address get behaviour on 404s

Author: vdusek

docs/04_upgrading/upgrading_to_v3.mdx

@@ -218,11 +218,26 @@ except RateLimitError:
     ...
 ```
 
-### Behavior change: `.get()` now returns `None` on any 404
+### Behavior change: `.get()` on chained clients now raises on 404
 
-As a consequence of the dispatch above, `.get()`-style convenience methods — which use `catch_not_found_or_throw` internally to swallow 404 responses and return `None` — now swallow **every** 404, regardless of the `error.type` string in the response body. Previously only 404 responses carrying the types `record-not-found` or `record-or-token-not-found` were swallowed; any other 404 was re-raised as `ApifyApiError`.
+`.get()` continues to swallow 404 into `None` for direct, ID-identified fetches like `client.dataset(id).get()` or `client.run(id).get()` — a 404 there unambiguously means the named resource does not exist.
 
-In practice this matters only if you relied on a `.get()` call raising for a 404 with an unusual error type — such cases now return `None` instead. If your code needs to distinguish between "resource missing" and "404 with an unexpected type", inspect `.type` on the returned response or catch <ApiLink to="class/NotFoundError">`NotFoundError`</ApiLink> from non-`.get()` calls that do not use `catch_not_found_or_throw`.
+For chained calls that target a default sub-resource without an ID — `run.dataset()`, `run.key_value_store()`, `run.request_queue()`, `run.log()` — a 404 is ambiguous (it could mean the parent run is missing OR the default sub-resource is missing, and the API body does not disambiguate). These now raise <ApiLink to="class/NotFoundError">`NotFoundError`</ApiLink> instead of silently returning `None`:
+
+```python
+from apify_client import ApifyClient
+from apify_client.errors import NotFoundError
+
+client = ApifyClient(token='MY-APIFY-TOKEN')
+
+try:
+    dataset = client.run('some-run-id').dataset().get()
+except NotFoundError:
+    # Previously this returned `None`; now you must handle it explicitly.
+    dataset = None
+```
+
+Direct `.get()` also now swallows every 404 regardless of the `error.type` string in the response body (previously only `record-not-found` and `record-or-token-not-found` types were swallowed). If your code needs to distinguish between "resource missing" and "404 with an unexpected type", inspect `.type` on a caught <ApiLink to="class/NotFoundError">`NotFoundError`</ApiLink> from a non-`.get()` call path.
 
 ## Snake_case `sort_by` values on `actors().list()`
 

src/apify_client/_resource_clients/_resource_client.py

@@ -194,7 +194,12 @@ def __init__(
         )
 
     def _get(self, *, timeout: Timeout) -> dict | None:
-        """Perform a GET request for this resource, returning the parsed response or None if not found."""
+        """Perform a GET request for this resource, returning the parsed response or None if not found.
+
+        404s collapse to `None` only when this client targets a specific resource by ID. For chained clients
+        without a `resource_id` (e.g. `run.dataset()`), a 404 could mean either the parent or the default
+        sub-resource is missing and the API body cannot disambiguate, so `NotFoundError` propagates to the caller.
+        """
         try:
             response = self._http_client.call(
                 url=self._build_url(),
@@ -204,6 +209,8 @@ def _get(self, *, timeout: Timeout) -> dict | None:
             )
             return response_to_dict(response)
         except ApifyApiError as exc:
+            if self._resource_id is None:
+                raise
             catch_not_found_or_throw(exc)
             return None
 
@@ -374,7 +381,12 @@ def __init__(
         )
 
     async def _get(self, *, timeout: Timeout) -> dict | None:
-        """Perform a GET request for this resource, returning the parsed response or None if not found."""
+        """Perform a GET request for this resource, returning the parsed response or None if not found.
+
+        404s collapse to `None` only when this client targets a specific resource by ID. For chained clients
+        without a `resource_id` (e.g. `run.dataset()`), a 404 could mean either the parent or the default
+        sub-resource is missing and the API body cannot disambiguate, so `NotFoundError` propagates to the caller.
+        """
         try:
             response = await self._http_client.call(
                 url=self._build_url(),
@@ -384,6 +396,8 @@ async def _get(self, *, timeout: Timeout) -> dict | None:
             )
             return response_to_dict(response)
         except ApifyApiError as exc:
+            if self._resource_id is None:
+                raise
             catch_not_found_or_throw(exc)
             return None
 

tests/unit/test_client_errors.py

@@ -6,6 +6,7 @@
 import pytest
 from werkzeug import Response
 
+from apify_client import ApifyClient, ApifyClientAsync
 from apify_client._http_clients import ImpitHttpClient, ImpitHttpClientAsync
 from apify_client.errors import (
     ApifyApiError,
@@ -211,3 +212,41 @@ def test_apify_api_error_falls_back_for_unparsable_body(httpserver: HTTPServer)
 
     assert type(exc.value) is ApifyApiError
     assert exc.value.type is None
+
+
+def _not_found_body() -> dict:
+    return {'error': {'type': 'record-not-found', 'message': 'not found'}}
+
+
+def test_direct_get_returns_none_on_404(httpserver: HTTPServer) -> None:
+    """`client.dataset("X").get()` — a direct, ID-identified fetch — swallows 404 into `None`."""
+    httpserver.expect_request('/v2/datasets/missing').respond_with_json(_not_found_body(), status=404)
+    client = ApifyClient(token='test', api_url=httpserver.url_for('/').removesuffix('/'))
+
+    assert client.dataset('missing').get() is None
+
+
+async def test_direct_get_returns_none_on_404_async(httpserver: HTTPServer) -> None:
+    """Async mirror: direct `.get()` swallows 404."""
+    httpserver.expect_request('/v2/datasets/missing').respond_with_json(_not_found_body(), status=404)
+    client = ApifyClientAsync(token='test', api_url=httpserver.url_for('/').removesuffix('/'))
+
+    assert await client.dataset('missing').get() is None
+
+
+def test_chained_get_raises_on_404(httpserver: HTTPServer) -> None:
+    """`run("X").dataset().get()` is ambiguous on 404 (run or dataset missing) — propagate instead of `None`."""
+    httpserver.expect_request('/v2/actor-runs/missing-run/dataset').respond_with_json(_not_found_body(), status=404)
+    client = ApifyClient(token='test', api_url=httpserver.url_for('/').removesuffix('/'))
+
+    with pytest.raises(NotFoundError):
+        client.run('missing-run').dataset().get()
+
+
+async def test_chained_get_raises_on_404_async(httpserver: HTTPServer) -> None:
+    """Async mirror: chained `.get()` propagates NotFoundError."""
+    httpserver.expect_request('/v2/actor-runs/missing-run/dataset').respond_with_json(_not_found_body(), status=404)
+    client = ApifyClientAsync(token='test', api_url=httpserver.url_for('/').removesuffix('/'))
+
+    with pytest.raises(NotFoundError):
+        await client.run('missing-run').dataset().get()