v0.3.14 release #50
Merged
v0.3.14 release #50
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ments-for-table-class-and-tables-helper Updated docstrings in _tables
…e-not-initialized-in-local-run-mode Inject catalogs in local runtime environment
* fix: Fix type mappings, format code * feat: Handle nested types correctly and set ids * chore: Fix formatting * chore: Add how to run tests * feat: Add tests for types
Updated implementations ensure that we equally check runs to detect failures part way through executions. Likewise, we add timeouts while talking to the Tower API in case there are some operational problems on that side of things.
Thanks @copilot for the recommendation!
Thanks @copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
…s-to-take-a-list-of-runs-or-a-single-run Add a simple `wait_for_runs` function
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR ultimately updates the Tower runtime’s API‐client behavior and test coverage, adds catalog injection in the local runtime environment, and enhances error handling and documentation across several modules.
- Updates test cases to validate new run-waiting behaviors
- Introduces catalog fetching and injection in the CLI runtime
- Enhances documentation and API interfaces in both Python and Rust components
Reviewed Changes
Copilot reviewed 20 out of 20 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
| tests/tower/test_client.py | Updated test fixtures and added tests for wait_for_run and wait_for_runs behavior |
| src/tower/utils/pyarrow.py | Refactored type conversion with new field ID management |
| src/tower/exceptions.py | Added new exception types for improved error clarity |
| src/tower/_tables.py | Updated documentation and method signatures for table operations |
| src/tower/_client.py | Introduced wait_for_runs, enhanced polling logic, and detailed argument documentation |
| src/tower/init.py | Exported wait_for_runs for public API |
| pyproject.toml | Version remains outdated relative to the PR title |
| crates/tower-cmd/** | Added catalog fetching/injection and improved error handling in CLI commands |
| crates/crypto/** | Updated encryption/decryption functions to return Results and use robust error handling |
| README.md | Extended test instructions for better developer guidance |
| Cargo.toml | Minor dependency updates; version number still reflects previous release |
Comments suppressed due to low confidence (1)
pyproject.toml:7
- The project version in pyproject.toml still shows '0.3.13' despite the PR title indicating a v0.3.14 release. Update the version number for consistency.
version = "0.3.13"
tests/tower/test_client.py
Outdated
| os.environ["TOWER_URL"] = "https://api.example.com" | ||
| os.environ["TOWER_API_KEY"] = "abc123" | ||
| tower = mock_api_config | ||
| run = create_run_object(number=run_number, status="crashed") |
There was a problem hiding this comment.
The test initializes a run object with a 'crashed' status while the mocked API responses simulate a transition from 'pending' to 'exited'. Consider initializing the run with 'pending' for clarity and consistency with the expected workflow.
Suggested change
| run = create_run_object(number=run_number, status="crashed") | |
| run = create_run_object(number=run_number, status="pending") |
src/tower/_client.py
Outdated
| # We need to re-add this run to the list so we check it again | ||
| # in the future. We add it to the back since we took it off the | ||
| # front, effectively moving to the next run. | ||
| awaiting_runs.append(run) |
There was a problem hiding this comment.
[nitpick] When polling run status, consider appending the updated run object (e.g., the 'desc' returned from _check_run_status) instead of the original 'run', to ensure subsequent checks reflect the latest state.
Suggested change
| awaiting_runs.append(run) | |
| awaiting_runs.append(desc) |
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR prepares the v0.3.14 release by injecting catalogs into the local runtime, updating the polling logic for run completion (including a new wait_for_runs function), enhancing documentation across the codebase, and bumping the version.
- Inject catalogs into the local runtime environment
- Update wait_for_run behavior and add wait_for_runs for improved run status detection
- Update documentation and version numbers across modules
Reviewed Changes
Copilot reviewed 21 out of 21 changed files in this pull request and generated no comments.
Show a summary per file
| File | Description |
|---|---|
| tests/tower/test_client.py | Updated tests for new fixtures and run-waiting behavior |
| src/tower/utils/pyarrow.py | Adjusted conversion functions and updated nested type conversion logic |
| src/tower/exceptions.py | Added new exception classes |
| src/tower/_tables.py | Expanded docstrings and improved schema/table methods documentation |
| src/tower/_client.py | Refactored run polling functions and added wait_for_runs |
| crates/tower-cmd/src/(secrets.rs, run.rs, lib.rs, error.rs, api.rs) | Updated secret encryption/decryption and runtime command error handling changes |
| crates/crypto | Updated cryptography functions to use AES and improved error handling |
| pyproject.toml & Cargo.toml | Bumped version numbers to v0.3.14 |
Comments suppressed due to low confidence (2)
src/tower/_client.py:158
- The variable 'WAIT_TIMEOUT' is used in wait_for_run() but is not defined in this module. Please define or import it as a constant to prevent runtime errors.
time.sleep(WAIT_TIMEOUT)
src/tower/_client.py:235
- The same undefined 'WAIT_TIMEOUT' is used in wait_for_runs(). Please ensure this constant is declared or imported for consistent behavior across run polling functions.
time.sleep(WAIT_TIMEOUT)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
wait_for_runand addwait_for_runsto detect failure