SDK-94: Try to fix pytest-sanity failing due to too many parallel runs and add Python 3.14 support

.github/workflows/pytest-sanity.yaml

@@ -9,20 +9,19 @@ on:
   merge_group:
     types: [checks_requested]
 
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
 jobs:
   pytest_sanity:
     runs-on: ${{ matrix.os }}
     permissions:
       contents: read
     strategy:
-      max-parallel: 4
+      max-parallel: 2
       matrix:
         os: [ubuntu-latest, macos-latest, windows-latest]
-        python-version: ["3.10", "3.11", "3.12", "3.13"]
+        python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
+    concurrency:
+      group: ${{ github.workflow }}-${{ github.ref }}-${{ matrix.os }}-${{ matrix.python-version }}
+      cancel-in-progress: true
     steps:
       - uses: actions/checkout@v4
         with:

VULNERABILITIES.md

@@ -0,0 +1,53 @@
+# Vulnerability Update Guide
+
+Use this file when updating dependency floors in [pyproject.toml](pyproject.toml) to address vulnerability findings.
+
+## Rules
+
+1. Keep the dependency line and its vulnerability note together.
+   Example:
+   ```toml
+   "requests>=2.33.0",
+   #  ⬆️ Required to fix vulnerability CVE-2026-25645
+   ```
+   The up-arrow comment goes immediately below the package line, not above it.
+
+2. Mention only the advisory that necessitates the current minimum version.
+   If `authlib>=1.6.11` is required because `GHSA-jj8c-mmj3-mmgv` is the first fix at that floor, mention only that advisory.
+   Do not list older advisories that are also fixed incidentally by the same newer version.
+
+3. Do not keep stale version-history commentary.
+   Keep only the final package floor and the advisory tied to that floor.
+
+4. Treat major-version upgrades as compatibility risks.
+   Before keeping a major bump such as `transformers` or `pytest`, add or run tests that exercise the affected public SDK behavior.
+
+5. Prefer the smallest safe version bump that clears the finding.
+   If a vulnerability is fixed in `46.0.6`, do not cite it as justification for `46.0.7` unless `46.0.7` is required by another active finding.
+
+## Workflow
+
+1. Update the minimum version in `pyproject.toml`.
+2. Place the vulnerability comment immediately below the changed dependency line.
+3. Recompile the dependency set from `pyproject.toml`.
+   Example:
+   ```bash
+   UV_CACHE_DIR=/tmp/uv-cache uv pip compile pyproject.toml --group dev --group docs --group deploy --extra pandas --extra polars --extra transformers -o /tmp/hirundo-all-requirements.txt
+   ```
+4. Audit the compiled output.
+   Example:
+   ```bash
+   UV_CACHE_DIR=/tmp/uv-cache uv run pip-audit --no-deps --disable-pip -r /tmp/hirundo-all-requirements.txt -f json
+   ```
+5. Run validation for compatibility-sensitive changes.
+   Commands:
+   ```bash
+   .venv/bin/pytest
+   .venv/bin/basedpyright
+   ```
+
+## Repo-specific notes
+
+- This repository has many integration-heavy tests that require credentials such as `AWS_ACCESS_KEY`, `GCP_CREDENTIALS`, and `HUGGINGFACE_ACCESS_TOKEN`.
+- If full `pytest` is unavailable because credentials are missing, report that explicitly and run any safe targeted tests that cover the changed behavior.
+- For `transformers` changes, keep coverage on the Hugging Face pipeline path in [tests/unlearning-llm/llm_pipeline_transformers_test.py](tests/unlearning-llm/llm_pipeline_transformers_test.py).

hirundo/_iter_sse_retrying.py

@@ -4,9 +4,9 @@
 from collections.abc import AsyncGenerator, Generator
 
 import httpx
-import urllib3
 from httpx_sse import ServerSentEvent, SSEError, aconnect_sse, connect_sse
 from stamina import retry
+from urllib3.exceptions import ReadTimeoutError
 
 from hirundo._http import requests
 from hirundo._timeouts import READ_TIMEOUT
@@ -41,7 +41,7 @@ def iter_sse_retrying(
         on=(
             httpx.ReadError,
             httpx.RemoteProtocolError,
-            urllib3.exceptions.ReadTimeoutError,
+            ReadTimeoutError,
         ),
         attempts=MAX_RETRIES,
     )
@@ -106,7 +106,7 @@ async def aiter_sse_retrying(
         on=(
             httpx.ReadError,
             httpx.RemoteProtocolError,
-            urllib3.exceptions.ReadTimeoutError,
+            ReadTimeoutError,
         ),
         attempts=MAX_RETRIES,
     )

hirundo/unlearning_llm.py

@@ -4,7 +4,7 @@
 from enum import Enum
 from typing import TYPE_CHECKING, Literal, overload
 
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel, ConfigDict, Field
 from tqdm import tqdm
 from tqdm.contrib.logging import logging_redirect_tqdm
 
@@ -198,15 +198,6 @@ class UnlearningLlmAdvancedOptions(BaseModel):
     max_tokens_for_model: dict[DatasetType, int] | int | None = None
 
 
-class UtilityType(str, Enum):
-    DEFAULT = "DEFAULT"
-    CUSTOM = "CUSTOM"
-
-
-class DefaultUtility(BaseModel):
-    utility_type: Literal[UtilityType.DEFAULT] = UtilityType.DEFAULT
-
-
 class HirundoCSVDataset(BaseModel):
     type: Literal["HirundoCSV"] = "HirundoCSV"
     csv_url: str
@@ -221,7 +212,6 @@ class HuggingFaceDataset(BaseModel):
 
 
 class CustomUtility(BaseModel):
-    utility_type: Literal[UtilityType.CUSTOM] = UtilityType.CUSTOM
     dataset: CustomDataset
 
 
@@ -256,44 +246,36 @@ class CustomBehavior(BaseModel):
     BiasBehavior | HallucinationBehavior | SecurityBehavior | CustomBehavior
 )
 
-TargetUtility = DefaultUtility | CustomUtility
-
 
 class LlmRunInfo(BaseModel):
     model_config = ConfigDict(protected_namespaces=("model_validate", "model_dump"))
 
     organization_id: int | None = None
     name: str | None = None
     target_behaviors: list[TargetBehavior]
-    target_utilities: list[TargetUtility]
+    target_utilities: list[CustomUtility] = Field(default_factory=list)
     advanced_options: UnlearningLlmAdvancedOptions | None = None
 
 
 class BiasRunInfo(BaseModel):
     bias_type: BBQBiasType
     organization_id: int | None = None
     name: str | None = None
-    target_utilities: list[TargetUtility] | None = None
+    target_utilities: list[CustomUtility] = Field(default_factory=list)
     advanced_options: UnlearningLlmAdvancedOptions | None = None
 
     def to_run_info(self) -> LlmRunInfo:
-        default_utilities: list[TargetUtility] = (
-            [DefaultUtility()]
-            if self.target_utilities is None
-            else list(self.target_utilities)
-        )
         return LlmRunInfo(
             organization_id=self.organization_id,
             name=self.name,
             target_behaviors=[BiasBehavior(bias_type=self.bias_type)],
-            target_utilities=default_utilities,
+            target_utilities=self.target_utilities,
             advanced_options=self.advanced_options,
         )
 
 
 OutputLlm = dict[str, object]
 BehaviorOptions = TargetBehavior
-UtilityOptions = TargetUtility
 CeleryTaskState = str
 
 
@@ -305,7 +287,7 @@ class OutputUnlearningLlmRun(BaseModel):
     model_id: int
     model: OutputLlm
     target_behaviors: list[BehaviorOptions]
-    target_utilities: list[UtilityOptions]
+    target_utilities: list[CustomUtility]
     advanced_options: UnlearningLlmAdvancedOptions | None
     run_id: str
     mlflow_run_id: str | None

pyproject.toml

@@ -22,18 +22,20 @@ requires-python = ">= 3.10"
 dependencies = [
     "pyyaml>=6.0.1",
     "types-PyYAML>=6.0.12",
-    "pydantic>=2.7.1",
-    "python-dotenv>=1.0.1",
+    "pydantic>=2.13.0",
+    #  ⬆️ Required for Python 3.14 support
+    "python-dotenv>=1.2.2",
+    #  ⬆️ Required to fix vulnerability CVE-2026-28684
     "types-requests>=2.31.0",
     "typer>=0.12.3",
     "httpx>=0.27.0",
     "stamina>=24.2.0",
     "httpx-sse>=0.4.0",
     "tqdm>=4.66.5",
     "h11>=0.16.0",
+    "requests>=2.33.0",
     #  ⬆️ Required to fix vulnerability GHSA-vqfr-h8mv-ghfj
-    "requests>=2.32.4",
-    #  ⬆️ Required to fix vulnerability GHSA-9hjg-9r4m-mvj7
+    #  ⬆️ Required to fix vulnerability CVE-2026-25645
     "urllib3>=2.6.3",
     #  ⬆️ Required to fix vulnerability CVE-2026-21441
     "setuptools>=78.1.1",
@@ -51,28 +53,34 @@ Homepage = "https://github.com/Hirundo-io/hirundo-python-sdk"
 [project.optional-dependencies]
 pandas = ["pandas>=2.2.3"]
 polars = ["polars>=1.0.0"]
-transformers = ["transformers>=4.57.3", "peft>=0.18.1", "accelerate>=1.12.0"]
+transformers = [
+    "transformers>=5.0.0rc3",
+    #  ⬆️ Required to fix vulnerability CVE-2026-1839
+    "peft>=0.18.1",
+    "accelerate>=1.12.0",
+]
 
 [dependency-groups]
 dev = [
     "hirundo[pandas,polars,transformers]",
     "numpy>=2.1.3; sys_platform == 'darwin'",
     #  ⬆️ Ensure macOS runners resolve a NumPy version with prebuilt wheels in `pytest_sanity`.
     "types-setuptools>=69.5.0",
-    "pytest>=8.2.0",
+    "pytest>=9.0.3",
+    #  ⬆️ Required to fix vulnerability CVE-2025-71176
     "pytest-asyncio>=0.23.6",
-    "uv>=0.9.29",
+    "uv>=0.11.6",
+    #  ⬆️ Required to fix vulnerability GHSA-pjjw-68hj-v9mw
     "pre-commit>=3.7.1",
     "basedpyright==1.37.1",
     "virtualenv>=20.36.1",
-    #  ⬆️ Needed for `pre-commit` version fix for vulnerability GHSA-rqc4-2hc7-8c8v
-    "authlib>=1.6.6",
-    #  ⬆️ Required to fix vulnerability CVE-2025-68158
+    "authlib>=1.6.11",
+    #  ⬆️ Required to fix vulnerability GHSA-jj8c-mmj3-mmgv
     "ruff>=0.12.0",
     "bumpver>=2025.1131",
     "platformdirs>=4.3.6",
-    "cryptography>=46.0.5",
-    #  ⬆️ Required to fix vulnerability CVE-2026-26007
+    "cryptography>=46.0.7",
+    #  ⬆️ Required to fix vulnerability CVE-2026-39892
     "jinja2>=3.1.6",
     #  ⬆️ Required to fix vulnerabilities GHSA-cpwx-vrp4-4pq7 , GHSA-gmj6-6f8f-6699 & GHSA-q2x7-8rv6-6q7h
     "filelock>=3.20.3",
@@ -204,4 +212,5 @@ exclude = [
     "private",
     "notebooks",
     ".venv",
+    "build",
 ]