PYTHON-5366 - test_pool_reset waits until Pool.reset() increments gen… (#2797)

Co-authored-by: Qi Deng <qdeng@aurascape.ai>

.codecov.yml

@@ -0,0 +1,4 @@
+# do not notify until at least 100 builds have been uploaded from the CI pipeline
+# you can also set after_n_builds on comments independently
+comment:
+  after_n_builds: 100

.evergreen/combine-coverage.sh

@@ -5,19 +5,12 @@
 
 set -eu
 
-. .evergreen/utils.sh
+# Set up the virtual env.
+. .evergreen/scripts/setup-dev-env.sh
+uv sync --group coverage
+source .venv/bin/activate
 
-if [ -z "${PYTHON_BINARY:-}" ]; then
-    PYTHON_BINARY=$(find_python3)
-fi
-
-createvirtualenv "$PYTHON_BINARY" covenv
-# Keep in sync with run-tests.sh
-# coverage >=5 is needed for relative_files=true.
-pip install -q "coverage[toml]>=5,<=7.5"
-
-pip list
 ls -la coverage/
 
-python -m coverage combine coverage/coverage.*
+coverage combine coverage/coverage.*
-python -m coverage html -d htmlcov
+coverage html -d htmlcov

.evergreen/config.yml

@@ -29,114 +29,6 @@ include:
   - filename: .evergreen/generated_configs/tasks.yml
   - filename: .evergreen/generated_configs/variants.yml
 
-functions:
-  "fetch source":
-    # Executes clone and applies the submitted patch, if any
-    - command: git.get_project
-      params:
-        directory: "src"
-    # Applies the subitted patch, if any
-    # Deprecated. Should be removed. But still needed for certain agents (ZAP)
-    - command: git.apply_patch
-
-  "setup system":
-    # Make an evergreen expansion file with dynamic values
-    - command: subprocess.exec
-      params:
-        include_expansions_in_env: ["is_patch", "project", "version_id"]
-        binary: bash
-        working_dir: "src"
-        args:
-          - .evergreen/scripts/setup-system.sh
-    # Load the expansion file to make an evergreen variable with the current unique version
-    - command: expansions.update
-      params:
-        file: src/expansion.yml
-
-  "upload test results":
-    - command: attach.results
-      params:
-        file_location: "${DRIVERS_TOOLS}/results.json"
-    - command: attach.xunit_results
-      params:
-        file: "src/xunit-results/TEST-*.xml"
-
-  "run server":
-    - command: subprocess.exec
-      params:
-        binary: bash
-        working_dir: "src"
-        include_expansions_in_env: [VERSION, TOPOLOGY, AUTH, SSL, ORCHESTRATION_FILE, PYTHON_BINARY, PYTHON_VERSION,
-          STORAGE_ENGINE, REQUIRE_API_VERSION, DRIVERS_TOOLS, TEST_CRYPT_SHARED, AUTH_AWS, LOAD_BALANCER, LOCAL_ATLAS]
-        args: [.evergreen/just.sh, run-server, "${TEST_NAME}"]
-    - command: expansions.update
-      params:
-        file: ${DRIVERS_TOOLS}/mo-expansion.yml
-
-  "run just script":
-    - command: subprocess.exec
-      type: test
-      params:
-       include_expansions_in_env: [AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_SESSION_TOKEN]
-       binary: bash
-       working_dir: "src"
-       args: [.evergreen/just.sh, "${JUSTFILE_TARGET}"]
-
-  "run tests":
-    - command: subprocess.exec
-      type: test
-      params:
-        include_expansions_in_env: [AUTH, SSL, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY,
-          AWS_SESSION_TOKEN, COVERAGE, PYTHON_BINARY, LIBMONGOCRYPT_URL, MONGODB_URI, PYTHON_VERSION,
-          DISABLE_TEST_COMMANDS, GREEN_FRAMEWORK, NO_EXT, COMPRESSORS, MONGODB_API_VERSION, DEBUG_LOG,
-          ORCHESTRATION_FILE, OCSP_SERVER_TYPE, VERSION]
-        binary: bash
-        working_dir: "src"
-        args: [.evergreen/just.sh, setup-tests, "${TEST_NAME}", "${SUB_TEST_NAME}"]
-    - command: subprocess.exec
-      type: test
-      params:
-        working_dir: "src"
-        binary: bash
-        args: [.evergreen/just.sh, run-tests]
-
-  "cleanup":
-    - command: subprocess.exec
-      params:
-        binary: bash
-        working_dir: "src"
-        args:
-          - .evergreen/scripts/cleanup.sh
-
-  "teardown system":
-    - command: subprocess.exec
-      params:
-          binary: bash
-          working_dir: "src"
-          args: [.evergreen/just.sh, teardown-tests]
-    - command: subprocess.exec
-      params:
-        binary: bash
-        working_dir: "src"
-        args:
-          - ${DRIVERS_TOOLS}/.evergreen/teardown.sh
-
-  "assume ec2 role":
-    - command: ec2.assume_role
-      params:
-        role_arn: ${aws_test_secrets_role}
-        duration_seconds: 3600
-
-  "attach benchmark test results":
-    - command: attach.results
-      params:
-        file_location: src/report.json
-
-  "send dashboard data":
-    - command: perf.send
-      params:
-        file: src/results.json
-
 pre:
   - func: "fetch source"
   - func: "setup system"
@@ -146,7 +38,28 @@ post:
   # Disabled, causing timeouts
   # - func: "upload working dir"
   - func: "teardown system"
+  - func: "upload codecov"
   - func: "upload coverage"
   - func: "upload mo artifacts"
   - func: "upload test results"
   - func: "cleanup"
+
+tasks:
+  - name: resync_specs
+    commands:
+      - command: subprocess.exec
+        params:
+          binary: bash
+          include_expansions_in_env: [AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_SESSION_TOKEN]
+          args:
+            - .evergreen/scripts/resync-all-specs.sh
+          working_dir: src
+
+buildvariants:
+  - name: resync_specs
+    display_name: "Resync Specs"
+    run_on: rhel80-small
+    cron: '0 16 * * MON'
+    patchable: true
+    tasks:
+      - name: resync_specs

.evergreen/generated_configs/functions.yml

@@ -1,4 +1,27 @@
 functions:
+  # Assume ec2 role
+  assume ec2 role:
+    - command: ec2.assume_role
+      params:
+        role_arn: ${aws_test_secrets_role}
+        duration_seconds: 3600
+
+  # Attach benchmark test results
+  attach benchmark test results:
+    - command: attach.results
+      params:
+        file_location: src/report.json
+
+  # Cleanup
+  cleanup:
+    - command: subprocess.exec
+      params:
+        binary: bash
+        args:
+          - .evergreen/scripts/cleanup.sh
+        working_dir: src
+      type: test
+
   # Download and merge coverage
   download and merge coverage:
     - command: ec2.assume_role
@@ -56,6 +79,200 @@ functions:
         optional: "true"
       type: setup
 
+  # Fetch source
+  fetch source:
+    - command: git.get_project
+      params:
+        directory: src
+
+  # Run server
+  run server:
+    - command: subprocess.exec
+      params:
+        binary: bash
+        args:
+          - .evergreen/just.sh
+          - run-server
+          - ${TEST_NAME}
+        working_dir: src
+        include_expansions_in_env:
+          - VERSION
+          - TOPOLOGY
+          - AUTH
+          - SSL
+          - ORCHESTRATION_FILE
+          - UV_PYTHON
+          - TOOLCHAIN_VERSION
+          - STORAGE_ENGINE
+          - REQUIRE_API_VERSION
+          - DRIVERS_TOOLS
+          - TEST_CRYPT_SHARED
+          - AUTH_AWS
+          - LOAD_BALANCER
+          - LOCAL_ATLAS
+          - NO_EXT
+      type: test
+    - command: expansions.update
+      params:
+        file: ${DRIVERS_TOOLS}/mo-expansion.yml
+
+  # Run tests
+  run tests:
+    - command: subprocess.exec
+      params:
+        binary: bash
+        args:
+          - .evergreen/just.sh
+          - setup-tests
+          - ${TEST_NAME}
+          - ${SUB_TEST_NAME}
+        working_dir: src
+        include_expansions_in_env:
+          - AUTH
+          - SSL
+          - AWS_ACCESS_KEY_ID
+          - AWS_SECRET_ACCESS_KEY
+          - AWS_SESSION_TOKEN
+          - COVERAGE
+          - UV_PYTHON
+          - LIBMONGOCRYPT_URL
+          - MONGODB_URI
+          - TOOLCHAIN_VERSION
+          - DISABLE_TEST_COMMANDS
+          - GREEN_FRAMEWORK
+          - NO_EXT
+          - COMPRESSORS
+          - MONGODB_API_VERSION
+          - REQUIRE_API_VERSION
+          - DEBUG_LOG
+          - DISABLE_FLAKY
+          - ORCHESTRATION_FILE
+          - OCSP_SERVER_TYPE
+          - VERSION
+          - IS_WIN32
+          - REQUIRE_FIPS
+          - TEST_MIN_DEPS
+      type: test
+    - command: subprocess.exec
+      params:
+        binary: bash
+        args:
+          - .evergreen/just.sh
+          - run-tests
+        working_dir: src
+      type: test
+
+  # Send dashboard data
+  send dashboard data:
+    - command: subprocess.exec
+      params:
+        binary: bash
+        args:
+          - .evergreen/scripts/perf-submission-setup.sh
+        working_dir: src
+        include_expansions_in_env:
+          - requester
+          - revision_order_id
+          - project_id
+          - version_id
+          - build_variant
+          - parsed_order_id
+          - task_name
+          - task_id
+          - execution
+          - is_mainline
+      type: test
+    - command: expansions.update
+      params:
+        file: src/expansion.yml
+    - command: subprocess.exec
+      params:
+        binary: bash
+        args:
+          - .evergreen/scripts/perf-submission.sh
+        working_dir: src
+        include_expansions_in_env:
+          - requester
+          - revision_order_id
+          - project_id
+          - version_id
+          - build_variant
+          - parsed_order_id
+          - task_name
+          - task_id
+          - execution
+          - is_mainline
+      type: test
+
+  # Setup system
+  setup system:
+    - command: subprocess.exec
+      params:
+        binary: bash
+        args:
+          - .evergreen/scripts/setup-system.sh
+        working_dir: src
+        include_expansions_in_env:
+          - is_patch
+          - project
+          - version_id
+      type: test
+    - command: expansions.update
+      params:
+        file: src/expansion.yml
+
+  # Teardown system
+  teardown system:
+    - command: subprocess.exec
+      params:
+        binary: bash
+        args:
+          - .evergreen/just.sh
+          - teardown-tests
+        working_dir: src
+      type: test
+    - command: subprocess.exec
+      params:
+        binary: bash
+        args:
+          - ${DRIVERS_TOOLS}/.evergreen/teardown.sh
+        working_dir: src
+      type: test
+
+  # Test numpy
+  test numpy:
+    - command: subprocess.exec
+      params:
+        binary: bash
+        args:
+          - .evergreen/just.sh
+          - test-numpy
+        working_dir: src
+        include_expansions_in_env:
+          - TOOLCHAIN_VERSION
+          - COVERAGE
+      type: test
+
+  # Upload coverage codecov
+  upload codecov:
+    - command: subprocess.exec
+      params:
+        binary: bash
+        args:
+          - .evergreen/scripts/upload-codecov.sh
+        working_dir: src
+        include_expansions_in_env:
+          - CODECOV_TOKEN
+          - build_variant
+          - task_name
+          - github_commit
+          - github_pr_number
+          - github_pr_head_branch
+          - github_author
+          - requester
+          - branch_name
+      type: test
+
   # Upload coverage
   upload coverage:
     - command: ec2.assume_role
@@ -115,3 +332,12 @@ functions:
         display_name: drivers-tools-logs.tar.gz
         optional: "true"
       type: setup
+
+  # Upload test results
+  upload test results:
+    - command: attach.results
+      params:
+        file_location: ${DRIVERS_TOOLS}/results.json
+    - command: attach.xunit_results
+      params:
+        file: src/xunit-results/TEST-*.xml

.evergreen/remove-unimplemented-tests.sh

@@ -0,0 +1,56 @@
+#!/bin/bash
+PYMONGO=$(dirname "$(cd "$(dirname "$0")" || exit; pwd)")
+
+rm $PYMONGO/test/transactions/legacy/errors-client.json  # PYTHON-1894
+rm $PYMONGO/test/connection_monitoring/wait-queue-fairness.json  # PYTHON-1873
+rm $PYMONGO/test/discovery_and_monitoring/unified/pool-clear-application-error.json  # PYTHON-4918
+rm $PYMONGO/test/discovery_and_monitoring/unified/pool-clear-checkout-error.json  # PYTHON-4918
+rm $PYMONGO/test/discovery_and_monitoring/unified/pool-clear-min-pool-size-error.json  # PYTHON-4918
+rm $PYMONGO/test/client-side-encryption/spec/unified/client-bulkWrite-qe.json  # PYTHON-4929
+
+# Python doesn't implement DRIVERS-3064
+rm $PYMONGO/test/collection_management/listCollections-rawdata.json
+rm $PYMONGO/test/crud/unified/aggregate-rawdata.json
+rm $PYMONGO/test/crud/unified/bulkWrite-deleteMany-rawdata.json
+rm $PYMONGO/test/crud/unified/bulkWrite-deleteOne-rawdata.json
+rm $PYMONGO/test/crud/unified/bulkWrite-replaceOne-rawdata.json
+rm $PYMONGO/test/crud/unified/bulkWrite-updateMany-rawdata.json
+rm $PYMONGO/test/crud/unified/bulkWrite-updateOne-rawdata.json
+rm $PYMONGO/test/crud/unified/client-bulkWrite-delete-rawdata.json
+rm $PYMONGO/test/crud/unified/client-bulkWrite-replaceOne-rawdata.json
+rm $PYMONGO/test/crud/unified/client-bulkWrite-update-rawdata.json
+rm $PYMONGO/test/crud/unified/count-rawdata.json
+rm $PYMONGO/test/crud/unified/countDocuments-rawdata.json
+rm $PYMONGO/test/crud/unified/db-aggregate-rawdata.json
+rm $PYMONGO/test/crud/unified/deleteMany-rawdata.json
+rm $PYMONGO/test/crud/unified/deleteOne-rawdata.json
+rm $PYMONGO/test/crud/unified/distinct-rawdata.json
+rm $PYMONGO/test/crud/unified/estimatedDocumentCount-rawdata.json
+rm $PYMONGO/test/crud/unified/find-rawdata.json
+rm $PYMONGO/test/crud/unified/findOneAndDelete-rawdata.json
+rm $PYMONGO/test/crud/unified/findOneAndReplace-rawdata.json
+rm $PYMONGO/test/crud/unified/findOneAndUpdate-rawdata.json
+rm $PYMONGO/test/crud/unified/insertMany-rawdata.json
+rm $PYMONGO/test/crud/unified/insertOne-rawdata.json
+rm $PYMONGO/test/crud/unified/replaceOne-rawdata.json
+rm $PYMONGO/test/crud/unified/updateMany-rawdata.json
+rm $PYMONGO/test/crud/unified/updateOne-rawdata.json
+rm $PYMONGO/test/index_management/index-rawdata.json
+
+# PyMongo does not support modifyCollection
+rm $PYMONGO/test/collection_management/modifyCollection-*.json
+
+# PYTHON-5248 - Remove support for MongoDB 4.0
+find /$PYMONGO/test -type f -name 'pre-42-*.json' -delete
+
+# PYTHON-3359 - Remove Database and Collection level timeout override
+rm $PYMONGO/test/csot/override-collection-timeoutMS.json
+rm $PYMONGO/test/csot/override-database-timeoutMS.json
+
+# PYTHON-2943 - Socks5 Proxy Support
+rm $PYMONGO/test/uri_options/proxy-options.json
+
+# PYTHON-5517 - Avoid clearing the connection pool when the server connection rate limiter triggers
+rm $PYMONGO/test/discovery_and_monitoring/unified/backpressure-*.json
+
+echo "Done removing unimplemented tests"

.evergreen/resync-specs.sh

@@ -45,9 +45,12 @@ then
 fi
 
 # Ensure the JSON files are up to date.
-cd $SPECS/source
+if ! [ -n "${CI:-}" ]
-make
+then
-cd -
+  cd $SPECS/source
+  make
+  cd -
+fi
 # cpjson unified-test-format/tests/invalid unified-test-format/invalid
 # * param1: Path to spec tests dir in specifications repo
 # * param2: Path to where the corresponding tests live in Python.
@@ -73,9 +76,6 @@ do
     auth)
       cpjson auth/tests/ auth
       ;;
-    atlas-data-lake-testing|data_lake)
-      cpjson atlas-data-lake-testing/tests/ data_lake
-      ;;
     bson-binary-vector|bson_binary_vector)
       cpjson bson-binary-vector/tests/ bson_binary_vector
       ;;
@@ -94,6 +94,9 @@ do
     change-streams|change_streams)
       cpjson change-streams/tests/ change_streams/
       ;;
+    client-backpressure|client_backpressure)
+      cpjson client-backpressure/tests client-backpressure
+      ;;
     client-side-encryption|csfle|fle)
       cpjson client-side-encryption/tests/ client-side-encryption/spec
       cpjson client-side-encryption/corpus/ client-side-encryption/corpus
@@ -110,7 +113,6 @@ do
     cmap|CMAP|connection-monitoring-and-pooling)
       cpjson connection-monitoring-and-pooling/tests/logging connection_logging
       cpjson connection-monitoring-and-pooling/tests/cmap-format connection_monitoring
-      rm $PYMONGO/test/connection_monitoring/wait-queue-fairness.json  # PYTHON-1873
       ;;
     apm|APM|command-monitoring|command_monitoring)
       cpjson command-logging-and-monitoring/tests/monitoring command_monitoring
@@ -131,6 +133,9 @@ do
     gridfs)
       cpjson gridfs/tests gridfs
       ;;
+    handshake)
+      cpjson mongodb-handshake/tests handshake
+      ;;
     index|index-management)
       cpjson index-management/tests index_management
       ;;
@@ -171,7 +176,7 @@ do
       ;;
     server-selection|server_selection)
       cpjson server-selection/tests/ server_selection
-      rm -rf $PYMONGO/test/server_selection/logging
+      rm -rf $PYMONGO/test/server_selection/logging  # these tests live in server_selection_logging
       cpjson server-selection/tests/logging server_selection_logging
       ;;
     server-selection-logging|server_selection_logging)
@@ -183,7 +188,6 @@ do
     transactions|transactions-convenient-api)
       cpjson transactions/tests/ transactions
       cpjson transactions-convenient-api/tests/ transactions-convenient-api
-      rm $PYMONGO/test/transactions/legacy/errors-client.json  # PYTHON-1894
       ;;
     unified|unified-test-format)
       cpjson unified-test-format/tests/ unified-test-format/

.evergreen/run-mongodb-aws-ecs-test.sh

@@ -19,15 +19,14 @@ fi
 # Now we can safely enable xtrace
 set -o xtrace
 
-# Install python with pip.
+# Install a c compiler.
-PYTHON_VER="python3.9"
 apt-get -qq update  < /dev/null > /dev/null
-apt-get -qq install $PYTHON_VER $PYTHON_VER-venv build-essential $PYTHON_VER-dev -y  < /dev/null > /dev/null
+apt-get -q install -y build-essential
 
-export PYTHON_BINARY=$PYTHON_VER
 export SET_XTRACE_ON=1
 cd src
 rm -rf .venv
 rm -f .evergreen/scripts/test-env.sh || true
+rm -f .evergreen/scripts/env.sh || true
 bash ./.evergreen/just.sh setup-tests auth_aws ecs-remote
 bash .evergreen/just.sh run-tests

.evergreen/run-mongodb-oidc-test.sh

@@ -8,7 +8,9 @@ if [ ${OIDC_ENV} == "k8s" ]; then
     SUB_TEST_NAME=$K8S_VARIANT-remote
 else
     SUB_TEST_NAME=$OIDC_ENV-remote
+    sudo apt-get install -y python3-dev build-essential
 fi
+
 bash ./.evergreen/just.sh setup-tests auth_oidc $SUB_TEST_NAME
 bash ./.evergreen/just.sh run-tests "${@:1}"
 

.evergreen/run-tests.sh

@@ -6,7 +6,8 @@ SCRIPT_DIR=$(dirname ${BASH_SOURCE:-$0})
 SCRIPT_DIR="$( cd -- "$SCRIPT_DIR" > /dev/null 2>&1 && pwd )"
 ROOT_DIR="$(dirname $SCRIPT_DIR)"
 
-pushd $ROOT_DIR
+PREV_DIR=$(pwd)
+cd $ROOT_DIR
 
 # Try to source the env file.
 if [ -f $SCRIPT_DIR/scripts/env.sh ]; then
@@ -25,14 +26,20 @@ else
   exit 1
 fi
 
-# List the packages.
+cleanup_tests() {
-uv sync ${UV_ARGS} --reinstall
+  # Avoid leaving the lock file in a changed state when we change the resolution type.
-uv pip list
+  if [ -n "${TEST_MIN_DEPS:-}" ]; then
+    git checkout uv.lock || true
+  fi
+  cd $PREV_DIR
+}
 
-# Ensure we go back to base environment after the test.
+trap "cleanup_tests" SIGINT ERR
-trap "uv sync" EXIT HUP
 
 # Start the test runner.
-uv run ${UV_ARGS} .evergreen/scripts/run_tests.py "$@"
+echo "Running tests with UV_PYTHON=${UV_PYTHON:-}..."
+echo "UV_ARGS=${UV_ARGS}"
+uv run ${UV_ARGS} --reinstall-package pymongo .evergreen/scripts/run_tests.py "$@"
+echo "Running tests with UV_PYTHON=${UV_PYTHON:-}... done."
 
-popd
+cleanup_tests

.evergreen/scripts/check-import-time.sh

@@ -11,11 +11,10 @@ pushd $HERE/../.. >/dev/null
 BASE_SHA="$1"
 HEAD_SHA="$2"
 
-. .evergreen/utils.sh
+# Set up the virtual env.
-
+. $HERE/setup-dev-env.sh
-if [ -z "${PYTHON_BINARY:-}" ]; then
+uv venv --seed
-    PYTHON_BINARY=$(find_python3)
+source .venv/bin/activate
-fi
 
 # Use the previous commit if this was not a PR run.
 if [ "$BASE_SHA" == "$HEAD_SHA" ]; then
@@ -24,7 +23,6 @@ fi
 
 function get_import_time() {
     local log_file
-    createvirtualenv "$PYTHON_BINARY" import-venv
     python -m pip install -q ".[aws,encryption,gssapi,ocsp,snappy,zstd]"
     # Import once to cache modules
     python -c "import pymongo"

.evergreen/scripts/configure-env.sh

@@ -96,7 +96,7 @@ EOT
 _bin_path=""
 if [ "Windows_NT" == "${OS:-}" ]; then
   _bin_path="/cygdrive/c/Python/Current/Scripts"
-elif [ "$(uname -s)" != "Darwin" ]; then
+elif [ "$(uname -s)" == "Darwin" ]; then
   _bin_path="/Library/Frameworks/Python.Framework/Versions/Current/bin"
 else
   _bin_path="/opt/python/Current/bin"
@@ -106,6 +106,7 @@ if [ -d "${_bin_path}" ]; then
   if [ "Windows_NT" == "${OS:-}" ]; then
     _suffix=".exe"
   fi
+  echo "Symlinking binaries from toolchain"
   mkdir -p $PYMONGO_BIN_DIR
   ln -s ${_bin_path}/just${_suffix} $PYMONGO_BIN_DIR/just${_suffix}
   ln -s ${_bin_path}/uv${_suffix} $PYMONGO_BIN_DIR/uv${_suffix}

.evergreen/scripts/create-spec-pr.sh

@@ -0,0 +1,50 @@
+#!/usr/bin/env bash
+
+tools="$(realpath -s "../drivers-tools")"
+pushd $tools/.evergreen/github_app || exit
+
+owner="mongodb"
+repo="mongo-python-driver"
+
+# Bootstrap the app.
+echo "bootstrapping"
+source utils.sh
+bootstrap drivers/comment-bot
+
+# Run the app.
+source ./secrets-export.sh
+
+# Get a github access token for the git checkout.
+echo "Getting github token..."
+
+token=$(bash ./get-access-token.sh $repo $owner)
+if [ -z "${token}" ]; then
+    echo "Failed to get github access token!"
+    popd || exit
+    exit 1
+fi
+echo "Getting github token... done."
+popd || exit
+
+# Make the git checkout and create a new branch.
+echo "Creating the git checkout..."
+branch="spec-resync-"$(date '+%m-%d-%Y')
+
+git remote set-url origin https://x-access-token:${token}@github.com/$owner/$repo.git
+git checkout -b $branch "origin/master"
+git add ./test
+git commit -am "resyncing specs $(date '+%m-%d-%Y')"
+echo "Creating the git checkout... done."
+
+git push origin $branch
+resp=$(curl -L \
+    -X POST \
+    -H "Accept: application/vnd.github+json" \
+    -H "Authorization: Bearer $token" \
+    -H "X-GitHub-Api-Version: 2022-11-28" \
+    -d "{\"title\":\"[Spec Resync] $(date '+%m-%d-%Y')\",\"body\":\"$(cat "$1")\",\"head\":\"${branch}\",\"base\":\"master\"}" \
+    --url https://api.github.com/repos/$owner/$repo/pulls)
+echo $resp | jq '.html_url'
+echo "Creating the PR... done."
+
+rm -rf $tools

.evergreen/scripts/generate_config_utils.py

@@ -0,0 +1,357 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from inspect import getmembers, isfunction
+from itertools import cycle, zip_longest
+from pathlib import Path
+from typing import Any
+
+from shrub.v3.evg_build_variant import BuildVariant
+from shrub.v3.evg_command import (
+    EvgCommandType,
+    ec2_assume_role,
+    s3_put,
+    subprocess_exec,
+)
+from shrub.v3.evg_project import EvgProject
+from shrub.v3.evg_task import EvgTaskRef
+from shrub.v3.shrub_service import ShrubService
+
+##############
+# Globals
+##############
+
+ALL_VERSIONS = ["4.2", "4.4", "5.0", "6.0", "7.0", "8.0", "rapid", "latest"]
+CPYTHONS = ["3.10", "3.11", "3.12", "3.13", "3.14t", "3.14"]
+PYPYS = ["pypy3.11"]
+MIN_SUPPORT_VERSIONS = ["3.9", "pypy3.9", "pypy3.10"]
+ALL_PYTHONS = CPYTHONS + PYPYS
+MIN_MAX_PYTHON = [CPYTHONS[0], CPYTHONS[-1]]
+BATCHTIME_WEEK = 10080
+BATCHTIME_DAY = 1440
+AUTH_SSLS = [("auth", "ssl"), ("noauth", "ssl"), ("noauth", "nossl")]
+TOPOLOGIES = ["standalone", "replica_set", "sharded_cluster"]
+C_EXTS = ["without_ext", "with_ext"]
+SYNCS = ["sync", "async"]
+DISPLAY_LOOKUP = dict(
+    ssl=dict(ssl="SSL", nossl="NoSSL"),
+    auth=dict(auth="Auth", noauth="NoAuth"),
+    topology=dict(
+        standalone="Standalone", replica_set="Replica Set", sharded_cluster="Sharded Cluster"
+    ),
+    test_suites=dict(default="Sync", default_async="Async"),
+    sync={"sync": "Sync", "async": "Async"},
+    coverage={"1": "cov"},
+    no_ext={"1": "No C"},
+    test_min_deps={"1": "Min Deps"},
+)
+HOSTS = dict()
+
+
+@dataclass
+class Host:
+    name: str
+    run_on: str
+    display_name: str
+    variables: dict[str, str] | None
+
+
+# Hosts with toolchains.
+HOSTS["rhel8"] = Host("rhel8", "rhel87-small", "RHEL8", dict())
+HOSTS["win64"] = Host("win64", "windows-64-vsMulti-small", "Win64", dict())
+HOSTS["win-latest"] = Host("win-latest", "windows-2022-latest-small", "WinLatest", dict())
+HOSTS["win32"] = Host("win32", "windows-64-vsMulti-small", "Win32", dict())
+HOSTS["macos"] = Host("macos", "macos-14", "macOS", dict())
+HOSTS["macos-arm64"] = Host("macos-arm64", "macos-14-arm64", "macOS Arm64", dict())
+HOSTS["ubuntu22"] = Host("ubuntu22", "ubuntu2204-small", "Ubuntu-22", dict())
+HOSTS["ubuntu24"] = Host("ubuntu24", "ubuntu2404-small", "Ubuntu-24", dict())
+HOSTS["perf"] = Host("perf", "rhel90-dbx-perf-large", "", dict())
+HOSTS["debian11"] = Host("debian11", "debian11-small", "Debian11", dict())
+DEFAULT_HOST = HOSTS["rhel8"]
+
+# Other hosts
+OTHER_HOSTS = ["RHEL9-FIPS", "RHEL8-zseries", "RHEL8-POWER8", "RHEL8-arm64", "Amazon2023"]
+for name, run_on in zip(
+    OTHER_HOSTS,
+    [
+        "rhel92-fips",
+        "rhel8-zseries-small",
+        "rhel8-power-small",
+        "rhel82-arm64-small",
+        "amazon2023-arm64-latest-large-m8g",
+    ],
+):
+    HOSTS[name] = Host(name, run_on, name, dict())
+
+##############
+# Helpers
+##############
+
+
+def create_variant_generic(
+    tasks: list[str | EvgTaskRef],
+    display_name: str,
+    *,
+    host: Host | str | None = None,
+    default_run_on="rhel87-small",
+    expansions: dict | None = None,
+    **kwargs: Any,
+) -> BuildVariant:
+    """Create a build variant for the given inputs."""
+    task_refs = []
+    if isinstance(host, str):
+        host = HOSTS[host]
+    for t in tasks:
+        if isinstance(t, EvgTaskRef):
+            task_refs.append(t)
+        else:
+            task_refs.append(EvgTaskRef(name=t))
+    expansions = expansions and expansions.copy() or dict()
+    if "run_on" in kwargs:
+        run_on = kwargs.pop("run_on")
+    elif host:
+        run_on = [host.run_on]
+        if host.variables:
+            expansions.update(host.variables)
+    else:
+        run_on = [default_run_on]
+    if isinstance(run_on, str):
+        run_on = [run_on]
+    name = display_name.replace(" ", "-").replace("*-", "").lower()
+    return BuildVariant(
+        name=name,
+        display_name=display_name,
+        tasks=task_refs,
+        expansions=expansions or None,
+        run_on=run_on,
+        **kwargs,
+    )
+
+
+def create_variant(
+    tasks: list[str | EvgTaskRef],
+    display_name: str,
+    *,
+    version: str | None = None,
+    host: Host | str | None = None,
+    expansions: dict | None = None,
+    **kwargs: Any,
+) -> BuildVariant:
+    expansions = expansions and expansions.copy() or dict()
+    if version:
+        expansions["VERSION"] = version
+    # 8.0+ Windows builds must run on win-latest
+    if (
+        "win64" in display_name.lower()
+        or "win32" in display_name.lower()
+        and version
+        and version >= "8.0"
+    ):
+        kwargs["run_on"] = HOSTS["win-latest"].run_on
+    return create_variant_generic(
+        tasks, display_name, version=version, host=host, expansions=expansions, **kwargs
+    )
+
+
+def get_versions_from(min_version: str) -> list[str]:
+    """Get all server versions starting from a minimum version."""
+    min_version_float = float(min_version)
+    rapid_latest = ["rapid", "latest"]
+    versions = [v for v in ALL_VERSIONS if v not in rapid_latest]
+    return [v for v in versions if float(v) >= min_version_float] + rapid_latest
+
+
+def get_versions_until(max_version: str) -> list[str]:
+    """Get all server version up to a max version."""
+    max_version_float = float(max_version)
+    versions = [v for v in ALL_VERSIONS if v not in ["rapid", "latest"]]
+    versions = [v for v in versions if float(v) <= max_version_float]
+    if not len(versions):
+        raise ValueError(f"No server versions found less <= {max_version}")
+    return versions
+
+
+def get_common_name(base: str, sep: str, **kwargs) -> str:
+    display_name = base
+    version = kwargs.pop("VERSION", None)
+    version = version or kwargs.pop("version", None)
+    if version:
+        if version not in ["rapid", "latest"]:
+            version = f"v{version}"
+        display_name = f"{display_name}{sep}{version}"
+    for key, value in kwargs.items():
+        name = value
+        if key.lower() in ["python", "toolchain_version"]:
+            if not value.startswith("pypy"):
+                name = f"Python{value}"
+            else:
+                name = f"PyPy{value.replace('pypy', '')}"
+        elif key.lower() in DISPLAY_LOOKUP and value in DISPLAY_LOOKUP[key.lower()]:
+            name = DISPLAY_LOOKUP[key.lower()][value]
+        else:
+            continue
+        display_name = f"{display_name}{sep}{name}"
+    return display_name
+
+
+def get_variant_name(base: str, host: str | Host | None = None, **kwargs) -> str:
+    """Get the display name of a variant."""
+    display_name = base
+    if isinstance(host, str):
+        host = HOSTS[host]
+    if host is not None:
+        display_name += f" {host.display_name}"
+    return get_common_name(display_name, " ", **kwargs)
+
+
+def get_task_name(base: str, **kwargs):
+    return get_common_name(base, "-", **kwargs).replace(" ", "-").lower()
+
+
+def zip_cycle(*iterables, empty_default=None):
+    """Get all combinations of the inputs, cycling over the shorter list(s)."""
+    cycles = [cycle(i) for i in iterables]
+    for _ in zip_longest(*iterables):
+        yield tuple(next(i, empty_default) for i in cycles)
+
+
+def handle_c_ext(c_ext, expansions) -> None:
+    """Handle c extension option."""
+    if c_ext == C_EXTS[0]:
+        expansions["NO_EXT"] = "1"
+
+
+def get_standard_auth_ssl(topology):
+    auth = "auth" if topology == "sharded_cluster" else "noauth"
+    ssl = "nossl" if topology == "standalone" else "ssl"
+    return auth, ssl
+
+
+def get_assume_role(**kwargs):
+    kwargs.setdefault("command_type", EvgCommandType.SETUP)
+    kwargs.setdefault("role_arn", "${assume_role_arn}")
+    return ec2_assume_role(**kwargs)
+
+
+def get_subprocess_exec(**kwargs):
+    kwargs.setdefault("binary", "bash")
+    kwargs.setdefault("working_dir", "src")
+    kwargs.setdefault("command_type", EvgCommandType.TEST)
+    return subprocess_exec(**kwargs)
+
+
+def get_s3_put(**kwargs):
+    kwargs["aws_key"] = "${AWS_ACCESS_KEY_ID}"
+    kwargs["aws_secret"] = "${AWS_SECRET_ACCESS_KEY}"  # noqa:S105
+    kwargs["aws_session_token"] = "${AWS_SESSION_TOKEN}"  # noqa:S105
+    kwargs["bucket"] = "${bucket_name}"
+    kwargs.setdefault("optional", "true")
+    kwargs.setdefault("permissions", "public-read")
+    kwargs.setdefault("content_type", "${content_type|application/x-gzip}")
+    kwargs.setdefault("command_type", EvgCommandType.SETUP)
+    return s3_put(**kwargs)
+
+
+def generate_yaml(tasks=None, variants=None):
+    """Generate the yaml for a given set of tasks and variants."""
+    project = EvgProject(tasks=tasks, buildvariants=variants)
+    out = ShrubService.generate_yaml(project)
+    # Dedent by two spaces to match what we use in config.yml
+    lines = [line[2:] for line in out.splitlines()]
+    print("\n".join(lines))
+
+
+##################
+# Generate Config
+##################
+
+
+def write_variants_to_file(mod):
+    here = Path(__file__).absolute().parent
+    target = here.parent / "generated_configs" / "variants.yml"
+    if target.exists():
+        target.unlink()
+    with target.open("w") as fid:
+        fid.write("buildvariants:\n")
+
+    for name, func in sorted(getmembers(mod, isfunction)):
+        if not name.endswith("_variants"):
+            continue
+        if not name.startswith("create_"):
+            raise ValueError("Variant creators must start with create_")
+        title = name.replace("create_", "").replace("_variants", "").replace("_", " ").capitalize()
+        project = EvgProject(tasks=None, buildvariants=func())
+        out = ShrubService.generate_yaml(project).splitlines()
+        with target.open("a") as fid:
+            fid.write(f"  # {title} tests\n")
+            for line in out[1:]:
+                fid.write(f"{line}\n")
+            fid.write("\n")
+
+    # Remove extra trailing newline:
+    data = target.read_text().splitlines()
+    with target.open("w") as fid:
+        for line in data[:-1]:
+            fid.write(f"{line}\n")
+
+
+def write_tasks_to_file(mod):
+    here = Path(__file__).absolute().parent
+    target = here.parent / "generated_configs" / "tasks.yml"
+    if target.exists():
+        target.unlink()
+    with target.open("w") as fid:
+        fid.write("tasks:\n")
+
+    for name, func in sorted(getmembers(mod, isfunction)):
+        if name.startswith("_") or not name.endswith("_tasks"):
+            continue
+        if not name.startswith("create_"):
+            raise ValueError("Task creators must start with create_")
+        title = name.replace("create_", "").replace("_tasks", "").replace("_", " ").capitalize()
+        project = EvgProject(tasks=func(), buildvariants=None)
+        out = ShrubService.generate_yaml(project).splitlines()
+        with target.open("a") as fid:
+            fid.write(f"  # {title} tests\n")
+            for line in out[1:]:
+                fid.write(f"{line}\n")
+            fid.write("\n")
+
+    # Remove extra trailing newline:
+    data = target.read_text().splitlines()
+    with target.open("w") as fid:
+        for line in data[:-1]:
+            fid.write(f"{line}\n")
+
+
+def write_functions_to_file(mod):
+    here = Path(__file__).absolute().parent
+    target = here.parent / "generated_configs" / "functions.yml"
+    if target.exists():
+        target.unlink()
+    with target.open("w") as fid:
+        fid.write("functions:\n")
+
+    functions = dict()
+    for name, func in sorted(getmembers(mod, isfunction)):
+        if name.startswith("_") or not name.endswith("_func"):
+            continue
+        if not name.startswith("create_"):
+            raise ValueError("Function creators must start with create_")
+        title = name.replace("create_", "").replace("_func", "").replace("_", " ").capitalize()
+        func_name, cmds = func()
+        functions = dict()
+        functions[func_name] = cmds
+        project = EvgProject(functions=functions, tasks=None, buildvariants=None)
+        out = ShrubService.generate_yaml(project).splitlines()
+        with target.open("a") as fid:
+            fid.write(f"  # {title}\n")
+            for line in out[1:]:
+                fid.write(f"{line}\n")
+            fid.write("\n")
+
+    # Remove extra trailing newline:
+    data = target.read_text().splitlines()
+    with target.open("w") as fid:
+        for line in data[:-1]:
+            fid.write(f"{line}\n")

.evergreen/scripts/install-dependencies.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
-# Install the dependencies needed for an evergreen run.
+# Install the necessary dependencies.
 set -eu
 
 HERE=$(dirname ${BASH_SOURCE:-$0})
@@ -10,60 +10,27 @@ if [ -f $HERE/env.sh ]; then
   . $HERE/env.sh
 fi
 
-_BIN_DIR=${PYMONGO_BIN_DIR:-$HOME/.local/bin}
+# Set up the default bin directory.
-export PATH="$PATH:${_BIN_DIR}"
+if [ -z "${PYMONGO_BIN_DIR:-}" ]; then
-
+  PYMONGO_BIN_DIR="$HOME/.local/bin"
-# Helper function to pip install a dependency using a temporary python env.
-function _pip_install() {
-  _HERE=$(dirname ${BASH_SOURCE:-$0})
-  . $_HERE/../utils.sh
-  _VENV_PATH=$(mktemp -d)
-  if [ "Windows_NT" = "${OS:-}" ]; then
-    _VENV_PATH=$(cygpath -m $_VENV_PATH)
-  fi
-  echo "Installing $2 using pip..."
-  createvirtualenv "$(find_python3)" $_VENV_PATH
-  python -m pip install $1
-  _suffix=""
-  if [ "Windows_NT" = "${OS:-}" ]; then
-    _suffix=".exe"
-  fi
-  ln -s "$(which $2)" $_BIN_DIR/${2}${_suffix}
-  # uv also comes with a uvx binary.
-  if [ $2 == "uv" ]; then
-    ln -s "$(which uvx)" $_BIN_DIR/uvx${_suffix}
-  fi
-  echo "Installed to ${_BIN_DIR}"
-  echo "Installing $2 using pip... done."
-}
-
-
-# Ensure just is installed.
-if ! command -v just >/dev/null 2>&1; then
-  # On most systems we can install directly.
-  _TARGET=""
-  if [ "Windows_NT" = "${OS:-}" ]; then
-    _TARGET="--target x86_64-pc-windows-msvc"
-  fi
-  echo "Installing just..."
-  mkdir -p "$_BIN_DIR" 2>/dev/null || true
-  curl --proto '=https' --tlsv1.2 -sSf https://just.systems/install.sh | bash -s -- $_TARGET --to "$_BIN_DIR" || {
-    _pip_install rust-just just
-  }
-  echo "Installing just... done."
 fi
 
-# Install uv.
+# Ensure uv is installed.
-if ! command -v uv >/dev/null 2>&1; then
+if ! command -v uv &>/dev/null; then
+  _BIN_DIR=$PYMONGO_BIN_DIR
+  mkdir -p ${_BIN_DIR}
   echo "Installing uv..."
-  # On most systems we can install directly.
+  curl -LsSf https://astral.sh/uv/install.sh | env UV_INSTALL_DIR="$_BIN_DIR" INSTALLER_NO_MODIFY_PATH=1 sh
-  curl -LsSf https://astral.sh/uv/install.sh | env UV_INSTALL_DIR="$_BIN_DIR" INSTALLER_NO_MODIFY_PATH=1 sh || {
-     _pip_install uv uv
-  }
   if [ "Windows_NT" = "${OS:-}" ]; then
     chmod +x "$(cygpath -u $_BIN_DIR)/uv.exe"
   fi
+  export PATH="$PYMONGO_BIN_DIR:$PATH"
   echo "Installing uv... done."
 fi
 
+# Ensure just is installed.
+if ! command -v just &>/dev/null; then
+  uv tool install rust-just
+fi
+
 popd > /dev/null

.evergreen/scripts/kms_tester.py

@@ -30,6 +30,9 @@ def _setup_azure_vm(base_env: dict[str, str]) -> None:
     env["AZUREKMS_CMD"] = "tar xf mongo-python-driver.tgz"
     run_command(f"{azure_dir}/run-command.sh", env=env)
 
+    env["AZUREKMS_CMD"] = "sudo apt-get install -y python3-dev build-essential"
+    run_command(f"{azure_dir}/run-command.sh", env=env)
+
     env["AZUREKMS_CMD"] = "bash .evergreen/just.sh setup-tests kms azure-remote"
     run_command(f"{azure_dir}/run-command.sh", env=env)
     LOGGER.info("Setting up Azure VM... done.")
@@ -47,6 +50,9 @@ def _setup_gcp_vm(base_env: dict[str, str]) -> None:
     env["GCPKMS_CMD"] = "tar xf mongo-python-driver.tgz"
     run_command(f"{gcp_dir}/run-command.sh", env=env)
 
+    env["GCPKMS_CMD"] = "sudo apt-get install -y python3-dev build-essential"
+    run_command(f"{gcp_dir}/run-command.sh", env=env)
+
     env["GCPKMS_CMD"] = "bash ./.evergreen/just.sh setup-tests kms gcp-remote"
     run_command(f"{gcp_dir}/run-command.sh", env=env)
     LOGGER.info("Setting up GCP VM...")
@@ -92,6 +98,13 @@ def setup_kms(sub_test_name: str) -> None:
         if sub_test_target == "azure":
             os.environ["AZUREKMS_VMNAME_PREFIX"] = "PYTHON_DRIVER"
 
+            # Found using "az vm image list --output table"
+            os.environ[
+                "AZUREKMS_IMAGE"
+            ] = "Canonical:0001-com-ubuntu-server-jammy:22_04-lts-gen2:latest"
+        else:
+            os.environ["GCPKMS_IMAGEFAMILY"] = "debian-12"
+
         run_command("./setup.sh", cwd=kms_dir)
         base_env = _load_kms_config(sub_test_target)
 

.evergreen/scripts/oidc_tester.py

@@ -2,7 +2,14 @@ from __future__ import annotations
 
 import os
 
-from utils import DRIVERS_TOOLS, TMP_DRIVER_FILE, create_archive, read_env, run_command, write_env
+from utils import (
+    DRIVERS_TOOLS,
+    TMP_DRIVER_FILE,
+    create_archive,
+    read_env,
+    run_command,
+    write_env,
+)
 
 K8S_NAMES = ["aks", "gke", "eks"]
 K8S_REMOTE_NAMES = [f"{n}-remote" for n in K8S_NAMES]
@@ -35,6 +42,11 @@ def setup_oidc(sub_test_name: str) -> dict[str, str] | None:
     if sub_test_name == "azure":
         env["AZUREOIDC_VMNAME_PREFIX"] = "PYTHON_DRIVER"
     if "-remote" not in sub_test_name:
+        if sub_test_name == "azure":
+            # Found using "az vm image list --output table"
+            env["AZUREOIDC_IMAGE"] = "Canonical:0001-com-ubuntu-server-jammy:22_04-lts-gen2:latest"
+        else:
+            env["GCPKMS_IMAGEFAMILY"] = "debian-12"
         run_command(f"bash {target_dir}/setup.sh", env=env)
     if sub_test_name in K8S_NAMES:
         run_command(f"bash {target_dir}/setup-pod.sh {sub_test_name}")

.evergreen/scripts/perf-submission-setup.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+# We use the requester expansion to determine whether the data is from a mainline evergreen run or not
+
+set -eu
+
+# shellcheck disable=SC2154
+if [ "${requester}" == "commit" ]; then
+  echo "is_mainline: true" >> expansion.yml
+else
+  echo "is_mainline: false" >> expansion.yml
+fi
+
+# We parse the username out of the order_id as patches append that in and SPS does not need that information
+# shellcheck disable=SC2154
+echo "parsed_order_id: $(echo "${revision_order_id}" | awk -F'_' '{print $NF}')"  >> expansion.yml

.evergreen/scripts/perf-submission.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+# We use the requester expansion to determine whether the data is from a mainline evergreen run or not
+
+set -eu
+
+# Submit the performance data to the SPS endpoint
+# shellcheck disable=SC2154
+response=$(curl -s -w "\nHTTP_STATUS:%{http_code}" -X 'POST' \
+  "https://performance-monitoring-api.corp.mongodb.com/raw_perf_results/cedar_report?project=${project_id}&version=${version_id}&variant=${build_variant}&order=${parsed_order_id}&task_name=${task_name}&task_id=${task_id}&execution=${execution}&mainline=${is_mainline}" \
+  -H 'accept: application/json' \
+  -H 'Content-Type: application/json' \
+  -d @results.json)
+
+http_status=$(echo "$response" | grep "HTTP_STATUS" | awk -F':' '{print $2}')
+response_body=$(echo "$response" | sed '/HTTP_STATUS/d')
+
+# We want to throw an error if the data was not successfully submitted
+if [ "$http_status" -ne 200 ]; then
+  echo "Error: Received HTTP status $http_status"
+  echo "Response Body: $response_body"
+  exit 1
+fi
+
+echo "Response Body: $response_body"
+echo "HTTP Status: $http_status"

.evergreen/scripts/resync-all-specs.py

@@ -0,0 +1,150 @@
+from __future__ import annotations
+
+import argparse
+import os
+import pathlib
+import subprocess
+from argparse import Namespace
+from subprocess import CalledProcessError
+
+JIRA_FILTER = "https://jira.mongodb.org/issues/?jql=labels%20%3D%20automated-sync%20AND%20status%20!%3D%20Closed"
+
+
+def resync_specs(directory: pathlib.Path, errored: dict[str, str]) -> None:
+    """Actually sync the specs"""
+    print("Beginning to sync specs")
+    for spec in os.scandir(directory):
+        if not spec.is_dir():
+            continue
+
+        if spec.name in ["asynchronous"]:
+            continue
+        try:
+            subprocess.run(
+                ["bash", "./.evergreen/resync-specs.sh", spec.name],  # noqa: S603, S607
+                capture_output=True,
+                text=True,
+                check=True,
+            )
+        except CalledProcessError as exc:
+            errored[spec.name] = exc.stderr
+    print("Done syncing specs")
+
+
+def apply_patches(errored):
+    print("Beginning to apply patches")
+    subprocess.run(
+        ["bash", "./.evergreen/remove-unimplemented-tests.sh"],  # noqa: S603, S607
+        check=True,
+    )
+    try:
+        # Avoid shell=True by passing arguments as a list.
+        # Note: glob expansion doesn't work in shell=False, so we use a list of files.
+        patches = [str(p) for p in pathlib.Path("./.evergreen/spec-patch/").glob("*")]
+        if patches:
+            subprocess.run(
+                [  # noqa: S603, S607
+                    "git",
+                    "apply",
+                    "-R",
+                    "--allow-empty",
+                    "--whitespace=fix",
+                    *patches,
+                ],
+                check=True,
+                stderr=subprocess.PIPE,
+            )
+    except CalledProcessError as exc:
+        errored["applying patches"] = exc.stderr
+
+
+def check_new_spec_directories(directory: pathlib.Path) -> list[str]:
+    """Check to see if there are any directories in the spec repo that don't exist in pymongo/test"""
+    spec_dir = pathlib.Path(os.environ["MDB_SPECS"]) / "source"
+    spec_set = {
+        entry.name.replace("-", "_")
+        for entry in os.scandir(spec_dir)
+        if entry.is_dir()
+        and (pathlib.Path(entry.path) / "tests").is_dir()
+        and len(list(os.scandir(pathlib.Path(entry.path) / "tests"))) > 1
+    }
+    test_set = {entry.name.replace("-", "_") for entry in os.scandir(directory) if entry.is_dir()}
+    known_mappings = {
+        "ocsp_support": "ocsp",
+        "client_side_operations_timeout": "csot",
+        "mongodb_handshake": "handshake",
+        "load_balancers": "load_balancer",
+        "connection_monitoring_and_pooling": "connection_monitoring",
+        "command_logging_and_monitoring": "command_logging",
+        "initial_dns_seedlist_discovery": "srv_seedlist",
+        "server_discovery_and_monitoring": "sdam_monitoring",
+    }
+
+    for k, v in known_mappings.items():
+        if k in spec_set:
+            spec_set.remove(k)
+            spec_set.add(v)
+    return list(spec_set - test_set)
+
+
+def write_summary(errored: dict[str, str], new: list[str], filename: str | None) -> None:
+    """Generate the PR description"""
+    pr_body = ""
+    # Avoid shell=True and complex pipes by using Python to process git output
+    process = subprocess.run(
+        ["git", "diff", "--name-only"],  # noqa: S603, S607
+        capture_output=True,
+        text=True,
+        check=True,
+    )
+    changed_files = process.stdout.strip().splitlines()
+    succeeded_set = set()
+    for f in changed_files:
+        parts = f.split("/")
+        if len(parts) > 1:
+            succeeded_set.add(parts[1])
+    succeeded = sorted(succeeded_set)
+
+    if len(succeeded) > 0:
+        pr_body += "The following specs were changed:\n -"
+        pr_body += "\n -".join(succeeded)
+        pr_body += "\n"
+    if len(errored) > 0:
+        pr_body += "\n\nThe following spec syncs encountered errors:"
+        for k, v in errored.items():
+            pr_body += f"\n -{k}\n```{v}\n```"
+        pr_body += "\n"
+    if len(new) > 0:
+        pr_body += "\n\nThe following directories are in the specification repository and not in our test directory:\n -"
+        pr_body += "\n -".join(new)
+        pr_body += "\n"
+    if pr_body != "":
+        pr_body = f"Jira tickets: {JIRA_FILTER}\n\n" + pr_body
+        if filename is None:
+            print(f"\n{pr_body}")
+        else:
+            with open(filename, "w") as f:
+                # replacements made for proper json
+                f.write(pr_body.replace("\n", "\\n").replace("\t", "\\t"))
+
+
+def main(args: Namespace):
+    directory = pathlib.Path("./test")
+    errored: dict[str, str] = {}
+    resync_specs(directory, errored)
+    apply_patches(errored)
+    new = check_new_spec_directories(directory)
+    write_summary(errored, new, args.filename)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="Python Script to resync all specs and generate summary for PR."
+    )
+    parser.add_argument(
+        "--filename",
+        help="Name of file for the summary to be written into.",
+        default=None,
+    )
+    args = parser.parse_args()
+    main(args)

.evergreen/scripts/resync-all-specs.sh

@@ -0,0 +1,43 @@
+#!/usr/bin/env bash
+# Run spec syncing script and create PR
+set -eu
+
+# SETUP
+SRC_URL="https://github.com/mongodb/specifications.git"
+# needs to be set for resync-specs.sh
+SPEC_SRC="$(realpath "../specifications")"
+SCRIPT="$(realpath "./.evergreen/resync-specs.sh")"
+
+# Clone the spec repo if the directory does not exist
+if [[ ! -d $SPEC_SRC ]]; then
+  git clone $SRC_URL $SPEC_SRC
+  if [[ $? -ne 0 ]]; then
+    echo "Error: Failed to clone repository."
+    exit 1
+  fi
+fi
+
+# Set environment variable to the cloned spec repo for resync-specs.sh
+export MDB_SPECS="$SPEC_SRC"
+
+# Check that resync-specs.sh exists and is executable
+if [[ ! -x $SCRIPT ]]; then
+  echo "Error: $SCRIPT not found or is not executable."
+  exit 1
+fi
+
+PR_DESC="spec_sync.txt"
+
+# run python script that actually does all the resyncing
+if ! [ -n "${CI:-}" ]
+then
+  # we're running locally
+  python3 ./.evergreen/scripts/resync-all-specs.py
+else
+  /opt/devtools/bin/python3.11 ./.evergreen/scripts/resync-all-specs.py --filename "$PR_DESC"
+  if [[ -f $PR_DESC ]]; then
+    # changes were made -> call scrypt to create PR for us
+    .evergreen/scripts/create-spec-pr.sh "$PR_DESC"
+    rm "$PR_DESC"
+  fi
+fi

.evergreen/scripts/run_server.py

@@ -12,7 +12,7 @@ def set_env(name: str, value: Any = "1") -> None:
 
 def start_server():
     opts, extra_opts = get_test_options(
-        "Run a MongoDB server.  All given flags will be passed to run-orchestration.sh in DRIVERS_TOOLS.",
+        "Run a MongoDB server.  All given flags will be passed to run-mongodb.sh in DRIVERS_TOOLS.",
         require_sub_test_name=False,
         allow_extra_opts=True,
     )
@@ -51,7 +51,7 @@ def start_server():
     elif opts.quiet:
         extra_opts.append("-q")
 
-    cmd = ["bash", f"{DRIVERS_TOOLS}/.evergreen/run-orchestration.sh", *extra_opts]
+    cmd = ["bash", f"{DRIVERS_TOOLS}/.evergreen/run-mongodb.sh", "start", *extra_opts]
     run_command(cmd, cwd=DRIVERS_TOOLS)
 
 

.evergreen/scripts/run_tests.py

@@ -4,12 +4,20 @@ import json
 import logging
 import os
 import platform
+import shlex
 import shutil
+import subprocess
 import sys
 from datetime import datetime
 from pathlib import Path
 from shutil import which
 
+try:
+    import importlib_metadata
+except ImportError:
+    from importlib import metadata as importlib_metadata
+
+
 import pytest
 from utils import DRIVERS_TOOLS, LOGGER, ROOT, run_command
 
@@ -23,6 +31,22 @@ TEST_NAME = os.environ.get("TEST_NAME")
 SUB_TEST_NAME = os.environ.get("SUB_TEST_NAME")
 
 
+def list_packages():
+    packages = set()
+    for distribution in importlib_metadata.distributions():
+        if distribution.name:
+            packages.add(distribution.name)
+    print("Package             Version     URL")
+    print("------------------- ----------- ----------------------------------------------------")
+    for name in sorted(packages):
+        distribution = importlib_metadata.distribution(name)
+        url = ""
+        if distribution.origin is not None:
+            url = distribution.origin.url
+        print(f"{name:20s}{distribution.version:12s}{url}")
+    print("------------------- ----------- ----------------------------------------------------\n")
+
+
 def handle_perf(start_time: datetime):
     end_time = datetime.now()
     elapsed_secs = (end_time - start_time).total_seconds()
@@ -46,13 +70,7 @@ def handle_perf(start_time: datetime):
 
 
 def handle_green_framework() -> None:
-    if GREEN_FRAMEWORK == "eventlet":
+    if GREEN_FRAMEWORK == "gevent":
-        import eventlet
-
-        # https://github.com/eventlet/eventlet/issues/401
-        eventlet.sleep()
-        eventlet.monkey_patch()
-    elif GREEN_FRAMEWORK == "gevent":
         from gevent import monkey
 
         monkey.patch_all()
@@ -90,10 +108,11 @@ def handle_aws_lambda() -> None:
     env["TEST_LAMBDA_DIRECTORY"] = str(target_dir)
     env.setdefault("AWS_REGION", "us-east-1")
     dirs = ["pymongo", "gridfs", "bson"]
-    # Store the original .so files.
+    # Remove the original .so files.
-    before_sos = []
     for dname in dirs:
-        before_sos.extend(f"{f.parent.name}/{f.name}" for f in (ROOT / dname).glob("*.so"))
+        so_paths = [f"{f.parent.name}/{f.name}" for f in (ROOT / dname).glob("*.so")]
+        for so_path in list(so_paths):
+            Path(so_path).unlink()
     # Build the c extensions.
     docker = which("docker") or which("podman")
     if not docker:
@@ -106,21 +125,23 @@ def handle_aws_lambda() -> None:
         target = ROOT / "test/lambda/mongodb" / dname
         shutil.rmtree(target, ignore_errors=True)
         shutil.copytree(ROOT / dname, target)
-    # Remove the original so files from the lambda directory.
-    for so_path in before_sos:
-        (ROOT / "test/lambda/mongodb" / so_path).unlink()
     # Remove the new so files from the ROOT directory.
     for dname in dirs:
         so_paths = [f"{f.parent.name}/{f.name}" for f in (ROOT / dname).glob("*.so")]
         for so_path in list(so_paths):
-            if so_path not in before_sos:
+            Path(so_path).unlink()
-                Path(so_path).unlink()
 
     script_name = "run-deployed-lambda-aws-tests.sh"
     run_command(f"bash {DRIVERS_TOOLS}/.evergreen/aws_lambda/{script_name}", env=env)
 
 
 def run() -> None:
+    # Add diagnostic for python version.
+    print("Running with python", sys.version)
+
+    # List the installed packages.
+    list_packages()
+
     # Handle green framework first so they can patch modules.
     if GREEN_FRAMEWORK:
         handle_green_framework()
@@ -152,6 +173,13 @@ def run() -> None:
         test_kms_send_to_remote(SUB_TEST_NAME)
         return
 
+    # Handle doctests.
+    if TEST_NAME == "doctest":
+        from sphinx.cmd.build import main
+
+        result = main("-E -b doctest doc ./doc/_build/doctest".split())
+        sys.exit(result)
+
     # Send ecs tests to run remotely.
     if TEST_NAME == "auth_aws" and SUB_TEST_NAME == "ecs":
         run_command(f"{DRIVERS_TOOLS}/.evergreen/auth_aws/aws_setup.sh ecs")
@@ -174,7 +202,17 @@ def run() -> None:
         return
 
     if os.environ.get("DEBUG_LOG"):
-        TEST_ARGS.extend(f"-o log_cli_level={logging.DEBUG} -o log_cli=1".split())
+        TEST_ARGS.extend(f"-o log_cli_level={logging.DEBUG}".split())
+
+    if os.environ.get("COVERAGE"):
+        binary = sys.executable.replace(os.sep, "/")
+        cmd = f"{binary} -m coverage run -m pytest {' '.join(TEST_ARGS)} {' '.join(sys.argv[1:])}"
+        result = subprocess.run(shlex.split(cmd), check=False)  # noqa: S603
+        cmd = f"{binary} -m coverage report"
+        subprocess.run(shlex.split(cmd), check=False)  # noqa: S603
+        if result.returncode != 0:
+            print(result.stderr)
+        sys.exit(result.returncode)
 
     # Run local tests.
     ret = pytest.main(TEST_ARGS + sys.argv[1:])

.evergreen/scripts/setup-dev-env.sh

@@ -1,17 +1,17 @@
 #!/bin/bash
-# Set up a development environment on an evergreen host.
+# Set up development environment.
 set -eu
 
 HERE=$(dirname ${BASH_SOURCE:-$0})
 HERE="$( cd -- "$HERE" > /dev/null 2>&1 && pwd )"
 ROOT=$(dirname "$(dirname $HERE)")
-pushd $ROOT > /dev/null
 
 # Source the env files to pick up common variables.
 if [ -f $HERE/env.sh ]; then
   . $HERE/env.sh
 fi
-# PYTHON_BINARY or PYTHON_VERSION may be defined in test-env.sh.
+
+# Get variables defined in test-env.sh.
 if [ -f $HERE/test-env.sh ]; then
   . $HERE/test-env.sh
 fi
@@ -19,41 +19,40 @@ fi
 # Ensure dependencies are installed.
 bash $HERE/install-dependencies.sh
 
-# Get the appropriate UV_PYTHON.
+# Handle the value for UV_PYTHON.
-. $ROOT/.evergreen/utils.sh
+. $HERE/setup-uv-python.sh
 
-if [ -z "${PYTHON_BINARY:-}" ]; then
+# Only run the next part if not running on CI.
-    if [ -n "${PYTHON_VERSION:-}" ]; then
+if [ -z "${CI:-}" ]; then
-      PYTHON_BINARY=$(get_python_binary $PYTHON_VERSION)
+  # Add the default install path to the path if needed.
-    else
+  if [ -z "${PYMONGO_BIN_DIR:-}" ]; then
-      PYTHON_BINARY=$(find_python3)
+    export PATH="$PATH:$HOME/.local/bin"
+  fi
+
+  # Set up venv, making sure c extensions build unless disabled.
+  if [ -z "${NO_EXT:-}" ]; then
+    export PYMONGO_C_EXT_MUST_BUILD=1
+  fi
+
+  (
+    cd $ROOT && uv sync
+  )
+
+  # Set up build utilities on Windows spawn hosts.
+  if [ -f $HOME/.visualStudioEnv.sh ]; then
+    set +u
+    SSH_TTY=1 source $HOME/.visualStudioEnv.sh
+    set -u
+  fi
+
+  # Only set up pre-commit if we are in a git checkout.
+  if [ -f $HERE/.git ]; then
+    if ! command -v pre-commit &>/dev/null; then
+      uv tool install pre-commit
     fi
-fi
-export UV_PYTHON=${PYTHON_BINARY}
-echo "Using python $UV_PYTHON"
 
-# Add the default install path to the path if needed.
+    if [ ! -f .git/hooks/pre-commit ]; then
-if [ -z "${PYMONGO_BIN_DIR:-}" ]; then
+      uvx pre-commit install
-  export PATH="$PATH:$HOME/.local/bin"
+    fi
+  fi
 fi
-
-# Set up venv, making sure c extensions build unless disabled.
-if [ -z "${NO_EXT:-}" ]; then
-  export PYMONGO_C_EXT_MUST_BUILD=1
-fi
-# Set up visual studio env on Windows spawn hosts.
-if [ -f $HOME/.visualStudioEnv.sh ]; then
-  set +u
-  SSH_TTY=1 source $HOME/.visualStudioEnv.sh
-  set -u
-fi
-uv sync --frozen
-
-echo "Setting up python environment... done."
-
-# Ensure there is a pre-commit hook if there is a git checkout.
-if [ -d .git ] && [ ! -f .git/hooks/pre-commit ]; then
-    uv run --frozen pre-commit install
-fi
-
-popd > /dev/null

.evergreen/scripts/setup-system.sh

@@ -8,9 +8,13 @@ echo "Setting up system..."
 bash .evergreen/scripts/configure-env.sh
 source .evergreen/scripts/env.sh
 bash $DRIVERS_TOOLS/.evergreen/setup.sh
-bash .evergreen/scripts/install-dependencies.sh
 popd
 
+# Run spawn host-specific tasks.
+if [ -z "${CI:-}" ]; then
+  bash $HERE/setup-dev-env.sh
+fi
+
 # Enable core dumps if enabled on the machine
 # Copied from https://github.com/mongodb/mongo/blob/master/etc/evergreen.yml
 if [ -f /proc/self/coredump_filter ]; then
@@ -38,4 +42,14 @@ if [ "$(uname -s)" = "Darwin" ]; then
     fi
 fi
 
+if [ -w /etc/hosts ]; then
+  SUDO=""
+else
+  SUDO="sudo"
+fi
+
+# Add 'server' and 'hostname_not_in_cert' as a hostnames
+echo "127.0.0.1 server" | $SUDO tee -a /etc/hosts
+echo "127.0.0.1 hostname_not_in_cert" | $SUDO tee -a /etc/hosts
+
 echo "Setting up system... done."

.evergreen/scripts/setup-tests.sh

@@ -12,6 +12,7 @@ set -eu
 #  TEST_CRYPT_SHARED    If non-empty, install crypt_shared lib.
 #  MONGODB_API_VERSION  The mongodb api version to use in tests.
 #  MONGODB_URI          If non-empty, use as the MONGODB_URI in tests.
+#  USE_ACTIVE_VENV      If non-empty, use the active virtual environment.
 
 SCRIPT_DIR=$(dirname ${BASH_SOURCE:-$0})
 
@@ -20,4 +21,6 @@ if [ -f $SCRIPT_DIR/env.sh ]; then
   source $SCRIPT_DIR/env.sh
 fi
 
-uv run $SCRIPT_DIR/setup_tests.py "$@"
+echo "Setting up tests with args \"$*\"..."
+uv run ${USE_ACTIVE_VENV:+--active} "$SCRIPT_DIR/setup_tests.py" "$@"
+echo "Setting up tests with args \"$*\"... done."

.evergreen/scripts/setup-uv-python.sh

@@ -0,0 +1,53 @@
+#!/bin/bash
+# Set up the UV_PYTHON variable.
+set -eu
+
+HERE=$(dirname ${BASH_SOURCE:-$0})
+HERE="$( cd -- "$HERE" > /dev/null 2>&1 && pwd )"
+
+# Use min supported version by default.
+_python="3.10"
+
+# Source the env files to pick up common variables.
+if [ -f $HERE/env.sh ]; then
+  . $HERE/env.sh
+fi
+
+# Get variables defined in test-env.sh.
+if [ -f $HERE/test-env.sh ]; then
+  . $HERE/test-env.sh
+fi
+
+if [ -z "${UV_PYTHON:-}" ]; then
+  set -x
+  # Translate a TOOLCHAIN_VERSION to UV_PYTHON.
+  if [ -n "${TOOLCHAIN_VERSION:-}" ]; then
+    _python=$TOOLCHAIN_VERSION
+    if [ "$(uname -s)" = "Darwin" ]; then
+        if [[ "$_python" == *"t"* ]]; then
+            binary_name="python3t"
+            framework_dir="PythonT"
+        else
+            binary_name="python3"
+            framework_dir="Python"
+        fi
+        _python=$(echo "$_python" | sed 's/t//g')
+        _python="/Library/Frameworks/$framework_dir.Framework/Versions/$_python/bin/$binary_name"
+    elif [ "Windows_NT" = "${OS:-}" ]; then
+        _python=$(echo $_python | cut -d. -f1,2 | sed 's/\.//g; s/t//g')
+        if [[ "$TOOLCHAIN_VERSION" == *"t"* ]]; then
+          _exe="python${TOOLCHAIN_VERSION}.exe"
+        else
+          _exe="python.exe"
+        fi
+        if [ -n "${IS_WIN32:-}" ]; then
+            _python="C:/python/32/Python${_python}/${_exe}"
+        else
+            _python="C:/python/Python${_python}/${_exe}"
+        fi
+    elif [ -d "/opt/python/$_python/bin" ]; then
+        _python="/opt/python/$_python/bin/python3"
+    fi
+  fi
+  export UV_PYTHON="$_python"
+fi

.evergreen/scripts/setup_tests.py

@@ -1,12 +1,10 @@
 from __future__ import annotations
 
 import base64
-import io
 import os
 import platform
 import shutil
 import stat
-import tarfile
 from pathlib import Path
 from urllib import request
 
@@ -31,8 +29,9 @@ PASS_THROUGH_ENV = [
     "NO_EXT",
     "MONGODB_API_VERSION",
     "DEBUG_LOG",
-    "PYTHON_BINARY",
+    "UV_PYTHON",
-    "PYTHON_VERSION",
+    "REQUIRE_FIPS",
+    "IS_WIN32",
 ]
 
 # Map the test name to test extra.
@@ -51,7 +50,7 @@ EXTRAS_MAP = {
 GROUP_MAP = dict(mockupdb="mockupdb", perf="perf")
 
 # The python version used for perf tests.
-PERF_PYTHON_VERSION = "3.9.13"
+PERF_PYTHON_VERSION = "3.10.11"
 
 
 def is_set(var: str) -> bool:
@@ -88,6 +87,13 @@ def setup_libmongocrypt():
         distro = get_distro()
         if distro.name.startswith("Debian"):
             target = f"debian{distro.version_id}"
+        elif distro.name.startswith("Ubuntu"):
+            if distro.version_id == "20.04":
+                target = "debian11"
+            elif distro.version_id == "22.04":
+                target = "debian12"
+            elif distro.version_id == "24.04":
+                target = "debian13"
         elif distro.name.startswith("Red Hat"):
             if distro.version_id.startswith("7"):
                 target = "rhel-70-64-bit"
@@ -109,9 +115,10 @@ def setup_libmongocrypt():
     LOGGER.info(f"Fetching {url}...")
     with request.urlopen(request.Request(url), timeout=15.0) as response:  # noqa: S310
         if response.status == 200:
-            fileobj = io.BytesIO(response.read())
+            with Path("libmongocrypt.tar.gz").open("wb") as f:
-        with tarfile.open("libmongocrypt.tar.gz", fileobj=fileobj) as fid:
+                f.write(response.read())
-            fid.extractall(Path.cwd() / "libmongocrypt")
+            Path("libmongocrypt").mkdir()
+            run_command("tar -xzf libmongocrypt.tar.gz -C libmongocrypt")
     LOGGER.info(f"Fetching {url}... done.")
 
     run_command("ls -la libmongocrypt")
@@ -146,6 +153,10 @@ def handle_test_env() -> None:
     # Start compiling the args we'll pass to uv.
     UV_ARGS = ["--extra test --no-group dev"]
 
+    # If USE_ACTIVE_VENV is set, add --active to UV_ARGS so run-tests.sh uses the active venv.
+    if is_set("USE_ACTIVE_VENV"):
+        UV_ARGS.append("--active")
+
     test_title = test_name
     if sub_test_name:
         test_title += f" {sub_test_name}"
@@ -158,11 +169,6 @@ def handle_test_env() -> None:
 
     write_env("PIP_QUIET")  # Quiet by default.
     write_env("PIP_PREFER_BINARY")  # Prefer binary dists by default.
-    write_env("UV_FROZEN")  # Do not modify lock files.
-
-    # Skip CSOT tests on non-linux platforms.
-    if PLATFORM != "linux":
-        write_env("SKIP_CSOT_TESTS")
 
     # Set an environment variable for the test name and sub test name.
     write_env(f"TEST_{test_name.upper()}")
@@ -180,6 +186,9 @@ def handle_test_env() -> None:
     if group := GROUP_MAP.get(test_name, ""):
         UV_ARGS.append(f"--group {group}")
 
+    if opts.test_min_deps:
+        UV_ARGS.append("--resolution=lowest-direct")
+
     if test_name == "auth_oidc":
         from oidc_tester import setup_oidc
 
@@ -216,26 +225,8 @@ def handle_test_env() -> None:
                 if key in os.environ:
                     write_env(key, os.environ[key])
 
-    if test_name == "data_lake":
-        # Stop any running mongo-orchestration which might be using the port.
-        run_command(f"bash {DRIVERS_TOOLS}/.evergreen/stop-orchestration.sh")
-        run_command(f"bash {DRIVERS_TOOLS}/.evergreen/atlas_data_lake/setup.sh")
-        AUTH = "auth"
-
     if AUTH != "noauth":
-        if test_name == "data_lake":
+        if test_name == "auth_oidc":
-            config = read_env(f"{DRIVERS_TOOLS}/.evergreen/atlas_data_lake/secrets-export.sh")
-            DB_USER = config["ADL_USERNAME"]
-            DB_PASSWORD = config["ADL_PASSWORD"]
-        elif test_name == "serverless":
-            run_command(f"bash {DRIVERS_TOOLS}/.evergreen/serverless/setup.sh")
-            config = read_env(f"{DRIVERS_TOOLS}/.evergreen/serverless/secrets-export.sh")
-            DB_USER = config["SERVERLESS_ATLAS_USER"]
-            DB_PASSWORD = config["SERVERLESS_ATLAS_PASSWORD"]
-            write_env("MONGODB_URI", config["SERVERLESS_URI"])
-            write_env("SINGLE_MONGOS_LB_URI", config["SERVERLESS_URI"])
-            write_env("MULTI_MONGOS_LB_URI", config["SERVERLESS_URI"])
-        elif test_name == "auth_oidc":
             DB_USER = config["OIDC_ADMIN_USER"]
             DB_PASSWORD = config["OIDC_ADMIN_PWD"]
         elif test_name == "search_index":
@@ -253,7 +244,7 @@ def handle_test_env() -> None:
     if is_set("MONGODB_URI"):
         write_env("PYMONGO_MUST_CONNECT", "true")
 
-    if is_set("DISABLE_TEST_COMMANDS") or opts.disable_test_commands:
+    if opts.disable_test_commands:
         write_env("PYMONGO_DISABLE_TEST_COMMANDS", "1")
 
     if test_name == "enterprise_auth":
@@ -283,6 +274,9 @@ def handle_test_env() -> None:
         write_env("GSSAPI_PORT", config["SASL_PORT"])
         write_env("GSSAPI_PRINCIPAL", config["PRINCIPAL"])
 
+    if test_name == "doctest":
+        UV_ARGS.append("--extra docs")
+
     if test_name == "load_balancer":
         SINGLE_MONGOS_LB_URI = os.environ.get(
             "SINGLE_MONGOS_LB_URI", "mongodb://127.0.0.1:8000/?loadBalanced=true"
@@ -334,7 +328,8 @@ def handle_test_env() -> None:
         version = os.environ.get("VERSION", "latest")
         cmd = [
             "bash",
-            f"{DRIVERS_TOOLS}/.evergreen/run-orchestration.sh",
+            f"{DRIVERS_TOOLS}/.evergreen/run-mongodb.sh",
+            "start",
             "--ssl",
             "--version",
             version,
@@ -362,8 +357,10 @@ def handle_test_env() -> None:
         if not (ROOT / "libmongocrypt").exists():
             setup_libmongocrypt()
 
-        # TODO: Test with 'pip install pymongocrypt'
+        if not opts.test_min_deps:
-        UV_ARGS.append("--group pymongocrypt_source")
+            UV_ARGS.append(
+                "--with pymongocrypt@git+https://github.com/mongodb/libmongocrypt@master#subdirectory=bindings/python"
+            )
 
         # Use the nocrypto build to avoid dependency issues with older windows/python versions.
         BASE = ROOT / "libmongocrypt/nocrypto"
@@ -385,14 +382,14 @@ def handle_test_env() -> None:
         if not DRIVERS_TOOLS:
             raise RuntimeError("Missing DRIVERS_TOOLS")
         csfle_dir = Path(f"{DRIVERS_TOOLS}/.evergreen/csfle")
-        run_command(f"bash {csfle_dir}/setup-secrets.sh", cwd=csfle_dir)
+        run_command(f"bash {csfle_dir.as_posix()}/setup-secrets.sh", cwd=csfle_dir)
         load_config_from_file(csfle_dir / "secrets-export.sh")
-        run_command(f"bash {csfle_dir}/start-servers.sh")
+        run_command(f"bash {csfle_dir.as_posix()}/start-servers.sh")
 
-        if sub_test_name == "pyopenssl":
+    if sub_test_name == "pyopenssl":
-            UV_ARGS.append("--extra ocsp")
+        UV_ARGS.append("--extra ocsp")
 
-    if is_set("TEST_CRYPT_SHARED") or opts.crypt_shared:
+    if opts.crypt_shared:
         config = read_env(f"{DRIVERS_TOOLS}/mo-expansion.sh")
         CRYPT_SHARED_DIR = Path(config["CRYPT_SHARED_LIB_PATH"]).parent.as_posix()
         LOGGER.info("Using crypt_shared_dir %s", CRYPT_SHARED_DIR)
@@ -424,10 +421,24 @@ def handle_test_env() -> None:
             run_command(f"bash {auth_aws_dir}/setup-secrets.sh")
 
     if test_name == "atlas_connect":
-        get_secrets("drivers/atlas_connect")
+        secrets = get_secrets("drivers/atlas_connect")
+
+        # Write file with Atlas X509 client certificate:
+        decoded = base64.b64decode(secrets["ATLAS_X509_DEV_CERT_BASE64"]).decode("utf8")
+        cert_file = ROOT / ".evergreen/atlas_x509_dev_client_certificate.pem"
+        with cert_file.open("w") as file:
+            file.write(decoded)
+        write_env(
+            "ATLAS_X509_DEV_WITH_CERT",
+            secrets["ATLAS_X509_DEV"] + "&tlsCertificateKeyFile=" + str(cert_file),
+        )
+
         # We do not want the default client_context to be initialized.
         write_env("DISABLE_CONTEXT")
 
+    if test_name == "numpy":
+        UV_ARGS.append("--with numpy")
+
     if test_name == "perf":
         data_dir = ROOT / "specifications/source/benchmarking/data"
         if not data_dir.exists():
@@ -451,21 +462,21 @@ def handle_test_env() -> None:
 
     # Add coverage if requested.
     # Only cover CPython. PyPy reports suspiciously low coverage.
-    if (is_set("COVERAGE") or opts.cov) and platform.python_implementation() == "CPython":
+    if opts.cov and platform.python_implementation() == "CPython":
         # Keep in sync with combine-coverage.sh.
         # coverage >=5 is needed for relative_files=true.
         UV_ARGS.append("--group coverage")
-        TEST_ARGS = f"{TEST_ARGS} --cov"
         write_env("COVERAGE")
 
-    if is_set("GREEN_FRAMEWORK") or opts.green_framework:
+    if opts.green_framework:
         framework = opts.green_framework or os.environ["GREEN_FRAMEWORK"]
         UV_ARGS.append(f"--group {framework}")
+        if framework == "gevent" and opts.test_min_deps:
+            # PYTHON-5729.  This can be removed when the min supported gevent is moved to 25.9.1.
+            UV_ARGS.append('--with "setuptools==81.0"')
 
     else:
-        # Use --capture=tee-sys so pytest prints test output inline:
+        TEST_ARGS = f"-v --durations=5 {TEST_ARGS}"
-        # https://docs.pytest.org/en/stable/how-to/capture-stdout-stderr.html
-        TEST_ARGS = f"-v --capture=tee-sys --durations=5 {TEST_ARGS}"
         TEST_SUITE = TEST_SUITE_MAP.get(test_name)
         if TEST_SUITE:
             TEST_ARGS = f"-m {TEST_SUITE} {TEST_ARGS}"

.evergreen/scripts/stop-server.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
-# Stop a server that was started using run-orchestration.sh in DRIVERS_TOOLS.
+# Stop a server that was started using run-mongodb.sh in DRIVERS_TOOLS.
 set -eu
 
 HERE=$(dirname ${BASH_SOURCE:-$0})
@@ -11,4 +11,4 @@ if [ -f $HERE/env.sh ]; then
   source $HERE/env.sh
 fi
 
-bash ${DRIVERS_TOOLS}/.evergreen/stop-orchestration.sh
+bash ${DRIVERS_TOOLS}/.evergreen/run-mongodb.sh stop

.evergreen/scripts/teardown_tests.py

@@ -36,10 +36,6 @@ elif TEST_NAME == "auth_oidc":
 elif TEST_NAME == "ocsp":
     run_command(f"bash {DRIVERS_TOOLS}/.evergreen/ocsp/teardown.sh")
 
-# Tear down serverless if applicable.
-elif TEST_NAME == "serverless":
-    run_command(f"bash {DRIVERS_TOOLS}/.evergreen/serverless/teardown.sh")
-
 # Tear down atlas cluster if applicable.
 if TEST_NAME in ["aws_lambda", "search_index"]:
     run_command(f"bash {DRIVERS_TOOLS}/.evergreen/atlas/teardown-atlas-cluster.sh")
@@ -61,10 +57,6 @@ elif TEST_NAME == "mod_wsgi":
 
     teardown_mod_wsgi()
 
-# Tear down data_lake if applicable.
-elif TEST_NAME == "data_lake":
-    run_command(f"{DRIVERS_TOOLS}/.evergreen/atlas_data_lake/teardown.sh")
-
 # Tear down coverage if applicable.
 if os.environ.get("COVERAGE"):
     shutil.rmtree(".pytest_cache", ignore_errors=True)

.evergreen/scripts/upload-codecov.sh

@@ -0,0 +1,57 @@
+#!/bin/bash
+# shellcheck disable=SC2154
+# Upload a coverate report to codecov.
+set -eu
+
+HERE=$(dirname ${BASH_SOURCE:-$0})
+ROOT=$(dirname "$(dirname $HERE)")
+
+pushd $ROOT > /dev/null
+export FNAME=coverage.xml
+REQUESTER=${requester:-}
+
+if [ ! -f ".coverage" ]; then
+  echo "There are no coverage results, not running codecov"
+  exit 0
+fi
+
+if [[ "${REQUESTER}" == "github_pr" || "${REQUESTER}" == "commit" ]]; then
+    echo "Uploading codecov for $REQUESTER..."
+else
+    echo "Error: requester must be 'github_pr' or 'commit', got '${REQUESTER}'" >&2
+    exit 1
+fi
+
+printf 'sha: %s\n' "$github_commit"
+printf 'flag: %s-%s\n' "$build_variant" "$task_name"
+printf 'file: %s\n' "$FNAME"
+uv tool run --with "coverage[toml]" coverage xml
+
+codecov_args=(
+  upload-process
+  --report-type coverage
+  --disable-search
+  --fail-on-error
+  --git-service github
+  --token "${CODECOV_TOKEN}"
+  --sha "${github_commit}"
+  --flag "${build_variant}-${task_name}"
+  --file "${FNAME}"
+)
+
+if [ -n "${github_pr_number:-}" ]; then
+  printf 'branch: %s:%s\n' "$github_author" "$github_pr_head_branch"
+  printf 'pr: %s\n' "$github_pr_number"
+  uv tool run --from codecov-cli codecovcli \
+    "${codecov_args[@]}" \
+    --pr "${github_pr_number}" \
+    --branch "${github_author}:${github_pr_head_branch}"
+else
+  printf 'branch: %s\n' "$branch_name"
+  uv tool run --from codecov-cli codecovcli \
+    "${codecov_args[@]}" \
+    --branch "${branch_name}"
+fi
+echo "Uploading codecov for $REQUESTER... done."
+
+popd > /dev/null

.evergreen/scripts/utils.py

@@ -33,7 +33,6 @@ TEST_SUITE_MAP = {
     "atlas_connect": "atlas_connect",
     "auth_aws": "auth_aws",
     "auth_oidc": "auth_oidc",
-    "data_lake": "data_lake",
     "default": "",
     "default_async": "default_async",
     "default_sync": "default",
@@ -43,19 +42,27 @@ TEST_SUITE_MAP = {
     "kms": "kms",
     "load_balancer": "load_balancer",
     "mockupdb": "mockupdb",
-    "pyopenssl": "",
     "ocsp": "ocsp",
     "perf": "perf",
-    "serverless": "",
+    "numpy": "",
 }
 
 # Tests that require a sub test suite.
 SUB_TEST_REQUIRED = ["auth_aws", "auth_oidc", "kms", "mod_wsgi", "perf"]
 
-EXTRA_TESTS = ["mod_wsgi", "aws_lambda"]
+EXTRA_TESTS = ["mod_wsgi", "aws_lambda", "doctest"]
 
-# Tests that do not use run-orchestration directly.
+# Tests that do not use run-mongodb directly.
-NO_RUN_ORCHESTRATION = ["auth_oidc", "atlas_connect", "data_lake", "mockupdb", "serverless", "ocsp"]
+NO_RUN_ORCHESTRATION = [
+    "auth_oidc",
+    "atlas_connect",
+    "aws_lambda",
+    "mockupdb",
+    "ocsp",
+]
+
+# Mapping of env variables to options
+OPTION_TO_ENV_VAR = {"cov": "COVERAGE", "crypt_shared": "TEST_CRYPT_SHARED"}
 
 
 def get_test_options(
@@ -78,7 +85,7 @@ def get_test_options(
     else:
         parser.add_argument(
             "test_name",
-            choices=set(TEST_SUITE_MAP) - set(NO_RUN_ORCHESTRATION),
+            choices=set(list(TEST_SUITE_MAP) + EXTRA_TESTS) - set(NO_RUN_ORCHESTRATION),
             nargs="?",
             default="default",
             help="The optional name of the test suite to be run, which informs the server configuration.",
@@ -91,6 +98,9 @@ def get_test_options(
     )
     parser.add_argument("--auth", action="store_true", help="Whether to add authentication.")
     parser.add_argument("--ssl", action="store_true", help="Whether to add TLS configuration.")
+    parser.add_argument(
+        "--test-min-deps", action="store_true", help="Test against minimum dependency versions"
+    )
 
     # Add the test modifiers.
     if require_sub_test_name:
@@ -101,7 +111,7 @@ def get_test_options(
         parser.add_argument(
             "--green-framework",
             nargs=1,
-            choices=["eventlet", "gevent"],
+            choices=["gevent"],
             help="Optional green framework to test against.",
         )
         parser.add_argument(
@@ -124,26 +134,53 @@ def get_test_options(
         opts, extra_opts = parser.parse_args(), []
     else:
         opts, extra_opts = parser.parse_known_args()
-    if opts.verbose:
+
-        LOGGER.setLevel(logging.DEBUG)
+    # Convert list inputs to strings.
-    elif opts.quiet:
+    for name in vars(opts):
-        LOGGER.setLevel(logging.WARNING)
+        value = getattr(opts, name)
+        if isinstance(value, list):
+            setattr(opts, name, value[0])
 
     # Handle validation and environment variable overrides.
     test_name = opts.test_name
     sub_test_name = opts.sub_test_name if require_sub_test_name else ""
     if require_sub_test_name and test_name in SUB_TEST_REQUIRED and not sub_test_name:
         raise ValueError(f"Test '{test_name}' requires a sub_test_name")
-    if "auth" in test_name or os.environ.get("AUTH") == "auth":
+    handle_env_overrides(parser, opts)
+    if "auth" in test_name:
         opts.auth = True
         # 'auth_aws ecs' shouldn't have extra auth set.
         if test_name == "auth_aws" and sub_test_name == "ecs":
             opts.auth = False
-    if os.environ.get("SSL") == "ssl":
+    if opts.verbose:
-        opts.ssl = True
+        LOGGER.setLevel(logging.DEBUG)
+    elif opts.quiet:
+        LOGGER.setLevel(logging.WARNING)
     return opts, extra_opts
 
 
+def handle_env_overrides(parser: argparse.ArgumentParser, opts: argparse.Namespace) -> None:
+    # Get the options, and then allow environment variable overrides.
+    for key in vars(opts):
+        if key in OPTION_TO_ENV_VAR:
+            env_var = OPTION_TO_ENV_VAR[key]
+        else:
+            env_var = key.upper()
+        if env_var in os.environ:
+            if parser.get_default(key) != getattr(opts, key):
+                LOGGER.info("Overriding env var '%s' with cli option", env_var)
+            elif env_var == "AUTH":
+                opts.auth = os.environ.get("AUTH") == "auth"
+            elif env_var == "SSL":
+                ssl_opt = os.environ.get("SSL", "")
+                opts.ssl = ssl_opt and ssl_opt.lower() != "nossl"
+            elif isinstance(getattr(opts, key), bool):
+                if os.environ[env_var]:
+                    setattr(opts, key, True)
+            else:
+                setattr(opts, key, os.environ[env_var])
+
+
 def read_env(path: Path | str) -> dict[str, str]:
     config = dict()
     with Path(path).open() as fid:
@@ -186,6 +223,6 @@ def run_command(cmd: str | list[str], **kwargs: Any) -> None:
 
 def create_archive() -> str:
     run_command("git add .", cwd=ROOT)
-    run_command('git commit -m "add files"', check=False, cwd=ROOT)
+    run_command('git commit --no-verify -m "add files"', check=False, cwd=ROOT)
     run_command(f"git archive -o {TMP_DRIVER_FILE} HEAD", cwd=ROOT)
     return TMP_DRIVER_FILE

.evergreen/setup-spawn-host.sh

@@ -15,5 +15,4 @@ echo "Copying files to $target..."
 rsync -az -e ssh --exclude '.git' --filter=':- .gitignore' -r . $target:$remote_dir
 echo "Copying files to $target... done"
 
-ssh $target $remote_dir/.evergreen/scripts/setup-system.sh
+ssh $target "$remote_dir/.evergreen/scripts/setup-system.sh"
-ssh $target "cd $remote_dir && PYTHON_BINARY=${PYTHON_BINARY:-} .evergreen/scripts/setup-dev-env.sh"

.evergreen/spec-patch/PYTHON-4918.patch

@@ -0,0 +1,24 @@
+diff --git a/test/connection_monitoring/pool-create-min-size-error.json b/test/connection_monitoring/pool-create-min-size-error.json
+index 1c744b85..509b2a23 100644
+--- a/test/connection_monitoring/pool-create-min-size-error.json
++++ b/test/connection_monitoring/pool-create-min-size-error.json
+@@ -49,15 +49,15 @@
+       "type": "ConnectionCreated",
+       "address": 42
+     },
++    {
++      "type": "ConnectionPoolCleared",
++      "address": 42
++    },
+     {
+       "type": "ConnectionClosed",
+       "address": 42,
+       "connectionId": 42,
+       "reason": "error"
+-    },
+-    {
+-      "type": "ConnectionPoolCleared",
+-      "address": 42
+     }
+   ],
+   "ignore": [

.evergreen/spec-patch/PYTHON-5052.patch

@@ -0,0 +1,440 @@
+diff --git a/test/unified-test-format/invalid/entity-client-observeTracingMessages-additionalProperties.json b/test/unified-test-format/invalid/entity-client-observeTracingMessages-additionalProperties.json
+new file mode 100644
+index 00000000..aa8046d2
+--- /dev/null
++++ b/test/unified-test-format/invalid/entity-client-observeTracingMessages-additionalProperties.json
+@@ -0,0 +1,20 @@
++{
++  "description": "entity-client-observeTracingMessages-additionalProperties",
++  "schemaVersion": "1.26",
++  "createEntities": [
++    {
++      "client": {
++        "id": "client0",
++        "observeTracingMessages": {
++          "foo": "bar"
++        }
++      }
++    }
++  ],
++  "tests": [
++    {
++      "description": "observeTracingMessages must not have additional properties'",
++      "operations": []
++    }
++  ]
++}
+diff --git a/test/unified-test-format/invalid/entity-client-observeTracingMessages-additionalPropertyType.json b/test/unified-test-format/invalid/entity-client-observeTracingMessages-additionalPropertyType.json
+new file mode 100644
+index 00000000..0b3a65f5
+--- /dev/null
++++ b/test/unified-test-format/invalid/entity-client-observeTracingMessages-additionalPropertyType.json
+@@ -0,0 +1,20 @@
++{
++  "description": "entity-client-observeTracingMessages-additionalPropertyType",
++  "schemaVersion": "1.26",
++  "createEntities": [
++    {
++      "client": {
++        "id": "client0",
++        "observeTracingMessages": {
++          "enableCommandPayload": 0
++        }
++      }
++    }
++  ],
++  "tests": [
++    {
++      "description": "observeTracingMessages enableCommandPayload must be boolean",
++      "operations": []
++    }
++  ]
++}
+diff --git a/test/unified-test-format/invalid/entity-client-observeTracingMessages-type.json b/test/unified-test-format/invalid/entity-client-observeTracingMessages-type.json
+new file mode 100644
+index 00000000..de3ef39a
+--- /dev/null
++++ b/test/unified-test-format/invalid/entity-client-observeTracingMessages-type.json
+@@ -0,0 +1,18 @@
++{
++  "description": "entity-client-observeTracingMessages-type",
++  "schemaVersion": "1.26",
++  "createEntities": [
++    {
++      "client": {
++        "id": "client0",
++        "observeTracingMessages": "foo"
++      }
++    }
++  ],
++  "tests": [
++    {
++      "description": "observeTracingMessages must be an object",
++      "operations": []
++    }
++  ]
++}
+diff --git a/test/unified-test-format/invalid/expectedTracingSpans-additionalProperties.json b/test/unified-test-format/invalid/expectedTracingSpans-additionalProperties.json
+new file mode 100644
+index 00000000..5947a286
+--- /dev/null
++++ b/test/unified-test-format/invalid/expectedTracingSpans-additionalProperties.json
+@@ -0,0 +1,30 @@
++{
++  "description": "expectedTracingSpans-additionalProperties",
++  "schemaVersion": "1.26",
++  "createEntities": [
++    {
++      "client": {
++        "id": "client0"
++      }
++    }
++  ],
++  "tests": [
++    {
++      "description": "additional property foo not allowed in expectTracingMessages",
++      "operations": [],
++      "expectTracingMessages": {
++        "client": "client0",
++        "ignoreExtraSpans": false,
++        "spans": [
++          {
++            "name": "command",
++            "tags": {
++              "db.system": "mongodb"
++            }
++          }
++        ],
++        "foo": 0
++      }
++    }
++  ]
++}
+diff --git a/test/unified-test-format/invalid/expectedTracingSpans-clientType.json b/test/unified-test-format/invalid/expectedTracingSpans-clientType.json
+new file mode 100644
+index 00000000..2fe7faea
+--- /dev/null
++++ b/test/unified-test-format/invalid/expectedTracingSpans-clientType.json
+@@ -0,0 +1,28 @@
++{
++  "description": "expectedTracingSpans-clientType",
++  "schemaVersion": "1.26",
++  "createEntities": [
++    {
++      "client": {
++        "id": "client0"
++      }
++    }
++  ],
++  "tests": [
++    {
++      "description": "client type must be string",
++      "operations": [],
++      "expectTracingMessages": {
++        "client": 0,
++        "spans": [
++          {
++            "name": "command",
++            "tags": {
++              "db.system": "mongodb"
++            }
++          }
++        ]
++      }
++    }
++  ]
++}
+diff --git a/test/unified-test-format/invalid/expectedTracingSpans-emptyNestedSpan.json b/test/unified-test-format/invalid/expectedTracingSpans-emptyNestedSpan.json
+new file mode 100644
+index 00000000..8a98d5ba
+--- /dev/null
++++ b/test/unified-test-format/invalid/expectedTracingSpans-emptyNestedSpan.json
+@@ -0,0 +1,29 @@
++{
++  "description": "expectedTracingSpans-emptyNestedSpan",
++  "schemaVersion": "1.26",
++  "createEntities": [
++    {
++      "client": {
++        "id": "client0"
++      }
++    }
++  ],
++  "tests": [
++    {
++      "description": "nested spans must not have fewer than 1 items'",
++      "operations": [],
++      "expectTracingMessages": {
++        "client": "client0",
++        "spans": [
++          {
++            "name": "command",
++            "tags": {
++              "db.system": "mongodb"
++            },
++            "nested": []
++          }
++        ]
++      }
++    }
++  ]
++}
+diff --git a/test/unified-test-format/invalid/expectedTracingSpans-invalidNestedSpan.json b/test/unified-test-format/invalid/expectedTracingSpans-invalidNestedSpan.json
+new file mode 100644
+index 00000000..79a86744
+--- /dev/null
++++ b/test/unified-test-format/invalid/expectedTracingSpans-invalidNestedSpan.json
+@@ -0,0 +1,31 @@
++{
++  "description": "expectedTracingSpans-invalidNestedSpan",
++  "schemaVersion": "1.26",
++  "createEntities": [
++    {
++      "client": {
++        "id": "client0"
++      }
++    }
++  ],
++  "tests": [
++    {
++      "description": "nested span must have required property name",
++      "operations": [],
++      "expectTracingMessages": {
++        "client": "client0",
++        "spans": [
++          {
++            "name": "command",
++            "tags": {
++              "db.system": "mongodb"
++            },
++            "nested": [
++              {}
++            ]
++          }
++        ]
++      }
++    }
++  ]
++}
+diff --git a/test/unified-test-format/invalid/expectedTracingSpans-missingPropertyClient.json b/test/unified-test-format/invalid/expectedTracingSpans-missingPropertyClient.json
+new file mode 100644
+index 00000000..2fb1cd5b
+--- /dev/null
++++ b/test/unified-test-format/invalid/expectedTracingSpans-missingPropertyClient.json
+@@ -0,0 +1,27 @@
++{
++  "description": "expectedTracingSpans-missingPropertyClient",
++  "schemaVersion": "1.26",
++  "createEntities": [
++    {
++      "client": {
++        "id": "client0"
++      }
++    }
++  ],
++  "tests": [
++    {
++      "description": "missing required property client",
++      "operations": [],
++      "expectTracingMessages": {
++        "spans": [
++          {
++            "name": "command",
++            "tags": {
++              "db.system": "mongodb"
++            }
++          }
++        ]
++      }
++    }
++  ]
++}
+diff --git a/test/unified-test-format/invalid/expectedTracingSpans-missingPropertySpans.json b/test/unified-test-format/invalid/expectedTracingSpans-missingPropertySpans.json
+new file mode 100644
+index 00000000..acd10307
+--- /dev/null
++++ b/test/unified-test-format/invalid/expectedTracingSpans-missingPropertySpans.json
+@@ -0,0 +1,20 @@
++{
++  "description": "expectedTracingSpans-missingPropertySpans",
++  "schemaVersion": "1.26",
++  "createEntities": [
++    {
++      "client": {
++        "id": "client0"
++      }
++    }
++  ],
++  "tests": [
++    {
++      "description": "missing required property spans",
++      "operations": [],
++      "expectTracingMessages": {
++        "client": "client0"
++      }
++    }
++  ]
++}
+diff --git a/test/unified-test-format/invalid/expectedTracingSpans-spanMalformedAdditionalProperties.json b/test/unified-test-format/invalid/expectedTracingSpans-spanMalformedAdditionalProperties.json
+new file mode 100644
+index 00000000..17299f86
+--- /dev/null
++++ b/test/unified-test-format/invalid/expectedTracingSpans-spanMalformedAdditionalProperties.json
+@@ -0,0 +1,28 @@
++{
++  "description": "expectedTracingSpans-spanMalformedAdditionalProperties",
++  "schemaVersion": "1.26",
++  "createEntities": [
++    {
++      "client": {
++        "id": "client0"
++      }
++    }
++  ],
++  "tests": [
++    {
++      "description": "Span must not have additional properties",
++      "operations": [],
++      "expectTracingMessages": {
++        "client": "client0",
++        "spans": [
++          {
++            "name": "foo",
++            "tags": {},
++            "nested": [],
++            "foo": "bar"
++          }
++        ]
++      }
++    }
++  ]
++}
+diff --git a/test/unified-test-format/invalid/expectedTracingSpans-spanMalformedMissingName.json b/test/unified-test-format/invalid/expectedTracingSpans-spanMalformedMissingName.json
+new file mode 100644
+index 00000000..0257cd9b
+--- /dev/null
++++ b/test/unified-test-format/invalid/expectedTracingSpans-spanMalformedMissingName.json
+@@ -0,0 +1,27 @@
++{
++  "description": "expectedTracingSpans-spanMalformedMissingName",
++  "schemaVersion": "1.26",
++  "createEntities": [
++    {
++      "client": {
++        "id": "client0"
++      }
++    }
++  ],
++  "tests": [
++    {
++      "description": "missing required span name",
++      "operations": [],
++      "expectTracingMessages": {
++        "client": "client0",
++        "spans": [
++          {
++            "tags": {
++              "db.system": "mongodb"
++            }
++          }
++        ]
++      }
++    }
++  ]
++}
+diff --git a/test/unified-test-format/invalid/expectedTracingSpans-spanMalformedMissingTags.json b/test/unified-test-format/invalid/expectedTracingSpans-spanMalformedMissingTags.json
+new file mode 100644
+index 00000000..a09ca31c
+--- /dev/null
++++ b/test/unified-test-format/invalid/expectedTracingSpans-spanMalformedMissingTags.json
+@@ -0,0 +1,25 @@
++{
++  "description": "expectedTracingSpans-spanMalformedMissingTags",
++  "schemaVersion": "1.26",
++  "createEntities": [
++    {
++      "client": {
++        "id": "client0"
++      }
++    }
++  ],
++  "tests": [
++    {
++      "description": "missing required span tags",
++      "operations": [],
++      "expectTracingMessages": {
++        "client": "client0",
++        "spans": [
++          {
++            "name": "foo"
++          }
++        ]
++      }
++    }
++  ]
++}
+diff --git a/test/unified-test-format/invalid/expectedTracingSpans-spanMalformedNestedMustBeArray.json b/test/unified-test-format/invalid/expectedTracingSpans-spanMalformedNestedMustBeArray.json
+new file mode 100644
+index 00000000..ccff0410
+--- /dev/null
++++ b/test/unified-test-format/invalid/expectedTracingSpans-spanMalformedNestedMustBeArray.json
+@@ -0,0 +1,27 @@
++{
++  "description": "expectedTracingSpans-spanMalformedNestedMustBeArray",
++  "schemaVersion": "1.26",
++  "createEntities": [
++    {
++      "client": {
++        "id": "client0"
++      }
++    }
++  ],
++  "tests": [
++    {
++      "description": "nested spans must be an array",
++      "operations": [],
++      "expectTracingMessages": {
++        "client": "client0",
++        "spans": [
++          {
++            "name": "foo",
++            "tags": {},
++            "nested": {}
++          }
++        ]
++      }
++    }
++  ]
++}
+diff --git a/test/unified-test-format/invalid/expectedTracingSpans-spanMalformedTagsMustBeObject.json b/test/unified-test-format/invalid/expectedTracingSpans-spanMalformedTagsMustBeObject.json
+new file mode 100644
+index 00000000..72af1c29
+--- /dev/null
++++ b/test/unified-test-format/invalid/expectedTracingSpans-spanMalformedTagsMustBeObject.json
+@@ -0,0 +1,26 @@
++{
++  "description": "expectedTracingSpans-spanMalformedNestedMustBeObject",
++  "schemaVersion": "1.26",
++  "createEntities": [
++    {
++      "client": {
++        "id": "client0"
++      }
++    }
++  ],
++  "tests": [
++    {
++      "description": "span tags must be an object",
++      "operations": [],
++      "expectTracingMessages": {
++        "client": "client0",
++        "spans": [
++          {
++            "name": "foo",
++            "tags": []
++          }
++        ]
++      }
++    }
++  ]
++}

.evergreen/spec-patch/PYTHON-5445.patch

@@ -0,0 +1,26 @@
+diff --git a/test/auth/legacy/connection-string.json b/test/auth/legacy/connection-string.json
+index 3a099c813..8982b61d5 100644
+--- a/test/auth/legacy/connection-string.json
++++ b/test/auth/legacy/connection-string.json
+@@ -440,6 +440,21 @@
+         }
+       }
+     },
++    {
++      "description": "should throw an exception if username provided (MONGODB-AWS)",
++      "uri": "mongodb://user@localhost.com/?authMechanism=MONGODB-AWS",
++      "valid": false
++    },
++    {
++      "description": "should throw an exception if username and password provided (MONGODB-AWS)",
++      "uri": "mongodb://user:pass@localhost.com/?authMechanism=MONGODB-AWS",
++      "valid": false
++    },
++    {
++      "description": "should throw an exception if AWS_SESSION_TOKEN provided (MONGODB-AWS)",
++      "uri": "mongodb://localhost/?authMechanism=MONGODB-AWS&authMechanismProperties=AWS_SESSION_TOKEN:token",
++      "valid": false
++    },
+     {
+       "description": "should recognise the mechanism with test environment (MONGODB-OIDC)",
+       "uri": "mongodb://localhost/?authMechanism=MONGODB-OIDC&authMechanismProperties=ENVIRONMENT:test",

.evergreen/spec-patch/PYTHON-5493.patch

@@ -0,0 +1,50 @@
+diff --git a/test/connection_logging/connection-logging.json b/test/connection_logging/connection-logging.json
+index 5799e834..72103b3c 100644
+--- a/test/connection_logging/connection-logging.json
++++ b/test/connection_logging/connection-logging.json
+@@ -446,6 +446,22 @@
+                 }
+               }
+             },
++            {
++              "level": "debug",
++              "component": "connection",
++              "data": {
++                "message": "Connection pool cleared",
++                "serverHost": {
++                  "$$type": "string"
++                },
++                "serverPort": {
++                  "$$type": [
++                    "int",
++                    "long"
++                  ]
++                }
++              }
++            },
+             {
+               "level": "debug",
+               "component": "connection",
+@@ -498,22 +514,6 @@
+                   ]
+                 }
+               }
+-            },
+-            {
+-              "level": "debug",
+-              "component": "connection",
+-              "data": {
+-                "message": "Connection pool cleared",
+-                "serverHost": {
+-                  "$$type": "string"
+-                },
+-                "serverPort": {
+-                  "$$type": [
+-                    "int",
+-                    "long"
+-                  ]
+-                }
+-              }
+             }
+           ]
+         }

.evergreen/spec-patch/PYTHON-5559.patch

@@ -0,0 +1,815 @@
+diff --git a/test/sessions/snapshot-sessions.json b/test/sessions/snapshot-sessions.json
+index 260f8b6f4..8f806ea75 100644
+--- a/test/sessions/snapshot-sessions.json
++++ b/test/sessions/snapshot-sessions.json
+@@ -988,6 +988,810 @@
+           }
+         }
+       ]
++    },
++    {
++      "description": "Find operation with snapshot and snapshot time",
++      "operations": [
++        {
++          "name": "find",
++          "object": "collection0",
++          "arguments": {
++            "session": "session0",
++            "filter": {}
++          },
++          "expectResult": [
++            {
++              "_id": 1,
++              "x": 11
++            },
++            {
++              "_id": 2,
++              "x": 11
++            }
++          ]
++        },
++        {
++          "name": "getSnapshotTime",
++          "object": "session0",
++          "saveResultAsEntity": "savedSnapshotTime"
++        },
++        {
++          "name": "insertOne",
++          "object": "collection0",
++          "arguments": {
++            "document": {
++              "_id": 3,
++              "x": 33
++            }
++          }
++        },
++        {
++          "name": "createEntities",
++          "object": "testRunner",
++          "arguments": {
++            "entities": [
++              {
++                "session": {
++                  "id": "session2",
++                  "client": "client0",
++                  "sessionOptions": {
++                    "snapshot": true,
++                    "snapshotTime": "savedSnapshotTime"
++                  }
++                }
++              }
++            ]
++          }
++        },
++        {
++          "name": "find",
++          "object": "collection0",
++          "arguments": {
++            "session": "session2",
++            "filter": {}
++          },
++          "expectResult": [
++            {
++              "_id": 1,
++              "x": 11
++            },
++            {
++              "_id": 2,
++              "x": 11
++            }
++          ]
++        },
++        {
++          "name": "find",
++          "object": "collection0",
++          "arguments": {
++            "session": "session2",
++            "filter": {}
++          },
++          "expectResult": [
++            {
++              "_id": 1,
++              "x": 11
++            },
++            {
++              "_id": 2,
++              "x": 11
++            }
++          ]
++        },
++        {
++          "name": "find",
++          "object": "collection0",
++          "arguments": {
++            "filter": {}
++          },
++          "expectResult": [
++            {
++              "_id": 1,
++              "x": 11
++            },
++            {
++              "_id": 2,
++              "x": 11
++            },
++            {
++              "_id": 3,
++              "x": 33
++            }
++          ]
++        }
++      ],
++      "expectEvents": [
++        {
++          "client": "client0",
++          "events": [
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "find": "collection0",
++                  "readConcern": {
++                    "level": "snapshot",
++                    "atClusterTime": {
++                      "$$exists": false
++                    }
++                  }
++                },
++                "databaseName": "database0"
++              }
++            },
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "find": "collection0",
++                  "readConcern": {
++                    "level": "snapshot",
++                    "atClusterTime": {
++                      "$$matchesEntity": "savedSnapshotTime"
++                    }
++                  }
++                },
++                "databaseName": "database0"
++              }
++            },
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "find": "collection0",
++                  "readConcern": {
++                    "level": "snapshot",
++                    "atClusterTime": {
++                      "$$matchesEntity": "savedSnapshotTime"
++                    }
++                  }
++                },
++                "databaseName": "database0"
++              }
++            },
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "find": "collection0",
++                  "readConcern": {
++                    "$$exists": false
++                  }
++                },
++                "databaseName": "database0"
++              }
++            }
++          ]
++        }
++      ]
++    },
++    {
++      "description": "Distinct operation with snapshot and snapshot time",
++      "operations": [
++        {
++          "name": "distinct",
++          "object": "collection0",
++          "arguments": {
++            "session": "session0",
++            "filter": {},
++            "fieldName": "x"
++          },
++          "expectResult": [
++            11
++          ]
++        },
++        {
++          "name": "getSnapshotTime",
++          "object": "session0",
++          "saveResultAsEntity": "savedSnapshotTime"
++        },
++        {
++          "name": "insertOne",
++          "object": "collection0",
++          "arguments": {
++            "document": {
++              "_id": 3,
++              "x": 33
++            }
++          }
++        },
++        {
++          "name": "createEntities",
++          "object": "testRunner",
++          "arguments": {
++            "entities": [
++              {
++                "session": {
++                  "id": "session2",
++                  "client": "client0",
++                  "sessionOptions": {
++                    "snapshot": true,
++                    "snapshotTime": "savedSnapshotTime"
++                  }
++                }
++              }
++            ]
++          }
++        },
++        {
++          "name": "distinct",
++          "object": "collection0",
++          "arguments": {
++            "session": "session2",
++            "filter": {},
++            "fieldName": "x"
++          },
++          "expectResult": [
++            11
++          ]
++        },
++        {
++          "name": "distinct",
++          "object": "collection0",
++          "arguments": {
++            "session": "session2",
++            "filter": {},
++            "fieldName": "x"
++          },
++          "expectResult": [
++            11
++          ]
++        },
++        {
++          "name": "distinct",
++          "object": "collection0",
++          "arguments": {
++            "filter": {},
++            "fieldName": "x"
++          },
++          "expectResult": [
++            11,
++            33
++          ]
++        }
++      ],
++      "expectEvents": [
++        {
++          "client": "client0",
++          "events": [
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "distinct": "collection0",
++                  "readConcern": {
++                    "level": "snapshot",
++                    "atClusterTime": {
++                      "$$exists": false
++                    }
++                  }
++                },
++                "databaseName": "database0"
++              }
++            },
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "distinct": "collection0",
++                  "readConcern": {
++                    "level": "snapshot",
++                    "atClusterTime": {
++                      "$$matchesEntity": "savedSnapshotTime"
++                    }
++                  }
++                },
++                "databaseName": "database0"
++              }
++            },
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "distinct": "collection0",
++                  "readConcern": {
++                    "level": "snapshot",
++                    "atClusterTime": {
++                      "$$matchesEntity": "savedSnapshotTime"
++                    }
++                  }
++                },
++                "databaseName": "database0"
++              }
++            },
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "distinct": "collection0",
++                  "readConcern": {
++                    "$$exists": false
++                  }
++                },
++                "databaseName": "database0"
++              }
++            }
++          ]
++        }
++      ]
++    },
++    {
++      "description": "Aggregate operation with snapshot and snapshot time",
++      "operations": [
++        {
++          "name": "aggregate",
++          "object": "collection0",
++          "arguments": {
++            "session": "session0",
++            "pipeline": [
++              {
++                "$match": {
++                  "_id": 1
++                }
++              }
++            ]
++          },
++          "expectResult": [
++            {
++              "_id": 1,
++              "x": 11
++            }
++          ]
++        },
++        {
++          "name": "getSnapshotTime",
++          "object": "session0",
++          "saveResultAsEntity": "savedSnapshotTime"
++        },
++        {
++          "name": "findOneAndUpdate",
++          "object": "collection0",
++          "arguments": {
++            "filter": {
++              "_id": 1
++            },
++            "update": {
++              "$inc": {
++                "x": 1
++              }
++            },
++            "returnDocument": "After"
++          },
++          "expectResult": {
++            "_id": 1,
++            "x": 12
++          }
++        },
++        {
++          "name": "createEntities",
++          "object": "testRunner",
++          "arguments": {
++            "entities": [
++              {
++                "session": {
++                  "id": "session2",
++                  "client": "client0",
++                  "sessionOptions": {
++                    "snapshot": true,
++                    "snapshotTime": "savedSnapshotTime"
++                  }
++                }
++              }
++            ]
++          }
++        },
++        {
++          "name": "aggregate",
++          "object": "collection0",
++          "arguments": {
++            "session": "session2",
++            "pipeline": [
++              {
++                "$match": {
++                  "_id": 1
++                }
++              }
++            ]
++          },
++          "expectResult": [
++            {
++              "_id": 1,
++              "x": 11
++            }
++          ]
++        },
++        {
++          "name": "aggregate",
++          "object": "collection0",
++          "arguments": {
++            "session": "session2",
++            "pipeline": [
++              {
++                "$match": {
++                  "_id": 1
++                }
++              }
++            ]
++          },
++          "expectResult": [
++            {
++              "_id": 1,
++              "x": 11
++            }
++          ]
++        },
++        {
++          "name": "aggregate",
++          "object": "collection0",
++          "arguments": {
++            "pipeline": [
++              {
++                "$match": {
++                  "_id": 1
++                }
++              }
++            ]
++          },
++          "expectResult": [
++            {
++              "_id": 1,
++              "x": 12
++            }
++          ]
++        }
++      ],
++      "expectEvents": [
++        {
++          "client": "client0",
++          "events": [
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "aggregate": "collection0",
++                  "readConcern": {
++                    "level": "snapshot",
++                    "atClusterTime": {
++                      "$$exists": false
++                    }
++                  }
++                },
++                "databaseName": "database0"
++              }
++            },
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "aggregate": "collection0",
++                  "readConcern": {
++                    "level": "snapshot",
++                    "atClusterTime": {
++                      "$$matchesEntity": "savedSnapshotTime"
++                    }
++                  }
++                },
++                "databaseName": "database0"
++              }
++            },
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "aggregate": "collection0",
++                  "readConcern": {
++                    "level": "snapshot",
++                    "atClusterTime": {
++                      "$$matchesEntity": "savedSnapshotTime"
++                    }
++                  }
++                },
++                "databaseName": "database0"
++              }
++            },
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "aggregate": "collection0",
++                  "readConcern": {
++                    "$$exists": false
++                  }
++                },
++                "databaseName": "database0"
++              }
++            }
++          ]
++        }
++      ]
++    },
++    {
++      "description": "countDocuments operation with snapshot and snapshot time",
++      "operations": [
++        {
++          "name": "countDocuments",
++          "object": "collection0",
++          "arguments": {
++            "session": "session0",
++            "filter": {}
++          },
++          "expectResult": 2
++        },
++        {
++          "name": "getSnapshotTime",
++          "object": "session0",
++          "saveResultAsEntity": "savedSnapshotTime"
++        },
++        {
++          "name": "insertOne",
++          "object": "collection0",
++          "arguments": {
++            "document": {
++              "_id": 3,
++              "x": 33
++            }
++          }
++        },
++        {
++          "name": "createEntities",
++          "object": "testRunner",
++          "arguments": {
++            "entities": [
++              {
++                "session": {
++                  "id": "session2",
++                  "client": "client0",
++                  "sessionOptions": {
++                    "snapshot": true,
++                    "snapshotTime": "savedSnapshotTime"
++                  }
++                }
++              }
++            ]
++          }
++        },
++        {
++          "name": "countDocuments",
++          "object": "collection0",
++          "arguments": {
++            "session": "session2",
++            "filter": {}
++          },
++          "expectResult": 2
++        },
++        {
++          "name": "countDocuments",
++          "object": "collection0",
++          "arguments": {
++            "session": "session2",
++            "filter": {}
++          },
++          "expectResult": 2
++        },
++        {
++          "name": "countDocuments",
++          "object": "collection0",
++          "arguments": {
++            "filter": {}
++          },
++          "expectResult": 3
++        }
++      ],
++      "expectEvents": [
++        {
++          "client": "client0",
++          "events": [
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "aggregate": "collection0",
++                  "readConcern": {
++                    "level": "snapshot",
++                    "atClusterTime": {
++                      "$$exists": false
++                    }
++                  }
++                },
++                "databaseName": "database0"
++              }
++            },
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "aggregate": "collection0",
++                  "readConcern": {
++                    "level": "snapshot",
++                    "atClusterTime": {
++                      "$$matchesEntity": "savedSnapshotTime"
++                    }
++                  }
++                },
++                "databaseName": "database0"
++              }
++            },
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "aggregate": "collection0",
++                  "readConcern": {
++                    "level": "snapshot",
++                    "atClusterTime": {
++                      "$$matchesEntity": "savedSnapshotTime"
++                    }
++                  }
++                },
++                "databaseName": "database0"
++              }
++            },
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "aggregate": "collection0",
++                  "readConcern": {
++                    "$$exists": false
++                  }
++                },
++                "databaseName": "database0"
++              }
++            }
++          ]
++        }
++      ]
++    },
++    {
++      "description": "Mixed operation with snapshot and snapshotTime",
++      "operations": [
++        {
++          "name": "find",
++          "object": "collection0",
++          "arguments": {
++            "session": "session0",
++            "filter": {
++              "_id": 1
++            }
++          },
++          "expectResult": [
++            {
++              "_id": 1,
++              "x": 11
++            }
++          ]
++        },
++        {
++          "name": "getSnapshotTime",
++          "object": "session0",
++          "saveResultAsEntity": "savedSnapshotTime"
++        },
++        {
++          "name": "findOneAndUpdate",
++          "object": "collection0",
++          "arguments": {
++            "filter": {
++              "_id": 1
++            },
++            "update": {
++              "$inc": {
++                "x": 1
++              }
++            },
++            "returnDocument": "After"
++          },
++          "expectResult": {
++            "_id": 1,
++            "x": 12
++          }
++        },
++        {
++          "name": "createEntities",
++          "object": "testRunner",
++          "arguments": {
++            "entities": [
++              {
++                "session": {
++                  "id": "session2",
++                  "client": "client0",
++                  "sessionOptions": {
++                    "snapshot": true,
++                    "snapshotTime": "savedSnapshotTime"
++                  }
++                }
++              }
++            ]
++          }
++        },
++        {
++          "name": "find",
++          "object": "collection0",
++          "arguments": {
++            "filter": {
++              "_id": 1
++            }
++          },
++          "expectResult": [
++            {
++              "_id": 1,
++              "x": 12
++            }
++          ]
++        },
++        {
++          "name": "aggregate",
++          "object": "collection0",
++          "arguments": {
++            "pipeline": [
++              {
++                "$match": {
++                  "_id": 1
++                }
++              }
++            ],
++            "session": "session2"
++          },
++          "expectResult": [
++            {
++              "_id": 1,
++              "x": 11
++            }
++          ]
++        },
++        {
++          "name": "distinct",
++          "object": "collection0",
++          "arguments": {
++            "fieldName": "x",
++            "filter": {},
++            "session": "session2"
++          },
++          "expectResult": [
++            11
++          ]
++        }
++      ],
++      "expectEvents": [
++        {
++          "client": "client0",
++          "events": [
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "find": "collection0",
++                  "readConcern": {
++                    "level": "snapshot",
++                    "atClusterTime": {
++                      "$$exists": false
++                    }
++                  }
++                }
++              }
++            },
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "find": "collection0",
++                  "readConcern": {
++                    "$$exists": false
++                  }
++                }
++              }
++            },
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "aggregate": "collection0",
++                  "readConcern": {
++                    "level": "snapshot",
++                    "atClusterTime": {
++                      "$$matchesEntity": "savedSnapshotTime"
++                    }
++                  }
++                }
++              }
++            },
++            {
++              "commandStartedEvent": {
++                "command": {
++                  "distinct": "collection0",
++                  "readConcern": {
++                    "level": "snapshot",
++                    "atClusterTime": {
++                      "$$matchesEntity": "savedSnapshotTime"
++                    }
++                  }
++                }
++              }
++            }
++          ]
++        }
++      ]
+     }
+   ]
+ }

.evergreen/spec-patch/PYTHON-5759.patch

@@ -0,0 +1,460 @@
+diff --git a/test/client-side-encryption/spec/unified/accessToken-azure.json b/test/client-side-encryption/spec/unified/accessToken-azure.json
+new file mode 100644
+index 00000000..510d8795
+--- /dev/null
++++ b/test/client-side-encryption/spec/unified/accessToken-azure.json
+@@ -0,0 +1,186 @@
++{
++  "description": "accessToken-azure",
++  "schemaVersion": "1.28",
++  "runOnRequirements": [
++    {
++      "minServerVersion": "4.1.10",
++      "csfle": {
++        "minLibmongocryptVersion": "1.6.0"
++      }
++    }
++  ],
++  "createEntities": [
++    {
++      "client": {
++        "id": "client",
++        "autoEncryptOpts": {
++          "keyVaultNamespace": "keyvault.datakeys",
++          "kmsProviders": {
++            "azure": {
++              "accessToken": {
++                "$$placeholder": 1
++              }
++            }
++          }
++        }
++      }
++    },
++    {
++      "database": {
++        "id": "db",
++        "client": "client",
++        "databaseName": "db"
++      }
++    },
++    {
++      "collection": {
++        "id": "coll",
++        "database": "db",
++        "collectionName": "coll"
++      }
++    },
++    {
++      "clientEncryption": {
++        "id": "clientEncryption",
++        "clientEncryptionOpts": {
++          "keyVaultClient": "client",
++          "keyVaultNamespace": "keyvault.datakeys",
++          "kmsProviders": {
++            "azure": {
++              "accessToken": {
++                "$$placeholder": 1
++              }
++            }
++          }
++        }
++      }
++    }
++  ],
++  "initialData": [
++    {
++      "databaseName": "db",
++      "collectionName": "coll",
++      "documents": [],
++      "createOptions": {
++        "validator": {
++          "$jsonSchema": {
++            "properties": {
++              "secret": {
++                "encrypt": {
++                  "keyId": [
++                    {
++                      "$binary": {
++                        "base64": "AZURE+AAAAAAAAAAAAAAAA==",
++                        "subType": "04"
++                      }
++                    }
++                  ],
++                  "bsonType": "string",
++                  "algorithm": "AEAD_AES_256_CBC_HMAC_SHA_512-Deterministic"
++                }
++              }
++            },
++            "bsonType": "object"
++          }
++        }
++      }
++    },
++    {
++      "databaseName": "keyvault",
++      "collectionName": "datakeys",
++      "documents": [
++        {
++          "_id": {
++            "$binary": {
++              "base64": "AZURE+AAAAAAAAAAAAAAAA==",
++              "subType": "04"
++            }
++          },
++          "keyAltNames": [
++            "my-key"
++          ],
++          "keyMaterial": {
++            "$binary": {
++              "base64": "n+HWZ0ZSVOYA3cvQgP7inN4JSXfOH85IngmeQxRpQHjCCcqT3IFqEWNlrsVHiz3AELimHhX4HKqOLWMUeSIT6emUDDoQX9BAv8DR1+E1w4nGs/NyEneac78EYFkK3JysrFDOgl2ypCCTKAypkn9CkAx1if4cfgQE93LW4kczcyHdGiH36CIxrCDGv1UzAvERN5Qa47DVwsM6a+hWsF2AAAJVnF0wYLLJU07TuRHdMrrphPWXZsFgyV+lRqJ7DDpReKNO8nMPLV/mHqHBHGPGQiRdb9NoJo8CvokGz4+KE8oLwzKf6V24dtwZmRkrsDV4iOhvROAzz+Euo1ypSkL3mw==",
++              "subType": "00"
++            }
++          },
++          "creationDate": {
++            "$date": {
++              "$numberLong": "1552949630483"
++            }
++          },
++          "updateDate": {
++            "$date": {
++              "$numberLong": "1552949630483"
++            }
++          },
++          "status": {
++            "$numberInt": "0"
++          },
++          "masterKey": {
++            "provider": "azure",
++            "keyVaultEndpoint": "key-vault-csfle.vault.azure.net",
++            "keyName": "key-name-csfle"
++          }
++        }
++      ]
++    }
++  ],
++  "tests": [
++    {
++      "description": "Auto encrypt using access token Azure credentials",
++      "operations": [
++        {
++          "name": "insertOne",
++          "arguments": {
++            "document": {
++              "_id": 1,
++              "secret": "string0"
++            }
++          },
++          "object": "coll"
++        }
++      ],
++      "outcome": [
++        {
++          "documents": [
++            {
++              "_id": 1,
++              "secret": {
++                "$binary": {
++                  "base64": "AQGVERPgAAAAAAAAAAAAAAAC5DbBSwPwfSlBrDtRuglvNvCXD1KzDuCKY2P+4bRFtHDjpTOE2XuytPAUaAbXf1orsPq59PVZmsbTZbt2CB8qaQ==",
++                  "subType": "06"
++                }
++              }
++            }
++          ],
++          "collectionName": "coll",
++          "databaseName": "db"
++        }
++      ]
++    },
++    {
++      "description": "Explicit encrypt using access token Azure credentials",
++      "operations": [
++        {
++          "name": "encrypt",
++          "object": "clientEncryption",
++          "arguments": {
++            "value": "string0",
++            "opts": {
++              "keyAltName": "my-key",
++              "algorithm": "AEAD_AES_256_CBC_HMAC_SHA_512-Deterministic"
++            }
++          },
++          "expectResult": {
++            "$binary": {
++              "base64": "AQGVERPgAAAAAAAAAAAAAAAC5DbBSwPwfSlBrDtRuglvNvCXD1KzDuCKY2P+4bRFtHDjpTOE2XuytPAUaAbXf1orsPq59PVZmsbTZbt2CB8qaQ==",
++              "subType": "06"
++            }
++          }
++        }
++      ]
++    }
++  ]
++}
+diff --git a/test/client-side-encryption/spec/unified/accessToken-gcp.json b/test/client-side-encryption/spec/unified/accessToken-gcp.json
+new file mode 100644
+index 00000000..f5cf8914
+--- /dev/null
++++ b/test/client-side-encryption/spec/unified/accessToken-gcp.json
+@@ -0,0 +1,188 @@
++{
++  "description": "accessToken-gcp",
++  "schemaVersion": "1.28",
++  "runOnRequirements": [
++    {
++      "minServerVersion": "4.1.10",
++      "csfle": {
++        "minLibmongocryptVersion": "1.6.0"
++      }
++    }
++  ],
++  "createEntities": [
++    {
++      "client": {
++        "id": "client",
++        "autoEncryptOpts": {
++          "keyVaultNamespace": "keyvault.datakeys",
++          "kmsProviders": {
++            "gcp": {
++              "accessToken": {
++                "$$placeholder": 1
++              }
++            }
++          }
++        }
++      }
++    },
++    {
++      "database": {
++        "id": "db",
++        "client": "client",
++        "databaseName": "db"
++      }
++    },
++    {
++      "collection": {
++        "id": "coll",
++        "database": "db",
++        "collectionName": "coll"
++      }
++    },
++    {
++      "clientEncryption": {
++        "id": "clientEncryption",
++        "clientEncryptionOpts": {
++          "keyVaultClient": "client",
++          "keyVaultNamespace": "keyvault.datakeys",
++          "kmsProviders": {
++            "gcp": {
++              "accessToken": {
++                "$$placeholder": 1
++              }
++            }
++          }
++        }
++      }
++    }
++  ],
++  "initialData": [
++    {
++      "databaseName": "db",
++      "collectionName": "coll",
++      "documents": [],
++      "createOptions": {
++        "validator": {
++          "$jsonSchema": {
++            "properties": {
++              "secret": {
++                "encrypt": {
++                  "keyId": [
++                    {
++                      "$binary": {
++                        "base64": "GCP+AAAAAAAAAAAAAAAAAA==",
++                        "subType": "04"
++                      }
++                    }
++                  ],
++                  "bsonType": "string",
++                  "algorithm": "AEAD_AES_256_CBC_HMAC_SHA_512-Deterministic"
++                }
++              }
++            },
++            "bsonType": "object"
++          }
++        }
++      }
++    },
++    {
++      "databaseName": "keyvault",
++      "collectionName": "datakeys",
++      "documents": [
++        {
++          "_id": {
++            "$binary": {
++              "base64": "GCP+AAAAAAAAAAAAAAAAAA==",
++              "subType": "04"
++            }
++          },
++          "keyAltNames": [
++            "my-key"
++          ],
++          "keyMaterial": {
++            "$binary": {
++              "base64": "CiQAIgLj0WyktnB4dfYHo5SLZ41K4ASQrjJUaSzl5vvVH0G12G0SiQEAjlV8XPlbnHDEDFbdTO4QIe8ER2/172U1ouLazG0ysDtFFIlSvWX5ZnZUrRMmp/R2aJkzLXEt/zf8Mn4Lfm+itnjgo5R9K4pmPNvvPKNZX5C16lrPT+aA+rd+zXFSmlMg3i5jnxvTdLHhg3G7Q/Uv1ZIJskKt95bzLoe0tUVzRWMYXLIEcohnQg==",
++              "subType": "00"
++            }
++          },
++          "creationDate": {
++            "$date": {
++              "$numberLong": "1552949630483"
++            }
++          },
++          "updateDate": {
++            "$date": {
++              "$numberLong": "1552949630483"
++            }
++          },
++          "status": {
++            "$numberInt": "0"
++          },
++          "masterKey": {
++            "provider": "gcp",
++            "projectId": "devprod-drivers",
++            "location": "global",
++            "keyRing": "key-ring-csfle",
++            "keyName": "key-name-csfle"
++          }
++        }
++      ]
++    }
++  ],
++  "tests": [
++    {
++      "description": "Auto encrypt using access token GCP credentials",
++      "operations": [
++        {
++          "name": "insertOne",
++          "arguments": {
++            "document": {
++              "_id": 1,
++              "secret": "string0"
++            }
++          },
++          "object": "coll"
++        }
++      ],
++      "outcome": [
++        {
++          "documents": [
++            {
++              "_id": 1,
++              "secret": {
++                "$binary": {
++                  "base64": "ARgj/gAAAAAAAAAAAAAAAAACwFd+Y5Ojw45GUXNvbcIpN9YkRdoHDHkR4kssdn0tIMKlDQOLFkWFY9X07IRlXsxPD8DcTiKnl6XINK28vhcGlg==",
++                  "subType": "06"
++                }
++              }
++            }
++          ],
++          "collectionName": "coll",
++          "databaseName": "db"
++        }
++      ]
++    },
++    {
++      "description": "Explicit encrypt using access token GCP credentials",
++      "operations": [
++        {
++          "name": "encrypt",
++          "object": "clientEncryption",
++          "arguments": {
++            "value": "string0",
++            "opts": {
++              "keyAltName": "my-key",
++              "algorithm": "AEAD_AES_256_CBC_HMAC_SHA_512-Deterministic"
++            }
++          },
++          "expectResult": {
++            "$binary": {
++              "base64": "ARgj/gAAAAAAAAAAAAAAAAACwFd+Y5Ojw45GUXNvbcIpN9YkRdoHDHkR4kssdn0tIMKlDQOLFkWFY9X07IRlXsxPD8DcTiKnl6XINK28vhcGlg==",
++              "subType": "06"
++            }
++          }
++        }
++      ]
++    }
++  ]
++}
+diff --git a/test/unified-test-format/invalid/clientEncryptionOpts-kmsProviders-azure-accessToken-type.json b/test/unified-test-format/invalid/clientEncryptionOpts-kmsProviders-azure-accessToken-type.json
+new file mode 100644
+index 00000000..8fe5c150
+--- /dev/null
++++ b/test/unified-test-format/invalid/clientEncryptionOpts-kmsProviders-azure-accessToken-type.json
+@@ -0,0 +1,31 @@
++{
++  "description": "clientEncryptionOpts-kmsProviders-azure-accessToken-type",
++  "schemaVersion": "1.28",
++  "createEntities": [
++    {
++      "client": {
++        "id": "client0"
++      }
++    },
++    {
++      "clientEncryption": {
++        "id": "clientEncryption0",
++        "clientEncryptionOpts": {
++          "keyVaultClient": "client0",
++          "keyVaultNamespace": "keyvault.datakeys",
++          "kmsProviders": {
++            "azure": {
++              "accessToken": 0
++            }
++          }
++        }
++      }
++    }
++  ],
++  "tests": [
++    {
++      "description": "",
++      "operations": []
++    }
++  ]
++}
+diff --git a/test/unified-test-format/invalid/clientEncryptionOpts-kmsProviders-gcp-accessToken-type.json b/test/unified-test-format/invalid/clientEncryptionOpts-kmsProviders-gcp-accessToken-type.json
+new file mode 100644
+index 00000000..2284e26c
+--- /dev/null
++++ b/test/unified-test-format/invalid/clientEncryptionOpts-kmsProviders-gcp-accessToken-type.json
+@@ -0,0 +1,31 @@
++{
++  "description": "clientEncryptionOpts-kmsProviders-gcp-accessToken-type",
++  "schemaVersion": "1.28",
++  "createEntities": [
++    {
++      "client": {
++        "id": "client0"
++      }
++    },
++    {
++      "clientEncryption": {
++        "id": "clientEncryption0",
++        "clientEncryptionOpts": {
++          "keyVaultClient": "client0",
++          "keyVaultNamespace": "keyvault.datakeys",
++          "kmsProviders": {
++            "gcp": {
++              "accessToken": 0
++            }
++          }
++        }
++      }
++    }
++  ],
++  "tests": [
++    {
++      "description": "",
++      "operations": []
++    }
++  ]
++}

.evergreen/utils.sh

@@ -1,136 +0,0 @@
-#!/bin/bash
-# Utility functions used by pymongo evergreen scripts.
-set -eu
-
-find_python3() {
-    PYTHON=""
-    # Find a suitable toolchain version, if available.
-    if [ "$(uname -s)" = "Darwin" ]; then
-        PYTHON="/Library/Frameworks/Python.Framework/Versions/3.9/bin/python3"
-    elif [ "Windows_NT" = "${OS:-}" ]; then # Magic variable in cygwin
-        PYTHON="C:/python/Python39/python.exe"
-    else
-        # Prefer our own toolchain, fall back to mongodb toolchain if it has Python 3.9+.
-        if [ -f "/opt/python/3.9/bin/python3" ]; then
-            PYTHON="/opt/python/Current/bin/python3"
-        elif is_python_39 "$(command -v /opt/mongodbtoolchain/v5/bin/python3)"; then
-            PYTHON="/opt/mongodbtoolchain/v5/bin/python3"
-        elif is_python_39 "$(command -v /opt/mongodbtoolchain/v4/bin/python3)"; then
-            PYTHON="/opt/mongodbtoolchain/v4/bin/python3"
-        elif is_python_39 "$(command -v /opt/mongodbtoolchain/v3/bin/python3)"; then
-            PYTHON="/opt/mongodbtoolchain/v3/bin/python3"
-        fi
-    fi
-    # Add a fallback system python3 if it is available and Python 3.9+.
-    if [ -z "$PYTHON" ]; then
-        if is_python_39 "$(command -v python3)"; then
-            PYTHON="$(command -v python3)"
-        fi
-    fi
-    if [ -z "$PYTHON" ]; then
-        echo "Cannot test without python3.9+ installed!"
-        exit 1
-    fi
-    echo "$PYTHON"
-}
-
-# Usage:
-# createvirtualenv /path/to/python /output/path/for/venv
-# * param1: Python binary to use for the virtualenv
-# * param2: Path to the virtualenv to create
-createvirtualenv () {
-    PYTHON=$1
-    VENVPATH=$2
-
-    # Prefer venv
-    VENV="$PYTHON -m venv"
-    if [ "$(uname -s)" = "Darwin" ]; then
-        VIRTUALENV="$PYTHON -m virtualenv"
-    else
-        VIRTUALENV=$(command -v virtualenv 2>/dev/null || echo "$PYTHON -m virtualenv")
-        VIRTUALENV="$VIRTUALENV -p $PYTHON"
-    fi
-    if ! $VENV $VENVPATH 2>/dev/null; then
-        # Workaround for bug in older versions of virtualenv.
-        $VIRTUALENV $VENVPATH 2>/dev/null || $VIRTUALENV $VENVPATH
-    fi
-    if [ "Windows_NT" = "${OS:-}" ]; then
-        # Workaround https://bugs.python.org/issue32451:
-        # mongovenv/Scripts/activate: line 3: $'\r': command not found
-        dos2unix $VENVPATH/Scripts/activate || true
-        . $VENVPATH/Scripts/activate
-    else
-        . $VENVPATH/bin/activate
-    fi
-
-    export PIP_QUIET=1
-    python -m pip install --upgrade pip
-}
-
-# Usage:
-# testinstall /path/to/python /path/to/.whl ["no-virtualenv"]
-# * param1: Python binary to test
-# * param2: Path to the wheel to install
-# * param3 (optional): If set to a non-empty string, don't create a virtualenv. Used in manylinux containers.
-testinstall () {
-    PYTHON=$1
-    RELEASE=$2
-    NO_VIRTUALENV=$3
-    PYTHON_IMPL=$(python -c "import platform; print(platform.python_implementation())")
-
-    if [ -z "$NO_VIRTUALENV" ]; then
-        createvirtualenv $PYTHON venvtestinstall
-        PYTHON=python
-    fi
-
-    $PYTHON -m pip install --upgrade $RELEASE
-    cd tools
-
-    if [ "$PYTHON_IMPL" = "CPython" ]; then
-        $PYTHON fail_if_no_c.py
-    fi
-
-    $PYTHON -m pip uninstall -y pymongo
-    cd ..
-
-    if [ -z "$NO_VIRTUALENV" ]; then
-        deactivate
-        rm -rf venvtestinstall
-    fi
-}
-
-# Function that returns success if the provided Python binary is version 3.9 or later
-# Usage:
-# is_python_39 /path/to/python
-# * param1: Python binary
-is_python_39() {
-    if [ -z "$1" ]; then
-        return 1
-    elif $1 -c "import sys; exit(sys.version_info[:2] < (3, 9))"; then
-        # runs when sys.version_info[:2] >= (3, 9)
-        return 0
-    else
-        return 1
-    fi
-}
-
-
-# Function that gets a python binary given a python version string.
-# Versions can be of the form 3.xx or pypy3.xx.
-get_python_binary() {
-    version=$1
-    if [ "$(uname -s)" = "Darwin" ]; then
-        PYTHON="/Library/Frameworks/Python.Framework/Versions/$version/bin/python3"
-    elif [ "Windows_NT" = "${OS:-}" ]; then
-        version=$(echo $version | cut -d. -f1,2 | sed 's/\.//g')
-        PYTHON="C:/python/Python$version/python.exe"
-    else
-        PYTHON="/opt/python/$version/bin/python3"
-    fi
-    if is_python_39 "$(command -v $PYTHON)"; then
-        echo "$PYTHON"
-    else
-        echo "Could not find suitable python binary for '$version'"  >&2
-        return 1
-    fi
-}

.github/CODEOWNERS

@@ -0,0 +1 @@
+* @mongodb/dbx-python

.github/copilot-instructions.md

@@ -0,0 +1,44 @@
+When reviewing code, focus on:
+
+## Security Critical Issues
+- Check for hardcoded secrets, API keys, or credentials.
+- Check for instances of potential method call injection, dynamic code execution, symbol injection or other code injection vulnerabilities.
+
+## Performance Red Flags
+- Spot inefficient loops and algorithmic issues.
+- Check for memory leaks and resource cleanup.
+
+## Code Quality Essentials
+- Methods should be focused and appropriately sized. If a method is doing too much, suggest refactorings to split it up.
+- Use clear, descriptive naming conventions.
+- Avoid encapsulation violations and ensure proper separation of concerns.
+- All public classes, modules, and methods should have clear documentation in Sphinx format.
+
+## PyMongo-specific Concerns
+- Do not review files within `pymongo/synchronous` or files in `test/` that also have a file of the same name in `test/asynchronous` unless the reviewed changes include a `_IS_SYNC` statement. PyMongo generates these files from `pymongo/asynchronous` and `test/asynchronous` using `tools/synchro.py`.
+- All asynchronous functions must not call any blocking I/O.
+
+## Review Style
+- Be specific and actionable in feedback.
+- Explain the "why" behind recommendations.
+- Acknowledge good patterns when you see them.
+- Ask clarifying questions when code intent is unclear.
+
+Always prioritize security vulnerabilities and performance issues that could impact users.
+
+Always suggest changes to improve readability and testability. For example, this suggestion seeks to make the code more readable, reusable, and testable:
+
+```python
+# Instead of:
+if user.email and "@" in user.email and len(user.email) > 5:
+    submit_button.enabled = True
+else:
+    submit_button.enabled = False
+
+# Consider:
+def valid_email(email):
+    return email and "@" in email and len(email) > 5
+
+
+submit_button.enabled = valid_email(user.email)
+```

.github/dependabot.yml

@@ -5,6 +5,8 @@ updates:
     directory: "/"
     schedule:
       interval: "weekly"
+    cooldown:
+      default-days: 7
     groups:
       actions:
         patterns:

.github/pull_request_template.md

@@ -0,0 +1,33 @@
+<!-- Thanks for contributing! -->
+<!-- Please ensure that the title of the PR is in the following form:
+[JIRA TICKET]: Issue Title
+
+If you are an external contributor and there is no JIRA ticket associated with your change, then use your best judgement
+for the PR title. A MongoDB employee will create a JIRA ticket and edit the name and links as appropriate.
+
+Note on AI Contributions:
+We only accept pull requests that are authored and submitted by human contributors who fully understand the changes they are proposing.
+All contributions must be written and understood by human contributors. Please read about our policy in our contributing guide.
+-->
+[JIRA TICKET]
+
+## Changes in this PR
+<!-- What changes did you make to the code? What new APIs (public or private) were added, removed, or edited to generate
+the desired outcome explained in the above summary? -->
+
+## Test Plan
+<!-- How did you test the code? If you added unit tests, you can say that. If you didn’t introduce unit tests, explain why.
+All code should be tested in some way – so please list what your validation strategy was. -->
+
+## Checklist
+<!-- Do not delete the items provided on this checklist. -->
+
+### Checklist for Author
+- [ ] Did you update the changelog (if necessary)?
+- [ ] Is there test coverage?
+- [ ] Is any followup work tracked in a JIRA ticket? If so, add link(s).
+
+### Checklist for Reviewer
+- [ ] Does the title of the PR reference a JIRA Ticket?
+- [ ] Do you fully understand the implementation? (Would you be comfortable explaining how this code works to someone else?)
+- [ ] Is all relevant documentation (README or docstring) updated?

.github/workflows/codeql.yml

@@ -38,15 +38,15 @@ jobs:
           build-mode: none
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v4
+      uses: actions/checkout@v6
       with:
         ref: ${{ inputs.ref }}
         persist-credentials: false
-    - uses: actions/setup-python@v5
+    - uses: actions/setup-python@v6
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v3
+      uses: github/codeql-action/init@5d4e8d1aca955e8d8589aabd499c5cae939e33c7 # v4
       with:
         languages: ${{ matrix.language }}
         build-mode: ${{ matrix.build-mode }}
@@ -54,7 +54,6 @@ jobs:
         queries: security-extended
         config: |
           paths-ignore:
-            - '.github/**'
             - 'doc/**'
             - 'tools/**'
             - 'test/**'
@@ -64,6 +63,6 @@ jobs:
         pip install -e .
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v3
+      uses: github/codeql-action/analyze@5d4e8d1aca955e8d8589aabd499c5cae939e33c7 # v4
       with:
         category: "/language:${{matrix.language}}"

.github/workflows/create-release-branch.yml

@@ -33,17 +33,19 @@ jobs:
     outputs:
       version: ${{ steps.pre-publish.outputs.version }}
     steps:
-      - uses: mongodb-labs/drivers-github-tools/secure-checkout@v2
+      - uses: mongodb-labs/drivers-github-tools/secure-checkout@v3
         with:
           app_id: ${{ vars.APP_ID }}
           private_key: ${{ secrets.APP_PRIVATE_KEY }}
-      - uses: mongodb-labs/drivers-github-tools/setup@v2
+      - uses: mongodb-labs/drivers-github-tools/setup@v3
         with:
           aws_role_arn: ${{ secrets.AWS_ROLE_ARN }}
           aws_region_name: ${{ vars.AWS_REGION_NAME }}
           aws_secret_id: ${{ secrets.AWS_SECRET_ID }}
           artifactory_username: ${{ vars.ARTIFACTORY_USERNAME }}
-      - uses: mongodb-labs/drivers-github-tools/create-branch@v2
+      - name: Get hatch
+        run: pip install hatch
+      - uses: mongodb-labs/drivers-github-tools/create-branch@v3
         id: create-branch
         with:
           branch_name: ${{ inputs.branch_name }}

.github/workflows/dist.yml

@@ -39,28 +39,29 @@ jobs:
         - [ubuntu-latest, "manylinux_ppc64le", "cp3*-manylinux_ppc64le"]
         - [ubuntu-latest, "manylinux_s390x", "cp3*-manylinux_s390x"]
         - [ubuntu-latest, "manylinux_i686", "cp3*-manylinux_i686"]
-        - [windows-2019, "win_amd6", "cp3*-win_amd64"]
+        - [windows-2022, "win_amd6", "cp3*-win_amd64"]
-        - [windows-2019, "win32", "cp3*-win32"]
+        - [windows-2022, "win32", "cp3*-win32"]
+        - [windows-11-arm, "win_arm64", "cp3*-win_arm64"]
         - [macos-14, "macos", "cp*-macosx_*"]
 
     steps:
       - name: Checkout pymongo
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
           persist-credentials: false
           ref: ${{ inputs.ref }}
 
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@v6
         with:
           cache: 'pip'
-          python-version: 3.9
+          python-version: 3.11
           cache-dependency-path: 'pyproject.toml'
           allow-prereleases: true
 
       - name: Set up QEMU
         if: runner.os == 'Linux'
-        uses: docker/setup-qemu-action@v3
+        uses: docker/setup-qemu-action@ce360397dd3f832beb865e1373c09c0e9f86d70a # v4.0.0
         with:
           # setup-qemu-action by default uses `tonistiigi/binfmt:latest` image,
           # which is out of date. This causes seg faults during build.
@@ -69,24 +70,16 @@ jobs:
           platforms: all
 
       - name: Install cibuildwheel
-        # Note: the default manylinux is manylinux2014
+        # Note: the default manylinux is manylinux_2_28
         run: |
           python -m pip install -U pip
-          python -m pip install "cibuildwheel>=2.20,<3"
+          python -m pip install "cibuildwheel>=3.2.0,<4"
 
       - name: Build wheels
         env:
           CIBW_BUILD: ${{ matrix.buildplat[2] }}
         run: python -m cibuildwheel --output-dir wheelhouse
 
-      - name: Build manylinux1 wheels
-        if: ${{ matrix.buildplat[1] == 'manylinux_x86_64' || matrix.buildplat[1] == 'manylinux_i686' }}
-        env:
-          CIBW_MANYLINUX_X86_64_IMAGE: manylinux1
-          CIBW_MANYLINUX_I686_IMAGE: manylinux1
-          CIBW_BUILD: "cp39-${{ matrix.buildplat[1] }} cp39-${{ matrix.buildplat[1] }}"
-        run: python -m cibuildwheel --output-dir wheelhouse
-
       - name: Assert all versions in wheelhouse
         if: ${{ ! startsWith(matrix.buildplat[1], 'macos') }}
         run: |
@@ -95,10 +88,11 @@ jobs:
           ls wheelhouse/*cp311*.whl
           ls wheelhouse/*cp312*.whl
           ls wheelhouse/*cp313*.whl
+          ls wheelhouse/*cp314*.whl
           # Free-threading builds:
-          ls wheelhouse/*cp313t*.whl
+          ls wheelhouse/*cp314t*.whl
 
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v7
         with:
           name: wheel-${{ matrix.buildplat[1] }}
           path: ./wheelhouse/*.whl
@@ -106,18 +100,18 @@ jobs:
 
   make_sdist:
     name: Make SDist
-    runs-on: macos-13
+    runs-on: macos-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
           persist-credentials: false
           ref: ${{ inputs.ref }}
 
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@v6
         with:
           # Build sdist on lowest supported Python
-          python-version: '3.9'
+          python-version: "3.9"
 
       - name: Build SDist
         run: |
@@ -131,7 +125,7 @@ jobs:
           cd ..
           python -c "from pymongo import has_c; assert has_c()"
 
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v7
         with:
           name: "sdist"
           path: ./dist/*.tar.gz
@@ -142,13 +136,13 @@ jobs:
     name: Download Wheels
     steps:
       - name: Download all workflow run artifacts
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@v8
       - name: Flatten directory
         working-directory: .
         run: |
           find . -mindepth 2 -type f -exec mv {} . \;
           find . -type d -empty -delete
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v7
         with:
           name: all-dist-${{ github.run_id }}
           path: "./*"

.github/workflows/pull_request_template.md

@@ -1,23 +0,0 @@
-# [JIRA Ticket ID](Link to Ticket)
-<!-- Please provide explicit URL link to the corresponding JIRA ticket. -->
-
-# Summary
-<!-- Please provide a high level overview of what changes have been made. -->
-
-# Changes in this PR
-<!-- Highlight any high level architecture changes if the summary doesn't already cover the scope. -->
-
-# Test Plan
-<!-- Talk through any unit tests added, and if this is a bug fix, please add repro steps in the event the fix needs to be verified. -->
-
-# Screenshots (Optional)
-<!-- Add a before and after picture to indicate changes. -->
-
-# Callouts or Follow-up items (Optional)
-<!-- Any additional info not already specified in the PR including but not limited to:
-
-1. Potential stakeholders
-2. Slack threads etc.
-3. Implementation details that need additional oversight
-4. Callouts on future tactics
- -->

.github/workflows/release-python.yml

@@ -3,12 +3,8 @@ name: Release
 on:
   workflow_dispatch:
     inputs:
-      version:
-        description: "The new version to set"
-        required: true
       following_version:
         description: "The post (dev) version to set"
-        required: true
       dry_run:
         description: "Dry Run?"
         default: false
@@ -26,7 +22,6 @@ env:
   # to 'false' when the input is set to 'false'.
   DRY_RUN: ${{ ! contains(inputs.dry_run, 'false') }}
   FOLLOWING_VERSION: ${{ inputs.following_version || '' }}
-  VERSION: ${{ inputs.version || '10.10.10.10' }}
 
 defaults:
   run:
@@ -43,20 +38,18 @@ jobs:
     outputs:
       version: ${{ steps.pre-publish.outputs.version }}
     steps:
-      - uses: mongodb-labs/drivers-github-tools/secure-checkout@v2
+      - uses: mongodb-labs/drivers-github-tools/secure-checkout@v3
         with:
           app_id: ${{ vars.APP_ID }}
           private_key: ${{ secrets.APP_PRIVATE_KEY }}
-      - uses: mongodb-labs/drivers-github-tools/setup@v2
+      - uses: mongodb-labs/drivers-github-tools/setup@v3
         with:
           aws_role_arn: ${{ secrets.AWS_ROLE_ARN }}
           aws_region_name: ${{ vars.AWS_REGION_NAME }}
           aws_secret_id: ${{ secrets.AWS_SECRET_ID }}
-          artifactory_username: ${{ vars.ARTIFACTORY_USERNAME }}
+      - uses: mongodb-labs/drivers-github-tools/python/pre-publish@v3
-      - uses: mongodb-labs/drivers-github-tools/python/pre-publish@v2
         id: pre-publish
         with:
-          version: ${{ env.VERSION }}
           dry_run: ${{ env.DRY_RUN }}
 
   build-dist:
@@ -82,19 +75,19 @@ jobs:
       id-token: write
     steps:
       - name: Download all the dists
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@v8
         with:
           name: all-dist-${{ github.run_id }}
           path: dist/
       - name: Publish package distributions to TestPyPI
-        uses: pypa/gh-action-pypi-publish@release/v1
+        uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e # release/v1
         with:
           repository-url: https://test.pypi.org/legacy/
           skip-existing: true
           attestations: ${{ env.DRY_RUN }}
       - name: Publish package distributions to PyPI
         if: startsWith(env.DRY_RUN, 'false')
-        uses: pypa/gh-action-pypi-publish@release/v1
+        uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e # release/v1
 
   post-publish:
     needs: [publish]
@@ -106,19 +99,17 @@ jobs:
       attestations: write
       security-events: write
     steps:
-      - uses: mongodb-labs/drivers-github-tools/secure-checkout@v2
+      - uses: mongodb-labs/drivers-github-tools/secure-checkout@v3
         with:
           app_id: ${{ vars.APP_ID }}
           private_key: ${{ secrets.APP_PRIVATE_KEY }}
-      - uses: mongodb-labs/drivers-github-tools/setup@v2
+      - uses: mongodb-labs/drivers-github-tools/setup@v3
         with:
           aws_role_arn: ${{ secrets.AWS_ROLE_ARN }}
           aws_region_name: ${{ vars.AWS_REGION_NAME }}
           aws_secret_id: ${{ secrets.AWS_SECRET_ID }}
-          artifactory_username: ${{ vars.ARTIFACTORY_USERNAME }}
+      - uses: mongodb-labs/drivers-github-tools/python/post-publish@v3
-      - uses: mongodb-labs/drivers-github-tools/python/post-publish@v2
         with:
-          version: ${{ env.VERSION }}
           following_version: ${{ env.FOLLOWING_VERSION }}
           product_name: ${{ env.PRODUCT_NAME }}
           evergreen_project: ${{ env.EVERGREEN_PROJECT }}

.github/workflows/sbom.yml

@@ -0,0 +1,104 @@
+name: Generate SBOM
+
+# This workflow uses cyclonedx-py and publishes an sbom.json artifact.
+# It runs on manual trigger or when package files change on main branch,
+# and creates a PR with the updated SBOM.
+# Internal documentation: go/sbom-scope
+
+on:
+  workflow_dispatch: {}
+  push:
+    branches: ['master']
+    paths:
+      - 'requirements.txt'
+      - 'requirements/**.txt'
+      - '!requirements/docs.txt'
+      - '!requirements/test.txt'
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  sbom:
+    name: Generate SBOM and Create PR
+    runs-on: ubuntu-latest
+    concurrency:
+      group: sbom-${{ github.ref }}
+      cancel-in-progress: false
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v6
+        with:
+          persist-credentials: false
+
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: "3.10"
+
+      - name: Generate SBOM
+        run: |
+          python -m venv .venv
+          source .venv/bin/activate
+          python tools/generate_sbom_requirements.py
+          pip install -r sbom-requirements.txt
+          pip install .
+          pip uninstall -y pip setuptools
+          deactivate
+          python -m venv .venv-sbom
+          source .venv-sbom/bin/activate
+          pip install cyclonedx-bom==7.2.1
+          cyclonedx-py environment --spec-version 1.5 --output-format JSON --output-file sbom.json .venv
+          # Add PURL for pymongo (local package doesn't get PURL automatically)
+          jq '(.components[] | select(.name == "pymongo" and .purl == null)) |= (. + {purl: ("pkg:pypi/pymongo@" + .version)})' sbom.json > sbom.tmp.json && mv sbom.tmp.json sbom.json
+
+      - name: Download CycloneDX CLI
+        run: |
+          curl -L -s -o /tmp/cyclonedx "https://github.com/CycloneDX/cyclonedx-cli/releases/download/v0.29.1/cyclonedx-linux-x64"
+          chmod +x /tmp/cyclonedx
+
+      - name: Validate SBOM
+        run: /tmp/cyclonedx validate --input-file sbom.json --fail-on-errors
+
+      - name: Cleanup
+        if: always()
+        run: rm -rf .venv .venv-sbom sbom-requirements.txt
+
+      - name: Upload SBOM artifact
+        uses: actions/upload-artifact@v7
+        with:
+          name: sbom
+          path: sbom.json
+          if-no-files-found: error
+
+      - name: Create Pull Request
+        uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0  # v8
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          commit-message: 'chore: Update SBOM after dependency changes'
+          branch: auto-update-sbom-${{ github.run_id }}
+          delete-branch: true
+          title: 'Automation: Update SBOM'
+          body: |
+            ## Automated SBOM Update
+
+            This PR was automatically generated because dependency manifest files changed.
+
+            ### Changes
+            - Updated `sbom.json` to reflect current dependencies
+
+            ### Verification
+            The SBOM was generated using cyclonedx-py v7.2.1 with the current Python environment.
+
+            ### Triggered by
+            - Commit: ${{ github.sha }}
+            - Workflow run: ${{ github.run_id }}
+
+            ---
+            _This PR was created automatically by the [SBOM workflow](${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }})_
+          labels: |
+            sbom
+            automated
+            dependencies

.github/workflows/test-python.yml

@@ -14,21 +14,24 @@ defaults:
   run:
     shell: bash -eux {0}
 
+permissions:
+  contents: read
+
 jobs:
 
   static:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           persist-credentials: false
-      - name: Install just
-        uses: extractions/setup-just@v3
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
         with:
           enable-cache: true
-          python-version: "3.9"
+          python-version: "3.10"
+      - name: Install just
+        run: uv tool install rust-just
       - name: Install Python dependencies
         run: |
           just install
@@ -50,71 +53,102 @@ jobs:
           cppcheck pymongo
 
   build:
-    # supercharge/mongodb-github-action requires containers so we don't test other platforms
     runs-on: ${{ matrix.os }}
     strategy:
       fail-fast: false
       matrix:
+        # Tests currently only pass on ubuntu on GitHub Actions.
         os: [ubuntu-latest]
-        python-version: ["3.9", "pypy-3.10", "3.13", "3.13t"]
+        python-version: ["3.10", "pypy-3.11", "3.13t"]
+        mongodb-version: ["8.0"]
+
     name: CPython ${{ matrix.python-version }}-${{ matrix.os }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           persist-credentials: false
-      - name: Install just
-        uses: extractions/setup-just@v3
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
         with:
           enable-cache: true
           python-version: ${{ matrix.python-version }}
-      - name: Install dependencies
+      - id: setup-mongodb
-        run: just install
+        uses: mongodb-labs/drivers-evergreen-tools@master
-      - name: Start MongoDB
-        uses: supercharge/mongodb-github-action@1.12.0
         with:
-          mongodb-version: 6.0
+          version: "${{ matrix.mongodb-version }}"
       - name: Run tests
-        run: just test
+        run: uv run --extra test pytest -v
 
+  coverage:
+    # This enables a coverage report for a given PR, which will be augmented by
+    # the combined codecov report uploaded in Evergreen.
+    runs-on: ubuntu-latest
+
+    name: Coverage
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          persist-credentials: false
+      - name: Install uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          enable-cache: true
+          python-version: "3.10"
+      - id: setup-mongodb
+        uses: mongodb-labs/drivers-evergreen-tools@master
+        with:
+          version: "8.0"
+      - name: Install just
+        run: uv tool install rust-just
+      - name: Setup tests
+        run: COVERAGE=1 just setup-tests
+      - name: Run tests
+        run: just run-tests
+      - name: Generate xml report
+        run: uv tool run --with "coverage[toml]" coverage xml
+      - name: Upload test results to Codecov
+        uses: codecov/codecov-action@671740ac38dd9b0130fbe1cec585b89eea48d3de # v5
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
   doctest:
     runs-on: ubuntu-latest
     name: DocTest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           persist-credentials: false
-      - name: Install just
-        uses: extractions/setup-just@v3
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
         with:
           enable-cache: true
-          python-version: "3.9"
+          python-version: "3.10"
-      - name: Start MongoDB
+      - name: Install just
-        uses: supercharge/mongodb-github-action@1.12.0
+        run: uv tool install rust-just
+      - id: setup-mongodb
+        uses: mongodb-labs/drivers-evergreen-tools@master
         with:
-          mongodb-version: '8.0.0-rc4'
+          version: "8.0"
       - name: Install dependencies
         run: just install
       - name: Run tests
-        run:  just docs-test
+        run:  |
+          just setup-tests doctest
+          just run-tests
 
   docs:
     name: Docs Checks
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           persist-credentials: false
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
         with:
           enable-cache: true
-          python-version: "3.9"
+          python-version: "3.10"
       - name: Install just
-        uses: extractions/setup-just@v3
+        run: uv tool install rust-just
       - name: Install dependencies
         run: just install
       - name: Build docs
@@ -124,16 +158,16 @@ jobs:
     name: Link Check
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           persist-credentials: false
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
         with:
           enable-cache: true
-          python-version: "3.9"
+          python-version: "3.10"
       - name: Install just
-        uses: extractions/setup-just@v3
+        run: uv tool install rust-just
       - name: Install dependencies
         run: just install
       - name: Build docs
@@ -144,18 +178,18 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python: ["3.9", "3.11"]
+        python: ["3.10", "3.11"]
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           persist-credentials: false
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
         with:
           enable-cache: true
           python-version: "${{matrix.python}}"
       - name: Install just
-        uses: extractions/setup-just@v3
+        run: uv tool install rust-just
       - name: Install dependencies
         run: |
           just install
@@ -163,25 +197,55 @@ jobs:
         run: |
           just typing
 
+  integration_tests:
+    runs-on: ubuntu-latest
+    name: Integration Tests
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          persist-credentials: false
+      - name: Install uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          enable-cache: true
+          python-version: "3.10"
+      - name: Install just
+        run: uv tool install rust-just
+      - name: Install dependencies
+        run: |
+          just install
+      - id: setup-mongodb
+        uses: mongodb-labs/drivers-evergreen-tools@master
+      - name: Run tests
+        run:  |
+          just integration-tests
+      - id: setup-mongodb-ssl
+        uses: mongodb-labs/drivers-evergreen-tools@master
+        with:
+          ssl: true
+      - name: Run tests
+        run: |
+          just integration-tests
+
   make_sdist:
     runs-on: ubuntu-latest
     name: "Make an sdist"
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           persist-credentials: false
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@v6
         with:
           cache: 'pip'
           cache-dependency-path: 'pyproject.toml'
           # Build sdist on lowest supported Python
-          python-version: '3.9'
+          python-version: "3.9"
       - name: Build SDist
         shell: bash
         run: |
           pip install build
           python -m build --sdist
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v7
         with:
           name: "sdist"
           path: dist/*.tar.gz
@@ -193,7 +257,9 @@ jobs:
       timeout-minutes: 20
       steps:
         - name: Download sdist
-          uses: actions/download-artifact@v4
+          uses: actions/download-artifact@v8
+          with:
+            path: sdist/
         - name: Unpack SDist
           shell: bash
           run: |
@@ -202,14 +268,14 @@ jobs:
             mkdir test
             tar --strip-components=1 -zxf *.tar.gz -C ./test
             ls test
-        - uses: actions/setup-python@v5
+        - uses: actions/setup-python@v6
           with:
             cache: 'pip'
             cache-dependency-path: 'sdist/test/pyproject.toml'
             # Test sdist on lowest supported Python
-            python-version: '3.9'
+            python-version: "3.9"
-        - name: Start MongoDB
+        - id: setup-mongodb
-          uses: supercharge/mongodb-github-action@1.12.0
+          uses: mongodb-labs/drivers-evergreen-tools@master
         - name: Run connect test from sdist
           shell: bash
           run: |
@@ -218,3 +284,28 @@ jobs:
             which python
             pip install -e ".[test]"
             PYMONGO_MUST_CONNECT=1 pytest -v -k client_context
+
+  test_minimum:
+      permissions:
+        contents: read
+      runs-on: ubuntu-latest
+      name: Test minimum dependencies and Python
+      steps:
+        - uses: actions/checkout@v6
+          with:
+            persist-credentials: false
+        - name: Install uv
+          uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+          with:
+            python-version: "3.9"
+        - id: setup-mongodb
+          uses: mongodb-labs/drivers-evergreen-tools@master
+          with:
+            version: "8.0"
+        - name: Run tests
+          shell: bash
+          run: |
+            uv venv
+            source .venv/bin/activate
+            uv pip install -e ".[test]" --resolution=lowest-direct --force-reinstall
+            pytest -v test/test_srv_polling.py test/test_dns.py test/asynchronous/test_srv_polling.py test/asynchronous/test_dns.py

.github/workflows/zizmor.yml

@@ -14,19 +14,8 @@ jobs:
       security-events: write
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           persist-credentials: false
-      - name: Setup Rust
-        uses: actions-rust-lang/setup-rust-toolchain@v1
-      - name: Get zizmor
-        run: cargo install zizmor
       - name: Run zizmor 🌈
-        run: zizmor --format sarif . > results.sarif
+        uses: zizmorcore/zizmor-action@71321a20a9ded102f6e9ce5718a2fcec2c4f70d8 # v0.5.2
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      - name: Upload SARIF file
-        uses: github/codeql-action/upload-sarif@v3
-        with:
-          sarif_file: results.sarif
-          category: zizmor

.github/zizmor.yml

@@ -0,0 +1,7 @@
+rules:
+  unpinned-uses:
+    config:
+      policies:
+        actions/*: ref-pin
+        mongodb-labs/drivers-github-tools/*: ref-pin
+        mongodb-labs/drivers-evergreen-tools: ref-pin

.gitignore

@@ -30,6 +30,7 @@ expansion.yml
 .evergreen/scripts/test-env.sh
 specifications/
 results.json
+.evergreen/atlas_x509_dev_client_certificate.pem
 
 # Lambda temp files
 test/lambda/.aws-sam
@@ -40,4 +41,6 @@ test/lambda/*.json
 
 # test results and logs
 xunit-results/
+coverage.xml
 server.log
+.coverage

.pre-commit-config.yaml

@@ -18,6 +18,14 @@ repos:
     exclude: .patch
     exclude_types: [json]
 
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  # Ruff version.
+  rev: v0.1.3
+  hooks:
+    - id: ruff
+      args: ["--fix", "--show-fixes"]
+    - id: ruff-format
+
 - repo: local
   hooks:
     - id: synchro
@@ -30,14 +38,6 @@ repos:
         - ruff==0.1.3
         - unasync
 
-- repo: https://github.com/astral-sh/ruff-pre-commit
-  # Ruff version.
-  rev: v0.1.3
-  hooks:
-    - id: ruff
-      args: ["--fix", "--show-fixes"]
-    - id: ruff-format
-
 - repo: https://github.com/adamchainz/blacken-docs
   rev: "1.16.0"
   hooks:
@@ -121,4 +121,15 @@ repos:
     entry: .evergreen/scripts/generate-config.sh
     language: python
     require_serial: true
-    additional_dependencies: ["shrub.py>=3.9.0", "pyyaml>=6.0.2"]
+    additional_dependencies: ["shrub.py>=3.10.0", "pyyaml>=6.0.2"]
+
+  - id: uv-lock
+    name: uv-lock
+    entry: uv lock
+    language: python
+    require_serial: true
+    files: ^(uv\.lock|pyproject\.toml|requirements.txt|requirements/.*\.txt)$
+    pass_filenames: false
+    fail_fast: true
+    additional_dependencies:
+      - "uv>=0.8.4"

CONTRIBUTING.md

@@ -16,7 +16,7 @@ be of interest or that has already been addressed.
 
 ## Supported Interpreters
 
-PyMongo supports CPython 3.9+ and PyPy3.10+. Language features not
+PyMongo supports CPython 3.9+ and PyPy3.9+. Language features not
 supported by all interpreters can not be used.
 
 ## Style Guide
@@ -85,49 +85,53 @@ likelihood for getting review sooner shoots up.
     -   `versionadded:: 3.11`
     -   `versionchanged:: 3.5`
 
-**Pull Request Template Breakdown**
+### AI-Generated Contributions Policy
 
--  **Github PR Title**
+#### Our Stance
 
-    -   The PR Title format should always be
+We only accept pull requests that are authored and submitted by human contributors who fully understand the changes they are proposing. Pull requests that are not clearly owned and understood by a human contributor may be closed. **All contributions must be submitted, reviewed, and understood by human contributors.**
-            `[JIRA-ID] : Jira Title or Blurb Summary`.
 
--  **JIRA LINK**
+##### Why This Policy Exists
 
--   Convenient link to the associated JIRA ticket.
+At MongoDB, we understand the power and prevalence of AI tools in software development. With that being said, many MongoDB libraries are foundational tools used in production systems worldwide. The nature of these libraries requires:
 
--   **Summary**
+- **Deep domain expertise**: MongoDB's wire protocol, BSON specification, connection pooling, authentication mechanisms, and concurrency patterns require an understanding that AI alone cannot substantiate.
 
-     -   Small blurb on why this is needed. The JIRA task should have
+- **Long-term maintainability**: Contributors need to be able to explain *why* code is written a certain way, explain design decisions, and be available to iterate on their contributions.
-            the more in-depth description, but this should still, at a
-            high level, give anyone looking an understanding of why the
-            PR has been checked in.
 
--    **Changes in this PR**
+- **Security responsibility**: Authentication, credential handling, and TLS implementation cannot be left to probabilistic code generation.
 
-     -   The explicit code changes that this PR is introducing. This
+##### What This Means for Contributors
-            should be more specific than just the task name. (Unless the
-            task name is very clear).
 
--   **Test Plan**
+**Required:**
 
-    -   Everything needs a test description. Describe what you did
+- Full understanding of every line of code you submit
-            to validate your changes actually worked; if you did
+- Ability to explain and defend your implementation choices
-            nothing, then document you did not test it. Aim to make
+- Willingness to iterate and maintain your contributions
-            these steps reproducible by other engineers, specifically
-            with your primary reviewer in mind.
 
--   **Screenshots**
+**Encouraged:**
 
-    -   Any images that provide more context to the PR. Usually,
+- Using AI assistants as learning tools to understand concepts
-            these just coincide with the test plan.
+- IDE autocomplete features that suggest standard patterns
+- AI help for brainstorming approaches (but write the code yourself)
+- Writing code using AI tools, reviewing each line and revising code as necessary.
 
--   **Callouts or follow-up items**
+**Not allowed:**
 
-    -   This is a good place for identifying "to-dos" that you've
+- Submitting PRs generated solely by AI tools
-            placed in the code (Must have an accompanying JIRA Ticket).
+- Copy-pasting AI-generated code without full understanding
-    -   Potential bugs that you are unsure how to test in the code.
+
-    -   Opinions you want to receive about your code.
+##### Disclosure
+
+If you used AI assistance in any way during your contribution, please disclose what the AI assistant was used for in your PR description. We would love to know what tools developers have found useful in iterating in their day to day.
+
+##### Questions?
+
+If you're unsure whether your contribution complies with this policy, please ask for guidance within the scope of the PR and clarify any uncertainty. We're happy to guide contributors toward successful contributions.
+
+---
+
+*This policy helps us maintain the reliability, security, and trustworthiness that production applications depend on. Thank you for understanding and for contributing thoughtfully to PyMongo.*
 
 ## Running Linters
 
@@ -190,19 +194,22 @@ just docs-serve
 Browse to the link provided, and then as you make changes to docstrings or narrative docs,
 the pages will re-render and the browser will automatically refresh.
 
-
 ## Running Tests Locally
 
--   Ensure you have started the appropriate Mongo Server(s).
 -   Run `just install` to set a local virtual environment, or you can manually
     create a virtual environment and run `pytest` directly.  If you want to use a specific
-    version of Python, remove the `.venv` folder and set `PYTHON_BINARY` before running `just install`.
+    version of Python, set `UV_PYTHON` before running `just install`.
+-   Ensure you have started the appropriate Mongo Server(s).  You can run `just run-server` with optional args
+    to set up the server.  All given options will be passed to
+    [`run-mongodb.sh`](https://github.com/mongodb-labs/drivers-evergreen-tools/blob/master/.evergreen/run-mongodb.sh).  Run `$DRIVERS_TOOLS/.evergreen/run-mongodb.sh start -h`
+    for a full list of options.
 -   Run `just test` or `pytest` to run all of the tests.
 -   Append `test/<mod_name>.py::<class_name>::<test_name>` to run
     specific tests. You can omit the `<test_name>` to test a full class
     and the `<class_name>` to test a full module. For example:
     `just test test/test_change_stream.py::TestUnifiedChangeStreamsErrors::test_change_stream_errors_on_ElectionInProgress`.
 -   Use the `-k` argument to select tests by pattern.
+-   Run `just test-coverage` to run tests with coverage and display a report. After running tests with coverage, use `just coverage-html` to generate an HTML report in `htmlcov/index.html`.
 
 
 ## Running tests that require secrets, services, or other configuration
@@ -213,24 +220,53 @@ the pages will re-render and the browser will automatically refresh.
     `git clone git@github.com:mongodb-labs/drivers-evergreen-tools.git`.
 - Run `export DRIVERS_TOOLS=$PWD/drivers-evergreen-tools`.  This can be put into a `.bashrc` file
   for convenience.
-- Set up access to [Drivers test secrets](https://github.com/mongodb-labs/drivers-evergreen-tools/tree/master/.evergreen/secrets_handling#secrets-handling).
+- Some tests require access to [Drivers test secrets](https://github.com/mongodb-labs/drivers-evergreen-tools/tree/master/.evergreen/secrets_handling#secrets-handling).
 
 ### Usage
 
-- Run `just run-server` with optional args to set up the server.  All given options will be passed to
+- Run `just run-server` with optional args to set up the server.
-  `run-orchestration.sh` in `$DRIVERS_TOOLS`.  See `$DRIVERS_TOOLS/evergreen/run-orchestration.sh -h`
-  for a full list of options.
 - Run `just setup-tests` with optional args to set up the test environment, secrets, etc.
   See `just setup-tests -h` for a full list of available options.
 - Run `just run-tests` to run the tests in an appropriate Python environment.
 - When done, run `just teardown-tests` to clean up and `just stop-server` to stop the server.
 
+### SSL tests
+
+- Run `just run-server --ssl` to start the server with TLS enabled.
+- Run `just setup-tests --ssl`.
+- Run `just run-tests`.
+
+Note: for general testing purposes with an TLS-enabled server, you can use the following (this should ONLY be used
+for local testing):
+
+```python
+from pymongo import MongoClient
+
+client = MongoClient(
+    "mongodb://localhost:27017?tls=true&tlsAllowInvalidCertificates=true"
+)
+```
+
+If you want to use the actual certificate file then set `tlsCertificateKeyFile` to the local path
+to `<repo_roo>/test/certificates/client.pem` and `tlsCAFile` to the local path to `<repo_roo>/test/certificates/ca.pem`.
+
 ### Encryption tests
 
 - Run `just run-server` to start the server.
 - Run `just setup-tests encryption`.
 - Run the tests with `just run-tests`.
 
+To test with `encryption` and `PyOpenSSL`, use `just setup-tests encryption pyopenssl`.
+
+### PyOpenSSL tests
+
+- Run `just run-server` to start the server.
+- Run `just setup-tests default_sync pyopenssl`.
+- Run the tests with `just run-tests`.
+
+Note: `PyOpenSSL` is not used in async tests, but you can use `just setup-tests default_async pyopenssl`
+to verify that PyMongo falls back to the standard library `OpenSSL`.
+
 ### Load balancer tests
 
 - Install `haproxy` (available as `brew install haproxy` on macOS).
@@ -294,7 +330,8 @@ Note: these tests can only be run from an Evergreen host.
 The doc tests require a running server.
 
 - Run `just run-server`.
-- Run `just docs-test`.
+- Run `just setup-tests doctest`.
+- Run `just run-tests`.
 
 ### Free-threaded Python Tests
 
@@ -303,7 +340,7 @@ Locally you can run:
 
 - Run `just run-server`.
 - Run `just setup-tests`.
-- Run `UV_PYTHON=3.13t just run-tests`.
+- Run `UV_PYTHON=3.14t just run-tests`.
 
 ### AWS Lambda tests
 
@@ -323,13 +360,6 @@ Note: these tests can only be run from an Evergreen Linux host that has the Pyth
 The `mode` can be `standalone` or `embedded`.  For the `replica_set` version of the tests, use
 `TOPOLOGY=replica_set just run-server`.
 
-### Atlas Data Lake tests.
-
-You must have `docker` or `podman` installed locally.
-
-- Run `just setup-tests data_lake`.
-- Run `just run-tests`.
-
 ### OCSP tests
 
 - Export the orchestration file, e.g. `export ORCHESTRATION_FILE=rsa-basic-tls-ocsp-disableStapling.json`.
@@ -351,17 +381,27 @@ If you are running one of the `no-responder` tests, omit the `run-server` step.
 
 ## Enable Debug Logs
 
-- Use `-o log_cli_level="DEBUG" -o log_cli=1` with `just test` or `pytest`.
+- Use `-o log_cli_level="DEBUG" -o log_cli=1` with `just test` or `pytest` to output all debug logs to the terminal. **Warning**: This will output a huge amount of logs.
-- Add `log_cli_level = "DEBUG` and `log_cli = 1` to the `tool.pytest.ini_options` section in `pyproject.toml` for Evergreen patches or to enable debug logs by default on your machine.
+- Add `log_cli=1` and `log_cli_level="DEBUG"` to the `tool.pytest.ini_options` section in `pyproject.toml` to enable debug logs in this manner by default on your machine.
-- You can also set `DEBUG_LOG=1` and run either `just setup-tests` or `just-test`.
+- Set `DEBUG_LOG=1` and run `just setup-tests`, `just-test`, or `pytest` to enable debug logs only for failed tests.
 - Finally, you can use `just setup-tests --debug-log`.
-- For evergreen patch builds, you can use `evergreen patch --param DEBUG_LOG=1` to enable debug logs for the patch.
+- For evergreen patch builds, you can use `evergreen patch --param DEBUG_LOG=1` to enable debug logs for failed tests in the patch.
+
+## Testing minimum dependencies
+
+To run any of the test suites with minimum supported dependencies, pass `--test-min-deps` to
+`just setup-tests`.
+
+## Testing time-dependent operations
+
+- `test.utils_shared.delay` - One can trigger an arbitrarily long-running operation on the server using this delay utility
+  in combination with a `$where` operation. Use this to test behaviors around timeouts or signals.
 
 ## Adding a new test suite
 
 - If adding new tests files that should only be run for that test suite, add a pytest marker to the file and add
   to the list of pytest markers in `pyproject.toml`.  Then add the test suite to the `TEST_SUITE_MAP` in `.evergreen/scripts/utils.py`.  If for some reason it is not a pytest-runnable test, add it to the list of `EXTRA_TESTS` instead.
-- If the test uses Atlas or otherwise doesn't use `run-orchestration.sh`, add it to the `NO_RUN_ORCHESTRATION` list in
+- If the test uses Atlas or otherwise doesn't use `run-mongodb.sh`, add it to the `NO_RUN_ORCHESTRATION` list in
   `.evergreen/scripts/utils.py`.
 - If there is something special required to run the local server or there is an extra flag that should always be set
   like `AUTH`, add that logic to `.evergreen/scripts/run_server.py`.
@@ -369,10 +409,44 @@ If you are running one of the `no-responder` tests, omit the `run-server` step.
 - If there are any special test considerations, including not running `pytest` at all, handle it in `.evergreen/scripts/run_tests.py`.
 - If there are any services or atlas clusters to teardown, handle them in `.evergreen/scripts/teardown_tests.py`.
 - Add functions to generate the test variant(s) and task(s) to the `.evergreen/scripts/generate_config.py`.
+- There are some considerations about the Python version used in the test:
+    - If a specific version of Python is needed in a task that is running on variants with a toolchain, use
+``TOOLCHAIN_VERSION`` (e.g. `TOOLCHAIN_VERSION=3.10`).  The actual path lookup needs to be done on the host, since
+tasks are host-agnostic.
+    - If a specific Python binary is needed (for example on the FIPS host), set `UV_PYTHON=/path/to/python`.
+    - If a specific Python version is needed and the toolchain will not be available, use `UV_PYTHON` (e.g. `UV_PYTHON=3.11`).
+    - The default if neither ``TOOLCHAIN_VERSION`` or ``UV_PYTHON`` is set is to use UV to install the minimum
+      supported version of Python and use that.  This ensures a consistent behavior across host types that do not
+      have the Python toolchain (e.g. Azure VMs), by having a known version of Python with the build headers (`Python.h`)
+      needed to build the C extensions.
 - Regenerate the test variants and tasks using `pre-commit run --all-files generate-config`.
 - Make sure to add instructions for running the test suite to `CONTRIBUTING.md`.
 
-## Re-sync Spec Tests
+## Handling flaky tests
+
+We have a custom `flaky` decorator in [test/asynchronous/utils.py](test/asynchronous/utils.py) that can be used for
+tests that are `flaky`.  By default the decorator only applies when not running on CPython on Linux, since other
+runtimes tend to have more variation.  When using the `flaky` decorator, open a corresponding ticket and
+a use the ticket number as the "reason" parameter to the decorator, e.g. `@flaky(reason="PYTHON-1234")`.
+When running tests locally (not in CI), the `flaky` decorator will be disabled unless `ENABLE_FLAKY` is set.
+To disable the `flaky` decorator in CI, you can use `evergreen patch --param DISABLE_FLAKY=1`.
+
+## Integration Tests
+
+The `integration_tests` directory has a set of scripts that verify the usage of PyMongo with downstream packages or frameworks.  See the [README](./integration_tests/README.md) for more information.
+
+To run the tests, use `just integration_tests`.
+
+The tests should be able to run with and without SSL enabled.
+
+## Specification Tests
+
+The MongoDB [specifications repository](https://github.com/mongodb/specifications)
+holds in progress and completed specifications for features of MongoDB, drivers,
+and associated products. PyMongo supports the [Unified Test Format](https://jira.mongodb.org/browse/DRIVERS-709)
+for running specification tests to confirm PyMongo behaves as expected.
+
+### Resynchronizing the Specification Tests
 
 If you would like to re-sync the copy of the specification tests in the
 PyMongo repository with that which is inside the [specifications
@@ -393,17 +467,58 @@ update in PyMongo. This is primarily helpful if you are implementing a
 new feature in PyMongo that has spec tests already implemented, or if
 you are attempting to validate new spec tests in PyMongo.
 
+### Automated Specification Test Resyncing
+The (`/.evergreen/scripts/resync-all-specs.sh`) script
+automatically runs once a week to resync all the specs with the [specifications repo](https://github.com/mongodb/specifications).
+A PR will be generated by mongodb-drivers-pr-bot containing any changes picked up by this resync.
+The PR description will display the name(s) of the updated specs along
+with any errors that occurred.
+
+Spec test changes associated with a behavioral change or bugfix that has yet to be implemented in PyMongo
+must be added to a patch file in `/.evergreen/spec-patch`. Each patch
+file must be named after the associated PYTHON ticket and contain the
+test differences between PyMongo's current tests and the specification.
+All changes listed in these patch files will be *undone* by the script and won't
+be applied to PyMongo's tests.
+
+When a new test file or folder is added to the spec repo before the associated code changes are implemented, that test's path must be added to  `.evergreen/remove-unimplemented-tests.sh` along with a comment indicating the associated PYTHON ticket for those changes.
+
+Any PR that implements a PYTHON ticket documented in a patch file or within  `.evergreen/remove-unimplemented-tests.sh` must also remove the associated patch file or entry in `remove-unimplemented-tests.sh`.
+
+#### Adding to a patch file
+To add to or create a patch file, run `git diff` to show the desired changes to undo and copy the
+results into the patch file.
+
+For example: the imaginary, unimplemented PYTHON-1234 ticket has associated spec test changes. To add those changes to `PYTHON-1234.patch`), do the following:
+```bash
+git diff HEAD~1 path/to/file >> .evergreen/spec-patch/PYTHON-1234.patch
+```
+
+#### Running Locally
+Both `resync-all-specs.sh` and `resync-all-specs.py` can be run locally (and won't generate a PR).
+```bash
+./.evergreen/scripts/resync-all-specs.sh
+python3 ./.evergreen/scripts/resync-all-specs.py
+```
+
 ## Making a Release
 
 Follow the [Python Driver Release Process Wiki](https://wiki.corp.mongodb.com/display/DRIVERS/Python+Driver+Release+Process).
 
-## Asyncio considerations
+## Project Structure and Asyncio Considerations
 
-PyMongo adds asyncio capability by modifying the source files in `*/asynchronous` to `*/synchronous` using
+This section describes the layout of the `pymongo/` package.
-[unasync](https://github.com/python-trio/unasync/) and some custom transforms.
 
-Where possible, edit the code in `*/asynchronous/*.py` and not the synchronous files.
+Within `pymongo/`, the code is further divided into the `pymongo/asynchronous` and `pymongo/synchronous` subdirectories.
-You can run `pre-commit run --all-files synchro` before running tests if you are testing synchronous code.
+Files in `pymongo/synchronous` are generated from `pymongo/asynchronous` using the `synchro` pre-commit hook, which uses [unasync](https://github.com/python-trio/unasync/) and some custom transforms.
+
+As a result, **all modifications** within `pymongo` must be made in either the top-level `pymongo` directory when they have to exhibit differing behavior between sync and async contexts or the `pymongo/asynchronous` directory, not `pymongo/synchronous`.
+Any changes made directly to files in the `pymongo/synchronous` directory will be overwritten by the `synchro` hook when it is run, which happens automatically on commit.
+
+Some top-level files (e.g. `pymongo/collection.py`) are re-export files for existing import compatibility and should not be modified directly.
+The other top-level files (e.g. `pymongo/network_layer.py`, `pymongo/pool_shared.py`) contain either shared code used in both the asynchronous and synchronous APIs, or code that is very different between the two APIs and therefore cannot be generated from the async version using `synchro`.
+
+Run `pre-commit run --all-files synchro` before running tests to generate the latest version of the synchronous code.
 
 To prevent the `synchro` hook from accidentally overwriting code, it first checks to see whether a sync version
 of a file is changing and not its async counterpart, and will fail.
@@ -415,8 +530,51 @@ run `pre-commit run --all-files --hook-stage manual ruff` and fix all reported e
 hook again.
 
 ## Converting a test to async
+
 The `tools/convert_test_to_async.py` script takes in an existing synchronous test file and outputs a
 partially-converted asynchronous version of the same name to the `test/asynchronous` directory.
 Use this generated file as a starting point for the completed conversion.
 
 The script is used like so: `python tools/convert_test_to_async.py [test_file.py]`
+
+## CPU profiling
+
+To profile a test script and generate a flame graph, follow these steps:
+
+1. Install `py-spy` if you haven't already:
+   ```bash
+   pip install py-spy
+   ```
+2. Inside your test script, perform any required setup and then loop over the code you want to profile for improved sampling.
+3. Run `py-spy record -o <output.svg> -r <sample_rate=100> -- python <path/to/script>` to generate a `.svg` file containing the flame graph.
+   (Note: on macOS you will need to run this command using `sudo` to allow `py-spy` to attach to the Python process.)
+4. If you need to include native code (for example the C extensions), profiling should be done on a Linux system, as macOS and Windows do not support the `--native` option of `py-spy`.
+   Creating an ubuntu Evergreen spawn host and using `scp` to copy the flamegraph `.svg` file back to your local machine is the best way to do this.
+5. You can then view the flamegraph using an SVG viewer like a browser.
+
+## Memory profiling
+
+To test for a memory leak or any memory-related issues, the current best tool is [memray](https://bloomberg.github.io/memray/overview.html).
+In order to include code from our C extensions, it must be run in native mode, on Linux.
+To do so, either spin up an Ubuntu docker container or an Ubuntu Evergreen spawn host.
+
+From the spawn host or Ubuntu image, do the following:
+
+1. Install `memray` if you haven't already:
+   ```bash
+   pip install memray
+   ```
+2. Inside your test script, perform any required setup and then loop over the code you want to profile for improved sampling.
+3. Run memray with the script under test with the `--native` flag, e.g. `python -m memray run --native -o test.bin <path/to/script>`.
+4. Generate the flamegraph with `python -m memray flamegraph -o test.html test.bin`.
+   See the [docs](https://bloomberg.github.io/memray/flamegraph.html) for more options.
+5. Then, from the host computer, use either scp or docker cp to copy the flamegraph, e.g. `scp ubuntu@ec2-3-82-52-49.compute-1.amazonaws.com:/home/ubuntu/test.html .`.
+6. You can then view the flamegraph html in a browser.
+
+## Dependabot updates
+
+Dependabot will raise PRs at most once per week, grouped by GitHub Actions updates and Python requirement
+file updates.  We have a pre-commit hook that will update the `uv.lock` file when requirements change.
+To update the lock file on a failing PR, you can use a method like `gh pr checkout <pr number>`, then run
+`just lint uv-lock` to update the lock file, and then push the changes.  If a typing dependency has changed,
+also run `just typing` and handle any new findings.

README.md

@@ -4,17 +4,25 @@
 [![Python Versions](https://img.shields.io/pypi/pyversions/pymongo)](https://pypi.org/project/pymongo)
 [![Monthly Downloads](https://static.pepy.tech/badge/pymongo/month)](https://pepy.tech/project/pymongo)
 [![API Documentation Status](https://readthedocs.org/projects/pymongo/badge/?version=stable)](http://pymongo.readthedocs.io/en/stable/api?badge=stable)
+[![codecov](https://codecov.io/gh/mongodb/mongo-python-driver/graph/badge.svg?branch=master)](https://codecov.io/gh/mongodb/mongo-python-driver)
 
 ## About
 
 The PyMongo distribution contains tools for interacting with MongoDB
 database from Python. The `bson` package is an implementation of the
 [BSON format](http://bsonspec.org) for Python. The `pymongo` package is
-a native Python driver for MongoDB. The `gridfs` package is a
+a native Python driver for MongoDB, offering both synchronous and asynchronous APIs. The `gridfs` package is a
 [gridfs](https://github.com/mongodb/specifications/blob/master/source/gridfs/gridfs-spec.md/)
 implementation on top of `pymongo`.
 
-PyMongo supports MongoDB 4.0, 4.2, 4.4, 5.0, 6.0, 7.0, and 8.0.
+PyMongo supports MongoDB 4.0, 4.2, 4.4, 5.0, 6.0, 7.0, and 8.0. PyMongo follows [semantic versioning](https://semver.org/spec/v2.0.0.html) for its releases.
+
+## Documentation
+
+Documentation is available at
+[mongodb.com](https://www.mongodb.com/docs/languages/python/pymongo-driver/current/).
+
+[API documentation](https://pymongo.readthedocs.io/en/stable/api/) and the [full changelog](https://pymongo.readthedocs.io/en/stable/changelog.html) for each release is available at [readthedocs.io](https://pymongo.readthedocs.io/en/stable/index.html).
 
 ## Support / Feedback
 
@@ -90,7 +98,7 @@ package that is incompatible with PyMongo.
 
 ## Dependencies
 
-PyMongo supports CPython 3.9+ and PyPy3.10+.
+PyMongo supports CPython 3.9+ and PyPy3.9+.
 
 Required dependencies:
 
@@ -132,7 +140,8 @@ python -m pip install "pymongo[snappy]"
 ```
 
 Wire protocol compression with zstandard requires
-[zstandard](https://pypi.org/project/zstandard):
+[backports.zstd](https://pypi.org/project/backports.zstd)
+when used with Python versions before 3.14:
 
 ```bash
 python -m pip install "pymongo[zstd]"
@@ -191,13 +200,6 @@ ObjectId('4aba160ee23f6b543e000002')
 [8, 11]
 ```
 
-## Documentation
-
-Documentation is available at
-[pymongo.readthedocs.io](https://pymongo.readthedocs.io/en/stable/).
-
-See the [contributing guide](./CONTRIBUTING.md#documentation) for how to build the documentation.
-
 ## Learning Resources
 
 - MongoDB Learn - [Python
@@ -214,4 +216,4 @@ pip install -e ".[test]"
 pytest
 ```
 
-For more advanced testing scenarios, see the [contributing guide](./CONTRIBUTING.md#running-tests-locally).
+For more advanced testing scenarios, see the [contributing guide](https://github.com/mongodb/mongo-python-driver/blob/master/CONTRIBUTING.md#running-tests-locally).

_setup.py

@@ -130,7 +130,11 @@ if "--no_ext" in sys.argv or os.environ.get("NO_EXT"):
     except ValueError:
         pass
     ext_modules = []
-elif sys.platform.startswith("java") or sys.platform == "cli" or "PyPy" in sys.version:
+elif (
+    sys.platform.startswith("java")
+    or sys.platform == "cli"
+    or sys.implementation.name in ("pypy", "graalpy")
+):
     sys.stdout.write(
         """
 *****************************************************\n

bson/__init__.py

@@ -58,10 +58,10 @@ bytes [#bytes]_                          binary         both
    the microsecond field is truncated.
 .. [#dt2] all datetime.datetime instances are encoded as UTC. By default, they
    are decoded as *naive* but timezone aware datetimes are also supported.
-   See :doc:`/examples/datetimes` for examples.
+   See `Dates and Times <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/dates-and-times/#dates-and-times>`_ for examples.
 .. [#dt3] To enable decoding a bson UTC datetime to a :class:`~bson.datetime_ms.DatetimeMS`
-   instance see :ref:`handling-out-of-range-datetimes`.
+   instance see `handling out of range datetimes <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/dates-and-times/#handling-out-of-range-datetimes>`_.
-.. [#uuid] For :py:class:`uuid.UUID` encoding and decoding behavior see :doc:`/examples/uuid`.
+.. [#uuid] For :py:class:`uuid.UUID` encoding and decoding behavior see `<https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/uuid/#universally-unique-ids--uuids->`_.
 .. [#re] :class:`~bson.regex.Regex` instances and regular expression
    objects from ``re.compile()`` are both saved as BSON regular expressions.
    BSON regular expressions are decoded as :class:`~bson.regex.Regex`
@@ -1009,7 +1009,7 @@ def _dict_to_bson(
                 try:
                     elements.append(_element_to_bson(key, value, check_keys, opts))
                 except InvalidDocument as err:
-                    raise InvalidDocument(f"Invalid document {doc} | {err}") from err
+                    raise InvalidDocument(f"Invalid document: {err}", doc) from err
     except AttributeError:
         raise TypeError(f"encoder expected a mapping type but got: {doc!r}") from None
 
@@ -1109,7 +1109,9 @@ def _decode_all(data: _ReadableBuffer, opts: CodecOptions[_DocumentType]) -> lis
         while position < end:
             obj_size = _UNPACK_INT_FROM(data, position)[0]
             if data_len - position < obj_size:
-                raise InvalidBSON("invalid object size")
+                raise InvalidBSON(
+                    f"invalid object size: expected {obj_size}, got {data_len - position}"
+                )
             obj_end = position + obj_size - 1
             if data[obj_end] != 0:
                 raise InvalidBSON("bad eoo")
@@ -1327,7 +1329,7 @@ def decode_iter(
         elements = data[position : position + obj_size]
         position += obj_size
 
-        yield _bson_to_dict(elements, opts)  # type:ignore[misc]
+        yield _bson_to_dict(elements, opts)
 
 
 @overload
@@ -1373,7 +1375,7 @@ def decode_file_iter(
             raise InvalidBSON("cut off in middle of objsize")
         obj_size = _UNPACK_INT_FROM(size_data, 0)[0] - 4
         elements = size_data + file_obj.read(max(0, obj_size))
-        yield _bson_to_dict(elements, opts)  # type:ignore[arg-type, misc]
+        yield _bson_to_dict(elements, opts)  # type:ignore[misc]
 
 
 def is_valid(bson: bytes) -> bool:

bson/_cbsonmodule.c

@@ -109,6 +109,7 @@ struct module_state {
 #define DATETIME_CLAMP 2
 #define DATETIME_MS 3
 #define DATETIME_AUTO 4
+#define PYTHON_3_12 0x030C0000
 
 /* Converts integer to its string representation in decimal notation. */
 extern int cbson_long_long_to_str(long long num, char* str, size_t size) {
@@ -249,6 +250,67 @@ static int _write_element_to_buffer(PyObject* self, buffer_t buffer,
  */
 static int write_raw_doc(buffer_t buffer, PyObject* raw, PyObject* _raw);
 
+#if PY_VERSION_HEX >= PYTHON_3_12
+/* Transfer traceback from old_exc to new_exc.
+ * Steals reference to old_exc. */
+static PyObject* _transfer_traceback(PyObject *old_exc, PyObject *new_exc) {
+    PyObject *tb = PyException_GetTraceback(old_exc);
+    if (tb) {
+        PyException_SetTraceback(new_exc, tb);
+        Py_DECREF(tb);
+    }
+    Py_DECREF(old_exc);
+    return new_exc;
+}
+#endif
+
+/* Rewrap the current exception as InvalidBSON(str(e)) if it is not already an InvalidBSON error. */
+static void _rewrap_as_invalid_bson(void) {
+#if PY_VERSION_HEX >= PYTHON_3_12
+    PyObject *exc = PyErr_GetRaisedException();
+    if (exc && PyErr_GivenExceptionMatches(exc, PyExc_Exception)) {
+        PyObject *InvalidBSON = _error("InvalidBSON");
+        if (InvalidBSON) {
+            if (!PyErr_GivenExceptionMatches(exc, InvalidBSON)) {
+                PyObject *err_msg = PyObject_Str(exc);
+                if (err_msg) {
+                    PyObject *new_exc = PyObject_CallOneArg(InvalidBSON, err_msg);
+                    if (new_exc) {
+                        exc = _transfer_traceback(exc, new_exc);
+                    }
+                }
+                Py_XDECREF(err_msg);
+            }
+            Py_DECREF(InvalidBSON);
+        }
+    }
+    /* Steals reference to exc. */
+    PyErr_SetRaisedException(exc);
+#else
+    PyObject *etype = NULL, *evalue = NULL, *etrace = NULL;
+    PyObject *InvalidBSON = NULL;
+    PyErr_Fetch(&etype, &evalue, &etrace);
+    if (PyErr_GivenExceptionMatches(etype, PyExc_Exception)) {
+        InvalidBSON = _error("InvalidBSON");
+        if (InvalidBSON) {
+            if (!PyErr_GivenExceptionMatches(etype, InvalidBSON)) {
+                Py_DECREF(etype);
+                etype = InvalidBSON;
+                if (evalue) {
+                    PyObject *msg = PyObject_Str(evalue);
+                    Py_DECREF(evalue);
+                    evalue = msg;
+                }
+                PyErr_NormalizeException(&etype, &evalue, &etrace);
+            } else {
+                Py_DECREF(InvalidBSON);
+            }
+        }
+    }
+    PyErr_Restore(etype, evalue, etrace);
+#endif
+}
+
 /* Date stuff */
 static PyObject* datetime_from_millis(long long millis) {
     /* To encode a datetime instance like datetime(9999, 12, 31, 23, 59, 59, 999999)
@@ -294,34 +356,57 @@ static PyObject* datetime_from_millis(long long millis) {
                                           timeinfo.tm_sec,
                                           microseconds);
     if(!datetime) {
-        PyObject *etype = NULL, *evalue = NULL, *etrace = NULL;
+        #if PY_VERSION_HEX >= PYTHON_3_12
+            PyObject *exc = PyErr_GetRaisedException();
 
-        /*
+            /* Only add additional error message on ValueError exceptions. */
-        * Calling _error clears the error state, so fetch it first.
+            if (exc && PyErr_GivenExceptionMatches(exc, PyExc_ValueError)) {
-        */
+                PyObject* err_msg = PyObject_Str(exc);
-        PyErr_Fetch(&etype, &evalue, &etrace);
-
-        /* Only add addition error message on ValueError exceptions. */
-        if (PyErr_GivenExceptionMatches(etype, PyExc_ValueError)) {
-            if (evalue) {
-                PyObject* err_msg = PyObject_Str(evalue);
                 if (err_msg) {
                     PyObject* appendage = PyUnicode_FromString(" (Consider Using CodecOptions(datetime_conversion=DATETIME_AUTO) or MongoClient(datetime_conversion='DATETIME_AUTO')). See: https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/dates-and-times/#handling-out-of-range-datetimes");
                     if (appendage) {
                         PyObject* msg = PyUnicode_Concat(err_msg, appendage);
                         if (msg) {
-                            Py_DECREF(evalue);
+                            PyObject* new_exc = PyObject_CallOneArg(PyExc_ValueError, msg);
-                            evalue = msg;
+                            if (new_exc) {
+                                exc = _transfer_traceback(exc, new_exc);
+                            }
+                            Py_DECREF(msg);
                         }
                     }
                     Py_XDECREF(appendage);
                 }
                 Py_XDECREF(err_msg);
             }
-            PyErr_NormalizeException(&etype, &evalue, &etrace);
+            /* Steals reference to exc. */
-        }
+            PyErr_SetRaisedException(exc);
-        /* Steals references to args. */
+        #else
-        PyErr_Restore(etype, evalue, etrace);
+            /* Calling _error clears the error state, so fetch it first.*/
+            PyObject *etype = NULL, *evalue = NULL, *etrace = NULL;
+            PyErr_Fetch(&etype, &evalue, &etrace);
+
+            /* Only add additional error message on ValueError exceptions. */
+            if (PyErr_GivenExceptionMatches(etype, PyExc_ValueError)) {
+                if (evalue) {
+                    PyObject* err_msg = PyObject_Str(evalue);
+                    if (err_msg) {
+                        PyObject* appendage = PyUnicode_FromString(" (Consider Using CodecOptions(datetime_conversion=DATETIME_AUTO) or MongoClient(datetime_conversion='DATETIME_AUTO')). See: https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/dates-and-times/#handling-out-of-range-datetimes");
+                        if (appendage) {
+                            PyObject* msg = PyUnicode_Concat(err_msg, appendage);
+                            if (msg) {
+                                Py_DECREF(evalue);
+                                evalue = msg;
+                            }
+                        }
+                        Py_XDECREF(appendage);
+                    }
+                    Py_XDECREF(err_msg);
+                }
+                PyErr_NormalizeException(&etype, &evalue, &etrace);
+            }
+            /* Steals references to args. */
+            PyErr_Restore(etype, evalue, etrace);
+        #endif
     }
     return datetime;
 }
@@ -356,7 +441,8 @@ static PyObject* datetime_ms_from_millis(PyObject* self, long long millis){
     if (!(ll_millis = PyLong_FromLongLong(millis))){
         return NULL;
     }
-    dt = PyObject_CallFunctionObjArgs(state->DatetimeMS, ll_millis, NULL);
+    PyObject* args[1] = {ll_millis};
+    dt = PyObject_Vectorcall(state->DatetimeMS, args, 1, NULL);
     Py_DECREF(ll_millis);
     return dt;
 }
@@ -401,7 +487,9 @@ static PyObject* decode_datetime(PyObject* self, long long millis, const codec_o
         int64_t min_millis_offset = 0;
         int64_t max_millis_offset = 0;
         if (options->tz_aware && options->tzinfo && options->tzinfo != Py_None) {
-            PyObject* utcoffset = PyObject_CallMethodObjArgs(options->tzinfo, state->_utcoffset_str, state->min_datetime, NULL);
+            PyObject* utcoffset_args[2] = {options->tzinfo, state->min_datetime};
+            PyObject* utcoffset = PyObject_VectorcallMethod(
+                state->_utcoffset_str, utcoffset_args, 2, NULL);
             if (utcoffset == NULL) {
                 return 0;
             }
@@ -420,7 +508,9 @@ static PyObject* decode_datetime(PyObject* self, long long millis, const codec_o
                                      (PyDateTime_DELTA_GET_MICROSECONDS(utcoffset) / 1000);
             }
             Py_DECREF(utcoffset);
-            utcoffset = PyObject_CallMethodObjArgs(options->tzinfo, state->_utcoffset_str, state->max_datetime, NULL);
+            utcoffset_args[1] = state->max_datetime;
+            utcoffset = PyObject_VectorcallMethod(
+                state->_utcoffset_str, utcoffset_args, 2, NULL);
             if (utcoffset == NULL) {
                 return 0;
             }
@@ -481,7 +571,9 @@ static PyObject* decode_datetime(PyObject* self, long long millis, const codec_o
 
     /* convert to local time */
     if (options->tzinfo != Py_None) {
-        PyObject* temp = PyObject_CallMethodObjArgs(value, state->_astimezone_str, options->tzinfo, NULL);
+        PyObject* astimezone_args[2] = {value, options->tzinfo};
+        PyObject* temp = PyObject_VectorcallMethod(
+            state->_astimezone_str, astimezone_args, 2, NULL);
         Py_DECREF(value);
         value = temp;
     }
@@ -688,7 +780,8 @@ static int _load_python_objects(PyObject* module) {
         return 1;
     }
 
-    compiled = PyObject_CallFunction(re_compile, "O", empty_string);
+    PyObject* compile_args[1] = {empty_string};
+    compiled = PyObject_Vectorcall(re_compile, compile_args, 1, NULL);
     Py_DECREF(re_compile);
     if (compiled == NULL) {
         state->REType = NULL;
@@ -711,13 +804,19 @@ static long _type_marker(PyObject* object, PyObject* _type_marker_str) {
     PyObject* type_marker = NULL;
     long type = 0;
 
-    if (PyObject_HasAttr(object, _type_marker_str)) {
+    #if PY_VERSION_HEX >= 0x030D0000
-        type_marker = PyObject_GetAttr(object, _type_marker_str);
+        // 3.13
-        if (type_marker == NULL) {
+        if (PyObject_GetOptionalAttr(object, _type_marker_str, &type_marker) == -1) {
             return -1;
         }
-    }
+    # else
-
+        if (PyObject_HasAttr(object, _type_marker_str)) {
+            type_marker = PyObject_GetAttr(object, _type_marker_str);
+            if (type_marker == NULL) {
+                return -1;
+            }
+        }
+    #endif
     /*
      * Python objects with broken __getattr__ implementations could return
      * arbitrary types for a call to PyObject_GetAttrString. For example
@@ -814,6 +913,7 @@ int convert_codec_options(PyObject* self, PyObject* options_obj, codec_options_t
     }
 
     options->is_raw_bson = (101 == type_marker);
+    options->is_dict_class = (options->document_class == (PyObject*)&PyDict_Type);
     options->options_obj = options_obj;
 
     Py_INCREF(options->options_obj);
@@ -1013,10 +1113,20 @@ static int _write_element_to_buffer(PyObject* self, buffer_t buffer,
     }
     /*
      * Use _type_marker attribute instead of PyObject_IsInstance for better perf.
+     *
+     * Skip _type_marker lookup for common built-in types
+     * that we know don't have a _type_marker attribute. This avoids the overhead
+     * of PyObject_HasAttr/PyObject_GetAttr calls for the most common cases.
      */
-    type = _type_marker(value, state->_type_marker_str);
+    if (PyUnicode_CheckExact(value) || PyLong_CheckExact(value) || PyFloat_CheckExact(value) ||
-    if (type < 0) {
+        PyBool_Check(value) || PyDict_CheckExact(value) || PyList_CheckExact(value) ||
-        return 0;
+        PyTuple_CheckExact(value) || PyBytes_CheckExact(value) || value == Py_None) {
+        type = 0;
+    } else {
+        type = _type_marker(value, state->_type_marker_str);
+        if (type < 0) {
+            return 0;
+        }
     }
 
     switch (type) {
@@ -1227,7 +1337,9 @@ static int _write_element_to_buffer(PyObject* self, buffer_t buffer,
     case 100:
         {
             /* DBRef */
-            PyObject* as_doc = PyObject_CallMethodObjArgs(value, state->_as_doc_str, NULL);
+            PyObject* as_doc_args[1] = {value};
+            PyObject* as_doc = PyObject_VectorcallMethod(
+                state->_as_doc_str, as_doc_args, 1, NULL);
             if (!as_doc) {
                 return 0;
             }
@@ -1383,7 +1495,9 @@ static int _write_element_to_buffer(PyObject* self, buffer_t buffer,
         return write_unicode(buffer, value);
     } else if (PyDateTime_Check(value)) {
         long long millis;
-        PyObject* utcoffset = PyObject_CallMethodObjArgs(value, state->_utcoffset_str , NULL);
+        PyObject* utcoffset_args[1] = {value};
+        PyObject* utcoffset = PyObject_VectorcallMethod(
+            state->_utcoffset_str, utcoffset_args, 1, NULL);
         if (utcoffset == NULL)
             return 0;
         if (utcoffset != Py_None) {
@@ -1422,7 +1536,9 @@ static int _write_element_to_buffer(PyObject* self, buffer_t buffer,
         if (!(uuid_rep_obj = PyLong_FromLong(options->uuid_rep))) {
             return 0;
         }
-        binary_value = PyObject_CallMethodObjArgs(state->Binary, state->_from_uuid_str, value, uuid_rep_obj, NULL);
+        PyObject* from_uuid_args[3] = {state->Binary, value, uuid_rep_obj};
+        binary_value = PyObject_VectorcallMethod(
+            state->_from_uuid_str, from_uuid_args, 3, NULL);
         Py_DECREF(uuid_rep_obj);
 
         if (binary_value == NULL) {
@@ -1452,7 +1568,8 @@ static int _write_element_to_buffer(PyObject* self, buffer_t buffer,
         if (converter != NULL) {
             /* Transform types that have a registered converter.
              * A new reference is created upon transformation. */
-            new_value = PyObject_CallFunctionObjArgs(converter, value, NULL);
+            PyObject* converter_args[1] = {value};
+            new_value = PyObject_Vectorcall(converter, converter_args, 1, NULL);
             if (new_value == NULL) {
                 return 0;
             }
@@ -1466,8 +1583,9 @@ static int _write_element_to_buffer(PyObject* self, buffer_t buffer,
     /* Try the fallback encoder if one is provided and we have not already
      * attempted to use the fallback encoder. */
     if (!in_fallback_call && options->type_registry.has_fallback_encoder) {
-        new_value = PyObject_CallFunctionObjArgs(
+        PyObject* fallback_args[1] = {value};
-            options->type_registry.fallback_encoder, value, NULL);
+        new_value = PyObject_Vectorcall(
+            options->type_registry.fallback_encoder, fallback_args, 1, NULL);
         if (new_value == NULL) {
             // propagate any exception raised by the callback
             return 0;
@@ -1645,11 +1763,51 @@ fail:
 }
 
 
-/* Update Invalid Document error message to include doc.
+/* Update Invalid Document error to include doc as a property.
  */
 void handle_invalid_doc_error(PyObject* dict) {
+#if PY_VERSION_HEX >= PYTHON_3_12
+    PyObject *exc = PyErr_GetRaisedException();
+    PyObject *msg = NULL, *new_msg = NULL;
+    PyObject *InvalidDocument = NULL;
+
+    if (exc == NULL) {
+        return;
+    }
+
+    InvalidDocument = _error("InvalidDocument");
+    if (InvalidDocument == NULL) {
+        goto cleanup;
+    }
+
+    if (PyErr_GivenExceptionMatches(exc, InvalidDocument)) {
+        msg = PyObject_Str(exc);
+        if (msg) {
+            const char *msg_utf8 = PyUnicode_AsUTF8(msg);
+            if (msg_utf8 == NULL) {
+                goto cleanup;
+            }
+            new_msg = PyUnicode_FromFormat("Invalid document: %s", msg_utf8);
+            if (new_msg == NULL) {
+                goto cleanup;
+            }
+            /* Add doc to the error instance as a property. */
+            PyObject* exc_args[2] = {new_msg, dict};
+            PyObject* new_exc = PyObject_Vectorcall(InvalidDocument, exc_args, 2, NULL);
+            if (new_exc) {
+                exc = _transfer_traceback(exc, new_exc);
+            }
+        }
+    }
+cleanup:
+    /* Steals reference to exc. */
+    PyErr_SetRaisedException(exc);
+    Py_XDECREF(msg);
+    Py_XDECREF(InvalidDocument);
+    Py_XDECREF(new_msg);
+#else
     PyObject *etype = NULL, *evalue = NULL, *etrace = NULL;
-    PyObject *msg = NULL, *dict_str = NULL, *new_msg = NULL;
+    PyObject *msg = NULL, *new_msg = NULL, *new_evalue = NULL;
     PyErr_Fetch(&etype, &evalue, &etrace);
     PyObject *InvalidDocument = _error("InvalidDocument");
     if (InvalidDocument == NULL) {
@@ -1657,30 +1815,29 @@ void handle_invalid_doc_error(PyObject* dict) {
     }
 
     if (evalue && PyErr_GivenExceptionMatches(etype, InvalidDocument)) {
-        PyObject *msg = PyObject_Str(evalue);
+        msg = PyObject_Str(evalue);
         if (msg) {
-            // Prepend doc to the existing message
-            PyObject *dict_str = PyObject_Str(dict);
-            if (dict_str == NULL) {
-                goto cleanup;
-            }
-            const char * dict_str_utf8 = PyUnicode_AsUTF8(dict_str);
-            if (dict_str_utf8 == NULL) {
-                goto cleanup;
-            }
             const char * msg_utf8 = PyUnicode_AsUTF8(msg);
             if (msg_utf8 == NULL) {
                 goto cleanup;
             }
-            PyObject *new_msg = PyUnicode_FromFormat("Invalid document %s | %s", dict_str_utf8, msg_utf8);
+            new_msg = PyUnicode_FromFormat("Invalid document: %s", msg_utf8);
+            if (new_msg == NULL) {
+                goto cleanup;
+            }
+            // Add doc to the error instance as a property.
+            PyObject* exc_args[2] = {new_msg, dict};
+            new_evalue = PyObject_Vectorcall(InvalidDocument, exc_args, 2, NULL);
             Py_DECREF(evalue);
             Py_DECREF(etype);
             etype = InvalidDocument;
             InvalidDocument = NULL;
-            if (new_msg) {
+            if (new_evalue) {
-                evalue = new_msg;
+                evalue = new_evalue;
+                new_evalue = NULL;
             } else {
                 evalue = msg;
+                msg = NULL;
             }
         }
         PyErr_NormalizeException(&etype, &evalue, &etrace);
@@ -1689,8 +1846,9 @@ cleanup:
     PyErr_Restore(etype, evalue, etrace);
     Py_XDECREF(msg);
     Py_XDECREF(InvalidDocument);
-    Py_XDECREF(dict_str);
+    Py_XDECREF(new_evalue);
     Py_XDECREF(new_msg);
+#endif
 }
 
 
@@ -1946,7 +2104,8 @@ static PyObject *_dbref_hook(PyObject* self, PyObject* value) {
             PyMapping_DelItem(value, state->_dollar_db_str);
         }
 
-        ret = PyObject_CallFunctionObjArgs(state->DBRef, ref, id, database, value, NULL);
+        PyObject* dbref_args[4] = {ref, id, database, value};
+        ret = PyObject_Vectorcall(state->DBRef, dbref_args, 4, NULL);
         Py_DECREF(value);
     } else {
         ret = value;
@@ -2122,7 +2281,7 @@ static PyObject* get_value(PyObject* self, PyObject* name, const char* buffer,
             }
             memcpy(&length, buffer + *position, 4);
             length = BSON_UINT32_FROM_LE(length);
-            if (max < length) {
+            if (max - 5 < length) { // Account for 5-byte header. max >= 5 guaranteed above
                 goto invalid;
             }
 
@@ -2162,7 +2321,13 @@ static PyObject* get_value(PyObject* self, PyObject* name, const char* buffer,
                     goto uuiderror;
                 }
 
-                binary_value = PyObject_CallFunction(state->Binary, "(Oi)", data, subtype);
+                PyObject* subtype_obj = PyLong_FromLong(subtype);
+                if (!subtype_obj) {
+                    goto uuiderror;
+                }
+                PyObject* binary_args[2] = {data, subtype_obj};
+                binary_value = PyObject_Vectorcall(state->Binary, binary_args, 2, NULL);
+                Py_DECREF(subtype_obj);
                 if (binary_value == NULL) {
                     goto uuiderror;
                 }
@@ -2177,7 +2342,9 @@ static PyObject* get_value(PyObject* self, PyObject* name, const char* buffer,
                     if (!uuid_rep_obj) {
                         goto uuiderror;
                     }
-                    value = PyObject_CallMethodObjArgs(binary_value, state->_as_uuid_str, uuid_rep_obj, NULL);
+                    PyObject* as_uuid_args[2] = {binary_value, uuid_rep_obj};
+                    value = PyObject_VectorcallMethod(
+                        state->_as_uuid_str, as_uuid_args, 2, NULL);
                     Py_DECREF(uuid_rep_obj);
                 }
 
@@ -2196,7 +2363,8 @@ static PyObject* get_value(PyObject* self, PyObject* name, const char* buffer,
                 Py_DECREF(data);
                 goto invalid;
             }
-            value = PyObject_CallFunctionObjArgs(state->Binary, data, st, NULL);
+            PyObject* binary_args[2] = {data, st};
+            value = PyObject_Vectorcall(state->Binary, binary_args, 2, NULL);
             Py_DECREF(st);
             Py_DECREF(data);
             if (!value) {
@@ -2217,7 +2385,13 @@ static PyObject* get_value(PyObject* self, PyObject* name, const char* buffer,
             if (max < 12) {
                 goto invalid;
             }
-            value = PyObject_CallFunction(state->ObjectId, "y#", buffer + *position, (Py_ssize_t)12);
+            PyObject* oid_bytes = PyBytes_FromStringAndSize(buffer + *position, 12);
+            if (!oid_bytes) {
+                goto invalid;
+            }
+            PyObject* oid_args[1] = {oid_bytes};
+            value = PyObject_Vectorcall(state->ObjectId, oid_args, 1, NULL);
+            Py_DECREF(oid_bytes);
             *position += 12;
             break;
         }
@@ -2296,7 +2470,14 @@ static PyObject* get_value(PyObject* self, PyObject* name, const char* buffer,
             }
             *position += (unsigned)flags_length + 1;
 
-            value = PyObject_CallFunction(state->Regex, "Oi", pattern, flags);
+            PyObject* flags_obj = PyLong_FromLong(flags);
+            if (!flags_obj) {
+                Py_DECREF(pattern);
+                goto invalid;
+            }
+            PyObject* regex_args[2] = {pattern, flags_obj};
+            value = PyObject_Vectorcall(state->Regex, regex_args, 2, NULL);
+            Py_DECREF(flags_obj);
             Py_DECREF(pattern);
             break;
         }
@@ -2329,13 +2510,21 @@ static PyObject* get_value(PyObject* self, PyObject* name, const char* buffer,
             }
             *position += coll_length;
 
-            id = PyObject_CallFunction(state->ObjectId, "y#", buffer + *position, (Py_ssize_t)12);
+            PyObject* oid_bytes = PyBytes_FromStringAndSize(buffer + *position, 12);
+            if (!oid_bytes) {
+                Py_DECREF(collection);
+                goto invalid;
+            }
+            PyObject* oid_args[1] = {oid_bytes};
+            id = PyObject_Vectorcall(state->ObjectId, oid_args, 1, NULL);
+            Py_DECREF(oid_bytes);
             if (!id) {
                 Py_DECREF(collection);
                 goto invalid;
             }
             *position += 12;
-            value = PyObject_CallFunctionObjArgs(state->DBRef, collection, id, NULL);
+            PyObject* dbref_args[2] = {collection, id};
+            value = PyObject_Vectorcall(state->DBRef, dbref_args, 2, NULL);
             Py_DECREF(collection);
             Py_DECREF(id);
             break;
@@ -2365,7 +2554,8 @@ static PyObject* get_value(PyObject* self, PyObject* name, const char* buffer,
                 goto invalid;
             }
             *position += value_length;
-            value = PyObject_CallFunctionObjArgs(state->Code, code, NULL, NULL);
+            PyObject* code_args[1] = {code};
+            value = PyObject_Vectorcall(state->Code, code_args, 1, NULL);
             Py_DECREF(code);
             break;
         }
@@ -2431,7 +2621,8 @@ static PyObject* get_value(PyObject* self, PyObject* name, const char* buffer,
             }
             *position += scope_size;
 
-            value = PyObject_CallFunctionObjArgs(state->Code, code, scope, NULL);
+            PyObject* code_scope_args[2] = {code, scope};
+            value = PyObject_Vectorcall(state->Code, code_scope_args, 2, NULL);
             Py_DECREF(code);
             Py_DECREF(scope);
             break;
@@ -2461,7 +2652,19 @@ static PyObject* get_value(PyObject* self, PyObject* name, const char* buffer,
             memcpy(&time, buffer + *position + 4, 4);
             inc = BSON_UINT32_FROM_LE(inc);
             time = BSON_UINT32_FROM_LE(time);
-            value = PyObject_CallFunction(state->Timestamp, "II", time, inc);
+            PyObject* time_obj = PyLong_FromUnsignedLong(time);
+            if (!time_obj) {
+                goto invalid;
+            }
+            PyObject* inc_obj = PyLong_FromUnsignedLong(inc);
+            if (!inc_obj) {
+                Py_DECREF(time_obj);
+                goto invalid;
+            }
+            PyObject* ts_args[2] = {time_obj, inc_obj};
+            value = PyObject_Vectorcall(state->Timestamp, ts_args, 2, NULL);
+            Py_DECREF(time_obj);
+            Py_DECREF(inc_obj);
             *position += 8;
             break;
         }
@@ -2473,7 +2676,13 @@ static PyObject* get_value(PyObject* self, PyObject* name, const char* buffer,
             }
             memcpy(&ll, buffer + *position, 8);
             ll = (int64_t)BSON_UINT64_FROM_LE(ll);
-            value = PyObject_CallFunction(state->BSONInt64, "L", ll);
+            PyObject* ll_obj = PyLong_FromLongLong(ll);
+            if (!ll_obj) {
+                goto invalid;
+            }
+            PyObject* int64_args[1] = {ll_obj};
+            value = PyObject_Vectorcall(state->BSONInt64, int64_args, 1, NULL);
+            Py_DECREF(ll_obj);
             *position += 8;
             break;
         }
@@ -2486,19 +2695,21 @@ static PyObject* get_value(PyObject* self, PyObject* name, const char* buffer,
             if (!_bytes_obj) {
                 goto invalid;
             }
-            value = PyObject_CallMethodObjArgs(state->Decimal128, state->_from_bid_str, _bytes_obj, NULL);
+            PyObject* dec128_args[2] = {state->Decimal128, _bytes_obj};
+            value = PyObject_VectorcallMethod(
+                state->_from_bid_str, dec128_args, 2, NULL);
             Py_DECREF(_bytes_obj);
             *position += 16;
             break;
         }
     case 255:
         {
-            value = PyObject_CallFunctionObjArgs(state->MinKey, NULL);
+            value = PyObject_Vectorcall(state->MinKey, NULL, 0, NULL);
             break;
         }
     case 127:
         {
-            value = PyObject_CallFunctionObjArgs(state->MaxKey, NULL);
+            value = PyObject_Vectorcall(state->MaxKey, NULL, 0, NULL);
             break;
         }
     default:
@@ -2550,7 +2761,8 @@ static PyObject* get_value(PyObject* self, PyObject* name, const char* buffer,
             }
             converter = PyDict_GetItem(options->type_registry.decoder_map, value_type);
             if (converter != NULL) {
-                PyObject* new_value = PyObject_CallFunctionObjArgs(converter, value, NULL);
+                PyObject* converter_args[1] = {value};
+                PyObject* new_value = PyObject_Vectorcall(converter, converter_args, 1, NULL);
                 Py_DECREF(value_type);
                 Py_DECREF(value);
                 return new_value;
@@ -2568,42 +2780,7 @@ static PyObject* get_value(PyObject* self, PyObject* name, const char* buffer,
      * Wrap any non-InvalidBSON errors in InvalidBSON.
      */
     if (PyErr_Occurred()) {
-        PyObject *etype = NULL, *evalue = NULL, *etrace = NULL;
+        _rewrap_as_invalid_bson();
-        PyObject *InvalidBSON = NULL;
-
-        /*
-         * Calling _error clears the error state, so fetch it first.
-         */
-        PyErr_Fetch(&etype, &evalue, &etrace);
-
-        /* Dont reraise anything but PyExc_Exceptions as InvalidBSON. */
-        if (PyErr_GivenExceptionMatches(etype, PyExc_Exception)) {
-            InvalidBSON = _error("InvalidBSON");
-            if (InvalidBSON) {
-                if (!PyErr_GivenExceptionMatches(etype, InvalidBSON)) {
-                    /*
-                     * Raise InvalidBSON(str(e)).
-                     */
-                    Py_DECREF(etype);
-                    etype = InvalidBSON;
-
-                    if (evalue) {
-                        PyObject *msg = PyObject_Str(evalue);
-                        Py_DECREF(evalue);
-                        evalue = msg;
-                    }
-                    PyErr_NormalizeException(&etype, &evalue, &etrace);
-                } else {
-                    /*
-                     * The current exception matches InvalidBSON, so we don't
-                     * need this reference after all.
-                     */
-                    Py_DECREF(InvalidBSON);
-                }
-            }
-        }
-        /* Steals references to args. */
-        PyErr_Restore(etype, evalue, etrace);
     } else {
         PyObject *InvalidBSON = _error("InvalidBSON");
         if (InvalidBSON) {
@@ -2641,25 +2818,7 @@ static int _element_to_dict(PyObject* self, const char* string,
     if (!*name) {
         /* If NULL is returned then wrap the UnicodeDecodeError
            in an InvalidBSON error */
-        PyObject *etype = NULL, *evalue = NULL, *etrace = NULL;
+        _rewrap_as_invalid_bson();
-        PyObject *InvalidBSON = NULL;
-
-        PyErr_Fetch(&etype, &evalue, &etrace);
-        if (PyErr_GivenExceptionMatches(etype, PyExc_Exception)) {
-            InvalidBSON = _error("InvalidBSON");
-            if (InvalidBSON) {
-                Py_DECREF(etype);
-                etype = InvalidBSON;
-
-                if (evalue) {
-                    PyObject *msg = PyObject_Str(evalue);
-                    Py_DECREF(evalue);
-                    evalue = msg;
-                }
-                PyErr_NormalizeException(&etype, &evalue, &etrace);
-            }
-        }
-        PyErr_Restore(etype, evalue, etrace);
         return -1;
     }
     position += (unsigned)name_length + 1;
@@ -2718,11 +2877,20 @@ static PyObject* _elements_to_dict(PyObject* self, const char* string,
                                    unsigned max,
                                    const codec_options_t* options) {
     unsigned position = 0;
-    PyObject* dict = PyObject_CallObject(options->document_class, NULL);
+    PyObject* dict;
+    int raw_array = 0;
+
+    /* Use PyDict_New() directly when document_class is dict.
+     * This avoids the overhead of PyObject_CallObject() for the common case. */
+    if (options->is_dict_class) {
+        dict = PyDict_New();
+    } else {
+        dict = PyObject_CallObject(options->document_class, NULL);
+    }
     if (!dict) {
         return NULL;
     }
-    int raw_array = 0;
+
     while (position < max) {
         PyObject* name = NULL;
         PyObject* value = NULL;
@@ -2737,7 +2905,24 @@ static PyObject* _elements_to_dict(PyObject* self, const char* string,
             position = (unsigned)new_position;
         }
 
-        PyObject_SetItem(dict, name, value);
+        /* Use PyDict_SetItem() when document_class is dict.
+         * PyDict_SetItem() is faster than PyObject_SetItem() because it
+         * avoids method lookup overhead. */
+        if (options->is_dict_class) {
+            if (PyDict_SetItem(dict, name, value) < 0) {
+                Py_DECREF(name);
+                Py_DECREF(value);
+                Py_DECREF(dict);
+                return NULL;
+            }
+        } else {
+            if (PyObject_SetItem(dict, name, value) < 0) {
+                Py_DECREF(name);
+                Py_DECREF(value);
+                Py_DECREF(dict);
+                return NULL;
+            }
+        }
         Py_DECREF(name);
         Py_DECREF(value);
     }
@@ -2749,9 +2934,14 @@ static PyObject* elements_to_dict(PyObject* self, const char* string,
                                   const codec_options_t* options) {
     PyObject* result;
     if (options->is_raw_bson) {
-        return PyObject_CallFunction(
+        PyObject* bson_bytes = PyBytes_FromStringAndSize(string, max);
-            options->document_class, "y#O",
+        if (!bson_bytes) {
-            string, max, options->options_obj);
+            return NULL;
+        }
+        PyObject* raw_args[2] = {bson_bytes, options->options_obj};
+        result = PyObject_Vectorcall(options->document_class, raw_args, 2, NULL);
+        Py_DECREF(bson_bytes);
+        return result;
     }
     if (Py_EnterRecursiveCall(" while decoding a BSON document"))
         return NULL;
@@ -3227,11 +3417,18 @@ _cbson_exec(PyObject *m)
         INITERROR;
     }
 
+#if PY_VERSION_HEX >= 0x030D0000
+    if (PyModule_Add(m, "_C_API", c_api_object) < 0) {
+        Py_DECREF(m);
+        INITERROR;
+    }
+# else
     if (PyModule_AddObject(m, "_C_API", c_api_object) < 0) {
         Py_DECREF(c_api_object);
         Py_DECREF(m);
         INITERROR;
     }
+#endif
 
     return 0;
 }

bson/_cbsonmodule.h

@@ -72,6 +72,7 @@ typedef struct codec_options_t {
     unsigned char datetime_conversion;
     PyObject* options_obj;
     unsigned char is_raw_bson;
+    unsigned char is_dict_class;
 } codec_options_t;
 
 /* C API functions */

bson/binary.py

@@ -14,6 +14,7 @@
 from __future__ import annotations
 
 import struct
+import warnings
 from enum import Enum
 from typing import TYPE_CHECKING, Any, Optional, Sequence, Tuple, Type, Union, overload
 from uuid import UUID
@@ -64,6 +65,9 @@ if TYPE_CHECKING:
     from array import array as _array
     from mmap import mmap as _mmap
 
+    import numpy as np
+    import numpy.typing as npt
+
 
 class UuidRepresentation:
     UNSPECIFIED = 0
@@ -78,7 +82,7 @@ class UuidRepresentation:
     :class:`~bson.binary.Binary` instance will be returned instead of a
     :class:`uuid.UUID` instance.
 
-    See :ref:`unspecified-representation-details` for details.
+    See `unspecified representation details <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/uuid/#unspecified>`_ for details.
 
     .. versionadded:: 3.11
     """
@@ -90,7 +94,7 @@ class UuidRepresentation:
     and decoded from BSON binary, using RFC-4122 byte order with
     binary subtype :data:`UUID_SUBTYPE`.
 
-    See :ref:`standard-representation-details` for details.
+    See `standard representation details <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/uuid/#standard>`_ for details.
 
     .. versionadded:: 3.11
     """
@@ -102,7 +106,7 @@ class UuidRepresentation:
     and decoded from BSON binary, using RFC-4122 byte order with
     binary subtype :data:`OLD_UUID_SUBTYPE`.
 
-    See :ref:`python-legacy-representation-details` for details.
+    See `python legacy representation details <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/uuid/#python_legacy>`_ for details.
 
     .. versionadded:: 3.11
     """
@@ -114,7 +118,7 @@ class UuidRepresentation:
     and decoded from BSON binary subtype :data:`OLD_UUID_SUBTYPE`,
     using the Java driver's legacy byte order.
 
-    See :ref:`java-legacy-representation-details` for details.
+    See `Java Legacy UUID <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/uuid/#java_legacy>`_ for details.
 
     .. versionadded:: 3.11
     """
@@ -126,7 +130,7 @@ class UuidRepresentation:
     and decoded from BSON binary subtype :data:`OLD_UUID_SUBTYPE`,
     using the C# driver's legacy byte order.
 
-    See :ref:`csharp-legacy-representation-details` for details.
+    See `C# Legacy UUID <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/uuid/#csharp_legacy>`_ for details.
 
     .. versionadded:: 3.11
     """
@@ -233,13 +237,20 @@ class BinaryVector:
 
     __slots__ = ("data", "dtype", "padding")
 
-    def __init__(self, data: Sequence[float | int], dtype: BinaryVectorDtype, padding: int = 0):
+    def __init__(
+        self,
+        data: Union[Sequence[float | int], npt.NDArray[np.number]],
+        dtype: BinaryVectorDtype,
+        padding: int = 0,
+    ):
         """
         :param data: Sequence of numbers representing the mathematical vector.
         :param dtype:  The data type stored in binary
         :param padding: The number of bits in the final byte that are to be ignored
           when a vector element's size is less than a byte
           and the length of the vector is not a multiple of 8.
+          (Padding is equivalent to a negative value of `count` in
+          `numpy.unpackbits <https://numpy.org/doc/stable/reference/generated/numpy.unpackbits.html>`_)
         """
         self.data = data
         self.dtype = dtype
@@ -255,6 +266,9 @@ class BinaryVector:
             self.dtype == other.dtype and self.padding == other.padding and self.data == other.data
         )
 
+    def __len__(self) -> int:
+        return len(self.data)
+
 
 class Binary(bytes):
     """Representation of BSON binary data.
@@ -294,7 +308,7 @@ class Binary(bytes):
 
     def __new__(
         cls: Type[Binary],
-        data: Union[memoryview, bytes, _mmap, _array[Any]],
+        data: Union[memoryview, bytes, bytearray, _mmap, _array[Any]],
         subtype: int = BINARY_SUBTYPE,
     ) -> Binary:
         if not isinstance(subtype, int):
@@ -324,7 +338,7 @@ class Binary(bytes):
         :param uuid_representation: A member of
             :class:`~bson.binary.UuidRepresentation`. Default:
             :const:`~bson.binary.UuidRepresentation.STANDARD`.
-            See :ref:`handling-uuid-data-example` for details.
+            See `UUID representations <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/uuid/#universally-unique-ids--uuids->`_ for details.
 
         .. versionadded:: 3.11
         """
@@ -373,7 +387,7 @@ class Binary(bytes):
         :param uuid_representation: A member of
             :class:`~bson.binary.UuidRepresentation`. Default:
             :const:`~bson.binary.UuidRepresentation.STANDARD`.
-            See :ref:`handling-uuid-data-example` for details.
+            See `UUID representations <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/uuid/#universally-unique-ids--uuids->`_ for details.
 
         .. versionadded:: 3.11
         """
@@ -421,9 +435,19 @@ class Binary(bytes):
         ...
 
     @classmethod
+    @overload
     def from_vector(
         cls: Type[Binary],
-        vector: Union[BinaryVector, list[int], list[float]],
+        vector: npt.NDArray[np.number],
+        dtype: BinaryVectorDtype,
+        padding: int = 0,
+    ) -> Binary:
+        ...
+
+    @classmethod
+    def from_vector(
+        cls: Type[Binary],
+        vector: Union[BinaryVector, list[int], list[float], npt.NDArray[np.number]],
         dtype: Optional[BinaryVectorDtype] = None,
         padding: Optional[int] = None,
     ) -> Binary:
@@ -439,6 +463,9 @@ class Binary(bytes):
         :param padding: For fractional bytes, number of bits to ignore at end of vector.
         :return: Binary packed data identified by dtype and padding.
 
+        .. versionchanged:: 4.14
+           When padding is non-zero, ignored bits should be zero. Raise exception on encoding, warn on decoding.
+
         .. versionadded:: 4.10
         """
         if isinstance(vector, BinaryVector):
@@ -452,30 +479,72 @@ class Binary(bytes):
             vector = vector.data  # type: ignore
 
         padding = 0 if padding is None else padding
-        if dtype == BinaryVectorDtype.INT8:  # pack ints in [-128, 127] as signed int8
+        if not isinstance(dtype, BinaryVectorDtype):
-            format_str = "b"
+            raise TypeError(
-            if padding:
+                "dtype must be a bson.BinaryVectorDtype of BinaryVectorDType.INT8, PACKED_BIT, FLOAT32"
-                raise ValueError(f"padding does not apply to {dtype=}")
+            )
-        elif dtype == BinaryVectorDtype.PACKED_BIT:  # pack ints in [0, 255] as unsigned uint8
-            format_str = "B"
-            if 0 <= padding > 7:
-                raise ValueError(f"{padding=}. It must be in [0,1, ..7].")
-            if padding and not vector:
-                raise ValueError("Empty vector with non-zero padding.")
-        elif dtype == BinaryVectorDtype.FLOAT32:  # pack floats as float32
-            format_str = "f"
-            if padding:
-                raise ValueError(f"padding does not apply to {dtype=}")
-        else:
-            raise NotImplementedError("%s not yet supported" % dtype)
-
         metadata = struct.pack("<sB", dtype.value, padding)
-        data = struct.pack(f"<{len(vector)}{format_str}", *vector)  # type: ignore
+
+        if isinstance(vector, list):
+            if dtype == BinaryVectorDtype.INT8:  # pack ints in [-128, 127] as signed int8
+                format_str = "b"
+                if padding:
+                    raise ValueError(f"padding does not apply to {dtype=}")
+            elif dtype == BinaryVectorDtype.PACKED_BIT:  # pack ints in [0, 255] as unsigned uint8
+                format_str = "B"
+                if 0 <= padding > 7:
+                    raise ValueError(f"{padding=}. It must be in [0,1, ..7].")
+                if padding and not vector:
+                    raise ValueError("Empty vector with non-zero padding.")
+            elif dtype == BinaryVectorDtype.FLOAT32:  # pack floats as float32
+                format_str = "f"
+                if padding:
+                    raise ValueError(f"padding does not apply to {dtype=}")
+            else:
+                raise NotImplementedError("%s not yet supported" % dtype)
+            data = struct.pack(f"<{len(vector)}{format_str}", *vector)
+        else:  # vector is numpy array or incorrect type.
+            try:
+                import numpy as np
+            except ImportError as exc:
+                raise ImportError(
+                    "Failed to create binary from vector. Check type. If numpy array, numpy must be installed."
+                ) from exc
+            if not isinstance(vector, np.ndarray):
+                raise TypeError(
+                    "Could not create Binary. Vector must be a BinaryVector, list[int], list[float] or numpy ndarray."
+                )
+            if vector.ndim != 1:
+                raise ValueError(
+                    "from_numpy_vector only supports 1D arrays as it creates a single vector."
+                )
+
+            if dtype == BinaryVectorDtype.FLOAT32:
+                vector = vector.astype(np.dtype("float32"), copy=False)
+            elif dtype == BinaryVectorDtype.INT8:
+                if vector.min() >= -128 and vector.max() <= 127:
+                    vector = vector.astype(np.dtype("int8"), copy=False)
+                else:
+                    raise ValueError("Values found outside INT8 range.")
+            elif dtype == BinaryVectorDtype.PACKED_BIT:
+                if vector.min() >= 0 and vector.max() <= 127:
+                    vector = vector.astype(np.dtype("uint8"), copy=False)
+                else:
+                    raise ValueError("Values found outside UINT8 range.")
+            else:
+                raise NotImplementedError("%s not yet supported" % dtype)
+            data = vector.tobytes()
+
+        if padding and len(vector) and not (data[-1] & ((1 << padding) - 1)) == 0:
+            raise ValueError(
+                "Vector has a padding P, but bits in the final byte lower than P are non-zero. They must be zero."
+            )
         return cls(metadata + data, subtype=VECTOR_SUBTYPE)
 
-    def as_vector(self) -> BinaryVector:
+    def as_vector(self, return_numpy: bool = False) -> BinaryVector:
-        """From the Binary, create a list of numbers, along with dtype and padding.
+        """From the Binary, create a list or 1-d numpy array of numbers, along with dtype and padding.
 
+        :param return_numpy: If True, BinaryVector.data will be a one-dimensional numpy array. By default, it is a list.
         :return: BinaryVector
 
         .. versionadded:: 4.10
@@ -484,39 +553,84 @@ class Binary(bytes):
         if self.subtype != VECTOR_SUBTYPE:
             raise ValueError(f"Cannot decode subtype {self.subtype} as a vector")
 
-        position = 0
+        dtype, padding = struct.unpack_from("<sB", self)
-        dtype, padding = struct.unpack_from("<sB", self, position)
-        position += 2
         dtype = BinaryVectorDtype(dtype)
-        n_values = len(self) - position
+        offset = 2
+        n_bytes = len(self) - offset
 
-        if dtype == BinaryVectorDtype.INT8:
+        if padding and dtype != BinaryVectorDtype.PACKED_BIT:
-            dtype_format = "b"
+            raise ValueError(
-            format_string = f"<{n_values}{dtype_format}"
+                f"Corrupt data. Padding ({padding}) must be 0 for all but PACKED_BIT dtypes. ({dtype=})"
-            vector = list(struct.unpack_from(format_string, self, position))
+            )
-            return BinaryVector(vector, dtype, padding)
 
-        elif dtype == BinaryVectorDtype.FLOAT32:
+        if not return_numpy:
-            n_bytes = len(self) - position
+            if dtype == BinaryVectorDtype.INT8:
-            n_values = n_bytes // 4
+                dtype_format = "b"
-            if n_bytes % 4:
+                format_string = f"<{n_bytes}{dtype_format}"
-                raise ValueError(
+                vector = list(struct.unpack_from(format_string, self, offset))
-                    "Corrupt data. N bytes for a float32 vector must be a multiple of 4."
+                return BinaryVector(vector, dtype, padding)
-                )
-            dtype_format = "f"
-            format_string = f"<{n_values}{dtype_format}"
-            vector = list(struct.unpack_from(format_string, self, position))
-            return BinaryVector(vector, dtype, padding)
 
-        elif dtype == BinaryVectorDtype.PACKED_BIT:
+            elif dtype == BinaryVectorDtype.FLOAT32:
-            # data packed as uint8
+                n_values = n_bytes // 4
-            dtype_format = "B"
+                if n_bytes % 4:
-            format_string = f"<{n_values}{dtype_format}"
+                    raise ValueError(
-            unpacked_uint8s = list(struct.unpack_from(format_string, self, position))
+                        "Corrupt data. N bytes for a float32 vector must be a multiple of 4."
-            return BinaryVector(unpacked_uint8s, dtype, padding)
+                    )
+                dtype_format = "f"
+                format_string = f"<{n_values}{dtype_format}"
+                vector = list(struct.unpack_from(format_string, self, offset))
+                return BinaryVector(vector, dtype, padding)
 
-        else:
+            elif dtype == BinaryVectorDtype.PACKED_BIT:
-            raise NotImplementedError("Binary Vector dtype %s not yet supported" % dtype.name)
+                # data packed as uint8
+                if padding and not n_bytes:
+                    raise ValueError("Corrupt data. Vector has a padding P, but no data.")
+                if padding > 7 or padding < 0:
+                    raise ValueError(f"Corrupt data. Padding ({padding}) must be between 0 and 7.")
+                dtype_format = "B"
+                format_string = f"<{n_bytes}{dtype_format}"
+                unpacked_uint8s = list(struct.unpack_from(format_string, self, offset))
+                if padding and n_bytes and unpacked_uint8s[-1] & (1 << padding) - 1 != 0:
+                    warnings.warn(
+                        "Vector has a padding P, but bits in the final byte lower than P are non-zero. For pymongo>=5.0, they must be zero.",
+                        DeprecationWarning,
+                        stacklevel=2,
+                    )
+                return BinaryVector(unpacked_uint8s, dtype, padding)
+
+            else:
+                raise NotImplementedError("Binary Vector dtype %s not yet supported" % dtype.name)
+        else:  # create a numpy array
+            try:
+                import numpy as np
+            except ImportError as exc:
+                raise ImportError(
+                    "Converting binary to numpy.ndarray requires numpy to be installed."
+                ) from exc
+            if dtype == BinaryVectorDtype.INT8:
+                data = np.frombuffer(self[offset:], dtype="int8")
+            elif dtype == BinaryVectorDtype.FLOAT32:
+                if n_bytes % 4:
+                    raise ValueError(
+                        "Corrupt data. N bytes for a float32 vector must be a multiple of 4."
+                    )
+                data = np.frombuffer(self[offset:], dtype="float32")
+            elif dtype == BinaryVectorDtype.PACKED_BIT:
+                # data packed as uint8
+                if padding and not n_bytes:
+                    raise ValueError("Corrupt data. Vector has a padding P, but no data.")
+                if padding > 7 or padding < 0:
+                    raise ValueError(f"Corrupt data. Padding ({padding}) must be between 0 and 7.")
+                data = np.frombuffer(self[offset:], dtype="uint8")
+                if padding and np.unpackbits(data[-1])[-padding:].sum() > 0:
+                    warnings.warn(
+                        "Vector has a padding P, but bits in the final byte lower than P are non-zero. For pymongo>=5.0, they must be zero.",
+                        DeprecationWarning,
+                        stacklevel=2,
+                    )
+            else:
+                raise NotImplementedError("Binary Vector dtype %s not yet supported" % dtype.name)
+            return BinaryVector(data, dtype, padding)
 
     @property
     def subtype(self) -> int:

bson/codec_options.py

@@ -57,7 +57,7 @@ class TypeEncoder(abc.ABC):
     Codec classes must implement the ``python_type`` attribute, and the
     ``transform_python`` method to support encoding.
 
-    See :ref:`custom-type-type-codec` documentation for an example.
+    See `encode data with type codecs <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/custom-types/type-codecs/#encode-data-with-type-codecs>`_ documentation for an example.
     """
 
     @abc.abstractproperty
@@ -76,7 +76,7 @@ class TypeDecoder(abc.ABC):
     Codec classes must implement the ``bson_type`` attribute, and the
     ``transform_bson`` method to support decoding.
 
-    See :ref:`custom-type-type-codec` documentation for an example.
+    See `encode data with type codecs <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/custom-types/type-codecs/#encode-data-with-type-codecs>`_ documentation for an example.
     """
 
     @abc.abstractproperty
@@ -98,7 +98,7 @@ class TypeCodec(TypeEncoder, TypeDecoder):
     ``bson_type`` attribute, and the ``transform_bson`` method to support
     decoding.
 
-    See :ref:`custom-type-type-codec` documentation for an example.
+    See `encode data with type codecs <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/custom-types/type-codecs/#encode-data-with-type-codecs>`_ documentation for an example.
     """
 
 
@@ -118,7 +118,7 @@ class TypeRegistry:
       >>> type_registry = TypeRegistry([Codec1, Codec2, Codec3, ...],
       ...                              fallback_encoder)
 
-    See :ref:`custom-type-type-registry` documentation for an example.
+    See `add codec to the type registry <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/custom-types/type-codecs/#add-codec-to-the-type-registry>`_ documentation for an example.
 
     :param type_codecs: iterable of type codec instances. If
         ``type_codecs`` contains multiple codecs that transform a single
@@ -128,7 +128,7 @@ class TypeRegistry:
         type.
     :param fallback_encoder: callable that accepts a single,
         unencodable python value and transforms it into a type that
-        :mod:`bson` can encode. See :ref:`fallback-encoder-callable`
+        :mod:`bson` can encode. See `define a fallback encoder <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/custom-types/type-codecs/#define-a-fallback-encoder>`_
         documentation for an example.
     """
 
@@ -160,6 +160,16 @@ class TypeRegistry:
                     f"Expected an instance of {TypeEncoder.__name__}, {TypeDecoder.__name__}, or {TypeCodec.__name__}, got {codec!r} instead"
                 )
 
+    @property
+    def codecs(self) -> list[TypeEncoder | TypeDecoder | TypeCodec]:
+        """The list of type codecs in this registry."""
+        return self.__type_codecs
+
+    @property
+    def fallback_encoder(self) -> Optional[_Fallback]:
+        """The fallback encoder in this registry."""
+        return self._fallback_encoder
+
     def _validate_type_encoder(self, codec: _Codec) -> None:
         from bson import _BUILT_IN_TYPES
 
@@ -263,9 +273,6 @@ if TYPE_CHECKING:
         def _arguments_repr(self) -> str:
             ...
 
-        def _options_dict(self) -> dict[Any, Any]:
-            ...
-
         # NamedTuple API
         @classmethod
         def _make(cls, obj: Iterable[Any]) -> CodecOptions[_DocumentType]:
@@ -317,10 +324,10 @@ else:
               >>> doc._id
               ObjectId('5b3016359110ea14e8c58b93')
 
-            See :doc:`/examples/datetimes` for examples using the `tz_aware` and
+            See `Dates and Times <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/dates-and-times/#dates-and-times>`_ for examples using the `tz_aware` and
             `tzinfo` options.
 
-            See :doc:`/examples/uuid` for examples using the `uuid_representation`
+            See `UUID <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/uuid/#universally-unique-ids--uuids->`_ for examples using the `uuid_representation`
             option.
 
             :param document_class: BSON documents returned in queries will be decoded
@@ -334,7 +341,7 @@ else:
                 :data:`~bson.binary.UuidRepresentation.UNSPECIFIED`. New
                 applications should consider setting this to
                 :data:`~bson.binary.UuidRepresentation.STANDARD` for cross language
-                compatibility. See :ref:`handling-uuid-data-example` for details.
+                compatibility. See `UUID representations <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/uuid/#universally-unique-ids--uuids->`_ for details.
             :param unicode_decode_error_handler: The error handler to apply when
                 a Unicode-related error occurs during BSON decoding that would
                 otherwise raise :exc:`UnicodeDecodeError`. Valid options include
@@ -456,19 +463,6 @@ else:
                 )
             )
 
-        def _options_dict(self) -> dict[str, Any]:
-            """Dictionary of the arguments used to create this object."""
-            # TODO: PYTHON-2442 use _asdict() instead
-            return {
-                "document_class": self.document_class,
-                "tz_aware": self.tz_aware,
-                "uuid_representation": self.uuid_representation,
-                "unicode_decode_error_handler": self.unicode_decode_error_handler,
-                "tzinfo": self.tzinfo,
-                "type_registry": self.type_registry,
-                "datetime_conversion": self.datetime_conversion,
-            }
-
         def __repr__(self) -> str:
             return f"{self.__class__.__name__}({self._arguments_repr()})"
 
@@ -484,7 +478,7 @@ else:
 
             .. versionadded:: 3.5
             """
-            opts = self._options_dict()
+            opts = self._asdict()
             opts.update(kwargs)
             return CodecOptions(**opts)
 

bson/datetime_ms.py

@@ -51,7 +51,7 @@ class DatetimeMS:
 
         To decode UTC datetimes as a ``DatetimeMS``, `datetime_conversion` in
         :class:`~bson.codec_options.CodecOptions` must be set to 'datetime_ms' or
-        'datetime_auto'. See :ref:`handling-out-of-range-datetimes` for
+        'datetime_auto'. See `handling out of range datetimes <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/dates-and-times/#handling-out-of-range-datetimes>`_ for
         details.
 
         :param value: An instance of :class:`datetime.datetime` to be

bson/decimal128.py

@@ -20,8 +20,11 @@ from __future__ import annotations
 
 import decimal
 import struct
+from decimal import Decimal
 from typing import Any, Sequence, Tuple, Type, Union
 
+from bson.codec_options import TypeDecoder, TypeEncoder
+
 _PACK_64 = struct.Struct("<Q").pack
 _UNPACK_64 = struct.Struct("<Q").unpack
 
@@ -58,6 +61,42 @@ _DEC128_CTX = decimal.Context(**_CTX_OPTIONS.copy())  # type: ignore
 _VALUE_OPTIONS = Union[decimal.Decimal, float, str, Tuple[int, Sequence[int], int]]
 
 
+class DecimalEncoder(TypeEncoder):
+    """Converts Python :class:`decimal.Decimal` to BSON :class:`Decimal128`.
+
+    For example::
+        opts = CodecOptions(type_registry=TypeRegistry([DecimalEncoder()]))
+        bson.encode({"d": decimal.Decimal('1.0')}, codec_options=opts)
+
+    .. versionadded:: 4.15
+    """
+
+    @property
+    def python_type(self) -> Type[Decimal]:
+        return Decimal
+
+    def transform_python(self, value: Any) -> Decimal128:
+        return Decimal128(value)
+
+
+class DecimalDecoder(TypeDecoder):
+    """Converts BSON :class:`Decimal128` to Python :class:`decimal.Decimal`.
+
+    For example::
+        opts = CodecOptions(type_registry=TypeRegistry([DecimalDecoder()]))
+        bson.decode(data, codec_options=opts)
+
+    .. versionadded:: 4.15
+    """
+
+    @property
+    def bson_type(self) -> Type[Decimal128]:
+        return Decimal128
+
+    def transform_bson(self, value: Any) -> decimal.Decimal:
+        return value.to_decimal()
+
+
 def create_decimal128_context() -> decimal.Context:
     """Returns an instance of :class:`decimal.Context` appropriate
     for working with IEEE-754 128-bit decimal floating point values.

bson/errors.py

@@ -15,6 +15,8 @@
 """Exceptions raised by the BSON package."""
 from __future__ import annotations
 
+from typing import Any, Optional
+
 
 class BSONError(Exception):
     """Base class for all BSON exceptions."""
@@ -31,6 +33,17 @@ class InvalidStringData(BSONError):
 class InvalidDocument(BSONError):
     """Raised when trying to create a BSON object from an invalid document."""
 
+    def __init__(self, message: str, document: Optional[Any] = None) -> None:
+        super().__init__(message)
+        self._document = document
+
+    @property
+    def document(self) -> Any:
+        """The invalid document that caused the error.
+
+        ..versionadded:: 4.16"""
+        return self._document
+
 
 class InvalidId(BSONError):
     """Raised when trying to create an ObjectId from invalid data."""

bson/json_util.py

@@ -281,7 +281,7 @@ class JSONOptions(_BASE_CLASS):
             return DatetimeMS objects when the underlying datetime is
             out-of-range and 'datetime_clamp' to clamp to the minimum and
             maximum possible datetimes. Defaults to 'datetime'. See
-            :ref:`handling-out-of-range-datetimes` for details.
+            `handling out of range datetimes <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/dates-and-times/#handling-out-of-range-datetimes>`_ for details.
         :param args: arguments to :class:`~bson.codec_options.CodecOptions`
         :param kwargs: arguments to :class:`~bson.codec_options.CodecOptions`
 
@@ -382,19 +382,6 @@ class JSONOptions(_BASE_CLASS):
             )
         )
 
-    def _options_dict(self) -> dict[Any, Any]:
-        # TODO: PYTHON-2442 use _asdict() instead
-        options_dict = super()._options_dict()
-        options_dict.update(
-            {
-                "strict_number_long": self.strict_number_long,
-                "datetime_representation": self.datetime_representation,
-                "strict_uuid": self.strict_uuid,
-                "json_mode": self.json_mode,
-            }
-        )
-        return options_dict
-
     def with_options(self, **kwargs: Any) -> JSONOptions:
         """
         Make a copy of this JSONOptions, overriding some options::
@@ -408,7 +395,7 @@ class JSONOptions(_BASE_CLASS):
 
         .. versionadded:: 3.12
         """
-        opts = self._options_dict()
+        opts = self._asdict()
         for opt in ("strict_number_long", "datetime_representation", "strict_uuid", "json_mode"):
             opts[opt] = kwargs.get(opt, getattr(self, opt))
         opts.update(kwargs)
@@ -844,7 +831,7 @@ def _encode_binary(data: bytes, subtype: int, json_options: JSONOptions) -> Any:
     return {"$binary": {"base64": base64.b64encode(data).decode(), "subType": "%02x" % subtype}}
 
 
-def _encode_datetimems(obj: Any, json_options: JSONOptions) -> dict:
+def _encode_datetimems(obj: Any, json_options: JSONOptions) -> dict:  # type: ignore[type-arg]
     if (
         json_options.datetime_representation == DatetimeRepresentation.ISO8601
         and 0 <= int(obj) <= _MAX_UTC_MS
@@ -855,7 +842,7 @@ def _encode_datetimems(obj: Any, json_options: JSONOptions) -> dict:
     return {"$date": {"$numberLong": str(int(obj))}}
 
 
-def _encode_code(obj: Code, json_options: JSONOptions) -> dict:
+def _encode_code(obj: Code, json_options: JSONOptions) -> dict:  # type: ignore[type-arg]
     if obj.scope is None:
         return {"$code": str(obj)}
     else:
@@ -873,7 +860,7 @@ def _encode_noop(obj: Any, dummy0: Any) -> Any:
     return obj
 
 
-def _encode_regex(obj: Any, json_options: JSONOptions) -> dict:
+def _encode_regex(obj: Any, json_options: JSONOptions) -> dict:  # type: ignore[type-arg]
     flags = ""
     if obj.flags & re.IGNORECASE:
         flags += "i"
@@ -918,7 +905,7 @@ def _encode_float(obj: float, json_options: JSONOptions) -> Any:
     return obj
 
 
-def _encode_datetime(obj: datetime.datetime, json_options: JSONOptions) -> dict:
+def _encode_datetime(obj: datetime.datetime, json_options: JSONOptions) -> dict:  # type: ignore[type-arg]
     if json_options.datetime_representation == DatetimeRepresentation.ISO8601:
         if not obj.tzinfo:
             obj = obj.replace(tzinfo=utc)
@@ -941,15 +928,15 @@ def _encode_datetime(obj: datetime.datetime, json_options: JSONOptions) -> dict:
     return {"$date": {"$numberLong": str(millis)}}
 
 
-def _encode_bytes(obj: bytes, json_options: JSONOptions) -> dict:
+def _encode_bytes(obj: bytes, json_options: JSONOptions) -> dict:  # type: ignore[type-arg]
     return _encode_binary(obj, 0, json_options)
 
 
-def _encode_binary_obj(obj: Binary, json_options: JSONOptions) -> dict:
+def _encode_binary_obj(obj: Binary, json_options: JSONOptions) -> dict:  # type: ignore[type-arg]
     return _encode_binary(obj, obj.subtype, json_options)
 
 
-def _encode_uuid(obj: uuid.UUID, json_options: JSONOptions) -> dict:
+def _encode_uuid(obj: uuid.UUID, json_options: JSONOptions) -> dict:  # type: ignore[type-arg]
     if json_options.strict_uuid:
         binval = Binary.from_uuid(obj, uuid_representation=json_options.uuid_representation)
         return _encode_binary(binval, binval.subtype, json_options)
@@ -957,27 +944,27 @@ def _encode_uuid(obj: uuid.UUID, json_options: JSONOptions) -> dict:
         return {"$uuid": obj.hex}
 
 
-def _encode_objectid(obj: ObjectId, dummy0: Any) -> dict:
+def _encode_objectid(obj: ObjectId, dummy0: Any) -> dict:  # type: ignore[type-arg]
     return {"$oid": str(obj)}
 
 
-def _encode_timestamp(obj: Timestamp, dummy0: Any) -> dict:
+def _encode_timestamp(obj: Timestamp, dummy0: Any) -> dict:  # type: ignore[type-arg]
     return {"$timestamp": {"t": obj.time, "i": obj.inc}}
 
 
-def _encode_decimal128(obj: Timestamp, dummy0: Any) -> dict:
+def _encode_decimal128(obj: Timestamp, dummy0: Any) -> dict:  # type: ignore[type-arg]
     return {"$numberDecimal": str(obj)}
 
 
-def _encode_dbref(obj: DBRef, json_options: JSONOptions) -> dict:
+def _encode_dbref(obj: DBRef, json_options: JSONOptions) -> dict:  # type: ignore[type-arg]
     return _json_convert(obj.as_doc(), json_options=json_options)
 
 
-def _encode_minkey(dummy0: Any, dummy1: Any) -> dict:
+def _encode_minkey(dummy0: Any, dummy1: Any) -> dict:  # type: ignore[type-arg]
     return {"$minKey": 1}
 
 
-def _encode_maxkey(dummy0: Any, dummy1: Any) -> dict:
+def _encode_maxkey(dummy0: Any, dummy1: Any) -> dict:  # type: ignore[type-arg]
     return {"$maxKey": 1}
 
 
@@ -985,7 +972,7 @@ def _encode_maxkey(dummy0: Any, dummy1: Any) -> dict:
 # Each encoder function's signature is:
 #   - obj: a Python data type, e.g. a Python int for _encode_int
 #   - json_options: a JSONOptions
-_ENCODERS: dict[Type, Callable[[Any, JSONOptions], Any]] = {
+_ENCODERS: dict[Type, Callable[[Any, JSONOptions], Any]] = {  # type: ignore[type-arg]
     bool: _encode_noop,
     bytes: _encode_bytes,
     datetime.datetime: _encode_datetime,
@@ -1056,7 +1043,7 @@ def _get_datetime_size(obj: datetime.datetime) -> int:
     return 5 + len(str(obj.time()))
 
 
-def _get_regex_size(obj: Regex) -> int:
+def _get_regex_size(obj: Regex) -> int:  # type: ignore[type-arg]
     return 18 + len(obj.pattern)
 
 

bson/objectid.py

@@ -15,7 +15,6 @@
 """Tools for working with MongoDB ObjectIds."""
 from __future__ import annotations
 
-import binascii
 import datetime
 import os
 import struct
@@ -98,11 +97,27 @@ class ObjectId:
            objectid.rst>`_.
         """
         if oid is None:
-            self.__generate()
+            # Generate a new value for this ObjectId.
+            with ObjectId._inc_lock:
+                inc = ObjectId._inc
+                ObjectId._inc = (inc + 1) % (_MAX_COUNTER_VALUE + 1)
+
+            # 4 bytes current time, 5 bytes random, 3 bytes inc.
+            self.__id = _PACK_INT_RANDOM(int(time.time()), ObjectId._random()) + _PACK_INT(inc)[1:4]
         elif isinstance(oid, bytes) and len(oid) == 12:
             self.__id = oid
+        elif isinstance(oid, str):
+            if len(oid) == 24:
+                try:
+                    self.__id = bytes.fromhex(oid)
+                except (TypeError, ValueError):
+                    _raise_invalid_id(oid)
+            else:
+                _raise_invalid_id(oid)
+        elif isinstance(oid, ObjectId):
+            self.__id = oid.binary
         else:
-            self.__validate(oid)
+            raise TypeError(f"id must be an instance of (bytes, str, ObjectId), not {type(oid)}")
 
     @classmethod
     def from_datetime(cls: Type[ObjectId], generation_time: datetime.datetime) -> ObjectId:
@@ -163,37 +178,6 @@ class ObjectId:
             cls.__random = _random_bytes()
         return cls.__random
 
-    def __generate(self) -> None:
-        """Generate a new value for this ObjectId."""
-        with ObjectId._inc_lock:
-            inc = ObjectId._inc
-            ObjectId._inc = (inc + 1) % (_MAX_COUNTER_VALUE + 1)
-
-        # 4 bytes current time, 5 bytes random, 3 bytes inc.
-        self.__id = _PACK_INT_RANDOM(int(time.time()), ObjectId._random()) + _PACK_INT(inc)[1:4]
-
-    def __validate(self, oid: Any) -> None:
-        """Validate and use the given id for this ObjectId.
-
-        Raises TypeError if id is not an instance of :class:`str`,
-        :class:`bytes`, or ObjectId. Raises InvalidId if it is not a
-        valid ObjectId.
-
-        :param oid: a valid ObjectId
-        """
-        if isinstance(oid, ObjectId):
-            self.__id = oid.binary
-        elif isinstance(oid, str):
-            if len(oid) == 24:
-                try:
-                    self.__id = bytes.fromhex(oid)
-                except (TypeError, ValueError):
-                    _raise_invalid_id(oid)
-            else:
-                _raise_invalid_id(oid)
-        else:
-            raise TypeError(f"id must be an instance of (bytes, str, ObjectId), not {type(oid)}")
-
     @property
     def binary(self) -> bytes:
         """12-byte binary representation of this ObjectId."""
@@ -234,7 +218,7 @@ class ObjectId:
             self.__id = oid
 
     def __str__(self) -> str:
-        return binascii.hexlify(self.__id).decode()
+        return self.__id.hex()
 
     def __repr__(self) -> str:
         return f"ObjectId('{self!s}')"

bson/raw_bson.py

@@ -60,7 +60,9 @@ from bson.codec_options import DEFAULT_CODEC_OPTIONS as DEFAULT
 
 
 def _inflate_bson(
-    bson_bytes: bytes, codec_options: CodecOptions[RawBSONDocument], raw_array: bool = False
+    bson_bytes: bytes | memoryview,
+    codec_options: CodecOptions[RawBSONDocument],
+    raw_array: bool = False,
 ) -> dict[str, Any]:
     """Inflates the top level fields of a BSON document.
 
@@ -85,7 +87,9 @@ class RawBSONDocument(Mapping[str, Any]):
     __codec_options: CodecOptions[RawBSONDocument]
 
     def __init__(
-        self, bson_bytes: bytes, codec_options: Optional[CodecOptions[RawBSONDocument]] = None
+        self,
+        bson_bytes: bytes | memoryview,
+        codec_options: Optional[CodecOptions[RawBSONDocument]] = None,
     ) -> None:
         """Create a new :class:`RawBSONDocument`
 
@@ -135,7 +139,7 @@ class RawBSONDocument(Mapping[str, Any]):
         _get_object_size(bson_bytes, 0, len(bson_bytes))
 
     @property
-    def raw(self) -> bytes:
+    def raw(self) -> bytes | memoryview:
         """The raw BSON bytes composing this document."""
         return self.__raw
 
@@ -153,7 +157,7 @@ class RawBSONDocument(Mapping[str, Any]):
 
     @staticmethod
     def _inflate_bson(
-        bson_bytes: bytes, codec_options: CodecOptions[RawBSONDocument]
+        bson_bytes: bytes | memoryview, codec_options: CodecOptions[RawBSONDocument]
     ) -> Mapping[str, Any]:
         return _inflate_bson(bson_bytes, codec_options)
 
@@ -180,7 +184,7 @@ class _RawArrayBSONDocument(RawBSONDocument):
 
     @staticmethod
     def _inflate_bson(
-        bson_bytes: bytes, codec_options: CodecOptions[RawBSONDocument]
+        bson_bytes: bytes | memoryview, codec_options: CodecOptions[RawBSONDocument]
     ) -> Mapping[str, Any]:
         return _inflate_bson(bson_bytes, codec_options, raw_array=True)
 

bson/son.py

@@ -22,6 +22,7 @@ from __future__ import annotations
 
 import copy
 import re
+import warnings
 from collections.abc import Mapping as _Mapping
 from typing import (
     Any,
@@ -99,13 +100,28 @@ class SON(Dict[_Key, _Value]):
         yield from self.__keys
 
     def has_key(self, key: _Key) -> bool:
+        warnings.warn(
+            "SON.has_key() is deprecated, use the in operator instead",
+            DeprecationWarning,
+            stacklevel=2,
+        )
         return key in self.__keys
 
     def iterkeys(self) -> Iterator[_Key]:
+        warnings.warn(
+            "SON.iterkeys() is deprecated, use the keys() method instead",
+            DeprecationWarning,
+            stacklevel=2,
+        )
         return self.__iter__()
 
     # fourth level uses definitions from lower levels
     def itervalues(self) -> Iterator[_Value]:
+        warnings.warn(
+            "SON.itervalues() is deprecated, use the values() method instead",
+            DeprecationWarning,
+            stacklevel=2,
+        )
         for _, v in self.items():
             yield v
 
@@ -143,7 +159,7 @@ class SON(Dict[_Key, _Value]):
         del self[k]
         return (k, v)
 
-    def update(self, other: Optional[Any] = None, **kwargs: _Value) -> None:  # type: ignore[override]
+    def update(self, other: Optional[Any] = None, **kwargs: _Value) -> None:
         # Make progressively weaker assumptions about "other"
         if other is None:
             pass

bson/typings.py

@@ -28,4 +28,4 @@ if TYPE_CHECKING:
 _DocumentOut = Union[MutableMapping[str, Any], "RawBSONDocument"]
 _DocumentType = TypeVar("_DocumentType", bound=Mapping[str, Any])
 _DocumentTypeArg = TypeVar("_DocumentTypeArg", bound=Mapping[str, Any])
-_ReadableBuffer = Union[bytes, memoryview, "mmap", "array"]
+_ReadableBuffer = Union[bytes, memoryview, bytearray, "mmap", "array"]  # type: ignore[type-arg]

doc/api/bson/binary.rst

@@ -16,6 +16,7 @@
    .. autodata:: MD5_SUBTYPE
    .. autodata:: COLUMN_SUBTYPE
    .. autodata:: SENSITIVE_SUBTYPE
+   .. autodata:: VECTOR_SUBTYPE
    .. autodata:: USER_DEFINED_SUBTYPE
 
    .. autoclass:: UuidRepresentation

doc/api/gridfs/asynchronous/index.rst

@@ -1,10 +1,6 @@
 :mod:`gridfs async` -- Async tools for working with GridFS
 ==========================================================
 
-.. warning:: This API is currently in beta, meaning the classes, methods,
-   and behaviors described within may change before the full release.
-   If you come across any bugs during your use of this API,
-   please file a Jira ticket in the "Python Driver" project at https://jira.mongodb.org/browse/PYTHON.
 
 .. automodule:: gridfs.asynchronous
    :synopsis: Async tools for working with GridFS

doc/api/pymongo/asynchronous/change_stream.rst

@@ -1,10 +1,6 @@
 :mod:`change_stream` -- Watch changes on a collection, database, or cluster
 ===========================================================================
 
-.. warning:: This API is currently in beta, meaning the classes, methods,
-   and behaviors described within may change before the full release.
-   If you come across any bugs during your use of this API,
-   please file a Jira ticket in the "Python Driver" project at https://jira.mongodb.org/browse/PYTHON.
 
 .. automodule:: pymongo.asynchronous.change_stream
    :members:

doc/api/pymongo/asynchronous/client_session.rst

@@ -1,10 +1,6 @@
 :mod:`client_session` -- Logical sessions for sequential operations
 ===================================================================
 
-.. warning:: This API is currently in beta, meaning the classes, methods,
-   and behaviors described within may change before the full release.
-   If you come across any bugs during your use of this API,
-   please file a Jira ticket in the "Python Driver" project at https://jira.mongodb.org/browse/PYTHON.
 
 .. automodule:: pymongo.asynchronous.client_session
    :members:

doc/api/pymongo/asynchronous/collection.rst

@@ -1,10 +1,6 @@
 :mod:`collection` -- Collection level operations
 ================================================
 
-.. warning:: This API is currently in beta, meaning the classes, methods,
-   and behaviors described within may change before the full release.
-   If you come across any bugs during your use of this API,
-   please file a Jira ticket in the "Python Driver" project at https://jira.mongodb.org/browse/PYTHON.
 
 .. automodule:: pymongo.asynchronous.collection
    :synopsis: Collection level operations

doc/api/pymongo/asynchronous/command_cursor.rst

@@ -1,11 +1,8 @@
 :mod:`command_cursor` -- Tools for iterating over MongoDB command results
 =========================================================================
 
-.. warning:: This API is currently in beta, meaning the classes, methods,
-   and behaviors described within may change before the full release.
-   If you come across any bugs during your use of this API,
-   please file a Jira ticket in the "Python Driver" project at https://jira.mongodb.org/browse/PYTHON.
 
 .. automodule:: pymongo.asynchronous.command_cursor
    :synopsis: Tools for iterating over MongoDB command results
    :members:
+   :inherited-members:

doc/api/pymongo/asynchronous/cursor.rst

@@ -1,16 +1,14 @@
 :mod:`cursor` -- Tools for iterating over MongoDB query results
 ===============================================================
 
-.. warning:: This API is currently in beta, meaning the classes, methods,
-   and behaviors described within may change before the full release.
-   If you come across any bugs during your use of this API,
-   please file a Jira ticket in the "Python Driver" project at https://jira.mongodb.org/browse/PYTHON.
 
 .. automodule:: pymongo.asynchronous.cursor
    :synopsis: Tools for iterating over MongoDB query results
 
    .. autoclass:: pymongo.asynchronous.cursor.AsyncCursor(collection, filter=None, projection=None, skip=0, limit=0, no_cursor_timeout=False, cursor_type=CursorType.NON_TAILABLE, sort=None, allow_partial_results=False, oplog_replay=False, batch_size=0, collation=None, hint=None, max_scan=None, max_time_ms=None, max=None, min=None, return_key=False, show_record_id=False, snapshot=False, comment=None, session=None, allow_disk_use=None)
       :members:
+      :inherited-members:
+
 
       .. describe:: c[index]
 

doc/api/pymongo/asynchronous/database.rst

@@ -1,10 +1,6 @@
 :mod:`database` -- Database level operations
 ============================================
 
-.. warning:: This API is currently in beta, meaning the classes, methods,
-   and behaviors described within may change before the full release.
-   If you come across any bugs during your use of this API,
-   please file a Jira ticket in the "Python Driver" project at https://jira.mongodb.org/browse/PYTHON.
 
 .. automodule:: pymongo.asynchronous.database
    :synopsis: Database level operations

doc/api/pymongo/asynchronous/index.rst

@@ -1,10 +1,6 @@
 :mod:`pymongo async` -- Async Python driver for MongoDB
 =======================================================
 
-.. warning:: This API is currently in beta, meaning the classes, methods,
-   and behaviors described within may change before the full release.
-   If you come across any bugs during your use of this API,
-   please file a Jira ticket in the "Python Driver" project at https://jira.mongodb.org/browse/PYTHON.
 
 .. automodule:: pymongo.asynchronous
    :synopsis: Asynchronous Python driver for MongoDB

doc/api/pymongo/asynchronous/mongo_client.rst

@@ -1,10 +1,6 @@
 :mod:`mongo_client` -- Tools for connecting to MongoDB
 ======================================================
 
-.. warning:: This API is currently in beta, meaning the classes, methods,
-   and behaviors described within may change before the full release.
-   If you come across any bugs during your use of this API,
-   please file a Jira ticket in the "Python Driver" project at https://jira.mongodb.org/browse/PYTHON.
 
 .. automodule:: pymongo.asynchronous.mongo_client
    :synopsis: Tools for connecting to MongoDB

doc/api/pymongo/command_cursor.rst

@@ -4,3 +4,4 @@
 .. automodule:: pymongo.command_cursor
    :synopsis: Tools for iterating over MongoDB command results
    :members:
+   :inherited-members:

doc/api/pymongo/cursor.rst

@@ -17,6 +17,7 @@
 
    .. autoclass:: pymongo.cursor.Cursor(collection, filter=None, projection=None, skip=0, limit=0, no_cursor_timeout=False, cursor_type=CursorType.NON_TAILABLE, sort=None, allow_partial_results=False, oplog_replay=False, batch_size=0, collation=None, hint=None, max_scan=None, max_time_ms=None, max=None, min=None, return_key=False, show_record_id=False, snapshot=False, comment=None, session=None, allow_disk_use=None)
       :members:
+      :inherited-members:
 
       .. describe:: c[index]
 

doc/async-tutorial.rst

@@ -1,429 +0,0 @@
-Async Tutorial
-==============
-
-.. warning:: This API is currently in beta, meaning the classes, methods,
-   and behaviors described within may change before the full release.
-   If you come across any bugs during your use of this API,
-   please file a Jira ticket in the "Python Driver" project at https://jira.mongodb.org/browse/PYTHON.
-
-.. code-block:: pycon
-
-  from pymongo import AsyncMongoClient
-
-  client = AsyncMongoClient()
-  await client.drop_database("test-database")
-
-This tutorial is intended as an introduction to working with
-**MongoDB** and **PyMongo** using the asynchronous API.
-
-Prerequisites
--------------
-Before we start, make sure that you have the **PyMongo** distribution
-:doc:`installed <installation>`. In the Python shell, the following
-should run without raising an exception:
-
-.. code-block:: pycon
-
-  >>> import pymongo
-
-This tutorial also assumes that a MongoDB instance is running on the
-default host and port. Assuming you have `downloaded and installed
-<https://www.mongodb.com/docs/manual/installation/>`_ MongoDB, you
-can start it like so:
-
-.. code-block:: bash
-
-  $ mongod
-
-Making a Connection with AsyncMongoClient
------------------------------------------
-The first step when working with **PyMongo** is to create a
-:class:`~pymongo.asynchronous.mongo_client.AsyncMongoClient` to the running **mongod**
-instance. Doing so is easy:
-
-.. code-block:: pycon
-
-  >>> from pymongo import AsyncMongoClient
-  >>> client = AsyncMongoClient()
-
-The above code will connect on the default host and port. We can also
-specify the host and port explicitly, as follows:
-
-.. code-block:: pycon
-
-  >>> client = AsyncMongoClient("localhost", 27017)
-
-Or use the MongoDB URI format:
-
-.. code-block:: pycon
-
-  >>> client = AsyncMongoClient("mongodb://localhost:27017/")
-
-By default, :class:`~pymongo.asynchronous.mongo_client.AsyncMongoClient` only connects to the database on its first operation.
-To explicitly connect before performing an operation, use :meth:`~pymongo.asynchronous.mongo_client.AsyncMongoClient.aconnect`:
-
-.. code-block:: pycon
-
-  >>> client = await AsyncMongoClient().aconnect()
-
-Getting a Database
-------------------
-A single instance of MongoDB can support multiple independent
-`databases <https://www.mongodb.com/docs/manual/core/databases-and-collections>`_. When
-working with PyMongo you access databases using attribute style access
-on :class:`~pymongo.asynchronous.mongo_client.AsyncMongoClient` instances:
-
-.. code-block:: pycon
-
-  >>> db = client.test_database
-
-If your database name is such that using attribute style access won't
-work (like ``test-database``), you can use dictionary style access
-instead:
-
-.. code-block:: pycon
-
-  >>> db = client["test-database"]
-
-Getting a Collection
---------------------
-A `collection <https://www.mongodb.com/docs/manual/core/databases-and-collections>`_ is a
-group of documents stored in MongoDB, and can be thought of as roughly
-the equivalent of a table in a relational database. Getting a
-collection in PyMongo works the same as getting a database:
-
-.. code-block:: pycon
-
-  >>> collection = db.test_collection
-
-or (using dictionary style access):
-
-.. code-block:: pycon
-
-  >>> collection = db["test-collection"]
-
-An important note about collections (and databases) in MongoDB is that
-they are created lazily - none of the above commands have actually
-performed any operations on the MongoDB server. Collections and
-databases are created when the first document is inserted into them.
-
-Documents
----------
-Data in MongoDB is represented (and stored) using JSON-style
-documents. In PyMongo we use dictionaries to represent documents. As
-an example, the following dictionary might be used to represent a blog
-post:
-
-.. code-block:: pycon
-
-  >>> import datetime
-  >>> post = {
-  ...     "author": "Mike",
-  ...     "text": "My first blog post!",
-  ...     "tags": ["mongodb", "python", "pymongo"],
-  ...     "date": datetime.datetime.now(tz=datetime.timezone.utc),
-  ... }
-
-Note that documents can contain native Python types (like
-:class:`datetime.datetime` instances) which will be automatically
-converted to and from the appropriate `BSON
-<https://bsonspec.org/>`_ types.
-
-Inserting a Document
---------------------
-To insert a document into a collection we can use the
-:meth:`~pymongo.asynchronous.collection.AsyncCollection.insert_one` method:
-
-.. code-block:: pycon
-
-  >>> posts = db.posts
-  >>> post_id = (await posts.insert_one(post)).inserted_id
-  >>> post_id
-  ObjectId('...')
-
-When a document is inserted a special key, ``"_id"``, is automatically
-added if the document doesn't already contain an ``"_id"`` key. The value
-of ``"_id"`` must be unique across the
-collection. :meth:`~pymongo.asynchronous.collection.AsyncCollection.insert_one` returns an
-instance of :class:`~pymongo.results.InsertOneResult`. For more information
-on ``"_id"``, see the `documentation on _id
-<https://www.mongodb.com/docs/manual/reference/method/ObjectId/>`_.
-
-After inserting the first document, the *posts* collection has
-actually been created on the server. We can verify this by listing all
-of the collections in our database:
-
-.. code-block:: pycon
-
-  >>> await db.list_collection_names()
-  ['posts']
-
-Getting a Single Document With :meth:`~pymongo.asynchronous.collection.AsyncCollection.find_one`
-------------------------------------------------------------------------------------------------
-The most basic type of query that can be performed in MongoDB is
-:meth:`~pymongo.asynchronous.collection.AsyncCollection.find_one`. This method returns a
-single document matching a query (or ``None`` if there are no
-matches). It is useful when you know there is only one matching
-document, or are only interested in the first match. Here we use
-:meth:`~pymongo.asynchronous.collection.AsyncCollection.find_one` to get the first
-document from the posts collection:
-
-.. code-block:: pycon
-
-  >>> import pprint
-  >>> pprint.pprint(await posts.find_one())
-  {'_id': ObjectId('...'),
-   'author': 'Mike',
-   'date': datetime.datetime(...),
-   'tags': ['mongodb', 'python', 'pymongo'],
-   'text': 'My first blog post!'}
-
-The result is a dictionary matching the one that we inserted previously.
-
-.. note:: The returned document contains an ``"_id"``, which was
-   automatically added on insert.
-
-:meth:`~pymongo.asynchronous.collection.AsyncCollection.find_one` also supports querying
-on specific elements that the resulting document must match. To limit
-our results to a document with author "Mike" we do:
-
-.. code-block:: pycon
-
-  >>> pprint.pprint(await posts.find_one({"author": "Mike"}))
-  {'_id': ObjectId('...'),
-   'author': 'Mike',
-   'date': datetime.datetime(...),
-   'tags': ['mongodb', 'python', 'pymongo'],
-   'text': 'My first blog post!'}
-
-If we try with a different author, like "Eliot", we'll get no result:
-
-.. code-block:: pycon
-
-  >>> await posts.find_one({"author": "Eliot"})
-  >>>
-
-.. _async-querying-by-objectid:
-
-Querying By ObjectId
---------------------
-We can also find a post by its ``_id``, which in our example is an ObjectId:
-
-.. code-block:: pycon
-
-  >>> post_id
-  ObjectId(...)
-  >>> pprint.pprint(await posts.find_one({"_id": post_id}))
-  {'_id': ObjectId('...'),
-   'author': 'Mike',
-   'date': datetime.datetime(...),
-   'tags': ['mongodb', 'python', 'pymongo'],
-   'text': 'My first blog post!'}
-
-Note that an ObjectId is not the same as its string representation:
-
-.. code-block:: pycon
-
-  >>> post_id_as_str = str(post_id)
-  >>> await posts.find_one({"_id": post_id_as_str})  # No result
-  >>>
-
-A common task in web applications is to get an ObjectId from the
-request URL and find the matching document. It's necessary in this
-case to **convert the ObjectId from a string** before passing it to
-``find_one``::
-
-  from bson.objectid import ObjectId
-
-  # The web framework gets post_id from the URL and passes it as a string
-  async def get(post_id):
-      # Convert from string to ObjectId:
-      document = await client.db.collection.find_one({'_id': ObjectId(post_id)})
-
-.. seealso:: :ref:`web-application-querying-by-objectid`
-
-Bulk Inserts
-------------
-In order to make querying a little more interesting, let's insert a
-few more documents. In addition to inserting a single document, we can
-also perform *bulk insert* operations, by passing a list as the
-first argument to :meth:`~pymongo.asynchronous.collection.AsyncCollection.insert_many`.
-This will insert each document in the list, sending only a single
-command to the server:
-
-.. code-block:: pycon
-
-  >>> new_posts = [
-  ...     {
-  ...         "author": "Mike",
-  ...         "text": "Another post!",
-  ...         "tags": ["bulk", "insert"],
-  ...         "date": datetime.datetime(2009, 11, 12, 11, 14),
-  ...     },
-  ...     {
-  ...         "author": "Eliot",
-  ...         "title": "MongoDB is fun",
-  ...         "text": "and pretty easy too!",
-  ...         "date": datetime.datetime(2009, 11, 10, 10, 45),
-  ...     },
-  ... ]
-  >>> result = await posts.insert_many(new_posts)
-  >>> result.inserted_ids
-  [ObjectId('...'), ObjectId('...')]
-
-There are a couple of interesting things to note about this example:
-
-  - The result from :meth:`~pymongo.asynchronous.collection.AsyncCollection.insert_many` now
-    returns two :class:`~bson.objectid.ObjectId` instances, one for
-    each inserted document.
-  - ``new_posts[1]`` has a different "shape" than the other posts -
-    there is no ``"tags"`` field and we've added a new field,
-    ``"title"``. This is what we mean when we say that MongoDB is
-    *schema-free*.
-
-Querying for More Than One Document
------------------------------------
-To get more than a single document as the result of a query we use the
-:meth:`~pymongo.asynchronous.collection.AsyncCollection.find`
-method. :meth:`~pymongo.asynchronous.collection.AsyncCollection.find` returns a
-:class:`~pymongo.asynchronous.cursor.AsyncCursor` instance, which allows us to iterate
-over all matching documents. For example, we can iterate over every
-document in the ``posts`` collection:
-
-.. code-block:: pycon
-
-  >>> async for post in posts.find():
-  ...     pprint.pprint(post)
-  ...
-  {'_id': ObjectId('...'),
-   'author': 'Mike',
-   'date': datetime.datetime(...),
-   'tags': ['mongodb', 'python', 'pymongo'],
-   'text': 'My first blog post!'}
-  {'_id': ObjectId('...'),
-   'author': 'Mike',
-   'date': datetime.datetime(...),
-   'tags': ['bulk', 'insert'],
-   'text': 'Another post!'}
-  {'_id': ObjectId('...'),
-   'author': 'Eliot',
-   'date': datetime.datetime(...),
-   'text': 'and pretty easy too!',
-   'title': 'MongoDB is fun'}
-
-Just like we did with :meth:`~pymongo.asynchronous.collection.AsyncCollection.find_one`,
-we can pass a document to :meth:`~pymongo.asynchronous.collection.AsyncCollection.find`
-to limit the returned results. Here, we get only those documents whose
-author is "Mike":
-
-.. code-block:: pycon
-
-  >>> async for post in posts.find({"author": "Mike"}):
-  ...     pprint.pprint(post)
-  ...
-  {'_id': ObjectId('...'),
-   'author': 'Mike',
-   'date': datetime.datetime(...),
-   'tags': ['mongodb', 'python', 'pymongo'],
-   'text': 'My first blog post!'}
-  {'_id': ObjectId('...'),
-   'author': 'Mike',
-   'date': datetime.datetime(...),
-   'tags': ['bulk', 'insert'],
-   'text': 'Another post!'}
-
-Counting
---------
-If we just want to know how many documents match a query we can
-perform a :meth:`~pymongo.asynchronous.collection.AsyncCollection.count_documents` operation
-instead of a full query. We can get a count of all of the documents
-in a collection:
-
-.. code-block:: pycon
-
-  >>> await posts.count_documents({})
-  3
-
-or just of those documents that match a specific query:
-
-.. code-block:: pycon
-
-  >>> await posts.count_documents({"author": "Mike"})
-  2
-
-Range Queries
--------------
-MongoDB supports many different types of `advanced queries
-<https://www.mongodb.com/docs/manual/reference/operator/>`_. As an
-example, lets perform a query where we limit results to posts older
-than a certain date, but also sort the results by author:
-
-.. code-block:: pycon
-
-  >>> d = datetime.datetime(2009, 11, 12, 12)
-  >>> async for post in posts.find({"date": {"$lt": d}}).sort("author"):
-  ...     pprint.pprint(post)
-  ...
-  {'_id': ObjectId('...'),
-   'author': 'Eliot',
-   'date': datetime.datetime(...),
-   'text': 'and pretty easy too!',
-   'title': 'MongoDB is fun'}
-  {'_id': ObjectId('...'),
-   'author': 'Mike',
-   'date': datetime.datetime(...),
-   'tags': ['bulk', 'insert'],
-   'text': 'Another post!'}
-
-Here we use the special ``"$lt"`` operator to do a range query, and
-also call :meth:`~pymongo.asynchronous.cursor.AsyncCursor.sort` to sort the results
-by author.
-
-Indexing
---------
-
-Adding indexes can help accelerate certain queries and can also add additional
-functionality to querying and storing documents. In this example, we'll
-demonstrate how to create a `unique index
-<https://mongodb.com/docs/manual/core/index-unique/>`_ on a key that rejects
-documents whose value for that key already exists in the index.
-
-First, we'll need to create the index:
-
-.. code-block:: pycon
-
-   >>> result = await db.profiles.create_index([("user_id", pymongo.ASCENDING)], unique=True)
-   >>> sorted(list(await db.profiles.index_information()))
-   ['_id_', 'user_id_1']
-
-Notice that we have two indexes now: one is the index on ``_id`` that MongoDB
-creates automatically, and the other is the index on ``user_id`` we just
-created.
-
-Now let's set up some user profiles:
-
-.. code-block:: pycon
-
-   >>> user_profiles = [{"user_id": 211, "name": "Luke"}, {"user_id": 212, "name": "Ziltoid"}]
-   >>> result = await db.profiles.insert_many(user_profiles)
-
-The index prevents us from inserting a document whose ``user_id`` is already in
-the collection:
-
-.. code-block:: pycon
-
-   >>> new_profile = {"user_id": 213, "name": "Drew"}
-   >>> duplicate_profile = {"user_id": 212, "name": "Tommy"}
-   >>> result = await db.profiles.insert_one(new_profile)  # This is fine.
-   >>> result = await db.profiles.insert_one(duplicate_profile)
-   Traceback (most recent call last):
-   DuplicateKeyError: E11000 duplicate key error index: test_database.profiles.$user_id_1 dup key: { : 212 }
-
-.. seealso:: The MongoDB documentation on `indexes <https://www.mongodb.com/docs/manual/indexes/>`_
-
-Task Cancellation
------------------
-`Cancelling <https://docs.python.org/3/library/asyncio-task.html#task-cancellation>`_ an asyncio Task
-that is running a PyMongo operation is treated as a fatal interrupt. Any connections, cursors, and transactions
-involved in a cancelled Task will be safely closed and cleaned up as part of the cancellation. If those resources are
-also used elsewhere, attempting to utilize them after the cancellation will result in an error.

doc/atlas.rst

@@ -1,43 +0,0 @@
-Using PyMongo with MongoDB Atlas
-================================
-
-`Atlas <https://www.mongodb.com/cloud>`_ is MongoDB, Inc.'s hosted MongoDB as a
-service offering. To connect to Atlas, pass the connection string provided by
-Atlas to :class:`~pymongo.mongo_client.MongoClient`::
-
-  client = pymongo.MongoClient(<Atlas connection string>)
-
-Connections to Atlas require TLS/SSL.
-
-.. warning:: Industry best practices recommend, and some regulations require,
-  the use of TLS 1.1 or newer. Though no application changes are required for
-  PyMongo to make use of the newest protocols, some operating systems or
-  versions may not provide an OpenSSL version new enough to support them.
-
-  Users of macOS older than 10.13 (High Sierra) will need to install Python
-  from `python.org`_, `homebrew`_, `macports`_, or another similar source.
-
-  Users of Linux or other non-macOS Unix can check their OpenSSL version like
-  this::
-
-    $ openssl version
-
-  If the version number is less than 1.0.1 support for TLS 1.1 or newer is not
-  available. Contact your operating system vendor for a solution or upgrade to
-  a newer distribution.
-
-  You can check your Python interpreter by installing the `requests`_ module
-  and executing the following command::
-
-    python -c "import requests; print(requests.get('https://www.howsmyssl.com/a/check', verify=False).json()['tls_version'])"
-
-  You should see "TLS 1.X" where X is >= 1.
-
-  You can read more about TLS versions and their security implications here:
-
-  `<https://cheatsheetseries.owasp.org/cheatsheets/Transport_Layer_Security_Cheat_Sheet.html#only-support-strong-protocols>`_
-
-.. _python.org: https://www.python.org/downloads/
-.. _homebrew: https://brew.sh/
-.. _macports: https://www.macports.org/
-.. _requests: https://pypi.python.org/pypi/requests

doc/changelog.rst

@@ -1,6 +1,279 @@
 Changelog
 =========
 
+Changes in Version 4.17.0 (2026/04/20)
+--------------------------------------
+
+PyMongo 4.17 brings a number of changes including:
+
+- ``has_key``, ``iterkeys`` and ``itervalues`` in :class:`bson.son.SON` have
+  been deprecated and will be removed in PyMongo 5.0. These methods were
+  deprecated in favor of the standard dictionary containment operator ``in``
+  and the ``keys()`` and ``values()`` methods, respectively.
+- Added the :meth:`~pymongo.asynchronous.client_session.AsyncClientSession.bind` and :meth:`~pymongo.client_session.ClientSession.bind` methods
+  that allow users to bind a session to all database operations within the scope of a context manager instead of having to explicitly pass the session to each individual operation.
+  See the `Transactions docs <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/crud/transactions/#methods>`_ for examples and more information.
+- Added support for MongoDB's Intelligent Workload Management (IWM) and ingress connection rate limiting features.
+  The driver now gracefully handles write-blocking scenarios and optimizes connection establishment during high-load conditions to maintain application availability.
+  See the `IWM <https://www.mongodb.com/docs/atlas/intelligent-workload-management>`_ or `Overload Errors <https://www.mongodb.com/docs/atlas/overload-errors/?interface=driver&language=python>`_ docs for more information.
+
+Changes in Version 4.16.0 (2026/01/07)
+--------------------------------------
+
+PyMongo 4.16 brings a number of changes including:
+
+- Removed invalid documents from :class:`bson.errors.InvalidDocument` error messages as
+  doing so may leak sensitive user data.
+  Instead, invalid documents are stored in :attr:`bson.errors.InvalidDocument.document`.
+- PyMongo now requires ``dnspython>=2.6.1``, since ``dnspython`` 1.0 is no longer maintained.
+  The minimum version is ``2.6.1`` to account for `CVE-2023-29483 <https://www.cve.org/CVERecord?id=CVE-2023-29483>`_.
+- Removed support for Eventlet.
+  Eventlet is actively being sunset by its maintainers and has compatibility issues with PyMongo's dnspython dependency.
+- Use Zstandard support from the standard library for Python 3.14+, and use ``backports.zstd`` for older versions.
+- Fixed return type annotation for ``find_one_and_*`` methods on :class:`~pymongo.asynchronous.collection.AsyncCollection`
+  and :class:`~pymongo.synchronous.collection.Collection` to include ``None``.
+- Added support for NumPy 1D-arrays in :class:`bson.binary.BinaryVector`.
+- Prevented :class:`~pymongo.encryption.ClientEncryption` from loading the crypt
+  shared library to fix "MongoCryptError: An existing crypt_shared library is
+  loaded by the application" unless the linked library search path is set.
+
+Changes in Version 4.15.5 (2025/12/02)
+--------------------------------------
+
+Version 4.15.5 is a bug fix release.
+
+- Fixed a bug that could cause ``AutoReconnect("connection pool paused")`` errors when cursors fetched more documents from the database after SDAM heartbeat failures.
+
+Changes in Version 4.15.4 (2025/10/21)
+--------------------------------------
+
+Version 4.15.4 is a bug fix release.
+
+- Relaxed the callback type of :meth:`~pymongo.asynchronous.client_session.AsyncClientSession.with_transaction` to allow the broader Awaitable type rather than only Coroutine objects.
+- Added the missing Python 3.14 trove classifier to the package metadata.
+
+Issues Resolved
+...............
+
+See the `PyMongo 4.15.4 release notes in JIRA`_ for the list of resolved issues
+in this release.
+
+.. _PyMongo 4.15.4 release notes in JIRA: https://jira.mongodb.org/secure/ReleaseNote.jspa?projectId=10004&version=47237
+
+Changes in Version 4.15.3 (2025/10/07)
+--------------------------------------
+
+Version 4.15.3 is a bug fix release.
+
+- Fixed a memory leak when raising :class:`bson.errors.InvalidDocument` with C extensions.
+- Fixed the return type of the  :meth:`~pymongo.asynchronous.collection.AsyncCollection.distinct`,
+  :meth:`~pymongo.synchronous.collection.Collection.distinct`, :meth:`pymongo.asynchronous.cursor.AsyncCursor.distinct`,
+  and :meth:`pymongo.asynchronous.cursor.AsyncCursor.distinct` methods.
+
+Issues Resolved
+...............
+
+See the `PyMongo 4.15.3 release notes in JIRA`_ for the list of resolved issues
+in this release.
+
+.. _PyMongo 4.15.3 release notes in JIRA: https://jira.mongodb.org/secure/ReleaseNote.jspa?projectId=10004&version=47293
+
+Changes in Version 4.15.2 (2025/10/01)
+--------------------------------------
+
+Version 4.15.2 is a bug fix release.
+
+- Add wheels for Python 3.14 and 3.14t that were missing from 4.15.0 release. Drop the 3.13t wheel.
+
+Issues Resolved
+...............
+
+See the `PyMongo 4.15.2 release notes in JIRA`_ for the list of resolved issues
+in this release.
+
+.. _PyMongo 4.15.2 release notes in JIRA: https://jira.mongodb.org/secure/ReleaseNote.jspa?projectId=10004&version=47186
+
+Changes in Version 4.15.1 (2025/09/16)
+--------------------------------------
+
+Version 4.15.1 is a bug fix release.
+
+- Fixed a bug in :meth:`~pymongo.synchronous.encryption.ClientEncryption.encrypt`
+  and :meth:`~pymongo.asynchronous.encryption.AsyncClientEncryption.encrypt`
+  that would cause a ``TypeError`` when using ``pymongocrypt<1.16`` by passing
+  an unsupported ``type_opts`` parameter even if Queryable Encryption text
+  queries beta was not used.
+
+- Fixed a bug in ``AsyncMongoClient`` that caused a ``ServerSelectionTimeoutError``
+  when used with ``uvicorn``, ``FastAPI``, or ``uvloop``.
+
+Issues Resolved
+...............
+
+See the `PyMongo 4.15.1 release notes in JIRA`_ for the list of resolved issues
+in this release.
+
+.. _PyMongo 4.15.1 release notes in JIRA: https://jira.mongodb.org/secure/ReleaseNote.jspa?projectId=10004&version=46486
+
+Changes in Version 4.15.0 (2025/09/10)
+--------------------------------------
+
+PyMongo 4.15 brings a number of changes including:
+
+- Added :class:`~pymongo.encryption_options.TextOpts`,
+  :attr:`~pymongo.encryption.Algorithm.TEXTPREVIEW`,
+  :attr:`~pymongo.encryption.QueryType.PREFIXPREVIEW`,
+  :attr:`~pymongo.encryption.QueryType.SUFFIXPREVIEW`,
+  :attr:`~pymongo.encryption.QueryType.SUBSTRINGPREVIEW`,
+  as part of the experimental Queryable Encryption text queries beta.
+  ``pymongocrypt>=1.16`` is required for text query support.
+- Added :class:`bson.decimal128.DecimalEncoder` and
+  :class:`bson.decimal128.DecimalDecoder`
+  to support encoding and decoding of BSON Decimal128 values to
+  decimal.Decimal values using the TypeRegistry API.
+- Added support for Windows ``arm64`` wheels.
+
+Changes in Version 4.14.1 (2025/08/19)
+--------------------------------------
+
+Version 4.14.1 is a bug fix release.
+
+- Fixed a bug in ``MongoClient.append_metadata()`` and
+  ``AsyncMongoClient.append_metadata()``
+  that allowed duplicate ``DriverInfo.name`` to be appended to the metadata.
+
+Issues Resolved
+...............
+
+See the `PyMongo 4.14.1 release notes in JIRA`_ for the list of resolved issues
+in this release.
+
+.. _PyMongo 4.14.1 release notes in JIRA: https://jira.mongodb.org/secure/ReleaseNote.jspa?projectId=10004&version=45256
+
+Changes in Version 4.14.0 (2025/08/06)
+--------------------------------------
+
+.. warning:: PyMongo 4.14 drops support for MongoDB 4.0. PyMongo now supports
+   MongoDB 4.2+.
+
+PyMongo 4.14 brings a number of changes including:
+
+- Dropped support for MongoDB 4.0.
+- Added preliminary support for Python 3.14 and 3.14 with free-threading. We do
+  not yet support the following with Python 3.14:
+
+  - Subinterpreters (``concurrent.interpreters``)
+  - Free-threading with Encryption
+  - mod_wsgi
+
+- Removed experimental support for free-threading support in Python 3.13.
+- Added :attr:`bson.codec_options.TypeRegistry.codecs` and
+  :attr:`bson.codec_options.TypeRegistry.fallback_encoder` properties
+  to allow users to directly access the type codecs and fallback encoder for a
+  given :class:`bson.codec_options.TypeRegistry`.
+- Added
+  :meth:`pymongo.asynchronous.mongo_client.AsyncMongoClient.append_metadata` and
+  :meth:`pymongo.mongo_client.MongoClient.append_metadata` to allow instantiated
+  MongoClients to send client metadata on-demand
+- Improved performance of selecting a server with the Primary selector.
+- Introduces a minor breaking change. When encoding
+  :class:`bson.binary.BinaryVector`, a ``ValueError`` will be raised if the
+  'padding' metadata field is < 0 or > 7, or non-zero for any type other than
+  PACKED_BIT.
+- Changed :meth:`~pymongo.uri_parser.parse_uri`'s ``options`` return value to be
+  type ``dict`` instead of ``_CaseInsensitiveDictionary``.
+
+Issues Resolved
+...............
+
+See the `PyMongo 4.14 release notes in JIRA`_ for the list of resolved issues
+in this release.
+
+.. _PyMongo 4.14 release notes in JIRA: https://jira.mongodb.org/secure/ReleaseNote.jspa?projectId=10004&version=43041
+
+Changes in Version 4.13.2 (2025/06/17)
+--------------------------------------
+
+Version 4.13.2 is a bug fix release.
+
+- Fixed a bug where ``AsyncMongoClient`` would block the event loop while creating new connections,
+  potentially significantly increasing latency for ongoing operations.
+
+Issues Resolved
+...............
+
+See the `PyMongo 4.13.2 release notes in JIRA`_ for the list of resolved issues
+in this release.
+
+.. _PyMongo 4.13.2 release notes in JIRA: https://jira.mongodb.org/secure/ReleaseNote.jspa?projectId=10004&version=43937
+
+
+Changes in Version 4.13.1 (2025/06/10)
+--------------------------------------
+
+Version 4.13.1 is a bug fix release.
+
+- Fixed a bug that could raise ``ServerSelectionTimeoutError`` when using timeouts with ``AsyncMongoClient``.
+- Fixed a bug that could raise ``NetworkTimeout`` errors on Windows.
+
+Issues Resolved
+...............
+
+See the `PyMongo 4.13.1 release notes in JIRA`_ for the list of resolved issues
+in this release.
+
+.. _PyMongo 4.13.1 release notes in JIRA: https://jira.mongodb.org/secure/ReleaseNote.jspa?projectId=10004&version=43924
+
+Changes in Version 4.13.0 (2025/05/14)
+--------------------------------------
+
+PyMongo 4.13 brings a number of changes including:
+
+- The asynchronous API is now stable and no longer in beta.
+  See the :mod:`pymongo.asynchronous` docs
+  or the `migration guide <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/reference/migration/>`_ for more information.
+- Fixed a bug where :class:`pymongo.write_concern.WriteConcern` repr was not eval-able
+  when using ``w="majority"``.
+- When padding is set, ignored bits in a BSON BinaryVector of PACKED_BIT dtype should be set to zero.
+  When encoding, this is enforced and is a breaking change.
+  It is not yet enforced when decoding, so reading from the database will not fail, however a warning will be triggered.
+  From PyMongo 5.0, this rule will be enforced for both encoding and decoding.
+
+Issues Resolved
+...............
+
+See the `PyMongo 4.13 release notes in JIRA`_ for the list of resolved issues
+in this release.
+
+.. _PyMongo 4.13 release notes in JIRA: https://jira.mongodb.org/secure/ReleaseNote.jspa?projectId=10004&version=42509
+
+Changes in Version 4.12.1 (2025/04/29)
+--------------------------------------
+
+Version 4.12.1 is a bug fix release.
+
+- Fixed a bug that could raise ``UnboundLocalError`` when creating asynchronous connections over SSL.
+- Fixed a bug causing SRV hostname validation to fail when resolver and resolved hostnames are identical with three domain levels.
+- Fixed a bug that caused direct use of ``pymongo.uri_parser`` to raise an ``AttributeError``.
+- Fixed a bug where clients created with connect=False and a "mongodb+srv://" connection string
+  could cause public ``pymongo.MongoClient`` and ``pymongo.AsyncMongoClient`` attributes (topology_description,
+  nodes, address, primary, secondaries, arbiters) to incorrectly return a Database, leading to type
+  errors such as: "NotImplementedError: Database objects do not implement truth value testing or bool()".
+- Removed Eventlet testing against Python versions newer than 3.9 since
+  Eventlet is actively being sunset by its maintainers and has compatibility issues with PyMongo's dnspython dependency.
+- Fixed a bug where MongoDB cluster topology changes could cause asynchronous operations to take much longer to complete
+  due to holding the Topology lock while closing stale connections.
+- Fixed a bug that would cause AsyncMongoClient to attempt to use PyOpenSSL when available, resulting in errors such as
+  "pymongo.errors.ServerSelectionTimeoutError: 'SSLContext' object has no attribute 'wrap_bio'".
+
+Issues Resolved
+...............
+
+See the `PyMongo 4.12.1 release notes in JIRA`_ for the list of resolved issues
+in this release.
+
+.. _PyMongo 4.12.1 release notes in JIRA: https://jira.mongodb.org/secure/ReleaseNote.jspa?projectId=10004&version=43094
+
 Changes in Version 4.12.0 (2025/04/08)
 --------------------------------------
 
@@ -12,7 +285,7 @@ PyMongo 4.12 brings a number of changes including:
 - Support for configuring DEK cache lifetime via the ``key_expiration_ms`` argument to
   :class:`~pymongo.encryption_options.AutoEncryptionOpts`.
 - Support for $lookup in CSFLE and QE supported on MongoDB 8.1+.
-- pymongocrypt>=1.13 is now required for :ref:`In-Use Encryption` support.
+- pymongocrypt>=1.13 is now required for `In-Use Encryption <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/in-use-encryption/#in-use-encryption>`_ support.
 - Added :meth:`gridfs.asynchronous.grid_file.AsyncGridFSBucket.rename_by_name` and :meth:`gridfs.grid_file.GridFSBucket.rename_by_name`
   for more performant renaming of a file with multiple revisions.
 - Added :meth:`gridfs.asynchronous.grid_file.AsyncGridFSBucket.delete_by_name` and :meth:`gridfs.grid_file.GridFSBucket.delete_by_name`
@@ -74,7 +347,7 @@ PyMongo 4.11 brings a number of changes including:
 - Dropped support for Python 3.8 and PyPy 3.9.
 - Dropped support for MongoDB 3.6.
 - Dropped support for the MONGODB-CR authenticate mechanism, which is no longer supported by MongoDB 4.0+.
-- pymongocrypt>=1.12 is now required for :ref:`In-Use Encryption` support.
+- pymongocrypt>=1.12 is now required for `In-Use Encryption <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/in-use-encryption/#in-use-encryption>`_ support.
 - Added support for free-threaded Python with the GIL disabled. For more information see:
   `Free-threaded CPython <https://docs.python.org/3.13/whatsnew/3.13.html#whatsnew313-free-threaded-cpython>`_.
   We do not yet support free-threaded Python on Windows (`PYTHON-5027`_) or with In-Use Encryption (`PYTHON-5024`_).
@@ -196,7 +469,7 @@ PyMongo 4.9 brings a number of improvements including:
   ``sparsity`` and ``trim_factor`` are now optional in :class:`~pymongo.encryption_options.RangeOpts`.
 - Added support for the "delegated" option for the KMIP ``master_key`` in
   :meth:`~pymongo.encryption.ClientEncryption.create_data_key`.
-- pymongocrypt>=1.10 is now required for :ref:`In-Use Encryption` support.
+- pymongocrypt>=1.10 is now required for `In-Use Encryption <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/in-use-encryption/#in-use-encryption>`_ support.
 - Added :meth:`~pymongo.cursor.Cursor.to_list` to :class:`~pymongo.cursor.Cursor`,
   :class:`~pymongo.command_cursor.CommandCursor`,
   :class:`~pymongo.asynchronous.cursor.AsyncCursor`,
@@ -206,7 +479,7 @@ PyMongo 4.9 brings a number of improvements including:
   and :class:`~pymongo.asynchronous.mongo_client.AsyncMongoClient`,
   enabling users to perform insert, update, and delete operations
   against mixed namespaces in a minimized number of round trips.
-  Please see :doc:`examples/client_bulk` for more information.
+  Please see `Client Bulk Write <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/crud/bulk-write/#client-bulk-write-example>`_ for more information.
 - Added support for the ``namespace`` parameter to the
   :class:`~pymongo.operations.InsertOne`,
   :class:`~pymongo.operations.ReplaceOne`,
@@ -236,7 +509,7 @@ PyMongo 4.9 brings a number of improvements including:
   unction-as-a-service (FaaS) like AWS Lambda, Google Cloud Functions, and Microsoft Azure Functions.
   On some FaaS systems, there is a ``fork()`` operation at function
   startup.  By delaying the connection to the first operation, we avoid a deadlock.  See
-  :ref:`pymongo-fork-safe` for more information.
+  `multiple forks <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/connect/mongoclient/#multiple-forks>`_ for more information.
 
 
 Issues Resolved
@@ -343,10 +616,10 @@ PyMongo 4.7 brings a number of improvements including:
   using an OpenID Connect (OIDC) access token.
   The driver supports OIDC for workload identity, defined as an identity you assign to a software workload
   (such as an application, service, script, or container) to authenticate and access other services and resources.
-  Please see :doc:`examples/authentication` for more information.
+  Please see `Authentication <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/authentication/#authentication-mechanisms>`_ for more information.
 - Added support for Python's `native logging library <https://docs.python.org/3/howto/logging.html>`_,
   enabling developers to customize the verbosity of log messages for their applications.
-  Please see :doc:`examples/logging` for more information.
+  Please see `Logging <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/monitoring-and-logging/logging/#logging>`_ for more information.
 - Significantly improved the performance of encoding BSON documents to JSON.
 - Added support for named KMS providers for client side field level encryption.
   Previously supported KMS providers were only: aws, azure, gcp, kmip, and local.
@@ -505,7 +778,7 @@ PyMongo 4.6 brings a number of improvements including:
   "mongodb://example.com?tls=true" is now a valid URI.
 - Fixed a bug where PyMongo would incorrectly promote all cursors to exhaust cursors
   when connected to load balanced MongoDB clusters or Serverless clusters.
-- Added the :ref:`network-compression-example` documentation page.
+- Added the `network compression <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/connect/connection-options/network-compression/#compress-network-traffic>`_ documentation page.
 - Added more timeout information to network errors.
 
 Issues Resolved
@@ -530,7 +803,7 @@ PyMongo 4.5 brings a number of improvements including:
 - Added :meth:`~pymongo.database.Database.cursor_command`
   and :meth:`~pymongo.command_cursor.CommandCursor.try_next` to support
   executing an arbitrary command that returns a cursor.
-- ``cryptography`` 2.5 or later is now required for :ref:`OCSP` support.
+- ``cryptography`` 2.5 or later is now required for `OCSP <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/tls/#ocsp>`_ support.
 - Improved bson encoding and decoding performance by up to 134%(`PYTHON-3729`_, `PYTHON-3797`_, `PYTHON-3816`_, `PYTHON-3817`_, `PYTHON-3820`_, `PYTHON-3824`_, and `PYTHON-3846`_).
 
 .. warning:: PyMongo no longer supports PyPy3 versions older than 3.8. Users
@@ -591,7 +864,7 @@ PyMongo 4.4 brings a number of improvements including:
   :class:`~pymongo.encryption_options.RangeOpts`,
   and :attr:`~pymongo.encryption.Algorithm.RANGEPREVIEW` as part of the experimental
   Queryable Encryption beta.
-- pymongocrypt 1.6.0 or later is now required for :ref:`In-Use Encryption` support. MongoDB
+- pymongocrypt 1.6.0 or later is now required for `In-Use Encryption <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/in-use-encryption/#in-use-encryption>`_ support. MongoDB
   Server 7.0 introduced a backwards breaking change to the QE protocol. Users taking
   advantage of the Queryable Encryption beta must now upgrade to MongoDB 7.0+ and
   PyMongo 4.4+.
@@ -619,9 +892,9 @@ Changes in Version 4.3.3 (2022/11/17)
 
 Version 4.3.3 documents support for the following:
 
-- :ref:`CSFLE on-demand credentials` for cloud KMS providers.
+- `CSFLE on-demand credentials <https://www.mongodb.com/docs/v7.0/core/csfle/tutorials/aws/aws-automatic/?interface=driver&language=python#use-automatic-client-side-field-level-encryption-with-aws>`_ for cloud KMS providers.
-- Authentication support for :ref:`EKS Clusters`.
+- Authentication support for `EKS Clusters <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/authentication/aws-iam/#assumerolewithwebidentity>`_.
-- Added the :ref:`timeout-example` example page to improve the documentation
+- Added the `timeout <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/connect/connection-options/csot/#limit-server-execution-time>`_ example page to improve the documentation
   for :func:`pymongo.timeout`.
 
 Bug Fixes
@@ -656,7 +929,7 @@ PyMongo 4.3 brings a number of improvements including:
 
 - Added support for decoding BSON datetimes outside of the range supported
   by Python's :class:`~datetime.datetime` builtin. See
-  :ref:`handling-out-of-range-datetimes` for examples, as well as
+  `handling out of range datetimes <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/dates-and-times/#handling-out-of-range-datetimes>`_ for examples, as well as
   :class:`bson.datetime_ms.DatetimeMS`,
   :class:`bson.codec_options.DatetimeConversion`, and
   :class:`bson.codec_options.CodecOptions`'s ``datetime_conversion``
@@ -665,7 +938,7 @@ PyMongo 4.3 brings a number of improvements including:
   after a :py:func:`os.fork` to reduce the frequency of deadlocks. Note that
   deadlocks are still possible because libraries that PyMongo depends like
   OpenSSL cannot be made fork() safe in multithreaded applications.
-  (`PYTHON-2484`_). For more info see :ref:`pymongo-fork-safe`.
+  (`PYTHON-2484`_). For more info see `multiple forks <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/connect/mongoclient/#multiple-forks>`_.
 - When used with MongoDB 6.0+, :class:`~pymongo.change_stream.ChangeStream` s
   now allow for new types of events (such as DDL and C2C replication events)
   to be recorded with the new parameter ``show_expanded_events``
@@ -675,7 +948,7 @@ PyMongo 4.3 brings a number of improvements including:
   credentials expire or an error is encountered.
 - When using the ``MONGODB-AWS`` authentication mechanism with the
   ``aws`` extra, the behavior of credential fetching has changed with
-  ``pymongo_auth_aws>=1.1.0``.  Please see :doc:`examples/authentication` for
+  ``pymongo_auth_aws>=1.1.0``.  Please see `Authentication <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/authentication/#authentication-mechanisms>`_ for
   more information.
 
 Bug fixes
@@ -708,9 +981,9 @@ PyMongo 4.2 brings a number of improvements including:
 
 - Support for MongoDB 6.0.
 - Support for the Queryable Encryption beta with MongoDB 6.0. Note that backwards-breaking
-  changes may be made before the final release.  See :ref:`automatic-queryable-client-side-encryption` for example usage.
+  changes may be made before the final release.  See `automatic queryable client-side encryption <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/in-use-encryption/#queryable-encryption>`_ for example usage.
 - Provisional (beta) support for :func:`pymongo.timeout` to apply a single timeout
-  to an entire block of pymongo operations. See :ref:`timeout-example` for examples.
+  to an entire block of pymongo operations. See `timeout <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/connect/connection-options/csot/#limit-server-execution-time>`_ for examples.
 - Added the ``timeoutMS`` URI and keyword argument to :class:`~pymongo.mongo_client.MongoClient`.
 - Added the :attr:`pymongo.errors.PyMongoError.timeout` property which is ``True`` when
   the error was caused by a timeout.
@@ -758,7 +1031,7 @@ Unavoidable breaking changes
   encryption support.
 - :meth:`~pymongo.collection.Collection.estimated_document_count` now always uses
   the `count`_ command. Due to an oversight in versions 5.0.0-5.0.8 of MongoDB,
-  the count command was not included in V1 of the :ref:`versioned-api-ref`.
+  the count command was not included in V1 of the `Stable API <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/connect/connection-options/stable-api/#stable-api>`_.
   Users of the Stable API with estimated_document_count are recommended to upgrade
   their server version to 5.0.9+ or set :attr:`pymongo.server_api.ServerApi.strict`
   to ``False`` to avoid encountering errors (`PYTHON-3167`_).
@@ -821,7 +1094,7 @@ Changes in Version 4.1 (2021/12/07)
 
 PyMongo 4.1 brings a number of improvements including:
 
-- Type Hinting support (formerly provided by `pymongo-stubs`_).  See :doc:`examples/type_hints` for more information.
+- Type Hinting support (formerly provided by `pymongo-stubs`_).  See `Type Hints <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/run-command/#type-hints>`_ for more information.
 - Added support for the ``comment`` parameter to all helpers. For example see
   :meth:`~pymongo.collection.Collection.insert_one`.
 - Added support for the ``let`` parameter to
@@ -910,7 +1183,7 @@ Breaking Changes in 4.0
   :data:`bson.binary.UuidRepresentation.PYTHON_LEGACY` to
   :data:`bson.binary.UuidRepresentation.UNSPECIFIED`. Attempting to encode a
   :class:`uuid.UUID` instance to BSON or JSON now produces an error by default.
-  See :ref:`handling-uuid-data-example` for details.
+  See `UUID representations <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/uuid/#universally-unique-ids--uuids->`_ for details.
 - Removed the ``waitQueueMultiple`` keyword argument to
   :class:`~pymongo.mongo_client.MongoClient` and removed
   :exc:`pymongo.errors.ExceededMaxWaiters`.
@@ -1249,7 +1522,7 @@ Notable improvements
 
 - Added support for MongoDB 5.0.
 - Support for MongoDB Stable API, see :class:`~pymongo.server_api.ServerApi`.
-- Support for snapshot reads on secondaries (see :ref:`snapshot-reads-ref`).
+- Support for snapshot reads on secondaries (see `snapshot reads <https://www.mongodb.com/docs/manual/reference/read-concern-snapshot/#read-concern--snapshot->`_).
 - Support for Azure and GCP KMS providers for client side field level
   encryption. See the docstring for :class:`~pymongo.mongo_client.MongoClient`,
   :class:`~pymongo.encryption_options.AutoEncryptionOpts`,
@@ -1306,7 +1579,7 @@ Deprecations
   same API.
 - Deprecated the :mod:`pymongo.messeage` module.
 - Deprecated the ``ssl_keyfile`` and ``ssl_certfile`` URI options in favor
-  of ``tlsCertificateKeyFile`` (see :doc:`examples/tls`).
+  of ``tlsCertificateKeyFile`` (see `TLS <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/tls/#configure-transport-layer-security--tls->`_).
 
 .. _PYTHON-2466: https://jira.mongodb.org/browse/PYTHON-2466
 .. _PYTHON-1690: https://jira.mongodb.org/browse/PYTHON-1690
@@ -1404,12 +1677,12 @@ Changes in Version 3.11.0 (2020/07/30)
 Version 3.11 adds support for MongoDB 4.4 and includes a number of bug fixes.
 Highlights include:
 
-- Support for :ref:`OCSP` (Online Certificate Status Protocol).
+- Support for `OCSP <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/tls/#ocsp>`_ (Online Certificate Status Protocol).
 - Support for `PyOpenSSL <https://pypi.org/project/pyOpenSSL/>`_ as an
-  alternative TLS implementation. PyOpenSSL is required for :ref:`OCSP`
+  alternative TLS implementation. PyOpenSSL is required for `OCSP <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/tls/#ocsp>`_
   support. It will also be installed when using the "tls" extra if the
   version of Python in use is older than 2.7.9.
-- Support for the :ref:`MONGODB-AWS` authentication mechanism.
+- Support for the `MONGODB-AWS <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/authentication/aws-iam/#aws-identity-and-access-management>`_ authentication mechanism.
 - Support for the ``directConnection`` URI option and kwarg to
   :class:`~pymongo.mongo_client.MongoClient`.
 - Support for speculative authentication attempts in connection handshakes
@@ -1435,7 +1708,7 @@ Highlights include:
 - Added support for :data:`bson.binary.UuidRepresentation.UNSPECIFIED` and
   ``MongoClient(uuidRepresentation='unspecified')`` which will become the
   default UUID representation starting in PyMongo 4.0. See
-  :ref:`handling-uuid-data-example` for details.
+  `UUID representations <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/uuid/#universally-unique-ids--uuids->`_ for details.
 - New methods :meth:`bson.binary.Binary.from_uuid` and
   :meth:`bson.binary.Binary.as_uuid`.
 - Added the ``background`` parameter to
@@ -1519,7 +1792,7 @@ Version 3.10 includes a number of improvements and bug fixes. Highlights
 include:
 
 - Support for Client-Side Field Level Encryption with MongoDB 4.2. See
-  :doc:`examples/encryption` for examples.
+  `Client-Side Field Level Encryption <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/in-use-encryption/#client-side-field-level-encryption>`_ for examples.
 - Support for Python 3.8.
 - Added :attr:`pymongo.client_session.ClientSession.in_transaction`.
 - Do not hold the Topology lock while creating connections in a MongoClient's
@@ -1545,7 +1818,7 @@ Changes in Version 3.9.0 (2019/08/13)
 Version 3.9 adds support for MongoDB 4.2. Highlights include:
 
 - Support for MongoDB 4.2 sharded transactions. Sharded transactions have
-  the same API as replica set transactions. See :ref:`transactions-ref`.
+  the same API as replica set transactions. See `Transactions <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/crud/transactions/#transactions>`_.
 - New method :meth:`pymongo.client_session.ClientSession.with_transaction` to
   support conveniently running a transaction in a session with automatic
   retries and at-most-once semantics.
@@ -1647,8 +1920,7 @@ Changes in Version 3.8.0 (2019/04/22)
 -------------------------------------
 
 .. warning:: PyMongo no longer supports Python 2.6. RHEL 6 users should install
-  Python 2.7 or newer from `Red Hat Software Collections
+  Python 2.7 or newer from Red Hat Software Collections.
-  <https://developers.redhat.com/products/softwarecollections/overview>`_.
   CentOS 6 users should install Python 2.7 or newer from `SCL
   <https://wiki.centos.org/AdditionalResources/Repositories/SCL>`_
 
@@ -1674,7 +1946,7 @@ Changes in Version 3.8.0 (2019/04/22)
 - Custom types can now be directly encoded to, and decoded from MongoDB using
   the :class:`~bson.codec_options.TypeCodec` and
   :class:`~bson.codec_options.TypeRegistry` APIs. For more information, see
-  the :doc:`custom type example <examples/custom_type>`.
+  `Custom Types <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/data-formats/custom-types/type-codecs/#encode-data-with-type-codecs>`_.
 - Attempting a multi-document transaction on a sharded cluster now raises a
   :exc:`~pymongo.errors.ConfigurationError`.
 - :meth:`pymongo.cursor.Cursor.distinct` and
@@ -1704,7 +1976,7 @@ Changes in Version 3.8.0 (2019/04/22)
 - Iterating over a :class:`~bson.raw_bson.RawBSONDocument` now maintains the
   same field order of the underlying raw BSON document.
 - Applications can now register a custom server selector. For more information
-  see the :doc:`server selector example <examples/server_selection>`.
+  see `Customize Server Selection <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/connect/connection-options/server-selection/#customize-server-selection>`_.
 - The connection pool now implements a LIFO policy.
 
 Unavoidable breaking changes:
@@ -1772,9 +2044,9 @@ Changes in Version 3.7.0 (2018/06/26)
 Version 3.7 adds support for MongoDB 4.0. Highlights include:
 
 - Support for single replica set multi-document ACID transactions.
-  See :ref:`transactions-ref`.
+  See `transactions <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/crud/transactions/#transactions>`_.
 - Support for wire protocol compression via the new ``compressors`` URI and keyword argument to
-  :meth:`~pymongo.mongo_client.MongoClient`. See :ref:`network-compression-example` for details.
+  :meth:`~pymongo.mongo_client.MongoClient`. See `network compression <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/connect/connection-options/network-compression/#compress-network-traffic>`_ for details.
 - Support for Python 3.7.
 - New count methods, :meth:`~pymongo.collection.Collection.count_documents`
   and :meth:`~pymongo.collection.Collection.estimated_document_count`.
@@ -1795,9 +2067,9 @@ Version 3.7 adds support for MongoDB 4.0. Highlights include:
   the following features and changes allow PyMongo to function when MD5 support
   is disabled in OpenSSL by the FIPS Object Module:
 
-  - Support for the :ref:`SCRAM-SHA-256 <scram_sha_256>`
+  - Support for the `SCRAM-SHA-256 <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/authentication/scram/#scram>`_
-    authentication mechanism. The :ref:`GSSAPI <gssapi>`,
+    authentication mechanism. The `GSSAPI <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/authentication/kerberos/#kerberos--gssapi->`_,
-    :ref:`PLAIN <sasl_plain>`, and :ref:`MONGODB-X509 <mongodb_x509>`
+    `PLAIN <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/authentication/ldap/#overview>`_, and `MONGODB-X509 <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/authentication/x509/#x.509>`_
     mechanisms can also be used to avoid issues with OpenSSL in FIPS
     environments.
   - MD5 checksums are now optional in GridFS. See the ``disable_md5`` option
@@ -1815,7 +2087,7 @@ Version 3.7 adds support for MongoDB 4.0. Highlights include:
   class which is a subclass of :class:`~pymongo.change_stream.ChangeStream`.
 - SCRAM client and server keys are cached for improved performance, following
   `RFC 5802 <https://tools.ietf.org/html/rfc5802>`_.
-- If not specified, the authSource for the :ref:`PLAIN <sasl_plain>`
+- If not specified, the authSource for the `PLAIN <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/authentication/ldap/#overview>`_
   authentication mechanism defaults to $external.
 - wtimeoutMS is once again supported as a URI option.
 - When using unacknowledged write concern and connected to MongoDB server
@@ -2065,7 +2337,7 @@ Changes and Deprecations:
   consistent across all MongoDB versions.
 - In Python 3, :meth:`~bson.json_util.loads` now automatically decodes JSON
   $binary with a subtype of 0 into :class:`bytes` instead of
-  :class:`~bson.binary.Binary`. See the :doc:`/python3` for more details.
+  :class:`~bson.binary.Binary`.
 - :meth:`~bson.json_util.loads` now raises ``TypeError`` or ``ValueError``
   when parsing JSON type wrappers with values of the wrong type or any
   extra keys.
@@ -2094,7 +2366,7 @@ Highlights include:
 
 - Complete support for MongoDB 3.4:
 
-  - Unicode aware string comparison using :doc:`examples/collations`.
+  - Unicode aware string comparison using `Collation <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/crud/configure/#collation>`_.
   - Support for the new :class:`~bson.decimal128.Decimal128` BSON type.
   - A new maxStalenessSeconds read preference option.
   - A username is no longer required for the MONGODB-X509 authentication
@@ -2432,7 +2704,7 @@ In PyMongo 3.0, the ``use_greenlets`` option is gone. To use PyMongo with
 Gevent simply call ``gevent.monkey.patch_all()``.
 
 For more information,
-see :doc:`PyMongo's Gevent documentation <examples/gevent>`.
+see `Gevent <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/integrations/#gevent>`_.
 
 :class:`~pymongo.mongo_client.MongoClient` changes
 ..................................................
@@ -2476,7 +2748,7 @@ the list, and used it until a network error prompted it to re-evaluate all
 mongoses' latencies and reconnect to one of them. In PyMongo 3, the client
 monitors its network latency to all the mongoses continuously, and distributes
 operations evenly among those with the lowest latency.
-See :ref:`mongos-load-balancing` for more information.
+See `load balancing <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/connect/connection-targets/#replica-sets>`_ for more information.
 
 The client methods ``start_request``, ``in_request``, and ``end_request``
 are removed, and so is the ``auto_start_request`` option. Requests were
@@ -2484,7 +2756,7 @@ designed to make read-your-writes consistency more likely with the ``w=0``
 write concern. Additionally, a thread in a request used the same member for
 all secondary reads in a replica set. To ensure read-your-writes consistency
 in PyMongo 3.0, do not override the default write concern with ``w=0``, and
-do not override the default :ref:`read preference <secondary-reads>` of
+do not override the default `read preference <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/crud/configure/#read-and-write-settings>`_ of
 PRIMARY.
 
 Support for the ``slaveOk`` (or ``slave_okay``), ``safe``, and
@@ -2498,8 +2770,7 @@ The ``max_pool_size`` option has been removed. It is replaced by the
 ``maxPoolSize`` MongoDB URI option. ``maxPoolSize`` is now a supported URI
 option in PyMongo and can be passed as a keyword argument.
 
-The ``copy_database`` method is removed, see the
+The ``copy_database`` method is removed, see `Copy and Clone Databases <https://www.mongodb.com/docs/database-tools/mongodump/mongodump-examples/#copy-and-clone-databases>`_ for alternatives.
-:doc:`copy_database examples </examples/copydb>` for alternatives.
 
 The ``disconnect`` method is removed. Use
 :meth:`~pymongo.mongo_client.MongoClient.close` instead.
@@ -2836,7 +3107,7 @@ Version 2.9.4 fixes issues reported since the release of 2.9.3.
 - Fixed :class:`~pymongo.mongo_replica_set_client.MongoReplicaSetClient` handling of
   uuidRepresentation.
 - Fixed building and testing the documentation with python 3.x.
-- New documentation for :doc:`examples/tls` and :doc:`atlas`.
+- New documentation for `TLS <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/tls/#configure-transport-layer-security--tls->`_ and `Atlas <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/connect/connection-targets/#atlas>`_.
 
 Issues Resolved
 ...............
@@ -3075,7 +3346,7 @@ PyMongo 2.7 is a major release with a large number of new features and bug
 fixes. Highlights include:
 
 - Full support for MongoDB 2.6.
-- A new :doc:`bulk write operations API </examples/bulk>`.
+- A new `bulk write operations API <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/crud/bulk-write/#collection-bulk-write-example>`_.
 - Support for server side query timeouts using
   :meth:`~pymongo.cursor.Cursor.max_time_ms`.
 - Support for writing :meth:`~pymongo.collection.Collection.aggregate`
@@ -3086,7 +3357,7 @@ fixes. Highlights include:
   error details from the server.
 - A new GridFS :meth:`~gridfs.GridFS.find` method that returns a
   :class:`~gridfs.grid_file.GridOutCursor`.
-- Greatly improved :doc:`support for mod_wsgi </examples/mod_wsgi>` when using
+- Greatly improved `support for mod_wsgi <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/integrations/#mod_wsgi>`_ when using
   PyMongo's C extensions. Read `Jesse's blog post
   <https://emptysqua.re/blog/python-c-extensions-and-mod-wsgi/>`_ for details.
 - Improved C extension support for ARM little endian.
@@ -3166,14 +3437,14 @@ Important new features:
   ``waitQueueTimeoutMS`` is set, an operation that blocks waiting for a socket
   will raise :exc:`~pymongo.errors.ConnectionFailure` after the timeout. By
   default ``waitQueueTimeoutMS`` is not set.
-  See :ref:`connection-pooling` for more information.
+  See `connection pooling <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/connect/connection-options/connection-pools/#connection-pools>`_ for more information.
 - The :meth:`~pymongo.collection.Collection.insert` method automatically splits
   large batches of documents into multiple insert messages based on
   :attr:`~pymongo.mongo_client.MongoClient.max_message_size`
 - Support for the exhaust cursor flag.
   See :meth:`~pymongo.collection.Collection.find` for details and caveats.
 - Support for the PLAIN and MONGODB-X509 authentication mechanisms.
-  See :doc:`the authentication docs </examples/authentication>` for more
+  See `the authentication docs <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/authentication/#authentication-mechanisms>`_ for more
   information.
 - Support aggregation output as a :class:`~pymongo.cursor.Cursor`. See
   :meth:`~pymongo.collection.Collection.aggregate` for details.
@@ -3186,7 +3457,7 @@ Important new features:
   to having a ``max_pool_size`` larger than necessary. Err towards a larger
   value.) If your application accepts the default, continue to do so.
 
-  See :ref:`connection-pooling` for more information.
+  See `connection pooling <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/connect/connection-options/connection-pools/#connection-pools>`_ for more information.
 
 Issues Resolved
 ...............
@@ -3232,7 +3503,7 @@ Version 2.5 includes changes to support new features in MongoDB 2.4.
 
 Important new features:
 
-- Support for :ref:`GSSAPI (Kerberos) authentication <gssapi>`.
+- Support for `GSSAPI (Kerberos) <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/security/authentication/kerberos/#kerberos--gssapi->`_.
 - Support for SSL certificate validation with hostname matching.
 - Support for delegated and role based authentication.
 - New GEOSPHERE (2dsphere) and HASHED index constants.
@@ -3339,7 +3610,7 @@ Version 2.3 adds support for new features and behavior changes in MongoDB
 Important New Features:
 
 - Support for expanded read preferences including directing reads to tagged
-  servers - See :ref:`secondary-reads` for more information.
+  servers - See `secondary reads <https://www.mongodb.com/docs/manual/core/read-preference/#mongodb-readmode-secondary>`_ for more information.
 - Support for mongos failover.
 - A new :meth:`~pymongo.collection.Collection.aggregate` method to support
   MongoDB's new `aggregation framework
@@ -3393,10 +3664,10 @@ to this release.
 
 Important New Features:
 
-- Support for Python 3 -
+- Support for Python 3.
-  See the :doc:`python3` for more information.
+  See `Python 3 <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/reference/upgrade/#upgrade-pymongo-versions>`_ for more information.
 - Support for Gevent -
-  See :doc:`examples/gevent` for more information.
+  See `Gevent <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/integrations/#gevent>`_ for more information.
 - Improved connection pooling.
   See `PYTHON-287 <https://jira.mongodb.org/browse/PYTHON-287>`_.
 
@@ -4002,7 +4273,7 @@ Other changes:
 - clean up all cases where :class:`~pymongo.errors.ConnectionFailure`
   is raised.
 - simplification of connection pooling - makes driver ~2x faster for
-  simple benchmarks. see :ref:`connection-pooling` for more information.
+  simple benchmarks. see `connection pooling <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/connect/connection-options/connection-pools/#connection-pools>`_ for more information.
 - DEPRECATED ``pool_size``, ``auto_start_request`` and ``timeout``
   parameters to :class:`~pymongo.connection.Connection`. DEPRECATED
   :meth:`~pymongo.connection.Connection.start_request`.
@@ -4069,7 +4340,7 @@ Changes in Version 1.2 (2009/12/09)
   get around some issues with queries on fields named ``query``
 - enforce 4MB document limit on the client side
 - added :meth:`~pymongo.collection.Collection.map_reduce` helper - see
-  :doc:`example <examples/aggregation>`
+  `Aggregation <https://www.mongodb.com/docs/languages/python/pymongo-driver/current/aggregation/#transform-your-data-with-aggregation>`_
 - added :meth:`~pymongo.cursor.Cursor.distinct` method on
   :class:`~pymongo.cursor.Cursor` instances to allow distinct with
   queries

doc/common-issues.rst

@@ -1,96 +0,0 @@
-Frequently Encountered Issues
-=============================
-
-Also see the :ref:`TLSErrors` section.
-
-Server reports wire version X, PyMongo requires Y
--------------------------------------------------
-
-When one attempts to connect to a <=3.6 version server, PyMongo will throw the following error::
-
-  >>> client.admin.command('ping')
-  ...
-  pymongo.errors.ConfigurationError: Server at localhost:27017 reports wire version 6, but this version of PyMongo requires at least 7 (MongoDB 4.0).
-
-This is caused by the driver being too new for the server it is being run against.
-To resolve this issue either upgrade your database to version >= 4.0 or downgrade to an early version of PyMongo which supports MongoDB < 4.0.
-
-
-'Cursor' object has no attribute '_Cursor__killed'
---------------------------------------------------
-
-On versions of PyMongo <3.9, when supplying invalid arguments the constructor of Cursor,
-there will be a TypeError raised, and an AttributeError printed to ``stderr``. The AttributeError is not relevant,
-instead look at the TypeError for debugging information::
-
-  >>> coll.find(wrong=1)
-  Exception ignored in: <function Cursor.__del__ at 0x1048129d8>
-  ...
-  AttributeError: 'Cursor' object has no attribute '_Cursor__killed'
-  ...
-  TypeError: __init__() got an unexpected keyword argument 'wrong'
-
-To fix this, make sure that you are supplying the correct keyword arguments.
-In addition, you can also upgrade to PyMongo >=3.9, which will remove the spurious error.
-
-
-MongoClient fails ConfigurationError
-------------------------------------
-
-This is a common issue stemming from using incorrect keyword argument names.
-
-  >>> client = MongoClient(wrong=1)
-  ...
-  pymongo.errors.ConfigurationError: Unknown option wrong
-
-To fix this, check your spelling and make sure that the keyword argument you are specifying exists.
-
-
-DeprecationWarning: count is deprecated
----------------------------------------
-
-PyMongo no longer supports :meth:`pymongo.cursor.count`.
-Instead, use :meth:`pymongo.collection.count_documents`::
-
-  >>> client = MongoClient()
-  >>> d = datetime.datetime(2009, 11, 12, 12)
-  >>> list(client.db.coll.find({"date": {"$lt": d}}, limit=2))
-  [{'_id': ObjectId('6247b058cebb8b179b7039f8'), 'date': datetime.datetime(1, 1, 1, 0, 0)}, {'_id': ObjectId('6247b059cebb8b179b7039f9'), 'date': datetime.datetime(1, 1, 1, 0, 0)}]
-  >>> client.db.coll.count_documents({"date": {"$lt": d}}, limit=2)
-  2
-
-Note that this is NOT the same as ``Cursor.count_documents`` (which does not exist),
-this is a method of the Collection class, so you must call it on a collection object
-or you will receive the following error::
-
-  >>> Cursor(MongoClient().db.coll).count()
-  Traceback (most recent call last):
-    File "<stdin>", line 1, in <module>
-  AttributeError: 'Cursor' object has no attribute 'count'
-  >>>
-
-Timeout when accessing MongoDB from PyMongo with tunneling
-----------------------------------------------------------
-
-When attempting to connect to a replica set MongoDB instance over an SSH tunnel you
-will receive the following error::
-
-  File "/Library/Python/2.7/site-packages/pymongo/collection.py", line 1560, in count
-    return self._count(cmd, collation, session)
-    File "/Library/Python/2.7/site-packages/pymongo/collection.py", line 1504, in _count
-    with self._socket_for_reads() as (connection, slave_ok):
-    File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/contextlib.py", line 17, in __enter__
-    return self.gen.next()
-    File "/Library/Python/2.7/site-packages/pymongo/mongo_client.py", line 982, in _socket_for_reads
-    server = topology.select_server(read_preference)
-    File "/Library/Python/2.7/site-packages/pymongo/topology.py", line 224, in select_server
-    address))
-    File "/Library/Python/2.7/site-packages/pymongo/topology.py", line 183, in select_servers
-    selector, server_timeout, address)
-    File "/Library/Python/2.7/site-packages/pymongo/topology.py", line 199, in _select_servers_loop
-    self._error_message(selector))
-  pymongo.errors.ServerSelectionTimeoutError: localhost:27017: timed out
-
-This is due to the fact that PyMongo discovers replica set members using the response from the isMaster command which
-then contains the address and ports of the other members. However, these addresses and ports will not be accessible through the SSH tunnel. Thus, this behavior is unsupported.
-You can, however, connect directly to a single MongoDB node using the directConnection=True option with SSH tunneling.

doc/compatibility-policy.rst

@@ -1,62 +0,0 @@
-Compatibility Policy
-====================
-
-Semantic Versioning
--------------------
-
-PyMongo's version numbers follow `semantic versioning`_: each version number
-is structured "major.minor.patch". Patch releases fix bugs, minor releases
-add features (and may fix bugs), and major releases include API changes that
-break backwards compatibility (and may add features and fix bugs).
-
-Deprecation
------------
-
-Before we remove a feature in a major release, PyMongo's maintainers make an
-effort to release at least one minor version that *deprecates* it. We add
-"**DEPRECATED**" to the feature's documentation, and update the code to raise a
-`DeprecationWarning`_. You can ensure your code is future-proof by running
-your code with the latest PyMongo release and looking for DeprecationWarnings.
-
-The interpreter silences DeprecationWarnings by default. For example, the
-following code uses the deprecated ``insert`` method but does not raise any
-warning:
-
-.. code-block:: python
-
-    # "insert.py" (with PyMongo 3.X)
-    from pymongo import MongoClient
-
-    client = MongoClient()
-    client.test.test.insert({})
-
-To print deprecation warnings to stderr, run python with "-Wd"::
-
-  $ python3 -Wd insert.py
-  insert.py:4: DeprecationWarning: insert is deprecated. Use insert_one or insert_many instead.
-    client.test.test.insert({})
-
-You can turn warnings into exceptions with "python -We"::
-
-  $ python3 -We insert.py
-  Traceback (most recent call last):
-    File "insert.py", line 4, in <module>
-      client.test.test.insert({})
-    File "/home/durin/work/mongo-python-driver/pymongo/collection.py", line 2906, in insert
-      "instead.", DeprecationWarning, stacklevel=2)
-  DeprecationWarning: insert is deprecated. Use insert_one or insert_many instead.
-
-If your own code's test suite passes with "python -We" then it uses no
-deprecated PyMongo features.
-
-.. seealso:: The Python documentation on `the warnings module`_,
-   and `the -W command line option`_.
-
-.. _semantic versioning: https://semver.org/
-
-.. _DeprecationWarning:
-  https://docs.python.org/3/library/exceptions.html#DeprecationWarning
-
-.. _the warnings module: https://docs.python.org/3/library/warnings.html
-
-.. _the -W command line option: https://docs.python.org/3/using/cmdline.html#cmdoption-W

doc/conf.py

@@ -82,15 +82,23 @@ pygments_style = "sphinx"
 # Options for link checking
 # The anchors on the rendered markdown page are created after the fact,
 # so those link results in a 404.
-# wiki.centos.org has been flakey.
+# wiki.centos.org has been flaky.
 # sourceforge.net is giving a 403 error, but is still accessible from the browser.
+# Links to release notes in jira give 401 error: unauthorized. PYTHON-5585
 linkcheck_ignore = [
     "https://github.com/mongodb/specifications/blob/master/source/server-discovery-and-monitoring/server-monitoring.md#requesting-an-immediate-check",
+    "https://github.com/mongodb/specifications/blob/master/source/transactions-convenient-api/transactions-convenient-api.md#handling-errors-inside-the-callback",
+    "https://github.com/mongodb/specifications/blob/master/source/uri-options/uri-options.md",
+    "https://github.com/mongodb/specifications/blob/master/source/uri-options/uri-options.md",
     "https://github.com/mongodb/libmongocrypt/blob/master/bindings/python/README.rst#installing-from-source",
     r"https://wiki.centos.org/[\w/]*",
     r"https://sourceforge.net/",
+    r"https://jira\.mongodb\.org/secure/ReleaseNote\.jspa.*",
 ]
 
+# Allow for flaky links.
+linkcheck_retries = 3
+
 # -- Options for extensions ----------------------------------------------------
 autoclass_content = "init"
 
@@ -105,6 +113,7 @@ from pymongo.mongo_client import MongoClient
 client = MongoClient()
 client.drop_database("doctest_test")
 db = client.doctest_test
+server_major_version = int(client.server_info()['version'].split()[-1][0])
 """
 
 # -- Options for HTML output ---------------------------------------------------
@@ -179,8 +188,8 @@ latex_documents = [
     ("index", "PyMongo.tex", "PyMongo Documentation", "Michael Dirolf", "manual"),
 ]
 
-# The name of an image file (relative to this directory) to place at the top of
+# The name of an image file (relative to this directory) to place at the top
-# the title page.
+# of the title page.
 # latex_logo = None
 
 # For "manual" documents, if this is true, then toplevel headings are parts,

doc/contributors.rst

@@ -103,3 +103,8 @@ The following is a list of people who have contributed to
 - Terry Patterson
 - Romain Morotti
 - Navjot Singh (navjots18)
+- Jib Adegunloye (Jibola)
+- Jeffrey A. Clark (aclark4life)
+- Steven Silvester (blink1073)
+- Noah Stapp (NoahStapp)
+- Cal Jacobson (cj81499)

doc/developer/index.rst

@@ -1,9 +0,0 @@
-Developer Guide
-===============
-
-Technical guide for contributors to PyMongo.
-
-.. toctree::
-   :maxdepth: 1
-
-   periodic_executor

doc/developer/periodic_executor.rst

@@ -1,113 +0,0 @@
-Periodic Executors
-==================
-
-.. currentmodule:: pymongo
-
-PyMongo implements a :class:`~periodic_executor.PeriodicExecutor` for two
-purposes: as the background thread for :class:`~monitor.Monitor`, and to
-regularly check if there are ``OP_KILL_CURSORS`` messages that must be sent to the server.
-
-Killing Cursors
----------------
-
-An incompletely iterated :class:`~cursor.Cursor` on the client represents an
-open cursor object on the server. In code like this, we lose a reference to
-the cursor before finishing iteration::
-
-    for doc in collection.find():
-        raise Exception()
-
-We try to send an ``OP_KILL_CURSORS`` to the server to tell it to clean up the
-server-side cursor. But we must not take any locks directly from the cursor's
-destructor (see `PYTHON-799`_), so we cannot safely use the PyMongo data
-structures required to send a message. The solution is to add the cursor's id
-to an array on the :class:`~mongo_client.MongoClient` without taking any locks.
-
-Each client has a :class:`~periodic_executor.PeriodicExecutor` devoted to
-checking the array for cursor ids. Any it sees are the result of cursors that
-were freed while the server-side cursor was still open. The executor can safely
-take the locks it needs in order to send the ``OP_KILL_CURSORS`` message.
-
-.. _PYTHON-799: https://jira.mongodb.org/browse/PYTHON-799
-
-Stopping Executors
-------------------
-
-Just as :class:`~cursor.Cursor` must not take any locks from its destructor,
-neither can :class:`~mongo_client.MongoClient` and :class:`~topology.Topology`.
-Thus, although the client calls :meth:`close` on its kill-cursors thread, and
-the topology calls :meth:`close` on all its monitor threads, the :meth:`close`
-method cannot actually call :meth:`wake` on the executor, since :meth:`wake`
-takes a lock.
-
-Instead, executors wake periodically to check if ``self.close`` is set,
-and if so they exit.
-
-A thread can log spurious errors if it wakes late in the Python interpreter's
-shutdown sequence, so we try to join threads before then. Each periodic
-executor (either a monitor or a kill-cursors thread) adds a weakref to itself
-to a set called ``_EXECUTORS``, in the ``periodic_executor`` module.
-
-An `exit handler`_ runs on shutdown and tells all executors to stop, then
-tries (with a short timeout) to join all executor threads.
-
-.. _exit handler: https://docs.python.org/2/library/atexit.html
-
-Monitoring
-----------
-
-For each server in the topology, :class:`~topology.Topology` uses a periodic
-executor to launch a monitor thread. This thread must not prevent the topology
-from being freed, so it weakrefs the topology. Furthermore, it uses a weakref
-callback to terminate itself soon after the topology is freed.
-
-Solid lines represent strong references, dashed lines weak ones:
-
-.. generated with graphviz: "dot -Tpng periodic-executor-refs.dot > periodic-executor-refs.png"
-
-.. image:: ../static/periodic-executor-refs.png
-
-See `Stopping Executors`_ above for an explanation of the ``_EXECUTORS`` set.
-
-It is a requirement of the `Server Discovery And Monitoring Spec`_ that a
-sleeping monitor can be awakened early. Aside from infrequent wakeups to do
-their appointed chores, and occasional interruptions, periodic executors also
-wake periodically to check if they should terminate.
-
-Our first implementation of this idea was the obvious one: use the Python
-standard library's threading.Condition.wait with a timeout. Another thread
-wakes the executor early by signaling the condition variable.
-
-A topology cannot signal the condition variable to tell the executor to
-terminate, because it would risk a deadlock in the garbage collector: no
-destructor or weakref callback can take a lock to signal the condition variable
-(see `PYTHON-863`_); thus the only way for a dying object to terminate a
-periodic executor is to set its "stopped" flag and let the executor see the
-flag next time it wakes.
-
-We erred on the side of prompt cleanup, and set the check interval at 100ms. We
-assumed that checking a flag and going back to sleep 10 times a second was
-cheap on modern machines.
-
-Starting in Python 3.2, the builtin C implementation of lock.acquire takes a
-timeout parameter, so Python 3.2+ Condition variables sleep simply by calling
-lock.acquire; they are implemented as efficiently as expected.
-
-But in Python 2, lock.acquire has no timeout. To wait with a timeout, a Python
-2 condition variable sleeps a millisecond, tries to acquire the lock, sleeps
-twice as long, and tries again. This exponential backoff reaches a maximum
-sleep time of 50ms.
-
-If PyMongo calls the condition variable's "wait" method with a short timeout,
-the exponential backoff is restarted frequently. Overall, the condition variable
-is not waking a few times a second, but hundreds of times. (See `PYTHON-983`_.)
-
-Thus the current design of periodic executors is surprisingly simple: they
-do a simple ``time.sleep`` for a half-second, check if it is time to wake or
-terminate, and sleep again.
-
-.. _Server Discovery And Monitoring Spec: https://github.com/mongodb/specifications/blob/master/source/server-discovery-and-monitoring/server-monitoring.md#requesting-an-immediate-check
-
-.. _PYTHON-863: https://jira.mongodb.org/browse/PYTHON-863
-
-.. _PYTHON-983: https://jira.mongodb.org/browse/PYTHON-983

doc/examples/aggregation.rst

@@ -1,90 +0,0 @@
-Aggregation Examples
-====================
-
-There are several methods of performing aggregations in MongoDB.  These
-examples cover the new aggregation framework, using map reduce and using the
-group method.
-
-.. testsetup::
-
-  from pymongo import MongoClient
-
-  client = MongoClient()
-  client.drop_database("aggregation_example")
-
-Setup
------
-To start, we'll insert some example data which we can perform
-aggregations on:
-
-.. doctest::
-
-  >>> from pymongo import MongoClient
-  >>> db = MongoClient().aggregation_example
-  >>> result = db.things.insert_many(
-  ...     [
-  ...         {"x": 1, "tags": ["dog", "cat"]},
-  ...         {"x": 2, "tags": ["cat"]},
-  ...         {"x": 2, "tags": ["mouse", "cat", "dog"]},
-  ...         {"x": 3, "tags": []},
-  ...     ]
-  ... )
-  >>> result.inserted_ids
-  [ObjectId('...'), ObjectId('...'), ObjectId('...'), ObjectId('...')]
-
-.. _aggregate-examples:
-
-Aggregation Framework
----------------------
-
-This example shows how to use the
-:meth:`~pymongo.collection.Collection.aggregate` method to use the aggregation
-framework.  We'll perform a simple aggregation to count the number of
-occurrences for each tag in the ``tags`` array, across the entire collection.
-To achieve this we need to pass in three operations to the pipeline.
-First, we need to unwind the ``tags`` array, then group by the tags and
-sum them up, finally we sort by count.
-
-Python dictionaries prior to 3.7 don't maintain order. You should use :class:`~bson.son.SON`
-or :class:`collections.OrderedDict` where explicit ordering is required for an older Python version
-eg "$sort":
-
-.. note::
-
-    aggregate requires server version **>= 2.1.0**.
-
-.. doctest::
-
-  >>> from bson.son import SON
-  >>> pipeline = [
-  ...     {"$unwind": "$tags"},
-  ...     {"$group": {"_id": "$tags", "count": {"$sum": 1}}},
-  ...     {"$sort": SON([("count", -1), ("_id", -1)])},
-  ... ]
-  >>> import pprint
-  >>> pprint.pprint(list(db.things.aggregate(pipeline)))
-  [{'_id': 'cat', 'count': 3},
-   {'_id': 'dog', 'count': 2},
-   {'_id': 'mouse', 'count': 1}]
-
-To run an explain plan for this aggregation use
-`PyMongoExplain <https://pypi.org/project/pymongoexplain/>`_,
-a companion library for PyMongo. It allows you to explain any CRUD operation
-by providing a few convenience classes::
-
-  >>> from pymongoexplain import ExplainableCollection
-  >>> ExplainableCollection(collection).aggregate(pipeline)
-  {'ok': 1.0, 'queryPlanner': [...]}
-
-Or, use the :meth:`~pymongo.database.Database.command` method::
-
-  >>> db.command('aggregate', 'things', pipeline=pipeline, explain=True)
-  {'ok': 1.0, 'stages': [...]}
-
-As well as simple aggregations the aggregation framework provides projection
-capabilities to reshape the returned data. Using projections and aggregation,
-you can add computed fields, create new virtual sub-objects, and extract
-sub-fields into the top-level of results.
-
-.. seealso:: The full documentation for MongoDB's `aggregation framework
-    <https://mongodb.com/docs/manual/applications/aggregation>`_

doc/examples/authentication.rst

@@ -1,528 +0,0 @@
-Authentication Examples
-=======================
-
-MongoDB supports several different authentication mechanisms. These examples
-cover all authentication methods currently supported by PyMongo, documenting
-Python module and MongoDB version dependencies.
-
-.. _percent escaped:
-
-Percent-Escaping Username and Password
---------------------------------------
-
-Username and password must be percent-escaped with
-:py:func:`urllib.parse.quote_plus`, to be used in a MongoDB URI. For example::
-
-  >>> from pymongo import MongoClient
-  >>> import urllib.parse
-  >>> username = urllib.parse.quote_plus('user')
-  >>> username
-  'user'
-  >>> password = urllib.parse.quote_plus('pass/word')
-  >>> password
-  'pass%2Fword'
-  >>> MongoClient('mongodb://%s:%s@127.0.0.1' % (username, password))
-  ...
-
-.. _scram_sha_256:
-
-SCRAM-SHA-256 (RFC 7677)
-------------------------
-.. versionadded:: 3.7
-
-SCRAM-SHA-256 is the default authentication mechanism supported by a cluster
-configured for authentication with MongoDB 4.0 or later. Authentication
-requires a username, a password, and a database name. The default database
-name is "admin", this can be overridden with the ``authSource`` option.
-Credentials can be specified as arguments to
-:class:`~pymongo.mongo_client.MongoClient`::
-
-  >>> from pymongo import MongoClient
-  >>> client = MongoClient('example.com',
-  ...                      username='user',
-  ...                      password='password',
-  ...                      authSource='the_database',
-  ...                      authMechanism='SCRAM-SHA-256')
-
-Or through the MongoDB URI::
-
-  >>> uri = "mongodb://user:password@example.com/?authSource=the_database&authMechanism=SCRAM-SHA-256"
-  >>> client = MongoClient(uri)
-
-SCRAM-SHA-1 (RFC 5802)
-----------------------
-.. versionadded:: 2.8
-
-SCRAM-SHA-1 is the default authentication mechanism supported by a cluster
-configured for authentication with MongoDB 3.0 or later. Authentication
-requires a username, a password, and a database name. The default database
-name is "admin", this can be overridden with the ``authSource`` option.
-Credentials can be specified as arguments to
-:class:`~pymongo.mongo_client.MongoClient`::
-
-  >>> from pymongo import MongoClient
-  >>> client = MongoClient('example.com',
-  ...                      username='user',
-  ...                      password='password',
-  ...                      authSource='the_database',
-  ...                      authMechanism='SCRAM-SHA-1')
-
-Or through the MongoDB URI::
-
-  >>> uri = "mongodb://user:password@example.com/?authSource=the_database&authMechanism=SCRAM-SHA-1"
-  >>> client = MongoClient(uri)
-
-For best performance on Python versions older than 2.7.8 install `backports.pbkdf2`_.
-
-.. _backports.pbkdf2: https://pypi.python.org/pypi/backports.pbkdf2/
-
-Default Authentication Mechanism
---------------------------------
-
-If no mechanism is specified, PyMongo automatically negotiates the mechanism to use (SCRAM-SHA-1
-or SCRAM-SHA-256) with the MongoDB server.
-
-Default Database and "authSource"
----------------------------------
-
-You can specify both a default database and the authentication database in the
-URI::
-
-    >>> uri = "mongodb://user:password@example.com/default_db?authSource=admin"
-    >>> client = MongoClient(uri)
-
-PyMongo will authenticate on the "admin" database, but the default database
-will be "default_db"::
-
-    >>> # get_database with no "name" argument chooses the DB from the URI
-    >>> db = MongoClient(uri).get_database()
-    >>> print(db.name)
-    'default_db'
-
-.. _mongodb_x509:
-
-MONGODB-X509
-------------
-.. versionadded:: 2.6
-
-The MONGODB-X509 mechanism authenticates via the X.509 certificate presented
-by the driver during TLS/SSL negotiation. This authentication method requires
-the use of TLS/SSL connections with certificate validation::
-
-  >>> from pymongo import MongoClient
-  >>> client = MongoClient('example.com',
-  ...                      authMechanism="MONGODB-X509",
-  ...                      tls=True,
-  ...                      tlsCertificateKeyFile='/path/to/client.pem',
-  ...                      tlsCAFile='/path/to/ca.pem')
-
-MONGODB-X509 authenticates against the $external virtual database, so you
-do not have to specify a database in the URI::
-
-  >>> uri = "mongodb://example.com/?authMechanism=MONGODB-X509"
-  >>> client = MongoClient(uri,
-  ...                      tls=True,
-  ...                      tlsCertificateKeyFile='/path/to/client.pem',
-  ...                      tlsCAFile='/path/to/ca.pem')
-  >>>
-
-.. _gssapi:
-
-GSSAPI (Kerberos)
------------------
-.. versionadded:: 2.5
-
-GSSAPI (Kerberos) authentication is available in the Enterprise Edition of
-MongoDB.
-
-Unix
-~~~~
-
-To authenticate using GSSAPI you must first install the python `kerberos`_ or
-`pykerberos`_ module using pip. Make sure you run kinit before
-using the following authentication methods::
-
-  $ kinit mongodbuser@EXAMPLE.COM
-  mongodbuser@EXAMPLE.COM's Password:
-  $ klist
-  Credentials cache: FILE:/tmp/krb5cc_1000
-          Principal: mongodbuser@EXAMPLE.COM
-
-    Issued                Expires               Principal
-  Feb  9 13:48:51 2013  Feb  9 23:48:51 2013  krbtgt/EXAMPLE.COM@EXAMPLE.COM
-
-Now authenticate using the MongoDB URI. GSSAPI authenticates against the
-$external virtual database so you do not have to specify a database in the
-URI::
-
-  >>> # Note: the kerberos principal must be url encoded.
-  >>> from pymongo import MongoClient
-  >>> uri = "mongodb://mongodbuser%40EXAMPLE.COM@mongo-server.example.com/?authMechanism=GSSAPI"
-  >>> client = MongoClient(uri)
-  >>>
-
-The default service name used by MongoDB and PyMongo is ``mongodb``. You can
-specify a custom service name with the ``authMechanismProperties`` option::
-
-  >>> from pymongo import MongoClient
-  >>> uri = "mongodb://mongodbuser%40EXAMPLE.COM@mongo-server.example.com/?authMechanism=GSSAPI&authMechanismProperties=SERVICE_NAME:myservicename"
-  >>> client = MongoClient(uri)
-
-Windows (SSPI)
-~~~~~~~~~~~~~~
-.. versionadded:: 3.3
-
-First install the `winkerberos`_ module. Unlike authentication on Unix kinit is
-not used. If the user to authenticate is different from the user that owns the
-application process provide a password to authenticate::
-
-  >>> uri = "mongodb://mongodbuser%40EXAMPLE.COM:mongodbuserpassword@example.com/?authMechanism=GSSAPI"
-
-Two extra ``authMechanismProperties`` are supported on Windows platforms:
-
-- CANONICALIZE_HOST_NAME - Uses the fully qualified domain name (FQDN) of the
-  MongoDB host for the server principal (GSSAPI libraries on Unix do this by
-  default)::
-
-    >>> uri = "mongodb://mongodbuser%40EXAMPLE.COM@example.com/?authMechanism=GSSAPI&authMechanismProperties=CANONICALIZE_HOST_NAME:true"
-
-- SERVICE_REALM - This is used when the user's realm is different from the service's realm::
-
-    >>> uri = "mongodb://mongodbuser%40EXAMPLE.COM@example.com/?authMechanism=GSSAPI&authMechanismProperties=SERVICE_REALM:otherrealm"
-
-
-.. _kerberos: https://pypi.python.org/pypi/kerberos
-.. _pykerberos: https://pypi.python.org/pypi/pykerberos
-.. _winkerberos: https://pypi.python.org/pypi/winkerberos/
-
-.. _sasl_plain:
-
-SASL PLAIN (RFC 4616)
----------------------
-.. versionadded:: 2.6
-
-MongoDB Enterprise Edition version 2.6 and newer support the SASL PLAIN
-authentication mechanism, initially intended for delegating authentication
-to an LDAP server. These examples use the $external virtual database for LDAP support::
-
-  >>> from pymongo import MongoClient
-  >>> uri = "mongodb://user:password@example.com/?authMechanism=PLAIN"
-  >>> client = MongoClient(uri)
-  >>>
-
-SASL PLAIN is a clear-text authentication mechanism. We **strongly** recommend
-that you connect to MongoDB using TLS/SSL with certificate validation when
-using the SASL PLAIN mechanism::
-
-  >>> from pymongo import MongoClient
-  >>> uri = "mongodb://user:password@example.com/?authMechanism=PLAIN"
-  >>> client = MongoClient(uri,
-  ...                      tls=True,
-  ...                      tlsCertificateKeyFile='/path/to/client.pem',
-  ...                      tlsCAFile='/path/to/ca.pem')
-  >>>
-
-.. _MONGODB-AWS:
-
-MONGODB-AWS
------------
-.. versionadded:: 3.11
-
-The MONGODB-AWS authentication mechanism is available in MongoDB 4.4+ and
-requires extra pymongo dependencies. To use it, install pymongo with the
-``aws`` extra::
-
-  $ python -m pip install 'pymongo[aws]'
-
-The MONGODB-AWS mechanism authenticates using AWS IAM credentials (an access
-key ID and a secret access key), `temporary AWS IAM credentials`_ obtained
-from an `AWS Security Token Service (STS)`_ `Assume Role`_ request,
-AWS Lambda `environment variables`_, or temporary AWS IAM credentials assigned
-to an `EC2 instance`_ or ECS task. The use of temporary credentials, in
-addition to an access key ID and a secret access key, also requires a
-security (or session) token.
-
-Credentials can be configured through the MongoDB URI, environment variables,
-or the local EC2 or ECS endpoint. The order in which the client searches for
-`credentials`_ is the same as the one used by the AWS ``boto3`` library
-when using ``pymongo_auth_aws>=1.1.0``.
-
-Because we are now using ``boto3`` to handle credentials, the order and
-locations of credentials are slightly different from before.  Particularly,
-if you have a shared AWS credentials or config file,
-then those credentials will be used by default if AWS auth environment
-variables are not set.  To override this behavior, set
-``AWS_SHARED_CREDENTIALS_FILE=""`` in your shell or add
-``os.environ["AWS_SHARED_CREDENTIALS_FILE"] = ""`` to your script or
-application.  Alternatively, you can create an AWS profile specifically for
-your MongoDB credentials and set ``AWS_PROFILE`` to that profile name.
-
-MONGODB-AWS authenticates against the "$external" virtual database, so none of
-the URIs in this section need to include the ``authSource`` URI option.
-
-.. _credentials: https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html
-
-AWS IAM credentials
-~~~~~~~~~~~~~~~~~~~
-
-Applications can authenticate using AWS IAM credentials by providing a valid
-access key id and secret access key pair as the username and password,
-respectively, in the MongoDB URI. A sample URI would be::
-
-  >>> from pymongo import MongoClient
-  >>> uri = "mongodb+srv://<access_key_id>:<secret_access_key>@example.mongodb.net/?authMechanism=MONGODB-AWS"
-  >>> client = MongoClient(uri)
-
-.. note:: The access_key_id and secret_access_key passed into the URI MUST
-          be `percent escaped`_.
-
-AssumeRole
-~~~~~~~~~~
-
-Applications can authenticate using temporary credentials returned from an
-assume role request. These temporary credentials consist of an access key
-ID, a secret access key, and a security token passed into the URI.
-A sample URI would be::
-
-  >>> from pymongo import MongoClient
-  >>> uri = "mongodb+srv://<access_key_id>:<secret_access_key>@example.mongodb.net/?authMechanism=MONGODB-AWS&authMechanismProperties=AWS_SESSION_TOKEN:<session_token>"
-  >>> client = MongoClient(uri)
-
-.. note:: The access_key_id, secret_access_key, and session_token passed into
-          the URI MUST be `percent escaped`_.
-
-
-AWS Lambda (Environment Variables)
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-When the username and password are not provided and the MONGODB-AWS mechanism
-is set, the client will fallback to using the `environment variables`_
-``AWS_ACCESS_KEY_ID``, ``AWS_SECRET_ACCESS_KEY``, and ``AWS_SESSION_TOKEN``
-for the access key ID, secret access key, and session token, respectively::
-
-  $ export AWS_ACCESS_KEY_ID=<access_key_id>
-  $ export AWS_SECRET_ACCESS_KEY=<secret_access_key>
-  $ export AWS_SESSION_TOKEN=<session_token>
-  $ python
-  >>> from pymongo import MongoClient
-  >>> uri = "mongodb+srv://example.mongodb.net/?authMechanism=MONGODB-AWS"
-  >>> client = MongoClient(uri)
-
-.. note:: No username, password, or session token is passed into the URI.
-          PyMongo will use credentials set via the environment variables.
-          These environment variables MUST NOT be `percent escaped`_.
-
-
-.. _EKS Clusters:
-
-EKS Clusters
-~~~~~~~~~~~~
-
-Applications using the `Authenticating users for your cluster from an OpenID Connect identity provider <https://docs.aws.amazon.com/eks/latest/userguide/authenticate-oidc-identity-provider.html>`_ capability on EKS can now
-use the provided credentials, by giving the associated IAM User
-`sts:AssumeRoleWithWebIdentity <https://docs.aws.amazon.com/STS/latest/APIReference/API_AssumeRoleWithWebIdentity.html>`_
-permission.
-
-When the username and password are not provided, the MONGODB-AWS mechanism
-is set, and ``AWS_WEB_IDENTITY_TOKEN_FILE``, ``AWS_ROLE_ARN``, and
-optional ``AWS_ROLE_SESSION_NAME`` are available, the driver will use
-an ``AssumeRoleWithWebIdentity`` call to retrieve temporary credentials.
-The application must be using ``pymongo_auth_aws`` >= 1.1.0 for EKS support.
-
-ECS Container
-~~~~~~~~~~~~~
-
-Applications can authenticate from an ECS container via temporary
-credentials assigned to the machine. A sample URI on an ECS container
-would be::
-
-  >>> from pymongo import MongoClient
-  >>> uri = "mongodb+srv://example.mongodb.com/?authMechanism=MONGODB-AWS"
-  >>> client = MongoClient(uri)
-
-.. note:: No username, password, or session token is passed into the URI.
-          PyMongo will query the ECS container endpoint to obtain these
-          credentials.
-
-EC2 Instance
-~~~~~~~~~~~~
-
-Applications can authenticate from an EC2 instance via temporary
-credentials assigned to the machine. A sample URI on an EC2 machine
-would be::
-
-  >>> from pymongo import MongoClient
-  >>> uri = "mongodb+srv://example.mongodb.com/?authMechanism=MONGODB-AWS"
-  >>> client = MongoClient(uri)
-
-.. note:: No username, password, or session token is passed into the URI.
-          PyMongo will query the EC2 instance endpoint to obtain these
-          credentials.
-
-.. _temporary AWS IAM credentials: https://docs.aws.amazon.com/IAM/latest/UserGuide/id_credentials_temp.html
-.. _AWS Security Token Service (STS): https://docs.aws.amazon.com/STS/latest/APIReference/Welcome.html
-.. _Assume Role: https://docs.aws.amazon.com/STS/latest/APIReference/API_AssumeRole.html
-.. _EC2 instance: https://docs.aws.amazon.com/IAM/latest/UserGuide/id_roles_use_switch-role-ec2.html
-.. _environment variables: https://docs.aws.amazon.com/lambda/latest/dg/configuration-envvars.html#configuration-envvars-runtime
-
-MONGODB-OIDC
-------------
-.. versionadded:: 4.7
-
-The `MONGODB-OIDC authentication mechanism`_ is available in MongoDB 7.0+ on Linux platforms.
-
-The MONGODB-OIDC mechanism authenticates using an OpenID Connect (OIDC) access token.
-The driver supports OIDC for workload identity, defined as an identity you assign to a software workload
-(such as an application, service, script, or container) to authenticate and access other services and resources.
-
-Credentials can be configured through the MongoDB URI or as arguments to
-:class:`~pymongo.mongo_client.MongoClient`.
-
-Built-in Support
-~~~~~~~~~~~~~~~~
-
-The driver has built-in support for Azure IMDS and GCP IMDS environments.  Other environments
-are supported with `Custom Callbacks`_.
-
-Azure IMDS
-^^^^^^^^^^
-
-For an application running on an Azure VM or otherwise using the `Azure Internal Metadata Service`_,
-you can use the built-in support for Azure. If using an Azure managed identity, the "<client_id>" is
-the client ID.  If using a service principal to represent an enterprise application, the "<client_id>" is
-the application ID of the service principal. The ``<audience>`` value is the ``audience``
-`configured on your MongoDB deployment`_.
-
-.. code-block:: python
-
-    import os
-
-    uri = os.environ["MONGODB_URI"]
-
-    props = {"ENVIRONMENT": "azure", "TOKEN_RESOURCE": "<audience>"}
-    c = MongoClient(
-        uri,
-        username="<client_id>",
-        authMechanism="MONGODB-OIDC",
-        authMechanismProperties=props,
-    )
-    c.test.test.insert_one({})
-    c.close()
-
-If the application is running on an Azure VM and only one managed identity is associated with the
-VM, ``username`` can be omitted.
-
-If providing the ``TOKEN_RESOURCE`` as part of a connection string, it can be given as follows.
-If the ``TOKEN_RESOURCE`` contains any of the following characters [``,``, ``+``, ``&``], then
-it MUST be url-encoded.
-
-.. code-block:: python
-
-    import os
-
-    uri = f'{os.environ["MONGODB_URI"]}?authMechanism=MONGODB-OIDC&authMechanismProperties=ENVIRONMENT:azure,TOKEN_RESOURCE:<audience>'
-    c = MongoClient(uri)
-    c.test.test.insert_one({})
-    c.close()
-
-GCP IMDS
-^^^^^^^^
-
-For an application running on an GCP VM or otherwise using the `GCP Internal Metadata Service`_,
-you can use the built-in support for GCP, where ``<audience>`` below is the ``audience``
-`configured on your MongoDB deployment`_.
-
-.. code-block:: python
-
-    import os
-
-    uri = os.environ["MONGODB_URI"]
-
-    props = {"ENVIRONMENT": "gcp", "TOKEN_RESOURCE": "<audience>"}
-    c = MongoClient(uri, authMechanism="MONGODB-OIDC", authMechanismProperties=props)
-    c.test.test.insert_one({})
-    c.close()
-
-If providing the ``TOKEN_RESOURCE`` as part of a connection string, it can be given as follows.
-If the ``TOKEN_RESOURCE`` contains any of the following characters [``,``, ``+``, ``&``], then
-it MUST be url-encoded.
-
-.. code-block:: python
-
-    import os
-
-    uri = f'{os.environ["MONGODB_URI"]}?authMechanism=MONGODB-OIDC&authMechanismProperties=ENVIRONMENT:gcp,TOKEN_RESOURCE:<audience>'
-    c = MongoClient(uri)
-    c.test.test.insert_one({})
-    c.close()
-
-Custom Callbacks
-~~~~~~~~~~~~~~~~
-
-For environments that are not directly supported by the driver, you can use :class:`~pymongo.auth_oidc.OIDCCallback`.
-Some examples are given below.
-
-Other Azure Environments
-^^^^^^^^^^^^^^^^^^^^^^^^
-
-For applications running on Azure Functions, App Service Environment (ASE), or
-Azure Kubernetes Service (AKS), you can use the `azure-identity package`_
-to fetch the credentials.  This example assumes you have set environment variables for
-the ``audience`` `configured on your MongoDB deployment`_, and for the client id of the Azure
-managed identity.
-
-.. code-block:: python
-
-  import os
-  from azure.identity import DefaultAzureCredential
-  from pymongo import MongoClient
-  from pymongo.auth_oidc import OIDCCallback, OIDCCallbackContext, OIDCCallbackResult
-
-  audience = os.environ["AZURE_AUDIENCE"]
-  client_id = os.environ["AZURE_IDENTITY_CLIENT_ID"]
-  uri = os.environ["MONGODB_URI"]
-
-
-  class MyCallback(OIDCCallback):
-      def fetch(self, context: OIDCCallbackContext) -> OIDCCallbackResult:
-          credential = DefaultAzureCredential(managed_identity_client_id=client_id)
-          token = credential.get_token(f"{audience}/.default").token
-          return OIDCCallbackResult(access_token=token)
-
-
-  props = {"OIDC_CALLBACK": MyCallback()}
-  c = MongoClient(uri, authMechanism="MONGODB-OIDC", authMechanismProperties=props)
-  c.test.test.insert_one({})
-  c.close()
-
-GCP GKE
-^^^^^^^
-
-For a Google Kubernetes Engine cluster with a `configured service account`_, the token can be read from the standard
-service account token file location.
-
-.. code-block:: python
-
-    import os
-    from pymongo.auth_oidc import OIDCCallback, OIDCCallbackContext, OIDCCallbackResult
-
-
-    class MyCallback(OIDCCallback):
-        def fetch(self, context: OIDCCallbackContext) -> OIDCCallbackResult:
-            with open("/var/run/secrets/kubernetes.io/serviceaccount/token") as fid:
-                token = fid.read()
-            return OIDCCallbackResult(access_token=token)
-
-
-    uri = os.environ["MONGODB_URI"]
-    props = {"OIDC_CALLBACK": MyCallback()}
-    c = MongoClient(uri, authMechanism="MONGODB-OIDC", authMechanismProperties=props)
-    c.test.test.insert_one({})
-    c.close()
-
-.. _MONGODB-OIDC authentication mechanism: https://www.mongodb.com/docs/manual/core/security-oidc/
-.. _Azure Internal Metadata Service: https://learn.microsoft.com/en-us/azure/virtual-machines/instance-metadata-service
-.. _configured on your MongoDB deployment: https://www.mongodb.com/docs/manual/reference/parameters/#mongodb-parameter-param.oidcIdentityProviders
-.. _GCP Internal Metadata Service: https://cloud.google.com/compute/docs/metadata/querying-metadata
-.. _azure-identity package: https://pypi.org/project/azure-identity/
-.. _configured service account: https://cloud.google.com/kubernetes-engine/docs/how-to/service-accounts

doc/examples/bulk.rst

@@ -1,184 +0,0 @@
-Bulk Write Operations
-=====================
-
-.. testsetup::
-
-  from pymongo import MongoClient
-
-  client = MongoClient()
-  client.drop_database("bulk_example")
-
-This tutorial explains how to take advantage of PyMongo's bulk
-write operation features. Executing write operations in batches
-reduces the number of network round trips, increasing write
-throughput.
-
-Bulk Insert
------------
-
-.. versionadded:: 2.6
-
-A batch of documents can be inserted by passing a list to the
-:meth:`~pymongo.collection.Collection.insert_many` method. PyMongo
-will automatically split the batch into smaller sub-batches based on
-the maximum message size accepted by MongoDB, supporting very large
-bulk insert operations.
-
-.. doctest::
-
-  >>> import pymongo
-  >>> db = pymongo.MongoClient().bulk_example
-  >>> db.test.insert_many([{"i": i} for i in range(10000)]).inserted_ids
-  [...]
-  >>> db.test.count_documents({})
-  10000
-
-Mixed Bulk Write Operations
----------------------------
-
-.. versionadded:: 2.7
-
-PyMongo also supports executing mixed bulk write operations. A batch
-of insert, update, and remove operations can be executed together using
-the bulk write operations API.
-
-.. _ordered_bulk:
-
-Ordered Bulk Write Operations
-.............................
-
-Ordered bulk write operations are batched and sent to the server in the
-order provided for serial execution. The return value is an instance of
-:class:`~pymongo.results.BulkWriteResult` describing the type and count
-of operations performed.
-
-.. doctest::
-  :options: +NORMALIZE_WHITESPACE
-
-  >>> from pprint import pprint
-  >>> from pymongo import InsertOne, DeleteMany, ReplaceOne, UpdateOne
-  >>> result = db.test.bulk_write(
-  ...     [
-  ...         DeleteMany({}),  # Remove all documents from the previous example.
-  ...         InsertOne({"_id": 1}),
-  ...         InsertOne({"_id": 2}),
-  ...         InsertOne({"_id": 3}),
-  ...         UpdateOne({"_id": 1}, {"$set": {"foo": "bar"}}),
-  ...         UpdateOne({"_id": 4}, {"$inc": {"j": 1}}, upsert=True),
-  ...         ReplaceOne({"j": 1}, {"j": 2}),
-  ...     ]
-  ... )
-  >>> pprint(result.bulk_api_result)
-  {'nInserted': 3,
-   'nMatched': 2,
-   'nModified': 2,
-   'nRemoved': 10000,
-   'nUpserted': 1,
-   'upserted': [{'_id': 4, 'index': 5}],
-   'writeConcernErrors': [],
-   'writeErrors': []}
-
-The first write failure that occurs (e.g. duplicate key error) aborts the
-remaining operations, and PyMongo raises
-:class:`~pymongo.errors.BulkWriteError`. The :attr:`details` attribute of
-the exception instance provides the execution results up until the failure
-occurred and details about the failure - including the operation that caused
-the failure.
-
-.. doctest::
-  :options: +NORMALIZE_WHITESPACE
-
-  >>> from pymongo import InsertOne, DeleteOne, ReplaceOne
-  >>> from pymongo.errors import BulkWriteError
-  >>> requests = [
-  ...     ReplaceOne({"j": 2}, {"i": 5}),
-  ...     InsertOne({"_id": 4}),  # Violates the unique key constraint on _id.
-  ...     DeleteOne({"i": 5}),
-  ... ]
-  >>> try:
-  ...     db.test.bulk_write(requests)
-  ... except BulkWriteError as bwe:
-  ...     pprint(bwe.details)
-  ...
-  {'nInserted': 0,
-   'nMatched': 1,
-   'nModified': 1,
-   'nRemoved': 0,
-   'nUpserted': 0,
-   'upserted': [],
-   'writeConcernErrors': [],
-   'writeErrors': [{'code': 11000,
-                    'errmsg': '...E11000...duplicate key error...',
-                    'index': 1,...
-                    'op': {'_id': 4}}]}
-
-.. _unordered_bulk:
-
-Unordered Bulk Write Operations
-...............................
-
-Unordered bulk write operations are batched and sent to the server in
-**arbitrary order** where they may be executed in parallel. Any errors
-that occur are reported after all operations are attempted.
-
-In the next example the first and third operations fail due to the unique
-constraint on _id. Since we are doing unordered execution the second
-and fourth operations succeed.
-
-.. doctest::
-  :options: +NORMALIZE_WHITESPACE
-
-  >>> requests = [
-  ...     InsertOne({"_id": 1}),
-  ...     DeleteOne({"_id": 2}),
-  ...     InsertOne({"_id": 3}),
-  ...     ReplaceOne({"_id": 4}, {"i": 1}),
-  ... ]
-  >>> try:
-  ...     db.test.bulk_write(requests, ordered=False)
-  ... except BulkWriteError as bwe:
-  ...     pprint(bwe.details)
-  ...
-  {'nInserted': 0,
-   'nMatched': 1,
-   'nModified': 1,
-   'nRemoved': 1,
-   'nUpserted': 0,
-   'upserted': [],
-   'writeConcernErrors': [],
-   'writeErrors': [{'code': 11000,
-                    'errmsg': '...E11000...duplicate key error...',
-                    'index': 0,...
-                    'op': {'_id': 1}},
-                   {'code': 11000,
-                    'errmsg': '...',
-                    'index': 2,...
-                    'op': {'_id': 3}}]}
-
-Write Concern
-.............
-
-Bulk operations are executed with the
-:attr:`~pymongo.collection.Collection.write_concern` of the collection they
-are executed against. Write concern errors (e.g. wtimeout) will be reported
-after all operations are attempted, regardless of execution order.
-
-::
-  >>> from pymongo import WriteConcern
-  >>> coll = db.get_collection(
-  ...     'test', write_concern=WriteConcern(w=3, wtimeout=1))
-  >>> try:
-  ...     coll.bulk_write([InsertOne({'a': i}) for i in range(4)])
-  ... except BulkWriteError as bwe:
-  ...     pprint(bwe.details)
-  ...
-  {'nInserted': 4,
-   'nMatched': 0,
-   'nModified': 0,
-   'nRemoved': 0,
-   'nUpserted': 0,
-   'upserted': [],
-   'writeConcernErrors': [{'code': 64...
-                           'errInfo': {'wtimeout': True},
-                           'errmsg': 'waiting for replication timed out'}],
-   'writeErrors': []}

doc/examples/client_bulk.rst

@@ -1,188 +0,0 @@
-Client Bulk Write Operations
-=============================
-
-.. testsetup::
-
-  from pymongo import MongoClient
-
-  client = MongoClient()
-  client.drop_database("client_bulk_example")
-  db = client.client_bulk_example
-  client.db.drop_collection("test_one")
-  client.db.drop_collection("test_two")
-  client.db.drop_collection("test_three")
-  client.db.drop_collection("test_four")
-  client.db.drop_collection("test_five")
-  client.db.drop_collection("test_six")
-
-The :meth:`~pymongo.mongo_client.MongoClient.bulk_write`
-method has been added to :class:`~pymongo.mongo_client.MongoClient` in PyMongo 4.9.
-This method enables users to perform batches of write operations **across
-multiple namespaces** in a minimized number of round trips, and
-to receive detailed results for each operation performed.
-
-.. note:: This method requires MongoDB server version 8.0+.
-
-Basic Usage
-------------
-
-A list of insert, update, and delete operations can be passed into the
-:meth:`~pymongo.mongo_client.MongoClient.bulk_write` method. Each request
-must include the namespace on which to perform the operation.
-
-PyMongo will automatically split the given requests into smaller sub-batches based on
-the maximum message size accepted by MongoDB, supporting very large bulk write operations.
-
-The return value is an instance of
-:class:`~pymongo.results.ClientBulkWriteResult`.
-
-.. _summary_client_bulk:
-
-Summary Results
-.................
-
-By default, the returned :class:`~pymongo.results.ClientBulkWriteResult` instance will contain a
-summary of the types of operations performed in the bulk write, along with their respective counts.
-
-.. doctest::
-  :options: +NORMALIZE_WHITESPACE
-
-  >>> from pymongo import InsertOne, DeleteOne, UpdateOne
-  >>> models = [
-  ...     InsertOne(namespace="db.test_one", document={"_id": 1}),
-  ...     InsertOne(namespace="db.test_two", document={"_id": 2}),
-  ...     DeleteOne(namespace="db.test_one", filter={"_id": 1}),
-  ...     UpdateOne(
-  ...         namespace="db.test_two",
-  ...         filter={"_id": 4},
-  ...         update={"$inc": {"j": 1}},
-  ...         upsert=True,
-  ...     ),
-  ... ]
-  >>> result = client.bulk_write(models)
-  >>> result.inserted_count
-  2
-  >>> result.deleted_count
-  1
-  >>> result.modified_count
-  0
-  >>> result.upserted_count
-  1
-
-.. _verbose_client_bulk:
-
-Verbose Results
-.................
-
-If the ``verbose_results`` parameter is set to True, the returned :class:`~pymongo.results.ClientBulkWriteResult`
-instance will also include detailed results about each successful operation performed as part of the bulk write.
-
-.. doctest::
-  :options: +NORMALIZE_WHITESPACE
-
-  >>> from pymongo import InsertOne, DeleteMany, ReplaceOne, UpdateMany
-  >>> models = [
-  ...     DeleteMany(
-  ...         namespace="db.test_two", filter={}
-  ...     ),  # Delete all documents from the previous example
-  ...     InsertOne(namespace="db.test_one", document={"_id": 1}),
-  ...     InsertOne(namespace="db.test_one", document={"_id": 2}),
-  ...     InsertOne(namespace="db.test_two", document={"_id": 3}),
-  ...     UpdateMany(namespace="db.test_one", filter={}, update={"$set": {"foo": "bar"}}),
-  ...     ReplaceOne(
-  ...         namespace="db.test_two", filter={"j": 1}, replacement={"_id": 4}, upsert=True
-  ...     ),
-  ... ]
-  >>> result = client.bulk_write(models, verbose_results=True)
-  >>> result.delete_results
-  {0: DeleteResult({'ok': 1.0, 'idx': 0, 'n': 2}, ...)}
-  >>> result.insert_results
-  {1: InsertOneResult(1, ...),
-   2: InsertOneResult(2, ...),
-   3: InsertOneResult(3, ...)}
-  >>> result.update_results
-  {4: UpdateResult({'ok': 1.0, 'idx': 4, 'n': 2, 'nModified': 2}, ...),
-   5: UpdateResult({'ok': 1.0, 'idx': 5, 'n': 1, 'nModified': 0, 'upserted': {'_id': 4}}, ...)}
-
-
-Handling Errors
-----------------
-
-If any errors occur during the bulk write, a :class:`~pymongo.errors.ClientBulkWriteException` will be raised.
-If a server, connection, or network error occurred, the ``error`` field of the exception will contain
-that error.
-
-Individual write errors or write concern errors get recorded in the ``write_errors`` and ``write_concern_errors`` fields of the exception.
-The ``partial_result`` field gets populated with the results of any operations that were successfully completed before the exception was raised.
-
-.. _ordered_client_bulk:
-
-Ordered Operations
-....................
-
-In an ordered bulk write (the default), if an individual write fails, no further operations will get executed.
-For example, a duplicate key error on the third operation below aborts the remaining two operations.
-
-.. doctest::
-  :options: +NORMALIZE_WHITESPACE
-
-  >>> from pymongo import InsertOne, DeleteOne
-  >>> from pymongo.errors import ClientBulkWriteException
-  >>> models = [
-  ...     InsertOne(namespace="db.test_three", document={"_id": 3}),
-  ...     InsertOne(namespace="db.test_four", document={"_id": 4}),
-  ...     InsertOne(namespace="db.test_three", document={"_id": 3}),  # Duplicate _id
-  ...     InsertOne(namespace="db.test_four", document={"_id": 5}),
-  ...     DeleteOne(namespace="db.test_three", filter={"_id": 3}),
-  ... ]
-  >>> try:
-  ...     client.bulk_write(models)
-  ... except ClientBulkWriteException as cbwe:
-  ...     exception = cbwe
-  ...
-  >>> exception.write_errors
-  [{'ok': 0.0,
-    'idx': 2,
-    'code': 11000,
-    'errmsg': 'E11000 duplicate key error ... dup key: { _id: 3 }', ...
-    'op': {'insert': 0, 'document': {'_id': 3}}}]
-  >>> exception.partial_result.inserted_count
-  2
-  >>> exception.partial_result.deleted_count
-  0
-
-.. _unordered_client_bulk:
-
-Unordered Operations
-.....................
-
-If the ``ordered`` parameter is set to False, all operations in the bulk write will be attempted, regardless of any individual write errors that occur.
-For example, the fourth and fifth write operations below get executed successfully, despite the duplicate key error on the third operation.
-
-.. doctest::
-  :options: +NORMALIZE_WHITESPACE
-
-  >>> from pymongo import InsertOne, DeleteOne
-  >>> from pymongo.errors import ClientBulkWriteException
-  >>> models = [
-  ...     InsertOne(namespace="db.test_five", document={"_id": 5}),
-  ...     InsertOne(namespace="db.test_six", document={"_id": 6}),
-  ...     InsertOne(namespace="db.test_five", document={"_id": 5}),  # Duplicate _id
-  ...     InsertOne(namespace="db.test_six", document={"_id": 7}),
-  ...     DeleteOne(namespace="db.test_five", filter={"_id": 5}),
-  ... ]
-  >>> try:
-  ...     client.bulk_write(models, ordered=False)
-  ... except ClientBulkWriteException as cbwe:
-  ...     exception = cbwe
-  ...
-  >>> exception.write_errors
-  [{'ok': 0.0,
-    'idx': 2,
-    'code': 11000,
-    'errmsg': 'E11000 duplicate key error ... dup key: { _id: 5 }', ...
-    'op': {'insert': 0, 'document': {'_id': 5}}}]
-  >>> exception.partial_result.inserted_count
-  3
-  >>> exception.partial_result.deleted_count
-  1

doc/examples/collations.rst

@@ -1,134 +0,0 @@
-Collations
-==========
-
-.. seealso:: The API docs for :mod:`~pymongo.collation`.
-
-Collations are a new feature in MongoDB version 3.4. They provide a set of rules
-to use when comparing strings that comply with the conventions of a particular
-language, such as Spanish or German. If no collation is specified, the server
-sorts strings based on a binary comparison. Many languages have specific
-ordering rules, and collations allow users to build applications that adhere to
-language-specific comparison rules.
-
-In French, for example, the last accent in a given word determines the sorting
-order. The correct sorting order for the following four words in French is::
-
-  cote < côte < coté < côté
-
-Specifying a French collation allows users to sort string fields using the
-French sort order.
-
-Usage
------
-
-Users can specify a collation for a
-:ref:`collection<collation-on-collection>`, an
-:ref:`index<collation-on-index>`, or a
-:ref:`CRUD command <collation-on-operation>`.
-
-Collation Parameters:
-~~~~~~~~~~~~~~~~~~~~~
-
-Collations can be specified with the :class:`~pymongo.collation.Collation` model
-or with plain Python dictionaries. The structure is the same::
-
-   Collation(locale=<string>,
-             caseLevel=<bool>,
-             caseFirst=<string>,
-             strength=<int>,
-             numericOrdering=<bool>,
-             alternate=<string>,
-             maxVariable=<string>,
-             backwards=<bool>)
-
-The only required parameter is ``locale``, which the server parses as
-an `ICU format locale ID <https://www.mongodb.com/docs/manual/reference/collation-locales-defaults/>`_.
-For example, set ``locale`` to ``en_US`` to represent US English
-or ``fr_CA`` to represent Canadian French.
-
-For a complete description of the available parameters, see the MongoDB `manual
-</>`_.
-
-.. COMMENT add link for manual entry.
-
-.. _collation-on-collection:
-
-Assign a Default Collation to a Collection
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-The following example demonstrates how to create a new collection called
-``contacts`` and assign a default collation with the ``fr_CA`` locale. This
-operation ensures that all queries that are run against the ``contacts``
-collection use the ``fr_CA`` collation unless another collation is explicitly
-specified::
-
-  from pymongo import MongoClient
-  from pymongo.collation import Collation
-
-  db = MongoClient().test
-  collection = db.create_collection('contacts',
-                                    collation=Collation(locale='fr_CA'))
-
-.. _collation-on-index:
-
-Assign a Default Collation to an Index
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-When creating a new index, you can specify a default collation.
-
-The following example shows how to create an index on the ``name``
-field of the ``contacts`` collection, with the ``unique`` parameter
-enabled and a default collation with ``locale`` set to ``fr_CA``::
-
-  from pymongo import MongoClient
-  from pymongo.collation import Collation
-
-  contacts = MongoClient().test.contacts
-  contacts.create_index('name',
-                        unique=True,
-                        collation=Collation(locale='fr_CA'))
-
-.. _collation-on-operation:
-
-Specify a Collation for a Query
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-Individual queries can specify a collation to use when sorting
-results. The following example demonstrates a query that runs on the
-``contacts`` collection in database ``test``. It matches on
-documents that contain ``New York`` in the ``city`` field,
-and sorts on the ``name`` field with the ``fr_CA`` collation::
-
-  from pymongo import MongoClient
-  from pymongo.collation import Collation
-
-  collection = MongoClient().test.contacts
-  docs = collection.find({'city': 'New York'}).sort('name').collation(
-      Collation(locale='fr_CA'))
-
-Other Query Types
-~~~~~~~~~~~~~~~~~
-
-You can use collations to control document matching rules for several different
-types of queries. All the various update and delete methods
-(:meth:`~pymongo.collection.Collection.update_one`,
-:meth:`~pymongo.collection.Collection.update_many`,
-:meth:`~pymongo.collection.Collection.delete_one`, etc.) support collation, and
-you can create query filters which employ collations to comply with any of the
-languages and variants available to the ``locale`` parameter.
-
-The following example uses a collation with ``strength`` set to
-:const:`~pymongo.collation.CollationStrength.SECONDARY`, which considers only
-the base character and character accents in string comparisons, but not case
-sensitivity, for example. All documents in the ``contacts`` collection with
-``jürgen`` (case-insensitive) in the ``first_name`` field are updated::
-
-  from pymongo import MongoClient
-  from pymongo.collation import Collation, CollationStrength
-
-  contacts = MongoClient().test.contacts
-  result = contacts.update_many(
-      {'first_name': 'jürgen'},
-      {'$set': {'verified': 1}},
-      collation=Collation(locale='de',
-                          strength=CollationStrength.SECONDARY))

doc/examples/copydb.rst

@@ -1,73 +0,0 @@
-Copying a Database
-==================
-
-MongoDB >= 4.2
---------------
-
-Starting in MongoDB version 4.2, the server removes the deprecated ``copydb`` command.
-As an alternative, users can use ``mongodump`` and ``mongorestore`` (with the ``mongorestore``
-options ``--nsFrom`` and ``--nsTo``).
-
-For example, to copy the ``test`` database from a local instance running on the
-default port 27017 to the ``examples`` database on the same instance, you can:
-
-#. Use ``mongodump`` to dump the test database to an archive ``mongodump-test-db``::
-
-    mongodump --archive="mongodump-test-db" --db=test
-
-#. Use ``mongorestore`` with ``--nsFrom`` and ``--nsTo`` to restore (with database name change)
-   from the archive::
-
-    mongorestore --archive="mongodump-test-db" --nsFrom='test.*' --nsTo='examples.*'
-
-Include additional options as necessary, such as to specify the uri or host, username,
-password and authentication database.
-
-For more info about using ``mongodump`` and ``mongorestore`` see the `Copy a Database`_ example
-in the official ``mongodump`` documentation.
-
-MongoDB <= 4.0
---------------
-
-When using MongoDB <= 4.0, it is possible to use the deprecated ``copydb`` command
-to copy a database. To copy a database within a single ``mongod`` process, or
-between ``mongod`` servers, connect to the target ``mongod`` and use the
-:meth:`~pymongo.database.Database.command` method::
-
-  >>> from pymongo import MongoClient
-  >>> client = MongoClient('target.example.com')
-  >>> client.admin.command('copydb',
-                           fromdb='source_db_name',
-                           todb='target_db_name')
-
-To copy from a different mongod server that is not password-protected::
-
-  >>> client.admin.command('copydb',
-                           fromdb='source_db_name',
-                           todb='target_db_name',
-                           fromhost='source.example.com')
-
-If the target server is password-protected, authenticate to the "admin"
-database::
-
-  >>> client = MongoClient('target.example.com',
-  ...                      username='administrator',
-  ...                      password='pwd')
-  >>> client.admin.command('copydb',
-                           fromdb='source_db_name',
-                           todb='target_db_name',
-                           fromhost='source.example.com')
-
-See the :doc:`authentication examples </examples/authentication>`.
-
-If the **source** server is password-protected, use the `copyDatabase
-function in the mongo shell`_.
-
-Versions of PyMongo before 3.0 included a ``copy_database`` helper method,
-but it has been removed.
-
-.. _copyDatabase function in the mongo shell:
-   https://mongodb.com/docs/manual/reference/method/db.copyDatabase/
-
-.. _Copy a Database:
-   https://www.mongodb.com/docs/database-tools/mongodump/mongodump-examples/#copy-and-clone-databases