fix: Prevent execution of conda in apptainer when not explicitly requested in software deployment method#3388
Conversation
…ot requested in the software deployment method.
📝 WalkthroughWalkthroughThe changes update the core logic in handling conda environments and container deployments. In the Changes
Sequence Diagram(s)sequenceDiagram
participant J as Job
participant C as CondaEnv Checker
participant L as LogInfo Constructor
J->>+J: get_log_error_info()
alt DeploymentMethod is CONDA and conda_env exists
J->>+C: Retrieve conda_env.address
C-->>-J: Return conda_env.address
else
J-->>J: Set conda_env to None
end
J->>L: Include container_img in log data
L-->>J: Return error info dictionary
sequenceDiagram
participant T as Test (test_issue_3202)
participant S as Workflow (Snakefile)
participant R as Rule Executor
T->>+S: Invoke run() with DeploymentMethod.APPTAINER
S->>R: Execute rule (run_in_container_and_conda)
R-->>S: Write "foo" to output.txt
S-->>T: Validate container workflow result
T->>+S: Invoke run() with DeploymentMethod.CONDA
S->>R: Execute rule (run_in_container_and_conda)
R-->>S: Write "foo" to output.txt
S-->>T: Validate conda workflow result
Possibly related PRs
Suggested reviewers
📜 Recent review detailsConfiguration used: CodeRabbit UI ⛔ Files ignored due to path filters (1)
📒 Files selected for processing (9)
✅ Files skipped from review due to trivial changes (1)
🧰 Additional context used📓 Path-based instructions (1)`**/*.py`: Do not try to improve formatting. Do not suggest ...
🪛 Ruff (0.8.2)snakemake/utils.py132-134: Within an (B904) 168-170: Within an (B904) 206-208: Within an (B904) 224-224: Within an (B904) ⏰ Context from checks skipped due to timeout of 90000ms (30)
🔇 Additional comments (20)
✨ Finishing Touches
🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
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 (
|
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (3)
snakemake/jobs.py (1)
1100-1113: Good fix for preventing conda instantiation in containers.This change properly checks if conda deployment is enabled before accessing the conda environment address, preventing the 'conda info --json' error when using a container with a rule that also includes a conda directive but isn't using conda for deployment.
However, there's a small typo in the variable name
conda_env_adress(should beconda_env_address).- conda_env_adress = ( + conda_env_address = (tests/test_issue_3202/test-env.yaml (1)
1-6: Good test environment configuration.This conda environment configuration specifies appropriate dependencies for testing the issue fix. It correctly defines the channels and required packages with version constraints.
Consider adding a newline at the end of the file to follow YAML best practices.
- melt ==1.0.3 - python <3.10 +🧰 Tools
🪛 YAMLlint (1.35.1)
[error] 6-6: no new line character at the end of file
(new-line-at-end-of-file)
tests/test_issue_3202/Snakefile (1)
8-8: Fix typo in comment.There's a spelling error in the comment.
-# Test that rule can be run idenpently in conda and apptainer +# Test that rule can be run independently in conda and apptainer
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (6)
snakemake/jobs.py(1 hunks)snakemake/persistence.py(2 hunks)tests/test_issue_3202/Snakefile(1 hunks)tests/test_issue_3202/expected-results/output.txt(1 hunks)tests/test_issue_3202/test-env.yaml(1 hunks)tests/tests_using_conda.py(1 hunks)
🧰 Additional context used
📓 Path-based instructions (1)
`**/*.py`: Do not try to improve formatting. Do not suggest ...
**/*.py: Do not try to improve formatting.
Do not suggest type annotations for functions that are defined inside of functions or methods.
Do not suggest type annotation of theselfargument of methods.
Do not suggest type annotation of theclsargument of classmethods.
Do not suggest return type annotation if a function or method does not contain areturnstatement.
tests/tests_using_conda.pysnakemake/persistence.pysnakemake/jobs.py
🪛 YAMLlint (1.35.1)
tests/test_issue_3202/test-env.yaml
[error] 6-6: no new line character at the end of file
(new-line-at-end-of-file)
🪛 GitHub Actions: CI
tests/tests_using_conda.py
[error] 1-1: Black formatting check failed. 1 file would be reformatted. Please run 'black' to fix code style issues in this file.
🔇 Additional comments (6)
snakemake/persistence.py (2)
33-33: Good addition of necessary import.Adding the import for
DeploymentMethodto support the conditional logic in the_software_stack_hashmethod.
522-532: Excellent fix to prevent conda instantiation when not explicitly requested.This change fixes the issue described in #3202 by ensuring that the MD5 hash is only updated for conda environments when conda is explicitly specified as a deployment method. Similarly, it only updates the hash for Apptainer when it's explicitly requested. This prevents the unnecessary instantiation of the
Condaclass when a rule includes both conda and container directives but conda isn't being used.snakemake/jobs.py (1)
1121-1122: Consistent handling of container image.The code now consistently includes the container image field regardless of deployment method, which is a good practice.
tests/test_issue_3202/expected-results/output.txt (1)
1-1: Appropriate test output file for issue #3202.This expected output file is used to verify that the rule with both conda and container directives runs correctly.
tests/test_issue_3202/Snakefile (2)
1-7: LGTM: Clear setup for test case.The configuration correctly sets up bash as the shell executable and defines the conda environment path.
9-17: LGTM: Well-structured test rule with both conda and container directives.This rule effectively demonstrates the scenario from issue #3202 by including both conda and container directives in a single rule. The simple shell command ensures the test is focused specifically on the deployment method conflict resolution.
|
There was a problem hiding this comment.
Caution
Inline review comments failed to post. This is likely due to GitHub's limits when posting large numbers of comments. If you are seeing this consistently it is likely a permissions issue. Please check "Moderation" -> "Code review limits" under your organization settings.
Actionable comments posted: 1
🧹 Nitpick comments (4)
snakemake/utils.py (4)
111-117: Consider adding a docstring for_validate_record
Providing a brief explanation of this function’s logic and parameter expectations (e.g., thatrecordshould be a dictionary) can aid maintainability and readability.
145-149: Consolidate return paths
Multiplereturn Falsestatements can make the flow less obvious. Consider combining them or restructuring for improved readability.if condition_A: return False if condition_B: return False return True
168-170: Raise from the original exception
Useraise WorkflowError(...) from eto better preserve the traceback chain.- raise WorkflowError( - f"Error validating row {i} of data frame.", e - ) + raise WorkflowError( + f"Error validating row {i} of data frame." + ) from e🧰 Tools
🪛 Ruff (0.8.2)
168-170: Within an
exceptclause, raise exceptions withraise ... from errorraise ... from Noneto distinguish them from errors in exception handling(B904)
206-208: Raise from the original exception
Same rationale here: attach the original exception to keep the traceback intact.- raise WorkflowError( - f"Error validating row {i} of data frame.", e - ) + raise WorkflowError( + f"Error validating row {i} of data frame." + ) from e🧰 Tools
🪛 Ruff (0.8.2)
206-208: Within an
exceptclause, raise exceptions withraise ... from errorraise ... from Noneto distinguish them from errors in exception handling(B904)
🛑 Comments failed to post (1)
docs/snakefiles/configuration.rst (1)
115-116: 💡 Verification agent
🧩 Analysis chain
Documentation update aligns with functionality changes but lacks connection to PR objective.
The documentation has been updated to reflect that validation now supports polars DataFrames and LazyFrames, which is good for user awareness. However, these changes don't seem directly related to the PR's objective of preventing conda execution in apptainer.
🌐 Web query:
What is Polars and how does it compare to Pandas for data processing?💡 Result:
Polars is a high-performance DataFrame library designed for fast data processing in Python, built in Rust and optimized for parallel computing. It leverages Apache Arrow's memory model for efficient columnar data handling, enabling speed improvements of 5–10x over pandas for common operations, with benchmarks showing up to 40x faster joins and 8–25x faster aggregations on large datasets[3][6][12]. Here's how they compare:
Key Differences
Feature Polars Pandas Execution Model Eager + lazy (with query optimizer) Eager only Core Language Rust Python/Cython Memory Management Apache Arrow (columnar) NumPy arrays (row-oriented) Parallelism Full CPU core utilization Single-threaded by default Memory Efficiency 2–4x dataset size in RAM required 5–10x dataset size in RAM required API Style Expressive method chaining Mix of methods + apply/lambdas Performance Highlights
Data Ingestion
- Reads CSV files 11x faster than pandas (1.25s vs 14.14s for 5GB datasets)[12]
- Handles joins 40x faster in some benchmarks[3][16]
Memory Efficiency
Polars consumes 63–87% less energy for large-scale operations while processing data 8x faster[10]Scalability
- Processes datasets up to 10x larger than pandas on the same hardware[4][8]
- Maintains performance with 100M+ row datasets where pandas fails[16]
When to Choose Polars
- Big data processing (1GB–100GB datasets)
- Complex ETL pipelines requiring parallel execution
- Memory-constrained environments
- Operations benefiting from query optimization (filter → groupby patterns)[6]
When to Prefer Pandas
- Small datasets (<1M rows) for exploratory analysis
- Tight integration with ML libraries (scikit-learn, PyTorch)
- Legacy codebases using pandas-specific features
- Interactive workflows requiring immediate feedback[2][6]
Ecosystem Considerations
While Polars excels at raw performance:
- Interoperability: Convert to/from pandas with
.to_pandas()andfrom_pandas()[9]- Visualization: Requires conversion to pandas for integration with Matplotlib/Seaborn[6]
- GPU Support: New RAPIDS integration enables 13x speedups on NVIDIA GPUs[11]
For most modern data engineering tasks, Polars provides substantial advantages in speed and memory efficiency while maintaining pandas-like syntax. However, pandas remains preferable for small-scale analytics and ML integration scenarios[4][6][16].
Citations:
- 1: https://www.datacamp.com/blog/an-introduction-to-polars-python-s-tool-for-large-scale-data-analysis
- 2: https://www.kdnuggets.com/pandas-vs-polars-a-comparative-analysis-of-python-dataframe-libraries
- 3: https://stuffbyyuki.com/pandas-vs-polars-speed-comparison/
- 4: https://deepnote.com/guides/data-science-and-analytics/pandas-vs-polars
- 5: https://realpython.com/polars-python/
- 6: https://blog.jetbrains.com/pycharm/2024/07/polars-vs-pandas/
- 7: https://towardsdatascience.com/high-performance-data-processing-pandas-2-vs-polars-a-vcpu-perspective-e922d3064f4e/
- 8: https://pola.rs
- 9: https://docs.pola.rs/user-guide/migration/pandas/
- 10: https://pola.rs/posts/benchmark-energy-performance/
- 11: https://developer.nvidia.com/blog/nvidia-cuda-x-now-accelerates-the-polars-data-processing-library/
- 12: https://towardsdatascience.com/polars-vs-pandas-an-independent-speed-comparison/
- 13: https://github.com/prrao87/duckdb-study
- 14: https://github.com/pola-rs/polars
- 15: https://discuss.python.org/t/future-of-pandas-vs-polars/54754
- 16: https://pola.rs/posts/benchmarks/
- 17: https://kevinheavey.github.io/modern-polars/
- 18: https://www.datacamp.com/tutorial/high-performance-data-manipulation-in-python-pandas2-vs-polars
- 19: https://www.datacamp.com/tutorial/benchmarking-high-performance-pandas-alternatives
- 20: https://www.statology.org/pandas-vs-polars-performance-benchmarks-for-common-data-operations/
Action Required: Link Documentation Update to PR Objective
- The updated documentation accurately reflects the new validation support for Polars DataFrame and LazyFrame types.
- However, it does not address the PR’s primary objective of preventing conda execution in Apptainer.
- Please clarify in the docs whether these changes are intended to be part of a broader initiative (including the Apptainer context) or if they should be documented separately.
🤖 I have created a release *beep* *boop* --- ## [9.0.0](v8.30.0...v9.0.0) (2025-03-14) ### ⚠ BREAKING CHANGES * Logging refactor & add LoggerPluginInterface ([#3107](#3107)) ### Features * [#3412](#3412) - keep shadow folder of failed job if --keep-incomplete flag is set. ([#3430](#3430)) ([22978c3](22978c3)) * add flag --report-after-run to automatically generate the report after a successfull workflow run ([#3428](#3428)) ([b0a7f03](b0a7f03)) * add flatten function to IO utils ([#3424](#3424)) ([67fa392](67fa392)) * add helper functions to parse input files ([#2918](#2918)) ([63e45a7](63e45a7)) * Add option to print redacted file names ([#3089](#3089)) ([ba4d264](ba4d264)) * add support for validation of polars dataframe and lazyframe ([#3262](#3262)) ([c7473a6](c7473a6)) * added support for rendering dag with mermaid js ([#3409](#3409)) ([7bf8381](7bf8381)) * adding --replace-workflow-config to fully replace workflow configs (from config: directive) with --configfile, instead of merging them ([#3381](#3381)) ([47504a0](47504a0)) * Dynamic module name ([#3401](#3401)) ([024dc32](024dc32)) * Enable saving and reloading IOCache object ([#3386](#3386)) ([c935953](c935953)) * files added in rule params with workflow.source_path will be available in used containers ([#3385](#3385)) ([a6e45bf](a6e45bf)) * Fix keep_local in storage directive and more freedom over remote retrieval behaviour ([#3410](#3410)) ([67b4739](67b4739)) * inherit parameters of use rule and extend/replace individual items them when using 'with' directive ([#3365](#3365)) ([93e4b92](93e4b92)) * Logging refactor & add LoggerPluginInterface ([#3107](#3107)) ([86f1d6e](86f1d6e)) * Maximal file size for checksums ([#3368](#3368)) ([b039f8a](b039f8a)) * Modernize package configuration using Pixi ([#3369](#3369)) ([77992d8](77992d8)) * multiext support for named input/output ([#3372](#3372)) ([05e1378](05e1378)) * optionally auto-group jobs via temp files in case of remote execution ([#3378](#3378)) ([cc9bba2](cc9bba2)) ### Bug Fixes * `--delete-all-output` ignores `--dry-run` ([#3265](#3265)) ([23fef82](23fef82)) * 3342 faster touch runs and warning messages for non-existing files ([#3398](#3398)) ([cd9c3c3](cd9c3c3)) * add default value to max-jobs-per-timespan ([#3043](#3043)) ([2959abe](2959abe)) * checkpoints inside modules are overwritten ([#3359](#3359)) ([fba3ac7](fba3ac7)) * Convert Path to IOFile ([#3405](#3405)) ([c58684c](c58684c)) * Do not perform storage object cleanup with --keep-storage-local-copies set ([#3358](#3358)) ([9a6d14b](9a6d14b)) * edgecases of source deployment in case of remote execution ([#3396](#3396)) ([5da13be](5da13be)) * enhance error message formatting for strict DAG-building mode ([#3376](#3376)) ([a1c39ee](a1c39ee)) * fix bug in checkpoint handling that led to exceptions in case checkpoint output was missing upon rerun ([#3423](#3423)) ([8cf4a2f](8cf4a2f)) * force check all required outputs ([#3341](#3341)) ([495a4e7](495a4e7)) * group job formatting ([#3442](#3442)) ([f0b10a3](f0b10a3)) * in remote jobs, upload storage in topological order such that modification dates are preserved (e.g. in case of group jobs) ([#3377](#3377)) ([eace08f](eace08f)) * only skip eval when resource depends on input ([#3374](#3374)) ([4574c92](4574c92)) * Prevent execution of conda in apptainer when not explicitly requested in software deployment method ([#3388](#3388)) ([c43c5c0](c43c5c0)) * print filenames with quotes around them in RuleException ([#3269](#3269)) ([6baeda5](6baeda5)) * Re-evaluation of free resources ([#3399](#3399)) ([6371293](6371293)) * ReadTheDocs layout issue due to src directory change ([#3419](#3419)) ([695b127](695b127)) * robustly escaping quotes in generated bash scripts (v2) ([#3297](#3297)) ([#3389](#3389)) ([58720bd](58720bd)) * Show apptainer image URL in snakemake report ([#3407](#3407)) ([45f0450](45f0450)) * Update ReadTheDocs configuration for documentation build to use Pixi ([#3433](#3433)) ([3f227a6](3f227a6)) ### Documentation * Add pixi setup instructions to general use tutorial ([#3382](#3382)) ([115e81b](115e81b)) * fix contribution section heading levels, fix docs testing setup order ([#3360](#3360)) ([051dc53](051dc53)) * fix link to github.com/snakemake/poetry-snakemake-plugin ([#3436](#3436)) ([ec6d97c](ec6d97c)) * fix quoting ([#3394](#3394)) ([b40f599](b40f599)) * fix rerun-triggers default ([#3403](#3403)) ([4430e23](4430e23)) * fix typo 'safe' -> 'save' ([#3384](#3384)) ([7755861](7755861)) * mention code formatting in the contribution section ([#3431](#3431)) ([e8682b7](e8682b7)) * remove duplicated 'functions'. ([#3356](#3356)) ([7c595db](7c595db)) * update broken links documentation ([#3437](#3437)) ([e3d0d88](e3d0d88)) * Updating contributing guidelines with new pixi dev setup ([#3415](#3415)) ([8e95a12](8e95a12)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). Co-authored-by: snakemake-bot <snakemake-bot-admin@googlegroups.com>
…ested in software deployment method (snakemake#3388) This is a quick fix for the issue described in snakemake#3202. From the original issue: > Snakemake crashes with a 'conda info --json' returned non-zero exit status 127 when a rule contains both conda and container directives. This behaviour was caused by the retrieval in `_software_stack_hash()` within the `Persistence` class. If a snakemake rule specified both a container and a conda file, this method would always try to get a hash value of the conda file, resulting in an instantiation of the `Conda` class using the container as the base image (ad-hoc combination). This happened even when conda was not specified with `--sdm`. This also happened in `get_log_error_info' of `jobs.py'. This PR fixes this issue and ensures that rules can be executed wither with conda, apptainer or the ad-hoc combination. ### QC * [ x] The PR contains a test case for the changes or the changes are already covered by an existing test case. * [ x] The documentation (`docs/`) is updated to reflect the changes or this is not necessary (e.g. if the change does neither modify the language nor the behavior or functionalities of Snakemake). <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **Bug Fixes** - Enhanced handling of environment details to prevent errors when specific deployment modes aren’t active. - Improved logic for updating environment-related configurations. - **New Features** - Introduced a workflow that supports execution in both containerized and Conda environments. - Added a dependency configuration file for consistent package management. - New output file created with expected results from the workflow. - Expanded validation capabilities for data structures, including support for both Pandas and Polars. - **Tests** - Implemented new tests to verify proper execution across varying deployment methods. - Enhanced validation tests for sample data against specified schemas. <!-- end of auto-generated comment: release notes by coderabbit.ai -->
🤖 I have created a release *beep* *boop* --- ## [9.0.0](snakemake/snakemake@v8.30.0...v9.0.0) (2025-03-14) ### ⚠ BREAKING CHANGES * Logging refactor & add LoggerPluginInterface ([snakemake#3107](snakemake#3107)) ### Features * [snakemake#3412](snakemake#3412) - keep shadow folder of failed job if --keep-incomplete flag is set. ([snakemake#3430](snakemake#3430)) ([22978c3](snakemake@22978c3)) * add flag --report-after-run to automatically generate the report after a successfull workflow run ([snakemake#3428](snakemake#3428)) ([b0a7f03](snakemake@b0a7f03)) * add flatten function to IO utils ([snakemake#3424](snakemake#3424)) ([67fa392](snakemake@67fa392)) * add helper functions to parse input files ([snakemake#2918](snakemake#2918)) ([63e45a7](snakemake@63e45a7)) * Add option to print redacted file names ([snakemake#3089](snakemake#3089)) ([ba4d264](snakemake@ba4d264)) * add support for validation of polars dataframe and lazyframe ([snakemake#3262](snakemake#3262)) ([c7473a6](snakemake@c7473a6)) * added support for rendering dag with mermaid js ([snakemake#3409](snakemake#3409)) ([7bf8381](snakemake@7bf8381)) * adding --replace-workflow-config to fully replace workflow configs (from config: directive) with --configfile, instead of merging them ([snakemake#3381](snakemake#3381)) ([47504a0](snakemake@47504a0)) * Dynamic module name ([snakemake#3401](snakemake#3401)) ([024dc32](snakemake@024dc32)) * Enable saving and reloading IOCache object ([snakemake#3386](snakemake#3386)) ([c935953](snakemake@c935953)) * files added in rule params with workflow.source_path will be available in used containers ([snakemake#3385](snakemake#3385)) ([a6e45bf](snakemake@a6e45bf)) * Fix keep_local in storage directive and more freedom over remote retrieval behaviour ([snakemake#3410](snakemake#3410)) ([67b4739](snakemake@67b4739)) * inherit parameters of use rule and extend/replace individual items them when using 'with' directive ([snakemake#3365](snakemake#3365)) ([93e4b92](snakemake@93e4b92)) * Logging refactor & add LoggerPluginInterface ([snakemake#3107](snakemake#3107)) ([86f1d6e](snakemake@86f1d6e)) * Maximal file size for checksums ([snakemake#3368](snakemake#3368)) ([b039f8a](snakemake@b039f8a)) * Modernize package configuration using Pixi ([snakemake#3369](snakemake#3369)) ([77992d8](snakemake@77992d8)) * multiext support for named input/output ([snakemake#3372](snakemake#3372)) ([05e1378](snakemake@05e1378)) * optionally auto-group jobs via temp files in case of remote execution ([snakemake#3378](snakemake#3378)) ([cc9bba2](snakemake@cc9bba2)) ### Bug Fixes * `--delete-all-output` ignores `--dry-run` ([snakemake#3265](snakemake#3265)) ([23fef82](snakemake@23fef82)) * 3342 faster touch runs and warning messages for non-existing files ([snakemake#3398](snakemake#3398)) ([cd9c3c3](snakemake@cd9c3c3)) * add default value to max-jobs-per-timespan ([snakemake#3043](snakemake#3043)) ([2959abe](snakemake@2959abe)) * checkpoints inside modules are overwritten ([snakemake#3359](snakemake#3359)) ([fba3ac7](snakemake@fba3ac7)) * Convert Path to IOFile ([snakemake#3405](snakemake#3405)) ([c58684c](snakemake@c58684c)) * Do not perform storage object cleanup with --keep-storage-local-copies set ([snakemake#3358](snakemake#3358)) ([9a6d14b](snakemake@9a6d14b)) * edgecases of source deployment in case of remote execution ([snakemake#3396](snakemake#3396)) ([5da13be](snakemake@5da13be)) * enhance error message formatting for strict DAG-building mode ([snakemake#3376](snakemake#3376)) ([a1c39ee](snakemake@a1c39ee)) * fix bug in checkpoint handling that led to exceptions in case checkpoint output was missing upon rerun ([snakemake#3423](snakemake#3423)) ([8cf4a2f](snakemake@8cf4a2f)) * force check all required outputs ([snakemake#3341](snakemake#3341)) ([495a4e7](snakemake@495a4e7)) * group job formatting ([snakemake#3442](snakemake#3442)) ([f0b10a3](snakemake@f0b10a3)) * in remote jobs, upload storage in topological order such that modification dates are preserved (e.g. in case of group jobs) ([snakemake#3377](snakemake#3377)) ([eace08f](snakemake@eace08f)) * only skip eval when resource depends on input ([snakemake#3374](snakemake#3374)) ([4574c92](snakemake@4574c92)) * Prevent execution of conda in apptainer when not explicitly requested in software deployment method ([snakemake#3388](snakemake#3388)) ([c43c5c0](snakemake@c43c5c0)) * print filenames with quotes around them in RuleException ([snakemake#3269](snakemake#3269)) ([6baeda5](snakemake@6baeda5)) * Re-evaluation of free resources ([snakemake#3399](snakemake#3399)) ([6371293](snakemake@6371293)) * ReadTheDocs layout issue due to src directory change ([snakemake#3419](snakemake#3419)) ([695b127](snakemake@695b127)) * robustly escaping quotes in generated bash scripts (v2) ([snakemake#3297](snakemake#3297)) ([snakemake#3389](snakemake#3389)) ([58720bd](snakemake@58720bd)) * Show apptainer image URL in snakemake report ([snakemake#3407](snakemake#3407)) ([45f0450](snakemake@45f0450)) * Update ReadTheDocs configuration for documentation build to use Pixi ([snakemake#3433](snakemake#3433)) ([3f227a6](snakemake@3f227a6)) ### Documentation * Add pixi setup instructions to general use tutorial ([snakemake#3382](snakemake#3382)) ([115e81b](snakemake@115e81b)) * fix contribution section heading levels, fix docs testing setup order ([snakemake#3360](snakemake#3360)) ([051dc53](snakemake@051dc53)) * fix link to github.com/snakemake/poetry-snakemake-plugin ([snakemake#3436](snakemake#3436)) ([ec6d97c](snakemake@ec6d97c)) * fix quoting ([snakemake#3394](snakemake#3394)) ([b40f599](snakemake@b40f599)) * fix rerun-triggers default ([snakemake#3403](snakemake#3403)) ([4430e23](snakemake@4430e23)) * fix typo 'safe' -> 'save' ([snakemake#3384](snakemake#3384)) ([7755861](snakemake@7755861)) * mention code formatting in the contribution section ([snakemake#3431](snakemake#3431)) ([e8682b7](snakemake@e8682b7)) * remove duplicated 'functions'. ([snakemake#3356](snakemake#3356)) ([7c595db](snakemake@7c595db)) * update broken links documentation ([snakemake#3437](snakemake#3437)) ([e3d0d88](snakemake@e3d0d88)) * Updating contributing guidelines with new pixi dev setup ([snakemake#3415](snakemake#3415)) ([8e95a12](snakemake@8e95a12)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). Co-authored-by: snakemake-bot <snakemake-bot-admin@googlegroups.com>
This is a quick fix for the issue described in #3202.
From the original issue:
This behaviour was caused by the retrieval in
_software_stack_hash()within thePersistenceclass. If a snakemake rule specified both a container and a conda file, this method would always try to get a hash value of the conda file, resulting in an instantiation of theCondaclass using the container as the base image (ad-hoc combination). This happened even when conda was not specified with--sdm. This also happened inget_log_error_info' ofjobs.py'. This PR fixes this issue and ensures that rules can be executed wither with conda, apptainer or the ad-hoc combination.QC
docs/) is updated to reflect the changes or this is not necessary (e.g. if the change does neither modify the language nor the behavior or functionalities of Snakemake).Summary by CodeRabbit
Bug Fixes
New Features
Tests