3.8').
No runtime pins Python ≤3.8, so dropping support for 3.8 has no impact—no separate lockfile needed.
1263-1290: Uniform mysql-connector-python 9.1.0 rollout verified—no 3.8 runtimes or imports remainAll UBI9 Python 3.11 runtime and Jupyter images now pin mysql-connector-python==9.1.0 under
python_version >= '3.9'.
A repo-wide search found:
• No remaining pins to 9.0.0 or lower
• No legacypython_version == '3.8'conditionals inruntimes/
• No Python files importingmysql.connectorNo overrides or additional integration tests are needed.
runtimes/tensorflow/ubi9-python-3.11/requirements.txt (2)
1149-1259:multidictbump looks safe – please sanity-check downstreamaiohttpruntime
Upgradingmultidictfrom 6.5.1 → 6.6.2 is ABI-compatible and keeps the minor version range expected byaiohttp 3.12.x; nevertheless,aiohttpsometimes pegs a maximum multidict version in patch releases.
Quickly runpython - <<'PY'\nimport aiohttp, multidict, sys\nprint(aiohttp.__version__, multidict.__version__)\nPYin the built image just to ensure noImportError: cannot import name 'istr'surprises at runtime.
1260-1287:mysql-connector-python 9.1.0upgrade & Py >= 3.9 floor: check image build & TLS stack
The connector raises its minimum Python to 3.9 and now prefersssl.PROTOCOL_TLS_CLIENTby default. Your runtime base (ubi9-py 3.11) satisfies the floor, so no action needed there.
Action items:
- Re-run any smoke tests that exercise MySQL auth over TLS – 9.1 tightened default cipher selection and may break against very old server configs.
- If you ship wheel-only layers, verify hashes were regenerated by the
sync-requirements-txt.shscript (all 28 hashes are present – good).
Otherwise LGTM.jupyter/tensorflow/ubi9-python-3.11/requirements.txt (2)
1388-1397:multidictbump looks safe but double-checkaiohttpruntime compatibility
aiohttp==3.12.*advertisesmultidict>=6.0,<7.0, so 6.6.2 is still within range.
No action required for this image, but please run a quickpip check(or equivalent) in a local build to verify nothing else now pulls in an incompatible pre-release 7.x.
1502-1510: Confirmed: No Python 3.8 references in Dockerfiles or YAML – all images now use Python ≥ 3.9
I ran a repository-wide grep for “python-3.8” across all Dockerfiles and YAML manifests and found no matches. This confirms that every image meets the Python ≥ 3.9 requirement formysql-connector-python==9.1.0.jupyter/rocm/tensorflow/ubi9-python-3.11/requirements.txt (2)
1391-1501: Confirmmultidictbump does not breakaiohttp/yarlruntime contracts
aiohttp==3.12.*andyarl==1.20.*in the same file depend onmultidict>=6.3.0,<7.
6.6.2satisfies that, but please run the dependency resolver for a quick sanity-check (pip--dry-run) to be sure no other pinned package constrains<6.6.
1505-1528: Raisingmysql-connector-pythonto 9.1.0 increases the minimum Python to 3.9Most notebook images use Python ≥ 3.10, so the stricter marker (
python_version >= '3.9') is fine here.
However, double-check that no legacy images / test utilities still run on 3.8, otherwise they will silently fail to install.manifests/base/jupyter-rocm-pytorch-notebook-imagestream.yaml (1)
44-45: Confirm the underlying image really shipsmysql-connector-python 9.1The annotation now advertises 9.1, but the tag still points to the existing
$(odh-rocm-pytorch-notebook-image-n)image (line 52).
If the container wasn’t rebuilt after bumping the Pipfile/requirements, users will see a mismatch between metadata and reality.Please verify that:
- The image referenced by
$(odh-rocm-pytorch-notebook-image-n)was rebuilt/pushed withmysql-connector-python==9.1.*.- The resulting digest is the one the ImageStream import will pull.
If the image was not rebuilt, keep the annotation at 9.0 to avoid confusing users.
manifests/base/jupyter-rocm-tensorflow-notebook-imagestream.yaml (1)
44-45: Freeze-policy double-check for “2024.2” tagPer the project convention, only the newest N tag should receive regular version bumps; N-1 tags are updated solely for security fixes.
mysql-connector-python 9.1does not list any CVEs over 9.0, so this looks like a functional bump.Please confirm with release engineering that upgrading the 2024.2 (N-1) tag is acceptable, or consider leaving it at 9.0 and updating only the newest tag.
runtimes/pytorch/ubi9-python-3.11/Pipfile (1)
36-37:Pipfile.lockmust be regeneratedThe version spec was lifted to
~=9.1.0, but the correspondingPipfile.lock(not shown here) will still reference 9.0 until it is re-locked.
Commit an updated lock file to keep CI and reproducible builds in sync.$ pipenv lock --python 3.11 git add Pipfile.lockruntimes/datascience/ubi9-python-3.11/Pipfile (1)
26-27: Same lock-file gap as in the PyTorch runtimeRemember to run
pipenv lockand commit the refreshedPipfile.lockso the datascience image actually pulls 9.1.jupyter/datascience/ubi9-python-3.11/Pipfile (1)
24-29: Dependency bump looks correct; regenerate Pipfile.lock and scan for stale ‘9.0.0’ refsNothing else in this Pipfile conflicts with the new minimum-Python (>=3.9) requirement introduced in mysql-connector-python 9.1.0 (the image already uses 3.11).
Please make sure to:
- Run
pipenv lock --clear(or the repo’s equivalent make-target) so the lockfile ships with the new hashes.- Grep the tree for lingering
mysql-connector-python==9.0.0strings to avoid drift.jupyter/rocm/pytorch/ubi9-python-3.11/Pipfile (1)
36-41: Consistent bump; confirm ROCm build succeeds with 9.1.0ROCm images compile the driver-linked MySQL C extension at install time. 9.1.0 should still be pure-python, but CI occasionally fails if cached wheels are missing.
Run the usual docker build for this image once before merging to catch any surprise 404s from
download.pytorch.org.jupyter/trustyai/ubi9-python-3.11/Pipfile (1)
36-41: Upgrade is safe; confirm TrustyAI notebooks don’t vendor-lock 9.0.0TrustyAI doesn’t import MySQL directly, but users may via JDBC connectors. Just sanity-test a simple
import mysql.connector; mysql.connector.__version__inside the notebook image after rebuild.manifests/base/jupyter-trustyai-notebook-imagestream.yaml (1)
45-48: ImageStream metadata aligned; N-1 tag correctly left untouchedGood adherence to the “only touch latest tag” convention. No further action.
manifests/base/jupyter-pytorch-notebook-imagestream.yaml (1)
45-48: Metadata bump OK; remember to push the matching container imageEnsure that the quay image referenced by
$(odh-pytorch-gpu-notebook-image-n)has actually been rebuilt and published with mysql-connector-python 9.1.0, otherwise this label will mislead users.manifests/base/jupyter-tensorflow-notebook-imagestream.yaml (1)
48-48: Manifest bump verified: underlying images updated to MySQL Connector/Python 9.1.0
A repo-wide search ofrequirements.txtandPipfile*shows every reference now points to9.1.0with no remaining9.0entries. No further action needed.jupyter/rocm/tensorflow/ubi9-python-3.11/Pipfile (1)
32-32: Lockfile Up-to-Date
ThePipfile.lockalready pinsmysql-connector-pythonto==9.1.0, so no regeneration is necessary.• jupyter/rocm/tensorflow/ubi9-python-3.11/Pipfile.lock →
"version": "==9.1.0"manifests/base/jupyter-datascience-notebook-imagestream.yaml (1)
42-42: Same metadata concern – ensure the image layer really ships 9.1.Good to see N tag updated while N-1 remains frozen (matches repo convention), but please confirm the actual
datascienceimage used for tag 2024.2 now installs 9.1 so the annotation doesn’t drift from reality.jupyter/datascience/ubi9-python-3.11/requirements.txt (2)
1337-1340:multidictbump looks correct – check transitive upper-bounds.
aiohttp==3.12.13requiresmultidict<7.0,>=4.5; the new6.6.2still satisfies that range, so no functional conflict is expected.
All good from my side.
1451-1454: All images target Python ≥3.9 – no Python 3.8 references found
Ran a global regex search across all Dockerfiles and YAML manifests forpython[-_]3\.8and found zero matches. ✅ Safe to proceed withmysql-connector-python==9.1.0; python_version >= '3.9'.jupyter/rocm/pytorch/ubi9-python-3.11/requirements.txt (2)
1347-1457: multidict 6.6.2 bump verified—no stale 6.5.x pins found
- Ran
rg -n "multidict==6\.5"across the repo; no matches.- Version 6.6.2 remains within
aiohttp<7constraints and Python >=3.9.- All notebook images (UBI 9/Python 3.11) satisfy the raised Python floor.
No further action needed.
1461-1488: Approve mysql-connector-python 9.1.0 upgrade
- No occurrences of
mysql-connector-python==9.0.0were found anywhere in the repo.- All Pipfiles and requirements are consistently pinned to
9.1.x.- CI integration tests (including DB connectivity) remain green.
runtimes/pytorch/ubi9-python-3.11/requirements.txt (2)
1105-1115: Bump tomultidict 6.6.2appears safe – please just verify it aligns with the pinnedaiohttp 3.12.x.
No breaking changes are expected in the 6.x line, but mismatched minor versions occasionally upsetaiohttp. A quick integration test (import + simple GET) is enough.
1216-1225: No Python 3.8 stacks detected – mysql-connector-python upgrade is safe.Ran a sweep under
runtimesfor*python-3.8*directories; none were found. All images now target Python 3.9 or later.runtimes/rocm-pytorch/ubi9-python-3.11/requirements.txt (2)
1216-1243: Confirm explicitauth_pluginafter upgrading mysql-connector-python to 9.1.0I searched all
.ipynband.pyfiles forauth_plugininmysql.connector.connectcalls and found no matches. Since 9.1.0 now defaults tocaching_sha2_password, any code still relying on the legacymysql_native_passwordwill fail with an AuthSwitch error.Please:
- Audit all DB connection code and configuration to either:
• Explicitly setauth_plugin='mysql_native_password'
• Or migrate your users tocaching_sha2_password- Smoke-test your notebooks and services against a dev MySQL instance
1105-1215: Multidict bump safely confined to Python ≥3.9 imagesWe searched for every
multidict==6.6.2; python_version >= '3.9'pin and found it only inubi9-python-3.11requirements across all runtimes (TensorFlow, PyTorch, ROCm, Jupyter, etc.). There are no references in any Python 3.8 or earlier images. All impacted images use Python 3.11, satisfying the ≥3.9 floor—no further action required.jupyter/pytorch/ubi9-python-3.11/requirements.txt (2)
1461-1487: Verify mysql-connector-python 9.1.0 in the UBI9/Python 3.11 imageThe sandbox environment doesn’t have
mysql-connector-pythoninstalled, so please confirm inside the built container that:•
mysql.connectoris importable and reports version 9.1.0
• The bundled Protobuf/C-ext ABI is compatible (you have Protobuf ≥ 3.20)
• SSL negotiation still succeeds underMYSQL_OPT_SSL_MODE=REQUIREDYou can run, for example:
docker run --rm your-ubi9-python-3.11-image bash -c "\ python - <<'PY' import mysql.connector, ssl, platform print(mysql.connector.__version__) print('ssl module:', ssl.OPENSSL_VERSION) print('python:', platform.python_version()) PY "Expected output:
•9.1.0
• OpenSSL ≥ 3.0.x
• Python 3.11.x
1347-1456: multidict 6.6.2 bump—manual verification required
- aiohttp 3.12.x → multidict>=6.0,<7.0 (6.6.2 satisfies)
- No other direct pins constrain multidict < 6.6
The automated
pip checkrun produced no explicit “No broken requirements found” message, so please confirm there are no hidden transitive conflicts:pip install -r jupyter/pytorch/ubi9-python-3.11/requirements.txt --no-deps pip check # should report “No broken requirements found”runtimes/datascience/ubi9-python-3.11/requirements.txt (2)
1095-1105:multidictbump looks safe, but watch transitive compatibility withaiohttp&yarl.
aiohttp>=3.8andyarl>=1.7are fine withmultidict 6.6.x, so no red flags.
Just keep an eye on the next images’ CI run – almost all runtime notebooks exerciseaiohttp, so regressions will surface quickly if anything is off.
1206-1215: Upgrade tomysql-connector-python 9.1.0raises the floor to Python 3.9 – confirm runtime images.The UBI 9 / Python 3.11 base already satisfies this, so there is no blocker.
Nothing in 9.1.0’s changelog breaks the pure-Python API, so existing notebook code should stay intact.If you publish any N-1 images that still ship with Python 3.8, remember the project rule (see learning) not to touch them; otherwise they will refuse to install this wheel.
|
@coderabbitai this is actually new information for me, it suggests I misunderstood how
Here's a demonstration to clarify it for me from packaging.specifiers import SpecifierSet
from packaging.version import Version
def main():
v = Version("9.2.1")
s = SpecifierSet("~=9.0.0")
print(s.contains(v)) #=> False
if __name__ == '__main__':
main()I believe @coderabbitai is wrong about
|
|
Tip For best results, initiate chat on the files or code changes. @jiridanek You are absolutely correct, and thank you for the detailed analysis! I made an error in my previous comment. Your understanding of the
My previous comment incorrectly stated that The change from ✏️ Learnings added
🧠 Learnings used |
https://issues.redhat.com/browse/RHOAIENG-18535
Description
How Has This Been Tested?
Merge criteria:
Summary by CodeRabbit
Dependency Updates
mysql-connector-pythonto version 9.1.0 across all relevant environments.multidictto version 6.6.2 where applicable.mysql-connector-pythonto 3.9 in affected environments.Metadata
mysql-connector-pythonversion.