Conversation
WalkthroughAdds a new async SWAPI v2 client and ORM-like layer: async HTTP client with token auth/auto-refresh, dynamic dot-access wrappers, a Q filter builder, querysets for list/core endpoints, APIModel base plus many endpoint models, utilities, and a custom exception hierarchy. Changes
Sequence Diagram(s)sequenceDiagram
participant Caller
participant SWAPIClient
participant LoginLock as AsyncLock
participant API
Caller->>SWAPIClient: _request(method, endpoint, ...)
activate SWAPIClient
alt token present
SWAPIClient->>API: request with Authorization
API-->>SWAPIClient: response
else token missing or 401
SWAPIClient->>LoginLock: acquire
activate LoginLock
SWAPIClient->>API: POST /_/security/login
API-->>SWAPIClient: {token: "..."}
SWAPIClient->>LoginLock: release
deactivate LoginLock
SWAPIClient->>API: retry request with Authorization
API-->>SWAPIClient: response
end
alt status >= 400
SWAPIClient-->>Caller: raise SWAPIError / subclass
else invalid JSON
SWAPIClient-->>Caller: raise SWAPISchemaError
else success
SWAPIClient-->>Caller: parsed JSON
end
deactivate SWAPIClient
sequenceDiagram
participant User
participant APIModel
participant SWAPIQuerySet
participant SWAPIClient
participant API
User->>APIModel: save()
activate APIModel
alt no pk (create)
APIModel->>SWAPIQuerySet: create(payload)
SWAPIQuerySet->>SWAPIClient: post(endpoint, json=payload)
SWAPIClient->>API: POST
API-->>SWAPIClient: created data
SWAPIClient-->>SWAPIQuerySet: response data
APIModel->>APIModel: _reload_from_data(response)
else has pk & dirty (update)
APIModel->>SWAPIQuerySet: patch(pk, json=dirty)
SWAPIQuerySet->>SWAPIClient: patch(...)
SWAPIClient->>API: PATCH
API-->>SWAPIClient: updated data
SWAPIClient-->>SWAPIQuerySet: response data
APIModel->>APIModel: _reload_from_data(response)
end
deactivate APIModel
Estimated code review effort🎯 4 (Complex) | ⏱️ ~75 minutes
Poem
Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
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. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 6
🧹 Nitpick comments (13)
src/swapi_client/v2/q.py (1)
103-118: Note the imperfect operator mapping for hasText.The mapping of
"hasText": "notLike"on line 113 is noted in the comment as lacking a perfect equivalent. This could lead to unexpected behavior when negating hasText filters. Ensure this is documented in user-facing documentation or consider raising a warning when this mapping is used.src/swapi_client/v2/dynamic.py (1)
1-59: Dynamic wrappers look good; just be aware of potential attribute collisionsImplementation of
DynamicObject/DynamicListis clean and should work well for nested JSON. Two minor points to keep in mind (no change strictly required now):
DynamicObjectexposes all keys as attributes. If SWAPI ever returns keys that are not valid identifiers or collide with Python internals (e.g.__dict__,to_dict), dot access will be awkward or ambiguous.to_dict()iterates overself.__dict__, so if you later add internal attributes onDynamicObjectitself, they’ll get serialized too. If that happens, consider filtering out keys starting with_into_dict().Otherwise this is solid and composable with the model layer.
src/swapi_client/v2/queryset_core.py (1)
48-64: Fix_build_paramsreturn type annotation
_build_paramscan returnNone(return params or None), but is annotated as-> Dict[str, Any]. This will confuse type-checkers.You can tighten this to an explicit optional:
-from typing import Any, Dict, Optional +from typing import Any, Dict, Optional @@ - def _build_params(self) -> Dict[str, Any]: + def _build_params(self) -> Optional[Dict[str, Any]]: params = {} @@ - return params or None + return params or NoneThis aligns the signature with the actual behavior and with the way you pass
paramsthrough to the client.src/swapi_client/v2/client.py (3)
135-142: Narrow JSON decode handling and chain the original exceptionCatching a bare
Exceptiononresp.json()and re‑raising an unchainedSWAPIErroris too broad and obscures the root cause.You can restrict to decode errors and keep the traceback:
- try: - return resp.json() - except Exception: - raise SWAPIError( - f"Invalid JSON response from SWAPI: {resp.text}" - ) + try: + return resp.json() + except ValueError as e: + # httpx.json() raises ValueError/JSONDecodeError on invalid JSON + raise SWAPIError( + f"Invalid JSON response from SWAPI: {resp.text}" + ) from eThis satisfies Ruff’s BLE001/B904 guidance and keeps debugging info when the API returns malformed JSON.
147-157: Make Optional argument types explicit in public methodsThe signatures
async def get(self, endpoint: str, params: dict = None) -> Dict[str, Any]: ... async def post(self, endpoint: str, json: dict = None) -> Dict[str, Any]: ...use implicit
Optional(defaultNonebut plaindicttype), which Ruff flags (RUF013). You can make intent explicit and slightly clearer:- async def get(self, endpoint: str, params: dict = None) -> Dict[str, Any]: + async def get(self, endpoint: str, params: dict | None = None) -> Dict[str, Any]: @@ - async def post(self, endpoint: str, json: dict = None) -> Dict[str, Any]: + async def post(self, endpoint: str, json: dict | None = None) -> Dict[str, Any]: @@ - async def patch(self, endpoint: str, json: dict = None) -> Dict[str, Any]: + async def patch(self, endpoint: str, json: dict | None = None) -> Dict[str, Any]: @@ - async def delete(self, endpoint: str, params: dict = None) -> Dict[str, Any]: + async def delete(self, endpoint: str, params: dict | None = None) -> Dict[str, Any]:(Or use
Optional[dict]instead if you need to support pre‑3.10 syntax.)
90-132: Consider mapping httpx transport errors toSWAPIConnectionError
_requestcurrently only converts HTTP status failures (status_code >= 400) intoSWAPIError. Network-level issues from httpx (ConnectError,ReadTimeout, etc.) will bubble up as raw httpx exceptions, even though you’ve definedSWAPIConnectionError.Not mandatory, but for a cleaner public API you might want to wrap these:
- async def _request(self, method: str, endpoint: str, **kwargs) -> Dict[str, Any]: + async def _request(self, method: str, endpoint: str, **kwargs) -> Dict[str, Any]: @@ - async with httpx.AsyncClient(timeout=self.timeout) as client: - - # 1) Jeśli pierwszy request → login() - if not self.token: - async with self._login_lock: - if not self.token: # drugi request czekał na lock - await self.login() - - # 2) Pierwsze podejście - resp = await client.request( - method, - url, - headers=await self._headers(), - **kwargs - ) + try: + async with httpx.AsyncClient(timeout=self.timeout) as client: + + # 1) Jeśli pierwszy request → login() + if not self.token: + async with self._login_lock: + if not self.token: # drugi request czekał na lock + await self.login() + + # 2) Pierwsze podejście + resp = await client.request( + method, + url, + headers=await self._headers(), + **kwargs + ) @@ - # 5) Obsługa błędów - if resp.status_code >= 400: - raise SWAPIError( - f"SWAPI HTTP {resp.status_code} on {method} {url}: {resp.text}" - ) + # 5) Obsługa błędów + if resp.status_code >= 400: + raise SWAPIError( + f"SWAPI HTTP {resp.status_code} on {method} {url}: {resp.text}" + ) @@ - try: - return resp.json() - except Exception: - raise SWAPIError( - f"Invalid JSON response from SWAPI: {resp.text}" - ) + try: + return resp.json() + except ValueError as e: + raise SWAPIError( + f"Invalid JSON response from SWAPI: {resp.text}" + ) from e + except httpx.RequestError as e: + # Opcjonalnie: spójny wyjątek dla problemów sieciowych + from .exceptions import SWAPIConnectionError + raise SWAPIConnectionError(f"Connection error talking to SWAPI: {e}") from eExact structure/imports can be adjusted, but the idea is to surface a uniform
SWAPIConnectionErrorfor all transport-level failures.src/swapi_client/v2/models/base.py (3)
39-50: Align_originalcontents between__init__and_reload_from_datafor stable dirty‑trackingIn
__init__(Line 39–49)_originalis populated with the rawdatadict, while_reload_from_data(Line 160–169) stores already‑wrapped values (DynamicObject/DynamicList) in_original. That means equality checks in__setattr__(Line 72–75) compare raw vs wrapped values depending on object lifecycle, which is inconsistent and can produce surprising dirty flags when reassigning dict/list fields.Consider initializing
_originalwith the same wrapped values you assign to attributes, mirroring_reload_from_data:@@ - # surowy JSON ze SWAPI - self._raw: Dict[str, Any] = data - - # dynamiczne pola + wrap - for key, value in data.items(): - super().__setattr__(key, self._wrap_dynamic(value)) - - # dirty tracking - self._original: Dict[str, Any] = dict(data) - self._dirty: Dict[str, Any] = {} + # surowy JSON ze SWAPI + self._raw: Dict[str, Any] = data + + # dirty tracking (przechowujemy wartości po wrapie) + self._original: Dict[str, Any] = {} + self._dirty: Dict[str, Any] = {} + + # dynamiczne pola + wrap + for key, value in data.items(): + wrapped = self._wrap_dynamic(value) + super().__setattr__(key, wrapped) + self._original[key] = wrappedThis keeps dirty‑tracking semantics consistent before and after a reload.
Also applies to: 160-169
175-188:__repr__uses_data, which is never set; consider switching to_raw
__repr__(Line 175–188) checks and readsself._data, but APIModel only ever sets_raw,_original, and_dirty. As a result, thehasattr(self, "_data")branch is always false and the method always returns a simple<ClassName>repr, never showing pk/fields.If you want a richer, safe repr, basing it on
_rawis more consistent:@@ def __repr__(self): - # Jeśli obiekt nie ma _data (np. SWAPIListResponse.items jest listą), - # to zwracamy prosty repr aby uniknąć błędów. - if not hasattr(self, "_data") or not isinstance(self._data, dict): - return f"<{self.__class__.__name__}>" - - cls = self.__class__.__name__ - pk = self._data.get("id") or self._data.get("pk") - - field_names = ", ".join(self._data.keys()) + raw = getattr(self, "_raw", None) + if not isinstance(raw, dict): + return f"<{self.__class__.__name__}>" + + cls = self.__class__.__name__ + pk = raw.get("id") or raw.get("pk") + + field_names = ", ".join(raw.keys()) if len(field_names) > 120: field_names = field_names[:117] + "..." return f"<{cls} pk={pk} fields={field_names}>"This keeps the defensive behavior while making the detailed repr actually reachable.
77-85: Clarify exception chaining in__getattr__In
__getattr__(Line 77–85) you intentionally translate aKeyErrorinto anAttributeError. To make the intent explicit and silence B904, consider usingfrom Noneto suppress the inner traceback:- try: - return self.__dict__[item] - except KeyError: - raise AttributeError(f"{self.__class__.__name__} has no attribute '{item}'") + try: + return self.__dict__[item] + except KeyError: + raise AttributeError( + f"{self.__class__.__name__} has no attribute '{item}'" + ) from NoneThis keeps user‑visible behavior unchanged while making the traceback cleaner.
src/swapi_client/v2/queryset.py (2)
450-482: Makeget()404 handling more robust and preserve the original exception contextIn
get()(Line 469–479), 404 detection is based on checking"404" in str(e)and the re‑raisedSWAPINotFoundErroris not chained:except SWAPIError as e: if "404" in str(e): raise SWAPINotFoundError( f"{self.model_cls.__name__} id={id} not found" ) raiseThis is brittle (depends on the error message formatting) and drops the original traceback.
If the client already distinguishes 404s, prefer raising
SWAPINotFoundErrorthere. If you keep this layer doing the mapping, consider:
- Matching on a structured attribute (e.g. status code) instead of the string, if available.
- Chaining the exception for easier debugging:
- except SWAPIError as e: - if "404" in str(e): - raise SWAPINotFoundError( - f"{self.model_cls.__name__} id={id} not found" - ) - raise + except SWAPIError as e: + if "404" in str(e): + raise SWAPINotFoundError( + f"{self.model_cls.__name__} id={id} not found" + ) from e + raisePlease verify what information
SWAPIErrorcarries today (e.g. HTTP status) so you can avoid relying on string parsing.
529-542: Preserve original cause when wrapping errors inmeta()In
meta()(Line 536–539) you catchSWAPIErrorand wrap it in a newSWAPIErrorwith a formatted message, but you don’t chain the original exception:except SWAPIError as e: raise SWAPIError(f"Failed to fetch meta for {self.endpoint}: {e}")This loses the root stack trace and also triggers B904.
You can keep the nicer message and still expose the original cause:
- except SWAPIError as e: - raise SWAPIError(f"Failed to fetch meta for {self.endpoint}: {e}") + except SWAPIError as e: + raise SWAPIError( + f"Failed to fetch meta for {self.endpoint}: {e}" + ) from eThat makes debugging upstream transport issues much easier.
src/swapi_client/v2/models/commission.py (2)
87-113: Interaction betweenCommission.attributesproxy and baseAPIModel.save()Commission strips
attributesout of the initial payload sent toAPIModel.__init__(Line 90–99) and then installs anAttributesProxyviaobject.__setattr__(Line 110–112). That means:
- Normal dirty‑tracking in
APIModelcompletely ignores changes to attributes (as intended).- All attribute persistence goes through
save_attributes()(Line 116–165), notsave().This is a good separation of concerns, but it also means:
await comm.save()will never persist attribute changes; callers must always callawait comm.save_attributes()explicitly.- If someone manually constructs a Commission with pre‑populated
attributesand callssave()for a create, those attributes will be ignored and only later managed through the proxy.If that’s intentional, consider documenting it more explicitly in the class docstring (e.g. “attributes are only saved via
save_attributes()”). Otherwise, you may want to add guardrails (like raising if both attribute proxy dirty state and_dirtyare non‑empty duringsave()).Also applies to: 116-165
1-10: Minor docs / endpoint consistency issuesA few small inconsistencies that might confuse users:
- The Commission usage example (Line 69–75) imports from
swapi_sdk, while the actual package seems to beswapi_client. Consider aligning the import path.- The docstring mentions “dodatkowe metody domenowe: change_phase(), assign_user(), close(), reopen()” (Line 4–10), but these methods are not defined on
Commission. Either implement or remove them from the docs to avoid surprises.CommissionUsers.endpointis set to"/api/commissions_user_userss"(Line 258–258). The doublesinusersslooks like a potential typo; please confirm against the real SW API schema.These are non‑blocking but worth cleaning up for clarity.
Also applies to: 69-85, 253-259
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
⛔ Files ignored due to path filters (1)
uv.lockis excluded by!**/*.lock
📒 Files selected for processing (16)
src/swapi_client/v2/client.py(1 hunks)src/swapi_client/v2/core_init.py(1 hunks)src/swapi_client/v2/dynamic.py(1 hunks)src/swapi_client/v2/exceptions.py(1 hunks)src/swapi_client/v2/models/account_company.py(1 hunks)src/swapi_client/v2/models/account_user.py(1 hunks)src/swapi_client/v2/models/base.py(1 hunks)src/swapi_client/v2/models/commission.py(1 hunks)src/swapi_client/v2/models/core.py(1 hunks)src/swapi_client/v2/models/document.py(1 hunks)src/swapi_client/v2/models/product.py(1 hunks)src/swapi_client/v2/models/user.py(1 hunks)src/swapi_client/v2/q.py(1 hunks)src/swapi_client/v2/queryset.py(1 hunks)src/swapi_client/v2/queryset_core.py(1 hunks)src/swapi_client/v2/utils.py(1 hunks)
🧰 Additional context used
🧬 Code graph analysis (12)
src/swapi_client/v2/core_init.py (3)
src/swapi_client/v2/models/core.py (3)
CoreModel(6-32)Core(35-52)objects(49-52)src/swapi_client/v2/queryset_core.py (1)
CoreQuerySet(7-145)src/swapi_client/v2/models/base.py (1)
objects(97-104)
src/swapi_client/v2/models/account_user.py (1)
src/swapi_client/v2/models/base.py (1)
APIModel(24-188)
src/swapi_client/v2/models/user.py (1)
src/swapi_client/v2/models/base.py (1)
APIModel(24-188)
src/swapi_client/v2/models/account_company.py (1)
src/swapi_client/v2/models/base.py (1)
APIModel(24-188)
src/swapi_client/v2/models/core.py (3)
src/swapi_client/v2/dynamic.py (1)
DynamicObject(1-35)src/swapi_client/v2/queryset_core.py (1)
CoreQuerySet(7-145)src/swapi_client/v2/core_init.py (2)
Core(5-22)objects(19-22)
src/swapi_client/v2/queryset_core.py (4)
src/swapi_client/v2/dynamic.py (1)
DynamicObject(1-35)src/swapi_client/v2/exceptions.py (1)
SWAPIError(1-6)src/swapi_client/v2/queryset.py (5)
fields(151-153)extra_fields(155-157)with_relations(132-134)_build_params(333-379)get(450-482)src/swapi_client/v2/client.py (4)
get(147-148)post(150-151)patch(153-154)delete(156-157)
src/swapi_client/v2/models/product.py (1)
src/swapi_client/v2/models/base.py (1)
APIModel(24-188)
src/swapi_client/v2/models/document.py (1)
src/swapi_client/v2/models/base.py (1)
APIModel(24-188)
src/swapi_client/v2/models/commission.py (4)
src/swapi_client/v2/models/base.py (2)
APIModel(24-188)pk(90-91)src/swapi_client/v2/exceptions.py (1)
SWAPIError(1-6)src/swapi_client/v2/client.py (2)
get(147-148)patch(153-154)src/swapi_client/v2/queryset.py (1)
get(450-482)
src/swapi_client/v2/queryset.py (4)
src/swapi_client/v2/dynamic.py (1)
DynamicObject(1-35)src/swapi_client/v2/exceptions.py (2)
SWAPIError(1-6)SWAPINotFoundError(17-21)src/swapi_client/v2/queryset_core.py (6)
with_relations(41-43)fields(33-35)extra_fields(37-39)get(80-97)_build_params(48-63)post(102-114)src/swapi_client/v2/client.py (2)
get(147-148)post(150-151)
src/swapi_client/v2/models/base.py (4)
src/swapi_client/v2/queryset.py (2)
SWAPIQuerySet(56-542)get(450-482)src/swapi_client/v2/exceptions.py (1)
SWAPIError(1-6)src/swapi_client/v2/dynamic.py (2)
DynamicObject(1-35)DynamicList(38-59)src/swapi_client/v2/client.py (4)
post(150-151)get(147-148)patch(153-154)delete(156-157)
src/swapi_client/v2/client.py (4)
src/swapi_client/v2/exceptions.py (2)
SWAPIError(1-6)SWAPIAuthError(9-15)src/swapi_client/v2/queryset_core.py (4)
post(102-114)get(80-97)patch(119-131)delete(136-145)src/swapi_client/v2/queryset.py (1)
get(450-482)src/swapi_client/v2/models/base.py (1)
delete(140-144)
🪛 Ruff (0.14.5)
src/swapi_client/v2/core_init.py
21-21: Avoid specifying long messages outside the exception class
(TRY003)
src/swapi_client/v2/models/core.py
51-51: Avoid specifying long messages outside the exception class
(TRY003)
src/swapi_client/v2/queryset_core.py
94-94: Within an except clause, raise exceptions with raise ... from err or raise ... from None to distinguish them from errors in exception handling
(B904)
94-94: Avoid specifying long messages outside the exception class
(TRY003)
111-111: Within an except clause, raise exceptions with raise ... from err or raise ... from None to distinguish them from errors in exception handling
(B904)
111-111: Avoid specifying long messages outside the exception class
(TRY003)
128-128: Within an except clause, raise exceptions with raise ... from err or raise ... from None to distinguish them from errors in exception handling
(B904)
128-128: Avoid specifying long messages outside the exception class
(TRY003)
143-143: Within an except clause, raise exceptions with raise ... from err or raise ... from None to distinguish them from errors in exception handling
(B904)
143-143: Avoid specifying long messages outside the exception class
(TRY003)
src/swapi_client/v2/models/commission.py
5-5: Docstring contains ambiguous – (EN DASH). Did you mean - (HYPHEN-MINUS)?
(RUF002)
50-52: Avoid specifying long messages outside the exception class
(TRY003)
132-132: Avoid specifying long messages outside the exception class
(TRY003)
135-135: Avoid specifying long messages outside the exception class
(TRY003)
src/swapi_client/v2/queryset.py
61-76: Mutable class attributes should be annotated with typing.ClassVar
(RUF012)
77-77: Mutable class attributes should be annotated with typing.ClassVar
(RUF012)
117-117: Comment contains ambiguous – (EN DASH). Did you mean - (HYPHEN-MINUS)?
(RUF003)
124-127: Avoid specifying long messages outside the exception class
(TRY003)
195-195: Avoid specifying long messages outside the exception class
(TRY003)
255-255: Avoid specifying long messages outside the exception class
(TRY003)
476-478: Within an except clause, raise exceptions with raise ... from err or raise ... from None to distinguish them from errors in exception handling
(B904)
476-478: Avoid specifying long messages outside the exception class
(TRY003)
521-521: Avoid specifying long messages outside the exception class
(TRY003)
539-539: Within an except clause, raise exceptions with raise ... from err or raise ... from None to distinguish them from errors in exception handling
(B904)
539-539: Avoid specifying long messages outside the exception class
(TRY003)
src/swapi_client/v2/models/base.py
84-84: Within an except clause, raise exceptions with raise ... from err or raise ... from None to distinguish them from errors in exception handling
(B904)
84-84: Avoid specifying long messages outside the exception class
(TRY003)
99-99: Avoid specifying long messages outside the exception class
(TRY003)
117-117: Avoid specifying long messages outside the exception class
(TRY003)
142-142: Avoid specifying long messages outside the exception class
(TRY003)
src/swapi_client/v2/client.py
64-66: Avoid specifying long messages outside the exception class
(TRY003)
71-71: Avoid specifying long messages outside the exception class
(TRY003)
130-132: Avoid specifying long messages outside the exception class
(TRY003)
139-139: Do not catch blind exception: Exception
(BLE001)
140-142: Within an except clause, raise exceptions with raise ... from err or raise ... from None to distinguish them from errors in exception handling
(B904)
140-142: Avoid specifying long messages outside the exception class
(TRY003)
147-147: PEP 484 prohibits implicit Optional
Convert to T | None
(RUF013)
150-150: PEP 484 prohibits implicit Optional
Convert to T | None
(RUF013)
153-153: PEP 484 prohibits implicit Optional
Convert to T | None
(RUF013)
156-156: PEP 484 prohibits implicit Optional
Convert to T | None
(RUF013)
🔇 Additional comments (8)
src/swapi_client/v2/models/document.py (1)
5-10: LGTM! Clean model definition.The
DocumentSeriesDefinitionmodel follows the established APIModel pattern with a clear endpoint declaration. All CRUD operations, dirty tracking, and queryset functionality are inherited from the base class.src/swapi_client/v2/models/account_user.py (1)
3-25: LGTM! Well-structured model definitions.All three models (
AccountUser,AccountUserAttribute,AccountUserHistory) correctly follow the APIModel pattern with properly defined endpoints. The structure is consistent with other model files in the v2 package.src/swapi_client/v2/utils.py (1)
8-41: LGTM! Clean utility functions for Django-style filtering.The utility functions are well-implemented for their intended purpose:
parse_filter_keycorrectly handles nested field paths with operatorsis_iterable_but_not_stringappropriately checks for collections used in 'in'/'notIn' operatorslist_to_csvprovides simple CSV conversion suitable for query parameterssrc/swapi_client/v2/q.py (1)
18-99: LGTM! Solid Django-style Q object implementation.The Q object implementation correctly handles:
- Leaf filters with field__operator=value syntax
- Logical composition via
&(AND) and|(OR)- Negation via
~operator- Proper tree structure with children and connectors
The implementation provides a clean, intuitive API for building complex filters.
src/swapi_client/v2/models/account_company.py (1)
4-25: LGTM! Consistent model definitions.All three account company models (
AccountCompany,AccountCompanyAttribute,AccountCompanyHistory) are well-structured and follow the established APIModel pattern. The implementation mirrors the account_user models appropriately.src/swapi_client/v2/models/user.py (1)
3-49: LGTM! Comprehensive user model definitions.All six user-related models are properly structured with clear endpoints:
- User, UserAbsence, UserAbsenceLimit, UserAttribute, UserHistory, UserProfile
Each model correctly inherits from APIModel and provides appropriate REST endpoints. The implementation is consistent with the broader v2 models suite.
src/swapi_client/v2/exceptions.py (1)
1-61: Exception hierarchy is clear and cohesiveThe exception tree is well-structured (
SWAPIErrorbase + specific subclasses) and maps cleanly to typical HTTP/API failure modes. This should make downstream error handling straightforward.src/swapi_client/v2/models/product.py (1)
2-59: Product model endpoints are consistent and minimalThe product-related
APIModelsubclasses correctly follow the pattern fromAPIModel(only settingendpoint). As long as the backend paths are accurate, this is a clean, declarative mapping.
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (3)
src/swapi_client/v2/__init__.py (1)
30-51: Consider sorting__all__alphabetically (optional).The linter suggests alphabetically sorting
__all__. While the current logical grouping (client/query, exceptions, utils) is readable, alphabetical sorting improves consistency and makes it easier to spot missing exports at scale.Apply this diff if you prefer linter-compliant alphabetical ordering:
__all__ = [ - "SWAPIClient", - "Q", - "SWAPIQuerySet", - "SWAPIListResponse", "CoreQuerySet", "DynamicObject", "DynamicList", - "models", - # exceptions - "SWAPIError", + "Q", "SWAPIAuthError", + "SWAPIConnectionError", + "SWAPIError", + "SWAPIListResponse", "SWAPINotFoundError", - "SWAPISchemaError", - "SWAPIValidationError", "SWAPIPermissionDenied", - "SWAPIConnectionError", - # utils - "parse_filter_key", + "SWAPIQuerySet", + "SWAPISchemaError", + "SWAPIValidationError", + "SWAPIClient", "is_iterable_but_not_string", "list_to_csv", + "models", + "parse_filter_key", ]src/swapi_client/v2/models/__init__.py (2)
16-16: Consider splitting the long import line for readability (optional).Line 16 imports seven product-related models on a single line, making it harder to scan. Splitting into multiple lines would improve readability.
Apply this diff:
-from .product import Product, ProductAttribute, ProductCategory, ProductTemplate, ProductToProductCategory, ServicedProduct, ServicedProductAttribute +from .product import ( + Product, + ProductAttribute, + ProductCategory, + ProductTemplate, + ProductToProductCategory, + ServicedProduct, + ServicedProductAttribute, +)
20-51: Consider sorting__all__alphabetically (optional).With 31 exports, alphabetical sorting would make it easier to verify completeness and spot duplicates.
Apply this diff for alphabetical ordering:
__all__ = [ - "APIModel", "AccountCompany", "AccountCompanyAttribute", "AccountCompanyHistory", "AccountUser", "AccountUserAttribute", "AccountUserHistory", + "APIModel", "Commission", "CommissionAttribute", "CommissionHistory", "CommissionPhase", "CommissionScopeType", "CommissionShortcut", "CommissionTemplate", "CommissionUsers", "CoreModel", "DocumentSeriesDefinition", "Product", "ProductAttribute", "ProductCategory", "ProductTemplate", "ProductToProductCategory", "ServicedProduct", "ServicedProductAttribute", "User", + "UserAbsence", + "UserAbsenceLimit", "UserAttribute", "UserHistory", - "UserAbsence", - "UserAbsenceLimit", "UserProfile", ]
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
src/swapi_client/v2/__init__.py(1 hunks)src/swapi_client/v2/models/__init__.py(1 hunks)
🧰 Additional context used
🧬 Code graph analysis (2)
src/swapi_client/v2/__init__.py (7)
src/swapi_client/v2/client.py (1)
SWAPIClient(9-157)src/swapi_client/v2/q.py (1)
Q(18-98)src/swapi_client/v2/queryset.py (2)
SWAPIQuerySet(56-542)SWAPIListResponse(27-53)src/swapi_client/v2/queryset_core.py (1)
CoreQuerySet(7-145)src/swapi_client/v2/dynamic.py (2)
DynamicObject(1-35)DynamicList(38-59)src/swapi_client/v2/exceptions.py (7)
SWAPIError(1-6)SWAPIAuthError(9-15)SWAPINotFoundError(17-21)SWAPISchemaError(24-31)SWAPIValidationError(34-46)SWAPIPermissionDenied(49-54)SWAPIConnectionError(57-61)src/swapi_client/v2/utils.py (3)
parse_filter_key(8-23)is_iterable_but_not_string(26-33)list_to_csv(36-41)
src/swapi_client/v2/models/__init__.py (2)
src/swapi_client/v2/models/commission.py (2)
Commission(63-179)CommissionUsers(253-258)src/swapi_client/v2/models/user.py (1)
User(3-8)
🪛 Ruff (0.14.5)
src/swapi_client/v2/__init__.py
30-51: __all__ is not sorted
Apply an isort-style sorting to __all__
(RUF022)
src/swapi_client/v2/models/__init__.py
20-51: __all__ is not sorted
Apply an isort-style sorting to __all__
(RUF022)
🔇 Additional comments (1)
src/swapi_client/v2/__init__.py (1)
1-28: LGTM!The imports are well-organized and clearly structured with logical groupings. The module docstring provides helpful usage examples.
There was a problem hiding this comment.
Actionable comments posted: 6
🧹 Nitpick comments (4)
src/swapi_client/v2/__init__.py (1)
31-53: Public API surface is coherent; consider whether you want__all__sortedThe exported symbols match the imports and give a clean v2 entry-point. Ruff’s RUF022 about sorting
__all__is purely stylistic here; if you prefer semantic grouping (top-level, exceptions, utils), you can either keep this order and adjust lint config, or alphabetize__all__to satisfy the rule.src/swapi_client/v2/queryset_core.py (1)
80-97: Guard against non-dict responses inCoreQuerySet.get
SWAPIClient.get()can return any JSON type, butCoreQuerySet.getassumes adict(resp.get("data")). If someone reuses this for an endpoint that returns a bare list, this will raise anAttributeError.If you want
CoreQuerySetto be safely reusable beyond strictly object-shaped/api/...endpoints, consider a small guard:- data = resp.get("data") or resp + if isinstance(resp, dict): + data = resp.get("data") or resp + else: + data = resp return self.model_cls(data)Same pattern could be applied to
post/patchif you expect any list-shaped responses there.src/swapi_client/v2/models/base.py (1)
62-76: Dirty-tracking skips new and nested changes – verify this matches intended semanticsTwo behavioral edge cases in the current dirty-tracking logic:
__setattr__only tracks keys already present in_original:
- New attributes added after initialization (
key not in self._original) are never added to_dirty, so they will not be included in PATCH payloads.- Nested updates on wrapped
DynamicObject/DynamicListaren’t tracked:
- Mutating
obj.address.cityupdates the nested wrapper, but_dirtyremains empty, sosave()’s PATCH branch early-returns and never persists those changes.This is fine if the design is “PATCH only existing top-level JSON fields and ignore new/nested field mutations,” but that’s a surprising limitation for an ORM-like API.
If you want PATCH to cover these cases, options include:
- Treat any assignment to a key not in
_originalas dirty (so new fields are sent).- When a wrapped field is mutated, mark the top-level key as dirty (e.g., via a helper on
DynamicObject/DynamicListor an explicitmark_dirty("field")API on the model).Happy to sketch a concrete approach if you want to extend dirty tracking rather than keep it minimal.
Also applies to: 149-169
src/swapi_client/v2/models/commission.py (1)
5-5: Optional: Replace EN DASH with HYPHEN-MINUS for consistency.The docstring contains an EN DASH (–) character. For better compatibility and consistency with standard ASCII text, consider using HYPHEN-MINUS (-) instead.
Based on static analysis hints.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (6)
src/swapi_client/v2/__init__.py(1 hunks)src/swapi_client/v2/core_init.py(1 hunks)src/swapi_client/v2/models/base.py(1 hunks)src/swapi_client/v2/models/commission.py(1 hunks)src/swapi_client/v2/models/core.py(1 hunks)src/swapi_client/v2/queryset_core.py(1 hunks)
🧰 Additional context used
🧬 Code graph analysis (6)
src/swapi_client/v2/__init__.py (8)
src/swapi_client/v2/client.py (1)
SWAPIClient(9-157)src/swapi_client/v2/q.py (1)
Q(18-98)src/swapi_client/v2/queryset.py (2)
SWAPIQuerySet(56-542)SWAPIListResponse(27-53)src/swapi_client/v2/queryset_core.py (1)
CoreQuerySet(7-145)src/swapi_client/v2/dynamic.py (2)
DynamicObject(1-35)DynamicList(38-59)src/swapi_client/v2/core_init.py (1)
Core(7-24)src/swapi_client/v2/exceptions.py (7)
SWAPIError(1-6)SWAPIAuthError(9-15)SWAPINotFoundError(17-21)SWAPISchemaError(24-31)SWAPIValidationError(34-46)SWAPIPermissionDenied(49-54)SWAPIConnectionError(57-61)src/swapi_client/v2/utils.py (3)
parse_filter_key(8-23)is_iterable_but_not_string(26-33)list_to_csv(36-41)
src/swapi_client/v2/queryset_core.py (4)
src/swapi_client/v2/dynamic.py (1)
DynamicObject(1-35)src/swapi_client/v2/exceptions.py (1)
SWAPIError(1-6)src/swapi_client/v2/queryset.py (5)
fields(151-153)extra_fields(155-157)with_relations(132-134)_build_params(333-379)get(450-482)src/swapi_client/v2/client.py (4)
get(147-148)post(150-151)patch(153-154)delete(156-157)
src/swapi_client/v2/models/commission.py (3)
src/swapi_client/v2/models/base.py (2)
APIModel(24-199)pk(90-91)src/swapi_client/v2/exceptions.py (1)
SWAPIError(1-6)src/swapi_client/v2/client.py (2)
get(147-148)patch(153-154)
src/swapi_client/v2/models/base.py (4)
src/swapi_client/v2/queryset.py (2)
SWAPIQuerySet(56-542)get(450-482)src/swapi_client/v2/exceptions.py (1)
SWAPIError(1-6)src/swapi_client/v2/dynamic.py (4)
DynamicObject(1-35)DynamicList(38-59)to_dict(20-32)to_list(53-59)src/swapi_client/v2/client.py (4)
post(150-151)get(147-148)patch(153-154)delete(156-157)
src/swapi_client/v2/models/core.py (2)
src/swapi_client/v2/dynamic.py (1)
DynamicObject(1-35)src/swapi_client/v2/models/base.py (1)
pk(90-91)
src/swapi_client/v2/core_init.py (3)
src/swapi_client/v2/queryset_core.py (1)
CoreQuerySet(7-145)src/swapi_client/v2/models/core.py (1)
CoreModel(5-28)src/swapi_client/v2/models/base.py (1)
objects(97-104)
🪛 Ruff (0.14.5)
src/swapi_client/v2/__init__.py
31-53: __all__ is not sorted
Apply an isort-style sorting to __all__
(RUF022)
src/swapi_client/v2/queryset_core.py
94-94: Avoid specifying long messages outside the exception class
(TRY003)
111-111: Avoid specifying long messages outside the exception class
(TRY003)
128-128: Avoid specifying long messages outside the exception class
(TRY003)
143-143: Avoid specifying long messages outside the exception class
(TRY003)
src/swapi_client/v2/models/commission.py
5-5: Docstring contains ambiguous – (EN DASH). Did you mean - (HYPHEN-MINUS)?
(RUF002)
50-52: Avoid specifying long messages outside the exception class
(TRY003)
140-140: Avoid specifying long messages outside the exception class
(TRY003)
143-143: Avoid specifying long messages outside the exception class
(TRY003)
src/swapi_client/v2/models/base.py
84-84: Within an except clause, raise exceptions with raise ... from err or raise ... from None to distinguish them from errors in exception handling
(B904)
84-84: Avoid specifying long messages outside the exception class
(TRY003)
99-99: Avoid specifying long messages outside the exception class
(TRY003)
117-117: Avoid specifying long messages outside the exception class
(TRY003)
142-142: Avoid specifying long messages outside the exception class
(TRY003)
src/swapi_client/v2/core_init.py
23-23: Avoid specifying long messages outside the exception class
(TRY003)
🔇 Additional comments (4)
src/swapi_client/v2/models/core.py (1)
11-28: CoreModel pk and__repr__now align with DynamicObject semantics
pkcorrectly mirrorsid, and__repr__inspects public attributes via__dict__, fixing the earlier reliance on non-existent_raw/_datawhile giving a useful field summary.src/swapi_client/v2/core_init.py (1)
18-24: Core.objects wiring to CoreQuerySet/CoreModel looks goodClient validation plus
CoreQuerySet(cls.client, CoreModel)is consistent with the rest of the API and gives a clear failure whenclientisn’t configured.src/swapi_client/v2/models/commission.py (2)
54-62: Excellent fix—in-memory view now stays consistent!The implementation correctly addresses the previous review concern by updating
_attributes_by_idimmediately (preserving metadata) while still recording changes in_attributes_dirtyfor the pending PATCH. This ensures thatget()andlist()reflect pending changes beforesave_attributes()is called.
98-120: Good design: Attributes handled separately from dynamic fields.The
__init__method correctly separates attributes from other fields, preventing them from being wrapped asDynamicObject/DynamicList. Usingobject.__setattr__for the proxy (line 119) properly bypasses dirty tracking for this internal field.
| async def delete(self) -> None: | ||
| if self.pk is None: | ||
| raise SWAPIError("Cannot delete object without primary key") | ||
|
|
||
| await self.client.delete(f"{self.endpoint}/{self.pk}") |
There was a problem hiding this comment.
delete() should validate client like save() does
save() guards against a missing client with a clear RuntimeError, but delete() goes straight to await self.client.delete(...). If client was never configured, this will fail with a less helpful 'NoneType' object has no attribute 'delete'.
Consider mirroring the save() check:
async def delete(self) -> None:
- if self.pk is None:
- raise SWAPIError("Cannot delete object without primary key")
-
- await self.client.delete(f"{self.endpoint}/{self.pk}")
+ if self.pk is None:
+ raise SWAPIError("Cannot delete object without primary key")
+
+ if self.client is None:
+ raise RuntimeError("Model has no API client assigned")
+
+ await self.client.delete(f"{self.endpoint}/{self.pk}")📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| async def delete(self) -> None: | |
| if self.pk is None: | |
| raise SWAPIError("Cannot delete object without primary key") | |
| await self.client.delete(f"{self.endpoint}/{self.pk}") | |
| async def delete(self) -> None: | |
| if self.pk is None: | |
| raise SWAPIError("Cannot delete object without primary key") | |
| if self.client is None: | |
| raise RuntimeError("Model has no API client assigned") | |
| await self.client.delete(f"{self.endpoint}/{self.pk}") |
🧰 Tools
🪛 Ruff (0.14.5)
142-142: Avoid specifying long messages outside the exception class
(TRY003)
🤖 Prompt for AI Agents
In src/swapi_client/v2/models/base.py around lines 140 to 144, the delete()
method does not validate that self.client is set and will raise an unclear
AttributeError if client is None; mirror save() by adding a guard that checks if
self.client is None and raise a RuntimeError with a clear message (e.g., "Client
not configured, cannot delete object") before the existing pk check/HTTP delete
call so the error is explicit and consistent with save().
| def __repr__(self): | ||
| # Jeśli obiekt nie ma _data (np. SWAPIListResponse.items jest listą), | ||
| # to zwracamy prosty repr aby uniknąć błędów. | ||
| if not hasattr(self, "_data") or not isinstance(self._data, dict): | ||
| return f"<{self.__class__.__name__}>" | ||
|
|
||
| cls = self.__class__.__name__ | ||
| pk = self._data.get("id") or self._data.get("pk") | ||
|
|
||
| field_names = ", ".join(self._data.keys()) | ||
| if len(field_names) > 120: | ||
| field_names = field_names[:117] + "..." | ||
|
|
||
| return f"<{cls} pk={pk} fields={field_names}>" |
There was a problem hiding this comment.
__repr__ references _data, which is never set → always falls back
APIModel.__repr__ checks and reads self._data, but neither __init__ nor _reload_from_data ever define _data (only _raw, _original, _dirty). As a result, hasattr(self, "_data") is always false and you always get a plain <ClassName> repr, losing the intended field/PK summary.
A minimal fix is to base the repr on _raw (or on public attributes) instead:
- def __repr__(self):
- # Jeśli obiekt nie ma _data (np. SWAPIListResponse.items jest listą),
- # to zwracamy prosty repr aby uniknąć błędów.
- if not hasattr(self, "_data") or not isinstance(self._data, dict):
- return f"<{self.__class__.__name__}>"
-
- cls = self.__class__.__name__
- pk = self._data.get("id") or self._data.get("pk")
-
- field_names = ", ".join(self._data.keys())
+ def __repr__(self):
+ cls = self.__class__.__name__
+
+ data = getattr(self, "_raw", None)
+ if not isinstance(data, dict):
+ return f"<{cls}>"
+
+ pk = data.get("id") or data.get("pk")
+
+ field_names = ", ".join(data.keys())
if len(field_names) > 120:
field_names = field_names[:117] + "..."
return f"<{cls} pk={pk} fields={field_names}>"Alternatively, you can mirror CoreModel and derive field_names from self.__dict__’s public keys if you prefer to reflect in-memory state rather than last raw JSON.
🤖 Prompt for AI Agents
In src/swapi_client/v2/models/base.py around lines 186 to 199, __repr__
currently checks for self._data which is never set causing it to always return
the simple "<ClassName>" form; update __repr__ to use the existing backing state
(preferably self._raw if present, else fall back to public attributes from
self.__dict__) to compute pk (from raw.get("id") or raw.get("pk") or attribute
'id'/'pk') and to build the comma-joined field list (truncate >120 chars),
preserving the existing fallback behavior when no suitable data is available;
ensure the function only reads existing attributes (no side effects) and keeps
the same string format "<ClassName pk=... fields=...>".
| if attr_id not in self._commission._attributes_by_id: | ||
| # Możesz to zmienić na silent ignore lub warning/log. | ||
| raise KeyError( | ||
| f"Attribute id={attr_id} does not exist on this Commission instance" | ||
| ) |
There was a problem hiding this comment.
Consider using a more specific exception type.
Raising KeyError for attribute validation is semantically correct but might be confused with internal dictionary key errors. Consider using SWAPIError or ValueError for clearer domain-level error signaling.
Apply this diff:
- if attr_id not in self._commission._attributes_by_id:
- # Możesz to zmienić na silent ignore lub warning/log.
- raise KeyError(
- f"Attribute id={attr_id} does not exist on this Commission instance"
- )
+ if attr_id not in self._commission._attributes_by_id:
+ # Możesz to zmienić na silent ignore lub warning/log.
+ raise SWAPIError(
+ f"Attribute id={attr_id} does not exist on this Commission instance"
+ )Committable suggestion skipped: line range outside the PR's diff.
🧰 Tools
🪛 Ruff (0.14.5)
50-52: Avoid specifying long messages outside the exception class
(TRY003)
🤖 Prompt for AI Agents
In src/swapi_client/v2/models/commission.py around lines 48 to 52, replace the
raised KeyError when an attribute id is missing with a more specific domain
error (prefer SWAPIError if available, otherwise ValueError) to avoid confusion
with internal dict key errors; import SWAPIError from its module at the top of
the file if necessary, update the raise line to use SWAPIError (or ValueError)
with the same message, and run tests/linters to ensure the new exception type is
recognized where this code is consumed.
| self._attributes_by_id = { | ||
| int(item["id"]): dict(item) | ||
| for item in raw_attrs | ||
| if "id" in item |
There was a problem hiding this comment.
Add error handling for non-integer or missing attribute IDs.
The int(item["id"]) conversion will raise an exception if item["id"] is None, missing, or not convertible to an integer. Consider adding validation or a try-except block to handle malformed data gracefully.
Apply this diff:
# 3. We własnej strukturze przechowujemy attributes
self._attributes_by_id = {
- int(item["id"]): dict(item)
- for item in raw_attrs
- if "id" in item
+ int(item["id"]): dict(item)
+ for item in raw_attrs
+ if item.get("id") is not None
}Note: This still allows int() to raise ValueError for non-numeric IDs, but at least prevents KeyError and TypeError for missing/None values. Consider wrapping in try-except if you want to silently skip malformed entries.
📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| self._attributes_by_id = { | |
| int(item["id"]): dict(item) | |
| for item in raw_attrs | |
| if "id" in item | |
| self._attributes_by_id = { | |
| int(item["id"]): dict(item) | |
| for item in raw_attrs | |
| if item.get("id") is not None | |
| } |
🤖 Prompt for AI Agents
In src/swapi_client/v2/models/commission.py around lines 109-112, the dict
comprehension uses int(item["id"]) which can raise KeyError/TypeError for
missing or None ids; replace the comprehension with an explicit loop that first
checks that "id" in item and item["id"] is not None, then attempts to convert to
int inside a try/except catching ValueError and TypeError and skipping (or
logging) malformed entries so only valid integer ids are used as keys.
| for item in new_attrs: | ||
| attr_id = item.get("id") | ||
| if attr_id is None: | ||
| continue | ||
| self._attributes_by_id[int(attr_id)] = dict(item) |
There was a problem hiding this comment.
Add error handling for non-integer attribute IDs in response.
Similar to __init__, the int(attr_id) conversion can fail if the API returns malformed data. Consider adding validation or error handling.
Apply this diff:
for item in new_attrs:
attr_id = item.get("id")
if attr_id is None:
continue
- self._attributes_by_id[int(attr_id)] = dict(item)
+ try:
+ self._attributes_by_id[int(attr_id)] = dict(item)
+ except (ValueError, TypeError):
+ # Skip malformed attribute entries
+ continue📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| for item in new_attrs: | |
| attr_id = item.get("id") | |
| if attr_id is None: | |
| continue | |
| self._attributes_by_id[int(attr_id)] = dict(item) | |
| for item in new_attrs: | |
| attr_id = item.get("id") | |
| if attr_id is None: | |
| continue | |
| try: | |
| self._attributes_by_id[int(attr_id)] = dict(item) | |
| except (ValueError, TypeError): | |
| # Skip malformed attribute entries | |
| continue |
🤖 Prompt for AI Agents
In src/swapi_client/v2/models/commission.py around lines 165 to 169, the code
calls int(attr_id) without guarding against malformed API data; wrap the
conversion in the same validation used in __init__: check that attr_id is not
None and is a valid integer (e.g. try: idx = int(attr_id) except (ValueError,
TypeError): log or warn about the bad id and continue), and only assign
self._attributes_by_id[idx] = dict(item) when the conversion succeeds so
malformed IDs are skipped instead of raising.
| class CommissionUsers(APIModel): | ||
| """ | ||
| Model Commission Usership (użytkownik zlecenia). | ||
| """ | ||
|
|
||
| endpoint = "/api/commissions_user_userss" | ||
|
|
There was a problem hiding this comment.
🧩 Analysis chain
Verify endpoint URL—possible typo with double "userss".
The endpoint /api/commissions_user_userss has a double "s" suffix ("userss") which appears unusual. Please verify whether this is the correct API endpoint or if it should be /api/commissions_user_users or /api/commission_users.
Run the following script to check for similar endpoint patterns in the codebase:
🏁 Script executed:
#!/bin/bash
# Search for other endpoints in model files to identify naming patterns
rg -n --type=py 'endpoint = "/api/commission' src/swapi_client/v2/models/Length of output: 997
Fix typo in endpoint URL at line 266.
The endpoint /api/commissions_user_userss contains a double "s" suffix. Based on the naming pattern used across all other endpoints in this file, it should be /api/commission_users.
🤖 Prompt for AI Agents
In src/swapi_client/v2/models/commission.py around lines 261 to 267, the
CommissionUsers.endpoint value is wrong: it currently reads
"/api/commissions_user_userss" — change this string to the correct endpoint
"/api/commission_users" to match the file's naming pattern and other endpoints;
update the constant in-place and run lint/tests to ensure no other references
need adjustment.
1 participant
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.