fix compatibility for python 3.10

[phenobarbital]

Summary by Sourcery

Ensure compatibility with Python 3.10 while improving model serialization behavior and bumping the library version.

Bug Fixes:

• Handle EnumType import for Python 3.10+ by falling back to EnumMeta when EnumType is unavailable.
• Prevent internal and excluded fields, including the _pgoutput attribute, from being included in collapsed value dictionaries.

Enhancements:

• Extend model serialization helpers to accept an exclude set for more flexible field exclusion.
• Update the library version metadata to reflect the latest release.

[sourcery-ai]

Reviewer's Guide

Updates datamodel serialization to better control excluded fields and restores enum compatibility for Python 3.10+, while bumping the library version.

Class diagram for updated datamodel BaseModel serialization methods

classDiagram
    class BaseModel {
        +to_dict(remove_nulls bool = False, convert_enums bool = False, as_values bool = False, exclude set = None) dict~str, Any~
        +__collapse_as_values__(remove_nulls bool = False, convert_enums bool = False, as_values bool = False, exclude set = None) dict~str, Any~
        +columns() dict~str, Field~
    }

    class Field {
        +metadata dict~str, Any~
    }

    BaseModel "*" --> "*" Field : uses

Loading

Flow diagram for updated to_dict and collapse_as_values exclusion logic

flowchart TD
    A[to_dict called] --> B[Initialize exclude set or use provided]
    B --> C[Add _pgoutput to exclude]
    C --> D{as_values?}
    D -- Yes --> E[Call __collapse_as_values__ with remove_nulls, convert_enums, as_values, exclude]
    D -- No --> F[Call as_dict to build dict]
    F --> G{convert_enums?}
    G -- Yes --> H[Convert enum values in dict]
    G -- No --> I[Skip enum conversion]
    H --> J[Optionally remove nulls]
    I --> J[Optionally remove nulls]
    J --> K[Return dict]

    subgraph CollapseValues[__collapse_as_values__]
        L[Iterate over columns] --> M{field name in exclude?}
        M -- Yes --> L
        M -- No --> N{field name starts with __ or equals __errors__?}
        N -- Yes --> L
        N -- No --> O{field.metadata.exclude is True?}
        O -- Yes --> L
        O -- No --> P[Get attribute value]
        P --> Q[Apply remove_nulls / convert_enums / collapse logic]
        Q --> R[Store in output dict]
        R --> L
    end

Loading

File-Level Changes

Change	Details	Files
Extend BaseModel.to_dict/collapse_as_values to support field exclusion and always omit internal attributes during value collapsing.	Add an optional exclude set parameter to to_dict and collapse_as_values and ensure _pgoutput is always excluded. Propagate the exclude set into collapse_as_values when serializing as values. Skip fields in value collapsing when their name is in the exclude set, when they are internal/error fields, or when field metadata requests exclusion.	datamodel/models.py
Adjust enum imports in JSON parser for compatibility with Python 3.10+ enum API changes.	Change direct EnumType import to a try/except that falls back to EnumMeta when EnumType is unavailable. Leave ORJSON_DEFAULT_OPTIONS unchanged aside from removing a commented-out option.	datamodel/parsers/json.pyx
Bump library version to reflect compatibility and serialization changes.	Increment version from 0.10.17 to 0.10.19.	datamodel/version.py

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey - I've found 1 issue, and left some high level feedback:

• The exclude = exclude or set(); exclude.add('_pgoutput') pattern in to_dict mutates a caller-provided exclude set in-place, which may be surprising; consider copying it before modification if you intend exclude to be local to this call.
• The new exclude handling is only applied in the __collapse_as_values__ branch of to_dict, so _pgoutput and other excluded fields will still appear when as_values=False; if the intent is to always exclude these fields, the non-as_values path should apply the same logic.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- The `exclude = exclude or set(); exclude.add('_pgoutput')` pattern in `to_dict` mutates a caller-provided `exclude` set in-place, which may be surprising; consider copying it before modification if you intend `exclude` to be local to this call.
- The new `exclude` handling is only applied in the `__collapse_as_values__` branch of `to_dict`, so `_pgoutput` and other excluded fields will still appear when `as_values=False`; if the intent is to always exclude these fields, the non-`as_values` path should apply the same logic.

## Individual Comments

### Comment 1
<location> `datamodel/models.py:214` </location>
<code_context>
         convert_enums: bool = False,
-        as_values: bool = False
+        as_values: bool = False,
+        exclude: Optional[set] = None
     ) -> dict[str, Any]:
+        exclude = exclude or set()
</code_context>

<issue_to_address>
**issue (bug_risk):** Avoid mutating the caller-provided `exclude` set inside `to_dict`.

Since `exclude` comes from the caller, `exclude = exclude or set(); exclude.add('_pgoutput')` will modify the caller’s set. If the same set is reused, it will unexpectedly keep accumulating entries like `_pgoutput`. Instead, copy it first, e.g. `exclude_local = set(exclude or ())`, then add `'_pgoutput'` to the copy so the function doesn’t mutate caller-provided data.
</issue_to_address>

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[sourcery-ai]

issue (bug_risk): Avoid mutating the caller-provided exclude set inside to_dict.

Since exclude comes from the caller, exclude = exclude or set(); exclude.add('_pgoutput') will modify the caller’s set. If the same set is reused, it will unexpectedly keep accumulating entries like _pgoutput. Instead, copy it first, e.g. exclude_local = set(exclude or ()), then add '_pgoutput' to the copy so the function doesn’t mutate caller-provided data.