fix: sanitize endpoint path params

Author: stainless-app[bot]

src/dedalus_sdk/_utils/__init__.py

@@ -1,3 +1,4 @@
+from ._path import path_template as path_template
 from ._sync import asyncify as asyncify
 from ._proxy import LazyProxy as LazyProxy
 from ._utils import (

src/dedalus_sdk/_utils/_path.py

@@ -0,0 +1,127 @@
+from __future__ import annotations
+
+import re
+from typing import (
+    Any,
+    Mapping,
+    Callable,
+)
+from urllib.parse import quote
+
+# Matches '.' or '..' where each dot is either literal or percent-encoded (%2e / %2E).
+_DOT_SEGMENT_RE = re.compile(r"^(?:\.|%2[eE]){1,2}$")
+
+_PLACEHOLDER_RE = re.compile(r"\{(\w+)\}")
+
+
+def _quote_path_segment_part(value: str) -> str:
+    """Percent-encode `value` for use in a URI path segment.
+
+    Considers characters not in `pchar` set from RFC 3986 §3.3 to be unsafe.
+    https://datatracker.ietf.org/doc/html/rfc3986#section-3.3
+    """
+    # quote() already treats unreserved characters (letters, digits, and -._~)
+    # as safe, so we only need to add sub-delims, ':', and '@'.
+    # Notably, unlike the default `safe` for quote(), / is unsafe and must be quoted.
+    return quote(value, safe="!$&'()*+,;=:@")
+
+
+def _quote_query_part(value: str) -> str:
+    """Percent-encode `value` for use in a URI query string.
+
+    Considers &, = and characters not in `query` set from RFC 3986 §3.4 to be unsafe.
+    https://datatracker.ietf.org/doc/html/rfc3986#section-3.4
+    """
+    return quote(value, safe="!$'()*+,;:@/?")
+
+
+def _quote_fragment_part(value: str) -> str:
+    """Percent-encode `value` for use in a URI fragment.
+
+    Considers characters not in `fragment` set from RFC 3986 §3.5 to be unsafe.
+    https://datatracker.ietf.org/doc/html/rfc3986#section-3.5
+    """
+    return quote(value, safe="!$&'()*+,;=:@/?")
+
+
+def _interpolate(
+    template: str,
+    values: Mapping[str, Any],
+    quoter: Callable[[str], str],
+) -> str:
+    """Replace {name} placeholders in `template`, quoting each value with `quoter`.
+
+    Placeholder names are looked up in `values`.
+
+    Raises:
+        KeyError: If a placeholder is not found in `values`.
+    """
+    # re.split with a capturing group returns alternating
+    # [text, name, text, name, ..., text] elements.
+    parts = _PLACEHOLDER_RE.split(template)
+
+    for i in range(1, len(parts), 2):
+        name = parts[i]
+        if name not in values:
+            raise KeyError(f"a value for placeholder {{{name}}} was not provided")
+        val = values[name]
+        if val is None:
+            parts[i] = "null"
+        elif isinstance(val, bool):
+            parts[i] = "true" if val else "false"
+        else:
+            parts[i] = quoter(str(values[name]))
+
+    return "".join(parts)
+
+
+def path_template(template: str, /, **kwargs: Any) -> str:
+    """Interpolate {name} placeholders in `template` from keyword arguments.
+
+    Args:
+        template: The template string containing {name} placeholders.
+        **kwargs: Keyword arguments to interpolate into the template.
+
+    Returns:
+        The template with placeholders interpolated and percent-encoded.
+
+        Safe characters for percent-encoding are dependent on the URI component.
+        Placeholders in path and fragment portions are percent-encoded where the `segment`
+        and `fragment` sets from RFC 3986 respectively are considered safe.
+        Placeholders in the query portion are percent-encoded where the `query` set from
+        RFC 3986 §3.3 is considered safe except for = and & characters.
+
+    Raises:
+        KeyError: If a placeholder is not found in `kwargs`.
+        ValueError: If resulting path contains /./ or /../ segments (including percent-encoded dot-segments).
+    """
+    # Split the template into path, query, and fragment portions.
+    fragment_template: str | None = None
+    query_template: str | None = None
+
+    rest = template
+    if "#" in rest:
+        rest, fragment_template = rest.split("#", 1)
+    if "?" in rest:
+        rest, query_template = rest.split("?", 1)
+    path_template = rest
+
+    # Interpolate each portion with the appropriate quoting rules.
+    path_result = _interpolate(path_template, kwargs, _quote_path_segment_part)
+
+    # Reject dot-segments (. and ..) in the final assembled path.  The check
+    # runs after interpolation so that adjacent placeholders or a mix of static
+    # text and placeholders that together form a dot-segment are caught.
+    # Also reject percent-encoded dot-segments to protect against incorrectly
+    # implemented normalization in servers/proxies.
+    for segment in path_result.split("/"):
+        if _DOT_SEGMENT_RE.match(segment):
+            raise ValueError(f"Constructed path {path_result!r} contains dot-segment {segment!r} which is not allowed")
+
+    result = path_result
+    if query_template is not None:
+        result += "?" + _interpolate(query_template, kwargs, _quote_query_part)
+    if fragment_template is not None:
+        result += "#" + _interpolate(fragment_template, kwargs, _quote_fragment_part)
+
+    return result

src/dedalus_sdk/resources/workspaces/artifacts.py

@@ -5,7 +5,7 @@
 import httpx
 
 from ..._types import Body, Omit, Query, Headers, NotGiven, omit, not_given
-from ..._utils import maybe_transform
+from ..._utils import path_template, maybe_transform
 from ..._compat import cached_property
 from ..._resource import SyncAPIResource, AsyncAPIResource
 from ..._response import (
@@ -71,7 +71,11 @@ def retrieve(
         if not artifact_id:
             raise ValueError(f"Expected a non-empty value for `artifact_id` but received {artifact_id!r}")
         return self._get(
-            f"/v1/workspaces/{workspace_id}/artifacts/{artifact_id}",
+            path_template(
+                "/v1/workspaces/{workspace_id}/artifacts/{artifact_id}",
+                workspace_id=workspace_id,
+                artifact_id=artifact_id,
+            ),
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
@@ -106,7 +110,7 @@ def list(
         if not workspace_id:
             raise ValueError(f"Expected a non-empty value for `workspace_id` but received {workspace_id!r}")
         return self._get_api_list(
-            f"/v1/workspaces/{workspace_id}/artifacts",
+            path_template("/v1/workspaces/{workspace_id}/artifacts", workspace_id=workspace_id),
             page=SyncCursorPage[Artifact],
             options=make_request_options(
                 extra_headers=extra_headers,
@@ -156,7 +160,11 @@ def delete(
         if not artifact_id:
             raise ValueError(f"Expected a non-empty value for `artifact_id` but received {artifact_id!r}")
         return self._delete(
-            f"/v1/workspaces/{workspace_id}/artifacts/{artifact_id}",
+            path_template(
+                "/v1/workspaces/{workspace_id}/artifacts/{artifact_id}",
+                workspace_id=workspace_id,
+                artifact_id=artifact_id,
+            ),
             options=make_request_options(
                 extra_headers=extra_headers,
                 extra_query=extra_query,
@@ -217,7 +225,11 @@ async def retrieve(
         if not artifact_id:
             raise ValueError(f"Expected a non-empty value for `artifact_id` but received {artifact_id!r}")
         return await self._get(
-            f"/v1/workspaces/{workspace_id}/artifacts/{artifact_id}",
+            path_template(
+                "/v1/workspaces/{workspace_id}/artifacts/{artifact_id}",
+                workspace_id=workspace_id,
+                artifact_id=artifact_id,
+            ),
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
@@ -252,7 +264,7 @@ def list(
         if not workspace_id:
             raise ValueError(f"Expected a non-empty value for `workspace_id` but received {workspace_id!r}")
         return self._get_api_list(
-            f"/v1/workspaces/{workspace_id}/artifacts",
+            path_template("/v1/workspaces/{workspace_id}/artifacts", workspace_id=workspace_id),
             page=AsyncCursorPage[Artifact],
             options=make_request_options(
                 extra_headers=extra_headers,
@@ -302,7 +314,11 @@ async def delete(
         if not artifact_id:
             raise ValueError(f"Expected a non-empty value for `artifact_id` but received {artifact_id!r}")
         return await self._delete(
-            f"/v1/workspaces/{workspace_id}/artifacts/{artifact_id}",
+            path_template(
+                "/v1/workspaces/{workspace_id}/artifacts/{artifact_id}",
+                workspace_id=workspace_id,
+                artifact_id=artifact_id,
+            ),
             options=make_request_options(
                 extra_headers=extra_headers,
                 extra_query=extra_query,

src/dedalus_sdk/resources/workspaces/executions.py

@@ -7,7 +7,7 @@
 import httpx
 
 from ..._types import Body, Omit, Query, Headers, NotGiven, SequenceNotStr, omit, not_given
-from ..._utils import maybe_transform, async_maybe_transform
+from ..._utils import path_template, maybe_transform, async_maybe_transform
 from ..._compat import cached_property
 from ..._resource import SyncAPIResource, AsyncAPIResource
 from ..._response import (
@@ -81,7 +81,7 @@ def create(
         if not workspace_id:
             raise ValueError(f"Expected a non-empty value for `workspace_id` but received {workspace_id!r}")
         return self._post(
-            f"/v1/workspaces/{workspace_id}/executions",
+            path_template("/v1/workspaces/{workspace_id}/executions", workspace_id=workspace_id),
             body=maybe_transform(
                 {
                     "command": command,
@@ -132,7 +132,11 @@ def retrieve(
         if not execution_id:
             raise ValueError(f"Expected a non-empty value for `execution_id` but received {execution_id!r}")
         return self._get(
-            f"/v1/workspaces/{workspace_id}/executions/{execution_id}",
+            path_template(
+                "/v1/workspaces/{workspace_id}/executions/{execution_id}",
+                workspace_id=workspace_id,
+                execution_id=execution_id,
+            ),
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
@@ -167,7 +171,7 @@ def list(
         if not workspace_id:
             raise ValueError(f"Expected a non-empty value for `workspace_id` but received {workspace_id!r}")
         return self._get_api_list(
-            f"/v1/workspaces/{workspace_id}/executions",
+            path_template("/v1/workspaces/{workspace_id}/executions", workspace_id=workspace_id),
             page=SyncCursorPage[Execution],
             options=make_request_options(
                 extra_headers=extra_headers,
@@ -217,7 +221,11 @@ def delete(
         if not execution_id:
             raise ValueError(f"Expected a non-empty value for `execution_id` but received {execution_id!r}")
         return self._delete(
-            f"/v1/workspaces/{workspace_id}/executions/{execution_id}",
+            path_template(
+                "/v1/workspaces/{workspace_id}/executions/{execution_id}",
+                workspace_id=workspace_id,
+                execution_id=execution_id,
+            ),
             options=make_request_options(
                 extra_headers=extra_headers,
                 extra_query=extra_query,
@@ -259,7 +267,11 @@ def events(
         if not execution_id:
             raise ValueError(f"Expected a non-empty value for `execution_id` but received {execution_id!r}")
         return self._get_api_list(
-            f"/v1/workspaces/{workspace_id}/executions/{execution_id}/events",
+            path_template(
+                "/v1/workspaces/{workspace_id}/executions/{execution_id}/events",
+                workspace_id=workspace_id,
+                execution_id=execution_id,
+            ),
             page=SyncCursorPage[ExecutionEvent],
             options=make_request_options(
                 extra_headers=extra_headers,
@@ -306,7 +318,11 @@ def output(
         if not execution_id:
             raise ValueError(f"Expected a non-empty value for `execution_id` but received {execution_id!r}")
         return self._get(
-            f"/v1/workspaces/{workspace_id}/executions/{execution_id}/output",
+            path_template(
+                "/v1/workspaces/{workspace_id}/executions/{execution_id}/output",
+                workspace_id=workspace_id,
+                execution_id=execution_id,
+            ),
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
@@ -369,7 +385,7 @@ async def create(
         if not workspace_id:
             raise ValueError(f"Expected a non-empty value for `workspace_id` but received {workspace_id!r}")
         return await self._post(
-            f"/v1/workspaces/{workspace_id}/executions",
+            path_template("/v1/workspaces/{workspace_id}/executions", workspace_id=workspace_id),
             body=await async_maybe_transform(
                 {
                     "command": command,
@@ -420,7 +436,11 @@ async def retrieve(
         if not execution_id:
             raise ValueError(f"Expected a non-empty value for `execution_id` but received {execution_id!r}")
         return await self._get(
-            f"/v1/workspaces/{workspace_id}/executions/{execution_id}",
+            path_template(
+                "/v1/workspaces/{workspace_id}/executions/{execution_id}",
+                workspace_id=workspace_id,
+                execution_id=execution_id,
+            ),
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
@@ -455,7 +475,7 @@ def list(
         if not workspace_id:
             raise ValueError(f"Expected a non-empty value for `workspace_id` but received {workspace_id!r}")
         return self._get_api_list(
-            f"/v1/workspaces/{workspace_id}/executions",
+            path_template("/v1/workspaces/{workspace_id}/executions", workspace_id=workspace_id),
             page=AsyncCursorPage[Execution],
             options=make_request_options(
                 extra_headers=extra_headers,
@@ -505,7 +525,11 @@ async def delete(
         if not execution_id:
             raise ValueError(f"Expected a non-empty value for `execution_id` but received {execution_id!r}")
         return await self._delete(
-            f"/v1/workspaces/{workspace_id}/executions/{execution_id}",
+            path_template(
+                "/v1/workspaces/{workspace_id}/executions/{execution_id}",
+                workspace_id=workspace_id,
+                execution_id=execution_id,
+            ),
             options=make_request_options(
                 extra_headers=extra_headers,
                 extra_query=extra_query,
@@ -547,7 +571,11 @@ def events(
         if not execution_id:
             raise ValueError(f"Expected a non-empty value for `execution_id` but received {execution_id!r}")
         return self._get_api_list(
-            f"/v1/workspaces/{workspace_id}/executions/{execution_id}/events",
+            path_template(
+                "/v1/workspaces/{workspace_id}/executions/{execution_id}/events",
+                workspace_id=workspace_id,
+                execution_id=execution_id,
+            ),
             page=AsyncCursorPage[ExecutionEvent],
             options=make_request_options(
                 extra_headers=extra_headers,
@@ -594,7 +622,11 @@ async def output(
         if not execution_id:
             raise ValueError(f"Expected a non-empty value for `execution_id` but received {execution_id!r}")
         return await self._get(
-            f"/v1/workspaces/{workspace_id}/executions/{execution_id}/output",
+            path_template(
+                "/v1/workspaces/{workspace_id}/executions/{execution_id}/output",
+                workspace_id=workspace_id,
+                execution_id=execution_id,
+            ),
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),