feat: use repr in code variables (#372 )

fix: avoid overwriting consumer list when using more than one consumer (#370 )
fix: avoid overwriting consumer list when using more than one consumer thread
2025-11-15 13:43:55 +01:00 · 2025-11-12 13:05:05 +01:00 · 2025-11-11 18:13:36 +00:00 · 2025-11-11 18:12:33 +00:00 · 2025-11-11 17:57:26 +00:00 · 2025-11-11 17:56:32 +00:00
54 changed files with 30832 additions and 197 deletions
@@ -3,6 +3,9 @@ name: CI
 on:
    - pull_request

+permissions:
+    contents: read
+
 jobs:
    code-quality:
        name: Code quality checks
@@ -33,6 +36,10 @@ jobs:
              run: |
                  ruff format --check .

+            - name: Lint with ruff
+              run: |
+                  ruff check .
+
            - name: Check types with mypy
              run: |
                  mypy --no-site-packages --config-file mypy.ini  . | mypy-baseline filter
@@ -42,7 +49,7 @@ jobs:
        runs-on: ubuntu-latest
        strategy:
            matrix:
-                python-version: ['3.9', '3.10', '3.11', '3.12', '3.13']
+                python-version: ['3.10', '3.11', '3.12', '3.13']

        steps:
            - uses: actions/checkout@85e6279cec87321a52edac9c87bce653a07cf6c2
@@ -68,3 +75,34 @@ jobs:
            - name: Run posthog tests
              run: |
                  pytest --verbose --timeout=30
+
+    django5-integration:
+        name: Django 5 integration tests
+        runs-on: ubuntu-latest
+
+        steps:
+            - uses: actions/checkout@85e6279cec87321a52edac9c87bce653a07cf6c2
+              with:
+                  fetch-depth: 1
+
+            - name: Set up Python 3.12
+              uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55
+              with:
+                  python-version: 3.12
+
+            - name: Install uv
+              uses: astral-sh/setup-uv@0c5e2b8115b80b4c7c5ddf6ffdd634974642d182 # v5.4.1
+              with:
+                  enable-cache: true
+                  pyproject-file: 'integration_tests/django5/pyproject.toml'
+
+            - name: Install Django 5 test project dependencies
+              shell: bash
+              working-directory: integration_tests/django5
+              run: |
+                  UV_PROJECT_ENVIRONMENT=$pythonLocation uv sync
+
+            - name: Run Django 5 middleware integration tests
+              working-directory: integration_tests/django5
+              run: |
+                  uv run pytest test_middleware.py test_exception_capture.py --verbose
@@ -19,3 +19,4 @@ pyrightconfig.json
 .env
 .DS_Store
 posthog-python-references.json
+.claude/settings.local.json
@@ -1,3 +1,63 @@
+# 7.0.1 - 2025-11-15
+
+Try to use repr() when formatting code variables
+
+# 7.0.0 - 2025-11-11
+
+NB Python 3.9 is no longer supported
+
+- chore(llma): update LLM provider SDKs to latest major versions
+  - openai: 1.102.0 → 2.7.1
+  - anthropic: 0.64.0 → 0.72.0
+  - google-genai: 1.32.0 → 1.49.0
+  - langchain-core: 0.3.75 → 1.0.3
+  - langchain-openai: 0.3.32 → 1.0.2
+  - langchain-anthropic: 0.3.19 → 1.0.1
+  - langchain-community: 0.3.29 → 0.4.1
+  - langgraph: 0.6.6 → 1.0.2
+
+# 6.9.3 - 2025-11-10
+
+- feat(ph-ai): PostHog properties dict in GenerationMetadata
+
+# 6.9.2 - 2025-11-10
+
+- fix(llma): fix cache token double subtraction in Langchain for non-Anthropic providers causing negative costs
+
+# 6.9.1 - 2025-11-07
+
+- fix(error-tracking): pass code variables config from init to client
+
+# 6.9.0 - 2025-11-06
+
+- feat(error-tracking): add local variables capture
+
+# 6.8.0 - 2025-11-03
+
+- feat(llma): send web search calls to be used for LLM cost calculations
+
+# 6.7.14 - 2025-11-03
+
+- fix(django): Handle request.user access in async middleware context to prevent SynchronousOnlyOperation errors in Django 5+ (fixes #355)
+- test(django): Add Django 5 integration test suite with real ASGI application testing async middleware behavior
+
+# 6.7.13 - 2025-11-02
+
+- fix(llma): cache cost calculation in the LangChain callback
+
+# 6.7.12 - 2025-11-02
+
+- fix(django): Restore process_exception method to capture view and downstream middleware exceptions (fixes #329)
+- fix(ai/langchain): Add LangChain 1.0+ compatibility for CallbackHandler imports (fixes #362)
+
+# 6.7.11 - 2025-10-28
+
+- feat(ai): Add `$ai_framework` property for framework integrations (e.g. LangChain)
+
+# 6.7.10 - 2025-10-24
+
+- fix(django): Make middleware truly hybrid - compatible with both sync (WSGI) and async (ASGI) Django stacks without breaking sync-only deployments
+
 # 6.7.9 - 2025-10-22

 - fix(flags): multi-condition flags with static cohorts returning wrong variants
@@ -30,8 +30,8 @@ We recommend using [uv](https://docs.astral.sh/uv/). It's super fast.
 ## PostHog recommends `uv` so...

 ```bash
-uv python install 3.9.19
-uv python pin 3.9.19
+uv python install 3.12
+uv python pin 3.12
 uv venv
 source env/bin/activate
 uv sync --extra dev --extra test
@@ -0,0 +1,4 @@
+db.sqlite3
+*.pyc
+__pycache__/
+.pytest_cache/
@@ -0,0 +1,23 @@
+#!/usr/bin/env python
+"""Django's command-line utility for administrative tasks."""
+
+import os
+import sys
+
+
+def main():
+    """Run administrative tasks."""
+    os.environ.setdefault("DJANGO_SETTINGS_MODULE", "testdjango.settings")
+    try:
+        from django.core.management import execute_from_command_line
+    except ImportError as exc:
+        raise ImportError(
+            "Couldn't import Django. Are you sure it's installed and "
+            "available on your PYTHONPATH environment variable? Did you "
+            "forget to activate a virtual environment?"
+        ) from exc
+    execute_from_command_line(sys.argv)
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,19 @@
+[project]
+name = "test-django5"
+version = "0.1.0"
+requires-python = ">=3.12"
+dependencies = [
+    "django~=5.2.7",
+    "uvicorn[standard]~=0.38.0",
+    "posthog",
+    "pytest~=8.4.2",
+    "pytest-asyncio~=1.2.0",
+    "pytest-django~=4.11.1",
+    "httpx~=0.28.1",
+]
+
+[tool.uv]
+required-version = ">=0.5"
+
+[tool.uv.sources]
+posthog = { path = "../..", editable = true }
@@ -0,0 +1,111 @@
+"""
+Test that verifies exception capture functionality.
+
+These tests verify that exceptions are actually captured to PostHog, not just that
+500 responses are returned.
+
+Without process_exception(), view exceptions are NOT captured to PostHog (v6.7.11 and earlier).
+With process_exception(), Django calls this method to capture exceptions before
+converting them to 500 responses.
+"""
+
+import os
+import django
+
+# Setup Django before importing anything else
+os.environ.setdefault("DJANGO_SETTINGS_MODULE", "testdjango.settings")
+django.setup()
+
+import pytest  # noqa: E402
+from httpx import AsyncClient, ASGITransport  # noqa: E402
+from django.core.asgi import get_asgi_application  # noqa: E402
+
+
+@pytest.fixture(scope="session")
+def asgi_app():
+    """Shared ASGI application for all tests."""
+    return get_asgi_application()
+
+
+@pytest.mark.asyncio
+async def test_async_exception_is_captured(asgi_app):
+    """
+    Test that async view exceptions are captured to PostHog.
+
+    The middleware's process_exception() method ensures exceptions are captured.
+    Without it (v6.7.11 and earlier), exceptions are NOT captured even though 500 is returned.
+    """
+    from unittest.mock import patch
+
+    # Track captured exceptions
+    captured = []
+
+    def mock_capture(exception, **kwargs):
+        """Mock capture_exception to record calls."""
+        captured.append(
+            {
+                "exception": exception,
+                "type": type(exception).__name__,
+                "message": str(exception),
+            }
+        )
+
+    # Patch at the posthog module level where middleware imports from
+    with patch("posthog.capture_exception", side_effect=mock_capture):
+        async with AsyncClient(
+            transport=ASGITransport(app=asgi_app), base_url="http://testserver"
+        ) as ac:
+            response = await ac.get("/test/async-exception")
+
+        # Django returns 500
+        assert response.status_code == 500
+
+        # CRITICAL: Verify PostHog captured the exception
+        assert len(captured) > 0, "Exception was NOT captured to PostHog!"
+
+        # Verify it's the right exception
+        exception_data = captured[0]
+        assert exception_data["type"] == "ValueError"
+        assert "Test exception from Django 5 async view" in exception_data["message"]
+
+
+@pytest.mark.asyncio
+async def test_sync_exception_is_captured(asgi_app):
+    """
+    Test that sync view exceptions are captured to PostHog.
+
+    The middleware's process_exception() method ensures exceptions are captured.
+    Without it (v6.7.11 and earlier), exceptions are NOT captured even though 500 is returned.
+    """
+    from unittest.mock import patch
+
+    # Track captured exceptions
+    captured = []
+
+    def mock_capture(exception, **kwargs):
+        """Mock capture_exception to record calls."""
+        captured.append(
+            {
+                "exception": exception,
+                "type": type(exception).__name__,
+                "message": str(exception),
+            }
+        )
+
+    # Patch at the posthog module level where middleware imports from
+    with patch("posthog.capture_exception", side_effect=mock_capture):
+        async with AsyncClient(
+            transport=ASGITransport(app=asgi_app), base_url="http://testserver"
+        ) as ac:
+            response = await ac.get("/test/sync-exception")
+
+        # Django returns 500
+        assert response.status_code == 500
+
+        # CRITICAL: Verify PostHog captured the exception
+        assert len(captured) > 0, "Exception was NOT captured to PostHog!"
+
+        # Verify it's the right exception
+        exception_data = captured[0]
+        assert exception_data["type"] == "ValueError"
+        assert "Test exception from Django 5 sync view" in exception_data["message"]
@@ -0,0 +1,170 @@
+"""
+Tests for PostHog Django middleware in async context.
+
+These tests verify that the middleware correctly handles:
+1. Async user access (request.auser() in Django 5)
+2. Exception capture in both sync and async views
+3. No SynchronousOnlyOperation errors in async context
+
+Tests run directly against the ASGI application without needing a server.
+"""
+
+import os
+import django
+
+# Setup Django before importing anything else
+os.environ.setdefault("DJANGO_SETTINGS_MODULE", "testdjango.settings")
+django.setup()
+
+import pytest  # noqa: E402
+from httpx import AsyncClient, ASGITransport  # noqa: E402
+from django.core.asgi import get_asgi_application  # noqa: E402
+
+
+@pytest.fixture(scope="session")
+def asgi_app():
+    """Shared ASGI application for all tests."""
+    return get_asgi_application()
+
+
+@pytest.mark.asyncio
+async def test_async_user_access(asgi_app):
+    """
+    Test that middleware can access request.user in async context.
+
+    In Django 5, this requires using await request.auser() instead of request.user
+    to avoid SynchronousOnlyOperation error.
+
+    Without authentication, request.user is AnonymousUser which doesn't
+    trigger the lazy loading bug. This test verifies the middleware works
+    in the common case.
+    """
+    async with AsyncClient(
+        transport=ASGITransport(app=asgi_app), base_url="http://testserver"
+    ) as ac:
+        response = await ac.get("/test/async-user")
+
+    assert response.status_code == 200
+    data = response.json()
+    assert data["status"] == "success"
+    assert "django_version" in data
+
+
+@pytest.mark.django_db(transaction=True)
+@pytest.mark.asyncio
+async def test_async_authenticated_user_access(asgi_app):
+    """
+    Test that middleware can access an authenticated user in async context.
+
+    This is the critical test that triggers the SynchronousOnlyOperation bug
+    in v6.7.11. When AuthenticationMiddleware sets request.user to a
+    SimpleLazyObject wrapping a database query, accessing user.pk or user.email
+    in async context causes the error.
+
+    In v6.7.11, extract_request_user() does getattr(user, "is_authenticated", False)
+    which triggers the lazy object evaluation synchronously.
+
+    The fix uses await request.auser() instead to avoid this.
+    """
+    from django.contrib.auth import get_user_model
+    from django.test import Client
+    from asgiref.sync import sync_to_async
+    from django.test import override_settings
+
+    # Create a test user (must use sync_to_async since we're in async test)
+    User = get_user_model()
+
+    @sync_to_async
+    def create_or_get_user():
+        user, created = User.objects.get_or_create(
+            username="testuser",
+            defaults={
+                "email": "test@example.com",
+            },
+        )
+        if created:
+            user.set_password("testpass123")
+            user.save()
+        return user
+
+    user = await create_or_get_user()
+
+    # Create a session with authenticated user (sync operation)
+    @sync_to_async
+    def create_session():
+        client = Client()
+        client.force_login(user)
+        return client.cookies.get("sessionid")
+
+    session_cookie = await create_session()
+
+    if not session_cookie:
+        pytest.skip("Could not create authenticated session")
+
+    # Make request with session cookie - this should trigger the bug in v6.7.11
+    # Disable exception capture to see the SynchronousOnlyOperation clearly
+    with override_settings(POSTHOG_MW_CAPTURE_EXCEPTIONS=False):
+        async with AsyncClient(
+            transport=ASGITransport(app=asgi_app),
+            base_url="http://testserver",
+            cookies={"sessionid": session_cookie.value},
+        ) as ac:
+            response = await ac.get("/test/async-user")
+
+        assert response.status_code == 200
+        data = response.json()
+        assert data["status"] == "success"
+        assert data["user_authenticated"]
+
+
+@pytest.mark.asyncio
+async def test_sync_user_access(asgi_app):
+    """
+    Test that middleware works with sync views.
+
+    This should always work regardless of middleware version.
+    """
+    async with AsyncClient(
+        transport=ASGITransport(app=asgi_app), base_url="http://testserver"
+    ) as ac:
+        response = await ac.get("/test/sync-user")
+
+    assert response.status_code == 200
+    data = response.json()
+    assert data["status"] == "success"
+
+
+@pytest.mark.asyncio
+async def test_async_exception_capture(asgi_app):
+    """
+    Test that middleware handles exceptions from async views.
+
+    The middleware's process_exception() method captures view exceptions to PostHog
+    before Django converts them to 500 responses. This test verifies the exception
+    causes a 500 response. See test_exception_capture.py for tests that verify
+    actual exception capture to PostHog.
+    """
+    async with AsyncClient(
+        transport=ASGITransport(app=asgi_app), base_url="http://testserver"
+    ) as ac:
+        response = await ac.get("/test/async-exception")
+
+    # Django returns 500 for unhandled exceptions
+    assert response.status_code == 500
+
+
+@pytest.mark.asyncio
+async def test_sync_exception_capture(asgi_app):
+    """
+    Test that middleware handles exceptions from sync views.
+
+    The middleware's process_exception() method captures view exceptions to PostHog.
+    This test verifies the exception causes a 500 response.
+    """
+    async with AsyncClient(
+        transport=ASGITransport(app=asgi_app), base_url="http://testserver"
+    ) as ac:
+        response = await ac.get("/test/sync-exception")
+
+    # Django returns 500 for unhandled exceptions
+    assert response.status_code == 500
@@ -0,0 +1,16 @@
+"""
+ASGI config for testdjango project.
+
+It exposes the ASGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/5.2/howto/deployment/asgi/
+"""
+
+import os
+
+from django.core.asgi import get_asgi_application
+
+os.environ.setdefault("DJANGO_SETTINGS_MODULE", "testdjango.settings")
+
+application = get_asgi_application()
@@ -0,0 +1,129 @@
+"""
+Django settings for testdjango project.
+
+Generated by 'django-admin startproject' using Django 5.2.7.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/5.2/topics/settings/
+
+For the full list of settings and their values, see
+https://docs.djangoproject.com/en/5.2/ref/settings/
+"""
+
+from pathlib import Path
+
+# Build paths inside the project like this: BASE_DIR / 'subdir'.
+BASE_DIR = Path(__file__).resolve().parent.parent
+
+
+# Quick-start development settings - unsuitable for production
+# See https://docs.djangoproject.com/en/5.2/howto/deployment/checklist/
+
+# SECURITY WARNING: keep the secret key used in production secret!
+SECRET_KEY = "django-insecure-q5(&wfw@_lb)noyowbfl$2ls8c82hl__0f9s5(mohlh2)aas#3"
+
+# SECURITY WARNING: don't run with debug turned on in production!
+DEBUG = True
+
+ALLOWED_HOSTS = ["*"]
+
+
+# Application definition
+
+INSTALLED_APPS = [
+    "django.contrib.admin",
+    "django.contrib.auth",
+    "django.contrib.contenttypes",
+    "django.contrib.sessions",
+    "django.contrib.messages",
+    "django.contrib.staticfiles",
+]
+
+MIDDLEWARE = [
+    "django.middleware.security.SecurityMiddleware",
+    "django.contrib.sessions.middleware.SessionMiddleware",
+    "django.middleware.common.CommonMiddleware",
+    "django.middleware.csrf.CsrfViewMiddleware",
+    "django.contrib.auth.middleware.AuthenticationMiddleware",
+    "django.contrib.messages.middleware.MessageMiddleware",
+    "django.middleware.clickjacking.XFrameOptionsMiddleware",
+    "posthog.integrations.django.PosthogContextMiddleware",  # Test PostHog middleware
+]
+
+ROOT_URLCONF = "testdjango.urls"
+
+TEMPLATES = [
+    {
+        "BACKEND": "django.template.backends.django.DjangoTemplates",
+        "DIRS": [],
+        "APP_DIRS": True,
+        "OPTIONS": {
+            "context_processors": [
+                "django.template.context_processors.request",
+                "django.contrib.auth.context_processors.auth",
+                "django.contrib.messages.context_processors.messages",
+            ],
+        },
+    },
+]
+
+WSGI_APPLICATION = "testdjango.wsgi.application"
+
+
+# Database
+# https://docs.djangoproject.com/en/5.2/ref/settings/#databases
+
+DATABASES = {
+    "default": {
+        "ENGINE": "django.db.backends.sqlite3",
+        "NAME": BASE_DIR / "db.sqlite3",
+    }
+}
+
+
+# Password validation
+# https://docs.djangoproject.com/en/5.2/ref/settings/#auth-password-validators
+
+AUTH_PASSWORD_VALIDATORS = [
+    {
+        "NAME": "django.contrib.auth.password_validation.UserAttributeSimilarityValidator",
+    },
+    {
+        "NAME": "django.contrib.auth.password_validation.MinimumLengthValidator",
+    },
+    {
+        "NAME": "django.contrib.auth.password_validation.CommonPasswordValidator",
+    },
+    {
+        "NAME": "django.contrib.auth.password_validation.NumericPasswordValidator",
+    },
+]
+
+
+# Internationalization
+# https://docs.djangoproject.com/en/5.2/topics/i18n/
+
+LANGUAGE_CODE = "en-us"
+
+TIME_ZONE = "UTC"
+
+USE_I18N = True
+
+USE_TZ = True
+
+
+# Static files (CSS, JavaScript, Images)
+# https://docs.djangoproject.com/en/5.2/howto/static-files/
+
+STATIC_URL = "static/"
+
+# Default primary key field type
+# https://docs.djangoproject.com/en/5.2/ref/settings/#default-auto-field
+
+DEFAULT_AUTO_FIELD = "django.db.models.BigAutoField"
+
+
+# PostHog settings for testing
+POSTHOG_API_KEY = "test-key"
+POSTHOG_HOST = "https://app.posthog.com"
+POSTHOG_MW_CAPTURE_EXCEPTIONS = True
@@ -0,0 +1,28 @@
+"""
+URL configuration for testdjango project.
+
+The `urlpatterns` list routes URLs to views. For more information please see:
+    https://docs.djangoproject.com/en/5.2/topics/http/urls/
+Examples:
+Function views
+    1. Add an import:  from my_app import views
+    2. Add a URL to urlpatterns:  path('', views.home, name='home')
+Class-based views
+    1. Add an import:  from other_app.views import Home
+    2. Add a URL to urlpatterns:  path('', Home.as_view(), name='home')
+Including another URLconf
+    1. Import the include() function: from django.urls import include, path
+    2. Add a URL to urlpatterns:  path('blog/', include('blog.urls'))
+"""
+
+from django.contrib import admin
+from django.urls import path
+from testdjango import views
+
+urlpatterns = [
+    path("admin/", admin.site.urls),
+    path("test/async-user", views.test_async_user),
+    path("test/sync-user", views.test_sync_user),
+    path("test/async-exception", views.test_async_exception),
+    path("test/sync-exception", views.test_sync_exception),
+]
@@ -0,0 +1,50 @@
+"""
+Test views for validating PostHog middleware with Django 5 ASGI.
+"""
+
+from django.http import JsonResponse
+
+
+async def test_async_user(request):
+    """
+    Async view that tests middleware with request.user access.
+
+    The middleware will access request.user (SimpleLazyObject) via auser()
+    in async context. Without the fix, this causes SynchronousOnlyOperation.
+    """
+    # The middleware has already accessed request.user via auser()
+    # If we got here, the fix works!
+    user = await request.auser()
+
+    return JsonResponse(
+        {
+            "status": "success",
+            "message": "Django 5 async middleware test passed!",
+            "django_version": "5.x",
+            "user_authenticated": user.is_authenticated if user else False,
+            "note": "Middleware used await request.auser() successfully",
+        }
+    )
+
+
+def test_sync_user(request):
+    """Sync view for comparison."""
+    return JsonResponse(
+        {
+            "status": "success",
+            "message": "Sync view works",
+            "user_authenticated": request.user.is_authenticated
+            if hasattr(request, "user")
+            else False,
+        }
+    )
+
+
+async def test_async_exception(request):
+    """Async view that raises an exception for testing exception capture."""
+    raise ValueError("Test exception from Django 5 async view")
+
+
+def test_sync_exception(request):
+    """Sync view that raises an exception for testing exception capture."""
+    raise ValueError("Test exception from Django 5 sync view")
@@ -0,0 +1,16 @@
+"""
+WSGI config for testdjango project.
+
+It exposes the WSGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/5.2/howto/deployment/wsgi/
+"""
+
+import os
+
+from django.core.wsgi import get_wsgi_application
+
+os.environ.setdefault("DJANGO_SETTINGS_MODULE", "testdjango.settings")
+
+application = get_wsgi_application()
@@ -0,0 +1,674 @@
+version = 1
+revision = 3
+requires-python = ">=3.12"
+
+[[package]]
+name = "anyio"
+version = "4.11.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "idna" },
+    { name = "sniffio" },
+    { name = "typing-extensions", marker = "python_full_version < '3.13'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/c6/78/7d432127c41b50bccba979505f272c16cbcadcc33645d5fa3a738110ae75/anyio-4.11.0.tar.gz", hash = "sha256:82a8d0b81e318cc5ce71a5f1f8b5c4e63619620b63141ef8c995fa0db95a57c4", size = 219094, upload-time = "2025-09-23T09:19:12.58Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/15/b3/9b1a8074496371342ec1e796a96f99c82c945a339cd81a8e73de28b4cf9e/anyio-4.11.0-py3-none-any.whl", hash = "sha256:0287e96f4d26d4149305414d4e3bc32f0dcd0862365a4bddea19d7a1ec38c4fc", size = 109097, upload-time = "2025-09-23T09:19:10.601Z" },
+]
+
+[[package]]
+name = "asgiref"
+version = "3.10.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/46/08/4dfec9b90758a59acc6be32ac82e98d1fbfc321cb5cfa410436dbacf821c/asgiref-3.10.0.tar.gz", hash = "sha256:d89f2d8cd8b56dada7d52fa7dc8075baa08fb836560710d38c292a7a3f78c04e", size = 37483, upload-time = "2025-10-05T09:15:06.557Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/17/9c/fc2331f538fbf7eedba64b2052e99ccf9ba9d6888e2f41441ee28847004b/asgiref-3.10.0-py3-none-any.whl", hash = "sha256:aef8a81283a34d0ab31630c9b7dfe70c812c95eba78171367ca8745e88124734", size = 24050, upload-time = "2025-10-05T09:15:05.11Z" },
+]
+
+[[package]]
+name = "backoff"
+version = "2.2.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/47/d7/5bbeb12c44d7c4f2fb5b56abce497eb5ed9f34d85701de869acedd602619/backoff-2.2.1.tar.gz", hash = "sha256:03f829f5bb1923180821643f8753b0502c3b682293992485b0eef2807afa5cba", size = 17001, upload-time = "2022-10-05T19:19:32.061Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/df/73/b6e24bd22e6720ca8ee9a85a0c4a2971af8497d8f3193fa05390cbd46e09/backoff-2.2.1-py3-none-any.whl", hash = "sha256:63579f9a0628e06278f7e47b7d7d5b6ce20dc65c5e96a6f3ca99a6adca0396e8", size = 15148, upload-time = "2022-10-05T19:19:30.546Z" },
+]
+
+[[package]]
+name = "certifi"
+version = "2025.10.5"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/4c/5b/b6ce21586237c77ce67d01dc5507039d444b630dd76611bbca2d8e5dcd91/certifi-2025.10.5.tar.gz", hash = "sha256:47c09d31ccf2acf0be3f701ea53595ee7e0b8fa08801c6624be771df09ae7b43", size = 164519, upload-time = "2025-10-05T04:12:15.808Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e4/37/af0d2ef3967ac0d6113837b44a4f0bfe1328c2b9763bd5b1744520e5cfed/certifi-2025.10.5-py3-none-any.whl", hash = "sha256:0f212c2744a9bb6de0c56639a6f68afe01ecd92d91f14ae897c4fe7bbeeef0de", size = 163286, upload-time = "2025-10-05T04:12:14.03Z" },
+]
+
+[[package]]
+name = "charset-normalizer"
+version = "3.4.4"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/13/69/33ddede1939fdd074bce5434295f38fae7136463422fe4fd3e0e89b98062/charset_normalizer-3.4.4.tar.gz", hash = "sha256:94537985111c35f28720e43603b8e7b43a6ecfb2ce1d3058bbe955b73404e21a", size = 129418, upload-time = "2025-10-14T04:42:32.879Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f3/85/1637cd4af66fa687396e757dec650f28025f2a2f5a5531a3208dc0ec43f2/charset_normalizer-3.4.4-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:0a98e6759f854bd25a58a73fa88833fba3b7c491169f86ce1180c948ab3fd394", size = 208425, upload-time = "2025-10-14T04:40:53.353Z" },
+    { url = "https://files.pythonhosted.org/packages/9d/6a/04130023fef2a0d9c62d0bae2649b69f7b7d8d24ea5536feef50551029df/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b5b290ccc2a263e8d185130284f8501e3e36c5e02750fc6b6bdeb2e9e96f1e25", size = 148162, upload-time = "2025-10-14T04:40:54.558Z" },
+    { url = "https://files.pythonhosted.org/packages/78/29/62328d79aa60da22c9e0b9a66539feae06ca0f5a4171ac4f7dc285b83688/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:74bb723680f9f7a6234dcf67aea57e708ec1fbdf5699fb91dfd6f511b0a320ef", size = 144558, upload-time = "2025-10-14T04:40:55.677Z" },
+    { url = "https://files.pythonhosted.org/packages/86/bb/b32194a4bf15b88403537c2e120b817c61cd4ecffa9b6876e941c3ee38fe/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:f1e34719c6ed0b92f418c7c780480b26b5d9c50349e9a9af7d76bf757530350d", size = 161497, upload-time = "2025-10-14T04:40:57.217Z" },
+    { url = "https://files.pythonhosted.org/packages/19/89/a54c82b253d5b9b111dc74aca196ba5ccfcca8242d0fb64146d4d3183ff1/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:2437418e20515acec67d86e12bf70056a33abdacb5cb1655042f6538d6b085a8", size = 159240, upload-time = "2025-10-14T04:40:58.358Z" },
+    { url = "https://files.pythonhosted.org/packages/c0/10/d20b513afe03acc89ec33948320a5544d31f21b05368436d580dec4e234d/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:11d694519d7f29d6cd09f6ac70028dba10f92f6cdd059096db198c283794ac86", size = 153471, upload-time = "2025-10-14T04:40:59.468Z" },
+    { url = "https://files.pythonhosted.org/packages/61/fa/fbf177b55bdd727010f9c0a3c49eefa1d10f960e5f09d1d887bf93c2e698/charset_normalizer-3.4.4-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:ac1c4a689edcc530fc9d9aa11f5774b9e2f33f9a0c6a57864e90908f5208d30a", size = 150864, upload-time = "2025-10-14T04:41:00.623Z" },
+    { url = "https://files.pythonhosted.org/packages/05/12/9fbc6a4d39c0198adeebbde20b619790e9236557ca59fc40e0e3cebe6f40/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:21d142cc6c0ec30d2efee5068ca36c128a30b0f2c53c1c07bd78cb6bc1d3be5f", size = 150647, upload-time = "2025-10-14T04:41:01.754Z" },
+    { url = "https://files.pythonhosted.org/packages/ad/1f/6a9a593d52e3e8c5d2b167daf8c6b968808efb57ef4c210acb907c365bc4/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:5dbe56a36425d26d6cfb40ce79c314a2e4dd6211d51d6d2191c00bed34f354cc", size = 145110, upload-time = "2025-10-14T04:41:03.231Z" },
+    { url = "https://files.pythonhosted.org/packages/30/42/9a52c609e72471b0fc54386dc63c3781a387bb4fe61c20231a4ebcd58bdd/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:5bfbb1b9acf3334612667b61bd3002196fe2a1eb4dd74d247e0f2a4d50ec9bbf", size = 162839, upload-time = "2025-10-14T04:41:04.715Z" },
+    { url = "https://files.pythonhosted.org/packages/c4/5b/c0682bbf9f11597073052628ddd38344a3d673fda35a36773f7d19344b23/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:d055ec1e26e441f6187acf818b73564e6e6282709e9bcb5b63f5b23068356a15", size = 150667, upload-time = "2025-10-14T04:41:05.827Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/24/a41afeab6f990cf2daf6cb8c67419b63b48cf518e4f56022230840c9bfb2/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:af2d8c67d8e573d6de5bc30cdb27e9b95e49115cd9baad5ddbd1a6207aaa82a9", size = 160535, upload-time = "2025-10-14T04:41:06.938Z" },
+    { url = "https://files.pythonhosted.org/packages/2a/e5/6a4ce77ed243c4a50a1fecca6aaaab419628c818a49434be428fe24c9957/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:780236ac706e66881f3b7f2f32dfe90507a09e67d1d454c762cf642e6e1586e0", size = 154816, upload-time = "2025-10-14T04:41:08.101Z" },
+    { url = "https://files.pythonhosted.org/packages/a8/ef/89297262b8092b312d29cdb2517cb1237e51db8ecef2e9af5edbe7b683b1/charset_normalizer-3.4.4-cp312-cp312-win32.whl", hash = "sha256:5833d2c39d8896e4e19b689ffc198f08ea58116bee26dea51e362ecc7cd3ed26", size = 99694, upload-time = "2025-10-14T04:41:09.23Z" },
+    { url = "https://files.pythonhosted.org/packages/3d/2d/1e5ed9dd3b3803994c155cd9aacb60c82c331bad84daf75bcb9c91b3295e/charset_normalizer-3.4.4-cp312-cp312-win_amd64.whl", hash = "sha256:a79cfe37875f822425b89a82333404539ae63dbdddf97f84dcbc3d339aae9525", size = 107131, upload-time = "2025-10-14T04:41:10.467Z" },
+    { url = "https://files.pythonhosted.org/packages/d0/d9/0ed4c7098a861482a7b6a95603edce4c0d9db2311af23da1fb2b75ec26fc/charset_normalizer-3.4.4-cp312-cp312-win_arm64.whl", hash = "sha256:376bec83a63b8021bb5c8ea75e21c4ccb86e7e45ca4eb81146091b56599b80c3", size = 100390, upload-time = "2025-10-14T04:41:11.915Z" },
+    { url = "https://files.pythonhosted.org/packages/97/45/4b3a1239bbacd321068ea6e7ac28875b03ab8bc0aa0966452db17cd36714/charset_normalizer-3.4.4-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:e1f185f86a6f3403aa2420e815904c67b2f9ebc443f045edd0de921108345794", size = 208091, upload-time = "2025-10-14T04:41:13.346Z" },
+    { url = "https://files.pythonhosted.org/packages/7d/62/73a6d7450829655a35bb88a88fca7d736f9882a27eacdca2c6d505b57e2e/charset_normalizer-3.4.4-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6b39f987ae8ccdf0d2642338faf2abb1862340facc796048b604ef14919e55ed", size = 147936, upload-time = "2025-10-14T04:41:14.461Z" },
+    { url = "https://files.pythonhosted.org/packages/89/c5/adb8c8b3d6625bef6d88b251bbb0d95f8205831b987631ab0c8bb5d937c2/charset_normalizer-3.4.4-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:3162d5d8ce1bb98dd51af660f2121c55d0fa541b46dff7bb9b9f86ea1d87de72", size = 144180, upload-time = "2025-10-14T04:41:15.588Z" },
+    { url = "https://files.pythonhosted.org/packages/91/ed/9706e4070682d1cc219050b6048bfd293ccf67b3d4f5a4f39207453d4b99/charset_normalizer-3.4.4-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:81d5eb2a312700f4ecaa977a8235b634ce853200e828fbadf3a9c50bab278328", size = 161346, upload-time = "2025-10-14T04:41:16.738Z" },
+    { url = "https://files.pythonhosted.org/packages/d5/0d/031f0d95e4972901a2f6f09ef055751805ff541511dc1252ba3ca1f80cf5/charset_normalizer-3.4.4-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:5bd2293095d766545ec1a8f612559f6b40abc0eb18bb2f5d1171872d34036ede", size = 158874, upload-time = "2025-10-14T04:41:17.923Z" },
+    { url = "https://files.pythonhosted.org/packages/f5/83/6ab5883f57c9c801ce5e5677242328aa45592be8a00644310a008d04f922/charset_normalizer-3.4.4-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a8a8b89589086a25749f471e6a900d3f662d1d3b6e2e59dcecf787b1cc3a1894", size = 153076, upload-time = "2025-10-14T04:41:19.106Z" },
+    { url = "https://files.pythonhosted.org/packages/75/1e/5ff781ddf5260e387d6419959ee89ef13878229732732ee73cdae01800f2/charset_normalizer-3.4.4-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:bc7637e2f80d8530ee4a78e878bce464f70087ce73cf7c1caf142416923b98f1", size = 150601, upload-time = "2025-10-14T04:41:20.245Z" },
+    { url = "https://files.pythonhosted.org/packages/d7/57/71be810965493d3510a6ca79b90c19e48696fb1ff964da319334b12677f0/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:f8bf04158c6b607d747e93949aa60618b61312fe647a6369f88ce2ff16043490", size = 150376, upload-time = "2025-10-14T04:41:21.398Z" },
+    { url = "https://files.pythonhosted.org/packages/e5/d5/c3d057a78c181d007014feb7e9f2e65905a6c4ef182c0ddf0de2924edd65/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:554af85e960429cf30784dd47447d5125aaa3b99a6f0683589dbd27e2f45da44", size = 144825, upload-time = "2025-10-14T04:41:22.583Z" },
+    { url = "https://files.pythonhosted.org/packages/e6/8c/d0406294828d4976f275ffbe66f00266c4b3136b7506941d87c00cab5272/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:74018750915ee7ad843a774364e13a3db91682f26142baddf775342c3f5b1133", size = 162583, upload-time = "2025-10-14T04:41:23.754Z" },
+    { url = "https://files.pythonhosted.org/packages/d7/24/e2aa1f18c8f15c4c0e932d9287b8609dd30ad56dbe41d926bd846e22fb8d/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:c0463276121fdee9c49b98908b3a89c39be45d86d1dbaa22957e38f6321d4ce3", size = 150366, upload-time = "2025-10-14T04:41:25.27Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/5b/1e6160c7739aad1e2df054300cc618b06bf784a7a164b0f238360721ab86/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:362d61fd13843997c1c446760ef36f240cf81d3ebf74ac62652aebaf7838561e", size = 160300, upload-time = "2025-10-14T04:41:26.725Z" },
+    { url = "https://files.pythonhosted.org/packages/7a/10/f882167cd207fbdd743e55534d5d9620e095089d176d55cb22d5322f2afd/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:9a26f18905b8dd5d685d6d07b0cdf98a79f3c7a918906af7cc143ea2e164c8bc", size = 154465, upload-time = "2025-10-14T04:41:28.322Z" },
+    { url = "https://files.pythonhosted.org/packages/89/66/c7a9e1b7429be72123441bfdbaf2bc13faab3f90b933f664db506dea5915/charset_normalizer-3.4.4-cp313-cp313-win32.whl", hash = "sha256:9b35f4c90079ff2e2edc5b26c0c77925e5d2d255c42c74fdb70fb49b172726ac", size = 99404, upload-time = "2025-10-14T04:41:29.95Z" },
+    { url = "https://files.pythonhosted.org/packages/c4/26/b9924fa27db384bdcd97ab83b4f0a8058d96ad9626ead570674d5e737d90/charset_normalizer-3.4.4-cp313-cp313-win_amd64.whl", hash = "sha256:b435cba5f4f750aa6c0a0d92c541fb79f69a387c91e61f1795227e4ed9cece14", size = 107092, upload-time = "2025-10-14T04:41:31.188Z" },
+    { url = "https://files.pythonhosted.org/packages/af/8f/3ed4bfa0c0c72a7ca17f0380cd9e4dd842b09f664e780c13cff1dcf2ef1b/charset_normalizer-3.4.4-cp313-cp313-win_arm64.whl", hash = "sha256:542d2cee80be6f80247095cc36c418f7bddd14f4a6de45af91dfad36d817bba2", size = 100408, upload-time = "2025-10-14T04:41:32.624Z" },
+    { url = "https://files.pythonhosted.org/packages/2a/35/7051599bd493e62411d6ede36fd5af83a38f37c4767b92884df7301db25d/charset_normalizer-3.4.4-cp314-cp314-macosx_10_13_universal2.whl", hash = "sha256:da3326d9e65ef63a817ecbcc0df6e94463713b754fe293eaa03da99befb9a5bd", size = 207746, upload-time = "2025-10-14T04:41:33.773Z" },
+    { url = "https://files.pythonhosted.org/packages/10/9a/97c8d48ef10d6cd4fcead2415523221624bf58bcf68a802721a6bc807c8f/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8af65f14dc14a79b924524b1e7fffe304517b2bff5a58bf64f30b98bbc5079eb", size = 147889, upload-time = "2025-10-14T04:41:34.897Z" },
+    { url = "https://files.pythonhosted.org/packages/10/bf/979224a919a1b606c82bd2c5fa49b5c6d5727aa47b4312bb27b1734f53cd/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:74664978bb272435107de04e36db5a9735e78232b85b77d45cfb38f758efd33e", size = 143641, upload-time = "2025-10-14T04:41:36.116Z" },
+    { url = "https://files.pythonhosted.org/packages/ba/33/0ad65587441fc730dc7bd90e9716b30b4702dc7b617e6ba4997dc8651495/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:752944c7ffbfdd10c074dc58ec2d5a8a4cd9493b314d367c14d24c17684ddd14", size = 160779, upload-time = "2025-10-14T04:41:37.229Z" },
+    { url = "https://files.pythonhosted.org/packages/67/ed/331d6b249259ee71ddea93f6f2f0a56cfebd46938bde6fcc6f7b9a3d0e09/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:d1f13550535ad8cff21b8d757a3257963e951d96e20ec82ab44bc64aeb62a191", size = 159035, upload-time = "2025-10-14T04:41:38.368Z" },
+    { url = "https://files.pythonhosted.org/packages/67/ff/f6b948ca32e4f2a4576aa129d8bed61f2e0543bf9f5f2b7fc3758ed005c9/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ecaae4149d99b1c9e7b88bb03e3221956f68fd6d50be2ef061b2381b61d20838", size = 152542, upload-time = "2025-10-14T04:41:39.862Z" },
+    { url = "https://files.pythonhosted.org/packages/16/85/276033dcbcc369eb176594de22728541a925b2632f9716428c851b149e83/charset_normalizer-3.4.4-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:cb6254dc36b47a990e59e1068afacdcd02958bdcce30bb50cc1700a8b9d624a6", size = 149524, upload-time = "2025-10-14T04:41:41.319Z" },
+    { url = "https://files.pythonhosted.org/packages/9e/f2/6a2a1f722b6aba37050e626530a46a68f74e63683947a8acff92569f979a/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:c8ae8a0f02f57a6e61203a31428fa1d677cbe50c93622b4149d5c0f319c1d19e", size = 150395, upload-time = "2025-10-14T04:41:42.539Z" },
+    { url = "https://files.pythonhosted.org/packages/60/bb/2186cb2f2bbaea6338cad15ce23a67f9b0672929744381e28b0592676824/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:47cc91b2f4dd2833fddaedd2893006b0106129d4b94fdb6af1f4ce5a9965577c", size = 143680, upload-time = "2025-10-14T04:41:43.661Z" },
+    { url = "https://files.pythonhosted.org/packages/7d/a5/bf6f13b772fbb2a90360eb620d52ed8f796f3c5caee8398c3b2eb7b1c60d/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:82004af6c302b5d3ab2cfc4cc5f29db16123b1a8417f2e25f9066f91d4411090", size = 162045, upload-time = "2025-10-14T04:41:44.821Z" },
+    { url = "https://files.pythonhosted.org/packages/df/c5/d1be898bf0dc3ef9030c3825e5d3b83f2c528d207d246cbabe245966808d/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:2b7d8f6c26245217bd2ad053761201e9f9680f8ce52f0fcd8d0755aeae5b2152", size = 149687, upload-time = "2025-10-14T04:41:46.442Z" },
+    { url = "https://files.pythonhosted.org/packages/a5/42/90c1f7b9341eef50c8a1cb3f098ac43b0508413f33affd762855f67a410e/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:799a7a5e4fb2d5898c60b640fd4981d6a25f1c11790935a44ce38c54e985f828", size = 160014, upload-time = "2025-10-14T04:41:47.631Z" },
+    { url = "https://files.pythonhosted.org/packages/76/be/4d3ee471e8145d12795ab655ece37baed0929462a86e72372fd25859047c/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:99ae2cffebb06e6c22bdc25801d7b30f503cc87dbd283479e7b606f70aff57ec", size = 154044, upload-time = "2025-10-14T04:41:48.81Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/6f/8f7af07237c34a1defe7defc565a9bc1807762f672c0fde711a4b22bf9c0/charset_normalizer-3.4.4-cp314-cp314-win32.whl", hash = "sha256:f9d332f8c2a2fcbffe1378594431458ddbef721c1769d78e2cbc06280d8155f9", size = 99940, upload-time = "2025-10-14T04:41:49.946Z" },
+    { url = "https://files.pythonhosted.org/packages/4b/51/8ade005e5ca5b0d80fb4aff72a3775b325bdc3d27408c8113811a7cbe640/charset_normalizer-3.4.4-cp314-cp314-win_amd64.whl", hash = "sha256:8a6562c3700cce886c5be75ade4a5db4214fda19fede41d9792d100288d8f94c", size = 107104, upload-time = "2025-10-14T04:41:51.051Z" },
+    { url = "https://files.pythonhosted.org/packages/da/5f/6b8f83a55bb8278772c5ae54a577f3099025f9ade59d0136ac24a0df4bde/charset_normalizer-3.4.4-cp314-cp314-win_arm64.whl", hash = "sha256:de00632ca48df9daf77a2c65a484531649261ec9f25489917f09e455cb09ddb2", size = 100743, upload-time = "2025-10-14T04:41:52.122Z" },
+    { url = "https://files.pythonhosted.org/packages/0a/4c/925909008ed5a988ccbb72dcc897407e5d6d3bd72410d69e051fc0c14647/charset_normalizer-3.4.4-py3-none-any.whl", hash = "sha256:7a32c560861a02ff789ad905a2fe94e3f840803362c84fecf1851cb4cf3dc37f", size = 53402, upload-time = "2025-10-14T04:42:31.76Z" },
+]
+
+[[package]]
+name = "click"
+version = "8.3.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/46/61/de6cd827efad202d7057d93e0fed9294b96952e188f7384832791c7b2254/click-8.3.0.tar.gz", hash = "sha256:e7b8232224eba16f4ebe410c25ced9f7875cb5f3263ffc93cc3e8da705e229c4", size = 276943, upload-time = "2025-09-18T17:32:23.696Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/db/d3/9dcc0f5797f070ec8edf30fbadfb200e71d9db6b84d211e3b2085a7589a0/click-8.3.0-py3-none-any.whl", hash = "sha256:9b9f285302c6e3064f4330c05f05b81945b2a39544279343e6e7c5f27a9baddc", size = 107295, upload-time = "2025-09-18T17:32:22.42Z" },
+]
+
+[[package]]
+name = "colorama"
+version = "0.4.6"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/d8/53/6f443c9a4a8358a93a6792e2acffb9d9d5cb0a5cfd8802644b7b1c9a02e4/colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44", size = 27697, upload-time = "2022-10-25T02:36:22.414Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6", size = 25335, upload-time = "2022-10-25T02:36:20.889Z" },
+]
+
+[[package]]
+name = "distro"
+version = "1.9.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/fc/f8/98eea607f65de6527f8a2e8885fc8015d3e6f5775df186e443e0964a11c3/distro-1.9.0.tar.gz", hash = "sha256:2fa77c6fd8940f116ee1d6b94a2f90b13b5ea8d019b98bc8bafdcabcdd9bdbed", size = 60722, upload-time = "2023-12-24T09:54:32.31Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/12/b3/231ffd4ab1fc9d679809f356cebee130ac7daa00d6d6f3206dd4fd137e9e/distro-1.9.0-py3-none-any.whl", hash = "sha256:7bffd925d65168f85027d8da9af6bddab658135b840670a223589bc0c8ef02b2", size = 20277, upload-time = "2023-12-24T09:54:30.421Z" },
+]
+
+[[package]]
+name = "django"
+version = "5.2.7"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "asgiref" },
+    { name = "sqlparse" },
+    { name = "tzdata", marker = "sys_platform == 'win32'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/b1/96/bd84e2bb997994de8bcda47ae4560991084e86536541d7214393880f01a8/django-5.2.7.tar.gz", hash = "sha256:e0f6f12e2551b1716a95a63a1366ca91bbcd7be059862c1b18f989b1da356cdd", size = 10865812, upload-time = "2025-10-01T14:22:12.081Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/8f/ef/81f3372b5dd35d8d354321155d1a38894b2b766f576d0abffac4d8ae78d9/django-5.2.7-py3-none-any.whl", hash = "sha256:59a13a6515f787dec9d97a0438cd2efac78c8aca1c80025244b0fe507fe0754b", size = 8307145, upload-time = "2025-10-01T14:22:49.476Z" },
+]
+
+[[package]]
+name = "h11"
+version = "0.16.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/01/ee/02a2c011bdab74c6fb3c75474d40b3052059d95df7e73351460c8588d963/h11-0.16.0.tar.gz", hash = "sha256:4e35b956cf45792e4caa5885e69fba00bdbc6ffafbfa020300e549b208ee5ff1", size = 101250, upload-time = "2025-04-24T03:35:25.427Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/04/4b/29cac41a4d98d144bf5f6d33995617b185d14b22401f75ca86f384e87ff1/h11-0.16.0-py3-none-any.whl", hash = "sha256:63cf8bbe7522de3bf65932fda1d9c2772064ffb3dae62d55932da54b31cb6c86", size = 37515, upload-time = "2025-04-24T03:35:24.344Z" },
+]
+
+[[package]]
+name = "httpcore"
+version = "1.0.9"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "certifi" },
+    { name = "h11" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/06/94/82699a10bca87a5556c9c59b5963f2d039dbd239f25bc2a63907a05a14cb/httpcore-1.0.9.tar.gz", hash = "sha256:6e34463af53fd2ab5d807f399a9b45ea31c3dfa2276f15a2c3f00afff6e176e8", size = 85484, upload-time = "2025-04-24T22:06:22.219Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/7e/f5/f66802a942d491edb555dd61e3a9961140fd64c90bce1eafd741609d334d/httpcore-1.0.9-py3-none-any.whl", hash = "sha256:2d400746a40668fc9dec9810239072b40b4484b640a8c38fd654a024c7a1bf55", size = 78784, upload-time = "2025-04-24T22:06:20.566Z" },
+]
+
+[[package]]
+name = "httptools"
+version = "0.7.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/b5/46/120a669232c7bdedb9d52d4aeae7e6c7dfe151e99dc70802e2fc7a5e1993/httptools-0.7.1.tar.gz", hash = "sha256:abd72556974f8e7c74a259655924a717a2365b236c882c3f6f8a45fe94703ac9", size = 258961, upload-time = "2025-10-10T03:55:08.559Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/53/7f/403e5d787dc4942316e515e949b0c8a013d84078a915910e9f391ba9b3ed/httptools-0.7.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:38e0c83a2ea9746ebbd643bdfb521b9aa4a91703e2cd705c20443405d2fd16a5", size = 206280, upload-time = "2025-10-10T03:54:39.274Z" },
+    { url = "https://files.pythonhosted.org/packages/2a/0d/7f3fd28e2ce311ccc998c388dd1c53b18120fda3b70ebb022b135dc9839b/httptools-0.7.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:f25bbaf1235e27704f1a7b86cd3304eabc04f569c828101d94a0e605ef7205a5", size = 110004, upload-time = "2025-10-10T03:54:40.403Z" },
+    { url = "https://files.pythonhosted.org/packages/84/a6/b3965e1e146ef5762870bbe76117876ceba51a201e18cc31f5703e454596/httptools-0.7.1-cp312-cp312-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:2c15f37ef679ab9ecc06bfc4e6e8628c32a8e4b305459de7cf6785acd57e4d03", size = 517655, upload-time = "2025-10-10T03:54:41.347Z" },
+    { url = "https://files.pythonhosted.org/packages/11/7d/71fee6f1844e6fa378f2eddde6c3e41ce3a1fb4b2d81118dd544e3441ec0/httptools-0.7.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:7fe6e96090df46b36ccfaf746f03034e5ab723162bc51b0a4cf58305324036f2", size = 511440, upload-time = "2025-10-10T03:54:42.452Z" },
+    { url = "https://files.pythonhosted.org/packages/22/a5/079d216712a4f3ffa24af4a0381b108aa9c45b7a5cc6eb141f81726b1823/httptools-0.7.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:f72fdbae2dbc6e68b8239defb48e6a5937b12218e6ffc2c7846cc37befa84362", size = 495186, upload-time = "2025-10-10T03:54:43.937Z" },
+    { url = "https://files.pythonhosted.org/packages/e9/9e/025ad7b65278745dee3bd0ebf9314934c4592560878308a6121f7f812084/httptools-0.7.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:e99c7b90a29fd82fea9ef57943d501a16f3404d7b9ee81799d41639bdaae412c", size = 499192, upload-time = "2025-10-10T03:54:45.003Z" },
+    { url = "https://files.pythonhosted.org/packages/6d/de/40a8f202b987d43afc4d54689600ff03ce65680ede2f31df348d7f368b8f/httptools-0.7.1-cp312-cp312-win_amd64.whl", hash = "sha256:3e14f530fefa7499334a79b0cf7e7cd2992870eb893526fb097d51b4f2d0f321", size = 86694, upload-time = "2025-10-10T03:54:45.923Z" },
+    { url = "https://files.pythonhosted.org/packages/09/8f/c77b1fcbfd262d422f12da02feb0d218fa228d52485b77b953832105bb90/httptools-0.7.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:6babce6cfa2a99545c60bfef8bee0cc0545413cb0018f617c8059a30ad985de3", size = 202889, upload-time = "2025-10-10T03:54:47.089Z" },
+    { url = "https://files.pythonhosted.org/packages/0a/1a/22887f53602feaa066354867bc49a68fc295c2293433177ee90870a7d517/httptools-0.7.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:601b7628de7504077dd3dcb3791c6b8694bbd967148a6d1f01806509254fb1ca", size = 108180, upload-time = "2025-10-10T03:54:48.052Z" },
+    { url = "https://files.pythonhosted.org/packages/32/6a/6aaa91937f0010d288d3d124ca2946d48d60c3a5ee7ca62afe870e3ea011/httptools-0.7.1-cp313-cp313-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:04c6c0e6c5fb0739c5b8a9eb046d298650a0ff38cf42537fc372b28dc7e4472c", size = 478596, upload-time = "2025-10-10T03:54:48.919Z" },
+    { url = "https://files.pythonhosted.org/packages/6d/70/023d7ce117993107be88d2cbca566a7c1323ccbaf0af7eabf2064fe356f6/httptools-0.7.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:69d4f9705c405ae3ee83d6a12283dc9feba8cc6aaec671b412917e644ab4fa66", size = 473268, upload-time = "2025-10-10T03:54:49.993Z" },
+    { url = "https://files.pythonhosted.org/packages/32/4d/9dd616c38da088e3f436e9a616e1d0cc66544b8cdac405cc4e81c8679fc7/httptools-0.7.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:44c8f4347d4b31269c8a9205d8a5ee2df5322b09bbbd30f8f862185bb6b05346", size = 455517, upload-time = "2025-10-10T03:54:51.066Z" },
+    { url = "https://files.pythonhosted.org/packages/1d/3a/a6c595c310b7df958e739aae88724e24f9246a514d909547778d776799be/httptools-0.7.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:465275d76db4d554918aba40bf1cbebe324670f3dfc979eaffaa5d108e2ed650", size = 458337, upload-time = "2025-10-10T03:54:52.196Z" },
+    { url = "https://files.pythonhosted.org/packages/fd/82/88e8d6d2c51edc1cc391b6e044c6c435b6aebe97b1abc33db1b0b24cd582/httptools-0.7.1-cp313-cp313-win_amd64.whl", hash = "sha256:322d00c2068d125bd570f7bf78b2d367dad02b919d8581d7476d8b75b294e3e6", size = 85743, upload-time = "2025-10-10T03:54:53.448Z" },
+    { url = "https://files.pythonhosted.org/packages/34/50/9d095fcbb6de2d523e027a2f304d4551855c2f46e0b82befd718b8b20056/httptools-0.7.1-cp314-cp314-macosx_10_13_universal2.whl", hash = "sha256:c08fe65728b8d70b6923ce31e3956f859d5e1e8548e6f22ec520a962c6757270", size = 203619, upload-time = "2025-10-10T03:54:54.321Z" },
+    { url = "https://files.pythonhosted.org/packages/07/f0/89720dc5139ae54b03f861b5e2c55a37dba9a5da7d51e1e824a1f343627f/httptools-0.7.1-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:7aea2e3c3953521c3c51106ee11487a910d45586e351202474d45472db7d72d3", size = 108714, upload-time = "2025-10-10T03:54:55.163Z" },
+    { url = "https://files.pythonhosted.org/packages/b3/cb/eea88506f191fb552c11787c23f9a405f4c7b0c5799bf73f2249cd4f5228/httptools-0.7.1-cp314-cp314-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:0e68b8582f4ea9166be62926077a3334064d422cf08ab87d8b74664f8e9058e1", size = 472909, upload-time = "2025-10-10T03:54:56.056Z" },
+    { url = "https://files.pythonhosted.org/packages/e0/4a/a548bdfae6369c0d078bab5769f7b66f17f1bfaa6fa28f81d6be6959066b/httptools-0.7.1-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:df091cf961a3be783d6aebae963cc9b71e00d57fa6f149025075217bc6a55a7b", size = 470831, upload-time = "2025-10-10T03:54:57.219Z" },
+    { url = "https://files.pythonhosted.org/packages/4d/31/14df99e1c43bd132eec921c2e7e11cda7852f65619bc0fc5bdc2d0cb126c/httptools-0.7.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:f084813239e1eb403ddacd06a30de3d3e09a9b76e7894dcda2b22f8a726e9c60", size = 452631, upload-time = "2025-10-10T03:54:58.219Z" },
+    { url = "https://files.pythonhosted.org/packages/22/d2/b7e131f7be8d854d48cb6d048113c30f9a46dca0c9a8b08fcb3fcd588cdc/httptools-0.7.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:7347714368fb2b335e9063bc2b96f2f87a9ceffcd9758ac295f8bbcd3ffbc0ca", size = 452910, upload-time = "2025-10-10T03:54:59.366Z" },
+    { url = "https://files.pythonhosted.org/packages/53/cf/878f3b91e4e6e011eff6d1fa9ca39f7eb17d19c9d7971b04873734112f30/httptools-0.7.1-cp314-cp314-win_amd64.whl", hash = "sha256:cfabda2a5bb85aa2a904ce06d974a3f30fb36cc63d7feaddec05d2050acede96", size = 88205, upload-time = "2025-10-10T03:55:00.389Z" },
+]
+
+[[package]]
+name = "httpx"
+version = "0.28.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "anyio" },
+    { name = "certifi" },
+    { name = "httpcore" },
+    { name = "idna" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/b1/df/48c586a5fe32a0f01324ee087459e112ebb7224f646c0b5023f5e79e9956/httpx-0.28.1.tar.gz", hash = "sha256:75e98c5f16b0f35b567856f597f06ff2270a374470a5c2392242528e3e3e42fc", size = 141406, upload-time = "2024-12-06T15:37:23.222Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/2a/39/e50c7c3a983047577ee07d2a9e53faf5a69493943ec3f6a384bdc792deb2/httpx-0.28.1-py3-none-any.whl", hash = "sha256:d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad", size = 73517, upload-time = "2024-12-06T15:37:21.509Z" },
+]
+
+[[package]]
+name = "idna"
+version = "3.11"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/6f/6d/0703ccc57f3a7233505399edb88de3cbd678da106337b9fcde432b65ed60/idna-3.11.tar.gz", hash = "sha256:795dafcc9c04ed0c1fb032c2aa73654d8e8c5023a7df64a53f39190ada629902", size = 194582, upload-time = "2025-10-12T14:55:20.501Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/0e/61/66938bbb5fc52dbdf84594873d5b51fb1f7c7794e9c0f5bd885f30bc507b/idna-3.11-py3-none-any.whl", hash = "sha256:771a87f49d9defaf64091e6e6fe9c18d4833f140bd19464795bc32d966ca37ea", size = 71008, upload-time = "2025-10-12T14:55:18.883Z" },
+]
+
+[[package]]
+name = "iniconfig"
+version = "2.3.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/72/34/14ca021ce8e5dfedc35312d08ba8bf51fdd999c576889fc2c24cb97f4f10/iniconfig-2.3.0.tar.gz", hash = "sha256:c76315c77db068650d49c5b56314774a7804df16fee4402c1f19d6d15d8c4730", size = 20503, upload-time = "2025-10-18T21:55:43.219Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/cb/b1/3846dd7f199d53cb17f49cba7e651e9ce294d8497c8c150530ed11865bb8/iniconfig-2.3.0-py3-none-any.whl", hash = "sha256:f631c04d2c48c52b84d0d0549c99ff3859c98df65b3101406327ecc7d53fbf12", size = 7484, upload-time = "2025-10-18T21:55:41.639Z" },
+]
+
+[[package]]
+name = "packaging"
+version = "25.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/a1/d4/1fc4078c65507b51b96ca8f8c3ba19e6a61c8253c72794544580a7b6c24d/packaging-25.0.tar.gz", hash = "sha256:d443872c98d677bf60f6a1f2f8c1cb748e8fe762d2bf9d3148b5599295b0fc4f", size = 165727, upload-time = "2025-04-19T11:48:59.673Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/20/12/38679034af332785aac8774540895e234f4d07f7545804097de4b666afd8/packaging-25.0-py3-none-any.whl", hash = "sha256:29572ef2b1f17581046b3a2227d5c611fb25ec70ca1ba8554b24b0e69331a484", size = 66469, upload-time = "2025-04-19T11:48:57.875Z" },
+]
+
+[[package]]
+name = "pluggy"
+version = "1.6.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f9/e2/3e91f31a7d2b083fe6ef3fa267035b518369d9511ffab804f839851d2779/pluggy-1.6.0.tar.gz", hash = "sha256:7dcc130b76258d33b90f61b658791dede3486c3e6bfb003ee5c9bfb396dd22f3", size = 69412, upload-time = "2025-05-15T12:30:07.975Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/54/20/4d324d65cc6d9205fabedc306948156824eb9f0ee1633355a8f7ec5c66bf/pluggy-1.6.0-py3-none-any.whl", hash = "sha256:e920276dd6813095e9377c0bc5566d94c932c33b27a3e3945d8389c374dd4746", size = 20538, upload-time = "2025-05-15T12:30:06.134Z" },
+]
+
+[[package]]
+name = "posthog"
+source = { editable = "../" }
+dependencies = [
+    { name = "backoff" },
+    { name = "distro" },
+    { name = "python-dateutil" },
+    { name = "requests" },
+    { name = "six" },
+    { name = "typing-extensions" },
+]
+
+[package.metadata]
+requires-dist = [
+    { name = "anthropic", marker = "extra == 'test'" },
+    { name = "backoff", specifier = ">=1.10.0" },
+    { name = "coverage", marker = "extra == 'test'" },
+    { name = "distro", specifier = ">=1.5.0" },
+    { name = "django", marker = "extra == 'test'" },
+    { name = "django-stubs", marker = "extra == 'dev'" },
+    { name = "freezegun", marker = "extra == 'test'", specifier = "==1.5.1" },
+    { name = "google-genai", marker = "extra == 'test'" },
+    { name = "langchain", marker = "extra == 'langchain'", specifier = ">=0.2.0" },
+    { name = "langchain-anthropic", marker = "extra == 'test'", specifier = ">=0.3.15" },
+    { name = "langchain-community", marker = "extra == 'test'", specifier = ">=0.3.25" },
+    { name = "langchain-core", marker = "extra == 'test'", specifier = ">=0.3.65" },
+    { name = "langchain-openai", marker = "extra == 'test'", specifier = ">=0.3.22" },
+    { name = "langgraph", marker = "extra == 'test'", specifier = ">=0.4.8" },
+    { name = "lxml", marker = "extra == 'dev'" },
+    { name = "mock", marker = "extra == 'test'", specifier = ">=2.0.0" },
+    { name = "mypy", marker = "extra == 'dev'" },
+    { name = "mypy-baseline", marker = "extra == 'dev'" },
+    { name = "openai", marker = "extra == 'test'" },
+    { name = "packaging", marker = "extra == 'dev'" },
+    { name = "parameterized", marker = "extra == 'test'", specifier = ">=0.8.1" },
+    { name = "pre-commit", marker = "extra == 'dev'" },
+    { name = "pydantic", marker = "extra == 'dev'" },
+    { name = "pydantic", marker = "extra == 'test'" },
+    { name = "pytest", marker = "extra == 'test'" },
+    { name = "pytest-asyncio", marker = "extra == 'test'" },
+    { name = "pytest-timeout", marker = "extra == 'test'" },
+    { name = "python-dateutil", specifier = ">=2.2" },
+    { name = "requests", specifier = ">=2.7,<3.0" },
+    { name = "ruff", marker = "extra == 'dev'" },
+    { name = "setuptools", marker = "extra == 'dev'" },
+    { name = "six", specifier = ">=1.5" },
+    { name = "tomli", marker = "extra == 'dev'" },
+    { name = "tomli-w", marker = "extra == 'dev'" },
+    { name = "twine", marker = "extra == 'dev'" },
+    { name = "types-mock", marker = "extra == 'dev'" },
+    { name = "types-python-dateutil", marker = "extra == 'dev'" },
+    { name = "types-requests", marker = "extra == 'dev'" },
+    { name = "types-setuptools", marker = "extra == 'dev'" },
+    { name = "types-six", marker = "extra == 'dev'" },
+    { name = "typing-extensions", specifier = ">=4.2.0" },
+    { name = "wheel", marker = "extra == 'dev'" },
+]
+provides-extras = ["langchain", "dev", "test"]
+
+[[package]]
+name = "pygments"
+version = "2.19.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/b0/77/a5b8c569bf593b0140bde72ea885a803b82086995367bf2037de0159d924/pygments-2.19.2.tar.gz", hash = "sha256:636cb2477cec7f8952536970bc533bc43743542f70392ae026374600add5b887", size = 4968631, upload-time = "2025-06-21T13:39:12.283Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c7/21/705964c7812476f378728bdf590ca4b771ec72385c533964653c68e86bdc/pygments-2.19.2-py3-none-any.whl", hash = "sha256:86540386c03d588bb81d44bc3928634ff26449851e99741617ecb9037ee5ec0b", size = 1225217, upload-time = "2025-06-21T13:39:07.939Z" },
+]
+
+[[package]]
+name = "pytest"
+version = "8.4.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "iniconfig" },
+    { name = "packaging" },
+    { name = "pluggy" },
+    { name = "pygments" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/a3/5c/00a0e072241553e1a7496d638deababa67c5058571567b92a7eaa258397c/pytest-8.4.2.tar.gz", hash = "sha256:86c0d0b93306b961d58d62a4db4879f27fe25513d4b969df351abdddb3c30e01", size = 1519618, upload-time = "2025-09-04T14:34:22.711Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a8/a4/20da314d277121d6534b3a980b29035dcd51e6744bd79075a6ce8fa4eb8d/pytest-8.4.2-py3-none-any.whl", hash = "sha256:872f880de3fc3a5bdc88a11b39c9710c3497a547cfa9320bc3c5e62fbf272e79", size = 365750, upload-time = "2025-09-04T14:34:20.226Z" },
+]
+
+[[package]]
+name = "pytest-asyncio"
+version = "1.2.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pytest" },
+    { name = "typing-extensions", marker = "python_full_version < '3.13'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/42/86/9e3c5f48f7b7b638b216e4b9e645f54d199d7abbbab7a64a13b4e12ba10f/pytest_asyncio-1.2.0.tar.gz", hash = "sha256:c609a64a2a8768462d0c99811ddb8bd2583c33fd33cf7f21af1c142e824ffb57", size = 50119, upload-time = "2025-09-12T07:33:53.816Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/04/93/2fa34714b7a4ae72f2f8dad66ba17dd9a2c793220719e736dda28b7aec27/pytest_asyncio-1.2.0-py3-none-any.whl", hash = "sha256:8e17ae5e46d8e7efe51ab6494dd2010f4ca8dae51652aa3c8d55acf50bfb2e99", size = 15095, upload-time = "2025-09-12T07:33:52.639Z" },
+]
+
+[[package]]
+name = "pytest-django"
+version = "4.11.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pytest" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/b1/fb/55d580352db26eb3d59ad50c64321ddfe228d3d8ac107db05387a2fadf3a/pytest_django-4.11.1.tar.gz", hash = "sha256:a949141a1ee103cb0e7a20f1451d355f83f5e4a5d07bdd4dcfdd1fd0ff227991", size = 86202, upload-time = "2025-04-03T18:56:09.338Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/be/ac/bd0608d229ec808e51a21044f3f2f27b9a37e7a0ebaca7247882e67876af/pytest_django-4.11.1-py3-none-any.whl", hash = "sha256:1b63773f648aa3d8541000c26929c1ea63934be1cfa674c76436966d73fe6a10", size = 25281, upload-time = "2025-04-03T18:56:07.678Z" },
+]
+
+[[package]]
+name = "python-dateutil"
+version = "2.9.0.post0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "six" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/66/c0/0c8b6ad9f17a802ee498c46e004a0eb49bc148f2fd230864601a86dcf6db/python-dateutil-2.9.0.post0.tar.gz", hash = "sha256:37dd54208da7e1cd875388217d5e00ebd4179249f90fb72437e91a35459a0ad3", size = 342432, upload-time = "2024-03-01T18:36:20.211Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ec/57/56b9bcc3c9c6a792fcbaf139543cee77261f3651ca9da0c93f5c1221264b/python_dateutil-2.9.0.post0-py2.py3-none-any.whl", hash = "sha256:a8b2bc7bffae282281c8140a97d3aa9c14da0b136dfe83f850eea9a5f7470427", size = 229892, upload-time = "2024-03-01T18:36:18.57Z" },
+]
+
+[[package]]
+name = "python-dotenv"
+version = "1.2.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f0/26/19cadc79a718c5edbec86fd4919a6b6d3f681039a2f6d66d14be94e75fb9/python_dotenv-1.2.1.tar.gz", hash = "sha256:42667e897e16ab0d66954af0e60a9caa94f0fd4ecf3aaf6d2d260eec1aa36ad6", size = 44221, upload-time = "2025-10-26T15:12:10.434Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/14/1b/a298b06749107c305e1fe0f814c6c74aea7b2f1e10989cb30f544a1b3253/python_dotenv-1.2.1-py3-none-any.whl", hash = "sha256:b81ee9561e9ca4004139c6cbba3a238c32b03e4894671e181b671e8cb8425d61", size = 21230, upload-time = "2025-10-26T15:12:09.109Z" },
+]
+
+[[package]]
+name = "pyyaml"
+version = "6.0.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/05/8e/961c0007c59b8dd7729d542c61a4d537767a59645b82a0b521206e1e25c2/pyyaml-6.0.3.tar.gz", hash = "sha256:d76623373421df22fb4cf8817020cbb7ef15c725b9d5e45f17e189bfc384190f", size = 130960, upload-time = "2025-09-25T21:33:16.546Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d1/33/422b98d2195232ca1826284a76852ad5a86fe23e31b009c9886b2d0fb8b2/pyyaml-6.0.3-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:7f047e29dcae44602496db43be01ad42fc6f1cc0d8cd6c83d342306c32270196", size = 182063, upload-time = "2025-09-25T21:32:11.445Z" },
+    { url = "https://files.pythonhosted.org/packages/89/a0/6cf41a19a1f2f3feab0e9c0b74134aa2ce6849093d5517a0c550fe37a648/pyyaml-6.0.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:fc09d0aa354569bc501d4e787133afc08552722d3ab34836a80547331bb5d4a0", size = 173973, upload-time = "2025-09-25T21:32:12.492Z" },
+    { url = "https://files.pythonhosted.org/packages/ed/23/7a778b6bd0b9a8039df8b1b1d80e2e2ad78aa04171592c8a5c43a56a6af4/pyyaml-6.0.3-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9149cad251584d5fb4981be1ecde53a1ca46c891a79788c0df828d2f166bda28", size = 775116, upload-time = "2025-09-25T21:32:13.652Z" },
+    { url = "https://files.pythonhosted.org/packages/65/30/d7353c338e12baef4ecc1b09e877c1970bd3382789c159b4f89d6a70dc09/pyyaml-6.0.3-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:5fdec68f91a0c6739b380c83b951e2c72ac0197ace422360e6d5a959d8d97b2c", size = 844011, upload-time = "2025-09-25T21:32:15.21Z" },
+    { url = "https://files.pythonhosted.org/packages/8b/9d/b3589d3877982d4f2329302ef98a8026e7f4443c765c46cfecc8858c6b4b/pyyaml-6.0.3-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ba1cc08a7ccde2d2ec775841541641e4548226580ab850948cbfda66a1befcdc", size = 807870, upload-time = "2025-09-25T21:32:16.431Z" },
+    { url = "https://files.pythonhosted.org/packages/05/c0/b3be26a015601b822b97d9149ff8cb5ead58c66f981e04fedf4e762f4bd4/pyyaml-6.0.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:8dc52c23056b9ddd46818a57b78404882310fb473d63f17b07d5c40421e47f8e", size = 761089, upload-time = "2025-09-25T21:32:17.56Z" },
+    { url = "https://files.pythonhosted.org/packages/be/8e/98435a21d1d4b46590d5459a22d88128103f8da4c2d4cb8f14f2a96504e1/pyyaml-6.0.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:41715c910c881bc081f1e8872880d3c650acf13dfa8214bad49ed4cede7c34ea", size = 790181, upload-time = "2025-09-25T21:32:18.834Z" },
+    { url = "https://files.pythonhosted.org/packages/74/93/7baea19427dcfbe1e5a372d81473250b379f04b1bd3c4c5ff825e2327202/pyyaml-6.0.3-cp312-cp312-win32.whl", hash = "sha256:96b533f0e99f6579b3d4d4995707cf36df9100d67e0c8303a0c55b27b5f99bc5", size = 137658, upload-time = "2025-09-25T21:32:20.209Z" },
+    { url = "https://files.pythonhosted.org/packages/86/bf/899e81e4cce32febab4fb42bb97dcdf66bc135272882d1987881a4b519e9/pyyaml-6.0.3-cp312-cp312-win_amd64.whl", hash = "sha256:5fcd34e47f6e0b794d17de1b4ff496c00986e1c83f7ab2fb8fcfe9616ff7477b", size = 154003, upload-time = "2025-09-25T21:32:21.167Z" },
+    { url = "https://files.pythonhosted.org/packages/1a/08/67bd04656199bbb51dbed1439b7f27601dfb576fb864099c7ef0c3e55531/pyyaml-6.0.3-cp312-cp312-win_arm64.whl", hash = "sha256:64386e5e707d03a7e172c0701abfb7e10f0fb753ee1d773128192742712a98fd", size = 140344, upload-time = "2025-09-25T21:32:22.617Z" },
+    { url = "https://files.pythonhosted.org/packages/d1/11/0fd08f8192109f7169db964b5707a2f1e8b745d4e239b784a5a1dd80d1db/pyyaml-6.0.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:8da9669d359f02c0b91ccc01cac4a67f16afec0dac22c2ad09f46bee0697eba8", size = 181669, upload-time = "2025-09-25T21:32:23.673Z" },
+    { url = "https://files.pythonhosted.org/packages/b1/16/95309993f1d3748cd644e02e38b75d50cbc0d9561d21f390a76242ce073f/pyyaml-6.0.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:2283a07e2c21a2aa78d9c4442724ec1eb15f5e42a723b99cb3d822d48f5f7ad1", size = 173252, upload-time = "2025-09-25T21:32:25.149Z" },
+    { url = "https://files.pythonhosted.org/packages/50/31/b20f376d3f810b9b2371e72ef5adb33879b25edb7a6d072cb7ca0c486398/pyyaml-6.0.3-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ee2922902c45ae8ccada2c5b501ab86c36525b883eff4255313a253a3160861c", size = 767081, upload-time = "2025-09-25T21:32:26.575Z" },
+    { url = "https://files.pythonhosted.org/packages/49/1e/a55ca81e949270d5d4432fbbd19dfea5321eda7c41a849d443dc92fd1ff7/pyyaml-6.0.3-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:a33284e20b78bd4a18c8c2282d549d10bc8408a2a7ff57653c0cf0b9be0afce5", size = 841159, upload-time = "2025-09-25T21:32:27.727Z" },
+    { url = "https://files.pythonhosted.org/packages/74/27/e5b8f34d02d9995b80abcef563ea1f8b56d20134d8f4e5e81733b1feceb2/pyyaml-6.0.3-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0f29edc409a6392443abf94b9cf89ce99889a1dd5376d94316ae5145dfedd5d6", size = 801626, upload-time = "2025-09-25T21:32:28.878Z" },
+    { url = "https://files.pythonhosted.org/packages/f9/11/ba845c23988798f40e52ba45f34849aa8a1f2d4af4b798588010792ebad6/pyyaml-6.0.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:f7057c9a337546edc7973c0d3ba84ddcdf0daa14533c2065749c9075001090e6", size = 753613, upload-time = "2025-09-25T21:32:30.178Z" },
+    { url = "https://files.pythonhosted.org/packages/3d/e0/7966e1a7bfc0a45bf0a7fb6b98ea03fc9b8d84fa7f2229e9659680b69ee3/pyyaml-6.0.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:eda16858a3cab07b80edaf74336ece1f986ba330fdb8ee0d6c0d68fe82bc96be", size = 794115, upload-time = "2025-09-25T21:32:31.353Z" },
+    { url = "https://files.pythonhosted.org/packages/de/94/980b50a6531b3019e45ddeada0626d45fa85cbe22300844a7983285bed3b/pyyaml-6.0.3-cp313-cp313-win32.whl", hash = "sha256:d0eae10f8159e8fdad514efdc92d74fd8d682c933a6dd088030f3834bc8e6b26", size = 137427, upload-time = "2025-09-25T21:32:32.58Z" },
+    { url = "https://files.pythonhosted.org/packages/97/c9/39d5b874e8b28845e4ec2202b5da735d0199dbe5b8fb85f91398814a9a46/pyyaml-6.0.3-cp313-cp313-win_amd64.whl", hash = "sha256:79005a0d97d5ddabfeeea4cf676af11e647e41d81c9a7722a193022accdb6b7c", size = 154090, upload-time = "2025-09-25T21:32:33.659Z" },
+    { url = "https://files.pythonhosted.org/packages/73/e8/2bdf3ca2090f68bb3d75b44da7bbc71843b19c9f2b9cb9b0f4ab7a5a4329/pyyaml-6.0.3-cp313-cp313-win_arm64.whl", hash = "sha256:5498cd1645aa724a7c71c8f378eb29ebe23da2fc0d7a08071d89469bf1d2defb", size = 140246, upload-time = "2025-09-25T21:32:34.663Z" },
+    { url = "https://files.pythonhosted.org/packages/9d/8c/f4bd7f6465179953d3ac9bc44ac1a8a3e6122cf8ada906b4f96c60172d43/pyyaml-6.0.3-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:8d1fab6bb153a416f9aeb4b8763bc0f22a5586065f86f7664fc23339fc1c1fac", size = 181814, upload-time = "2025-09-25T21:32:35.712Z" },
+    { url = "https://files.pythonhosted.org/packages/bd/9c/4d95bb87eb2063d20db7b60faa3840c1b18025517ae857371c4dd55a6b3a/pyyaml-6.0.3-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:34d5fcd24b8445fadc33f9cf348c1047101756fd760b4dacb5c3e99755703310", size = 173809, upload-time = "2025-09-25T21:32:36.789Z" },
+    { url = "https://files.pythonhosted.org/packages/92/b5/47e807c2623074914e29dabd16cbbdd4bf5e9b2db9f8090fa64411fc5382/pyyaml-6.0.3-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:501a031947e3a9025ed4405a168e6ef5ae3126c59f90ce0cd6f2bfc477be31b7", size = 766454, upload-time = "2025-09-25T21:32:37.966Z" },
+    { url = "https://files.pythonhosted.org/packages/02/9e/e5e9b168be58564121efb3de6859c452fccde0ab093d8438905899a3a483/pyyaml-6.0.3-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:b3bc83488de33889877a0f2543ade9f70c67d66d9ebb4ac959502e12de895788", size = 836355, upload-time = "2025-09-25T21:32:39.178Z" },
+    { url = "https://files.pythonhosted.org/packages/88/f9/16491d7ed2a919954993e48aa941b200f38040928474c9e85ea9e64222c3/pyyaml-6.0.3-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c458b6d084f9b935061bc36216e8a69a7e293a2f1e68bf956dcd9e6cbcd143f5", size = 794175, upload-time = "2025-09-25T21:32:40.865Z" },
+    { url = "https://files.pythonhosted.org/packages/dd/3f/5989debef34dc6397317802b527dbbafb2b4760878a53d4166579111411e/pyyaml-6.0.3-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:7c6610def4f163542a622a73fb39f534f8c101d690126992300bf3207eab9764", size = 755228, upload-time = "2025-09-25T21:32:42.084Z" },
+    { url = "https://files.pythonhosted.org/packages/d7/ce/af88a49043cd2e265be63d083fc75b27b6ed062f5f9fd6cdc223ad62f03e/pyyaml-6.0.3-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:5190d403f121660ce8d1d2c1bb2ef1bd05b5f68533fc5c2ea899bd15f4399b35", size = 789194, upload-time = "2025-09-25T21:32:43.362Z" },
+    { url = "https://files.pythonhosted.org/packages/23/20/bb6982b26a40bb43951265ba29d4c246ef0ff59c9fdcdf0ed04e0687de4d/pyyaml-6.0.3-cp314-cp314-win_amd64.whl", hash = "sha256:4a2e8cebe2ff6ab7d1050ecd59c25d4c8bd7e6f400f5f82b96557ac0abafd0ac", size = 156429, upload-time = "2025-09-25T21:32:57.844Z" },
+    { url = "https://files.pythonhosted.org/packages/f4/f4/a4541072bb9422c8a883ab55255f918fa378ecf083f5b85e87fc2b4eda1b/pyyaml-6.0.3-cp314-cp314-win_arm64.whl", hash = "sha256:93dda82c9c22deb0a405ea4dc5f2d0cda384168e466364dec6255b293923b2f3", size = 143912, upload-time = "2025-09-25T21:32:59.247Z" },
+    { url = "https://files.pythonhosted.org/packages/7c/f9/07dd09ae774e4616edf6cda684ee78f97777bdd15847253637a6f052a62f/pyyaml-6.0.3-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:02893d100e99e03eda1c8fd5c441d8c60103fd175728e23e431db1b589cf5ab3", size = 189108, upload-time = "2025-09-25T21:32:44.377Z" },
+    { url = "https://files.pythonhosted.org/packages/4e/78/8d08c9fb7ce09ad8c38ad533c1191cf27f7ae1effe5bb9400a46d9437fcf/pyyaml-6.0.3-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:c1ff362665ae507275af2853520967820d9124984e0f7466736aea23d8611fba", size = 183641, upload-time = "2025-09-25T21:32:45.407Z" },
+    { url = "https://files.pythonhosted.org/packages/7b/5b/3babb19104a46945cf816d047db2788bcaf8c94527a805610b0289a01c6b/pyyaml-6.0.3-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6adc77889b628398debc7b65c073bcb99c4a0237b248cacaf3fe8a557563ef6c", size = 831901, upload-time = "2025-09-25T21:32:48.83Z" },
+    { url = "https://files.pythonhosted.org/packages/8b/cc/dff0684d8dc44da4d22a13f35f073d558c268780ce3c6ba1b87055bb0b87/pyyaml-6.0.3-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:a80cb027f6b349846a3bf6d73b5e95e782175e52f22108cfa17876aaeff93702", size = 861132, upload-time = "2025-09-25T21:32:50.149Z" },
+    { url = "https://files.pythonhosted.org/packages/b1/5e/f77dc6b9036943e285ba76b49e118d9ea929885becb0a29ba8a7c75e29fe/pyyaml-6.0.3-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:00c4bdeba853cc34e7dd471f16b4114f4162dc03e6b7afcc2128711f0eca823c", size = 839261, upload-time = "2025-09-25T21:32:51.808Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/88/a9db1376aa2a228197c58b37302f284b5617f56a5d959fd1763fb1675ce6/pyyaml-6.0.3-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:66e1674c3ef6f541c35191caae2d429b967b99e02040f5ba928632d9a7f0f065", size = 805272, upload-time = "2025-09-25T21:32:52.941Z" },
+    { url = "https://files.pythonhosted.org/packages/da/92/1446574745d74df0c92e6aa4a7b0b3130706a4142b2d1a5869f2eaa423c6/pyyaml-6.0.3-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:16249ee61e95f858e83976573de0f5b2893b3677ba71c9dd36b9cf8be9ac6d65", size = 829923, upload-time = "2025-09-25T21:32:54.537Z" },
+    { url = "https://files.pythonhosted.org/packages/f0/7a/1c7270340330e575b92f397352af856a8c06f230aa3e76f86b39d01b416a/pyyaml-6.0.3-cp314-cp314t-win_amd64.whl", hash = "sha256:4ad1906908f2f5ae4e5a8ddfce73c320c2a1429ec52eafd27138b7f1cbe341c9", size = 174062, upload-time = "2025-09-25T21:32:55.767Z" },
+    { url = "https://files.pythonhosted.org/packages/f1/12/de94a39c2ef588c7e6455cfbe7343d3b2dc9d6b6b2f40c4c6565744c873d/pyyaml-6.0.3-cp314-cp314t-win_arm64.whl", hash = "sha256:ebc55a14a21cb14062aa4162f906cd962b28e2e9ea38f9b4391244cd8de4ae0b", size = 149341, upload-time = "2025-09-25T21:32:56.828Z" },
+]
+
+[[package]]
+name = "requests"
+version = "2.32.5"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "certifi" },
+    { name = "charset-normalizer" },
+    { name = "idna" },
+    { name = "urllib3" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/c9/74/b3ff8e6c8446842c3f5c837e9c3dfcfe2018ea6ecef224c710c85ef728f4/requests-2.32.5.tar.gz", hash = "sha256:dbba0bac56e100853db0ea71b82b4dfd5fe2bf6d3754a8893c3af500cec7d7cf", size = 134517, upload-time = "2025-08-18T20:46:02.573Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/1e/db/4254e3eabe8020b458f1a747140d32277ec7a271daf1d235b70dc0b4e6e3/requests-2.32.5-py3-none-any.whl", hash = "sha256:2462f94637a34fd532264295e186976db0f5d453d1cdd31473c85a6a161affb6", size = 64738, upload-time = "2025-08-18T20:46:00.542Z" },
+]
+
+[[package]]
+name = "six"
+version = "1.17.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/94/e7/b2c673351809dca68a0e064b6af791aa332cf192da575fd474ed7d6f16a2/six-1.17.0.tar.gz", hash = "sha256:ff70335d468e7eb6ec65b95b99d3a2836546063f63acc5171de367e834932a81", size = 34031, upload-time = "2024-12-04T17:35:28.174Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b7/ce/149a00dd41f10bc29e5921b496af8b574d8413afcd5e30dfa0ed46c2cc5e/six-1.17.0-py2.py3-none-any.whl", hash = "sha256:4721f391ed90541fddacab5acf947aa0d3dc7d27b2e1e8eda2be8970586c3274", size = 11050, upload-time = "2024-12-04T17:35:26.475Z" },
+]
+
+[[package]]
+name = "sniffio"
+version = "1.3.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/a2/87/a6771e1546d97e7e041b6ae58d80074f81b7d5121207425c964ddf5cfdbd/sniffio-1.3.1.tar.gz", hash = "sha256:f4324edc670a0f49750a81b895f35c3adb843cca46f0530f79fc1babb23789dc", size = 20372, upload-time = "2024-02-25T23:20:04.057Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e9/44/75a9c9421471a6c4805dbf2356f7c181a29c1879239abab1ea2cc8f38b40/sniffio-1.3.1-py3-none-any.whl", hash = "sha256:2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2", size = 10235, upload-time = "2024-02-25T23:20:01.196Z" },
+]
+
+[[package]]
+name = "sqlparse"
+version = "0.5.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/e5/40/edede8dd6977b0d3da179a342c198ed100dd2aba4be081861ee5911e4da4/sqlparse-0.5.3.tar.gz", hash = "sha256:09f67787f56a0b16ecdbde1bfc7f5d9c3371ca683cfeaa8e6ff60b4807ec9272", size = 84999, upload-time = "2024-12-10T12:05:30.728Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a9/5c/bfd6bd0bf979426d405cc6e71eceb8701b148b16c21d2dc3c261efc61c7b/sqlparse-0.5.3-py3-none-any.whl", hash = "sha256:cf2196ed3418f3ba5de6af7e82c694a9fbdbfecccdfc72e281548517081f16ca", size = 44415, upload-time = "2024-12-10T12:05:27.824Z" },
+]
+
+[[package]]
+name = "test-django5"
+version = "0.1.0"
+source = { virtual = "." }
+dependencies = [
+    { name = "django" },
+    { name = "httpx" },
+    { name = "posthog" },
+    { name = "pytest" },
+    { name = "pytest-asyncio" },
+    { name = "pytest-django" },
+    { name = "uvicorn", extra = ["standard"] },
+]
+
+[package.metadata]
+requires-dist = [
+    { name = "django", specifier = "~=5.2.7" },
+    { name = "httpx", specifier = "~=0.28.1" },
+    { name = "posthog", editable = "../" },
+    { name = "pytest", specifier = "~=8.4.2" },
+    { name = "pytest-asyncio", specifier = "~=1.2.0" },
+    { name = "pytest-django", specifier = "~=4.11.1" },
+    { name = "uvicorn", extras = ["standard"], specifier = "~=0.38.0" },
+]
+
+[[package]]
+name = "typing-extensions"
+version = "4.15.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/72/94/1a15dd82efb362ac84269196e94cf00f187f7ed21c242792a923cdb1c61f/typing_extensions-4.15.0.tar.gz", hash = "sha256:0cea48d173cc12fa28ecabc3b837ea3cf6f38c6d1136f85cbaaf598984861466", size = 109391, upload-time = "2025-08-25T13:49:26.313Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/18/67/36e9267722cc04a6b9f15c7f3441c2363321a3ea07da7ae0c0707beb2a9c/typing_extensions-4.15.0-py3-none-any.whl", hash = "sha256:f0fa19c6845758ab08074a0cfa8b7aecb71c999ca73d62883bc25cc018c4e548", size = 44614, upload-time = "2025-08-25T13:49:24.86Z" },
+]
+
+[[package]]
+name = "tzdata"
+version = "2025.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/95/32/1a225d6164441be760d75c2c42e2780dc0873fe382da3e98a2e1e48361e5/tzdata-2025.2.tar.gz", hash = "sha256:b60a638fcc0daffadf82fe0f57e53d06bdec2f36c4df66280ae79bce6bd6f2b9", size = 196380, upload-time = "2025-03-23T13:54:43.652Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/5c/23/c7abc0ca0a1526a0774eca151daeb8de62ec457e77262b66b359c3c7679e/tzdata-2025.2-py2.py3-none-any.whl", hash = "sha256:1a403fada01ff9221ca8044d701868fa132215d84beb92242d9acd2147f667a8", size = 347839, upload-time = "2025-03-23T13:54:41.845Z" },
+]
+
+[[package]]
+name = "urllib3"
+version = "2.5.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/15/22/9ee70a2574a4f4599c47dd506532914ce044817c7752a79b6a51286319bc/urllib3-2.5.0.tar.gz", hash = "sha256:3fc47733c7e419d4bc3f6b3dc2b4f890bb743906a30d56ba4a5bfa4bbff92760", size = 393185, upload-time = "2025-06-18T14:07:41.644Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a7/c2/fe1e52489ae3122415c51f387e221dd0773709bad6c6cdaa599e8a2c5185/urllib3-2.5.0-py3-none-any.whl", hash = "sha256:e6b01673c0fa6a13e374b50871808eb3bf7046c4b125b216f6bf1cc604cff0dc", size = 129795, upload-time = "2025-06-18T14:07:40.39Z" },
+]
+
+[[package]]
+name = "uvicorn"
+version = "0.38.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "click" },
+    { name = "h11" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/cb/ce/f06b84e2697fef4688ca63bdb2fdf113ca0a3be33f94488f2cadb690b0cf/uvicorn-0.38.0.tar.gz", hash = "sha256:fd97093bdd120a2609fc0d3afe931d4d4ad688b6e75f0f929fde1bc36fe0e91d", size = 80605, upload-time = "2025-10-18T13:46:44.63Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ee/d9/d88e73ca598f4f6ff671fb5fde8a32925c2e08a637303a1d12883c7305fa/uvicorn-0.38.0-py3-none-any.whl", hash = "sha256:48c0afd214ceb59340075b4a052ea1ee91c16fbc2a9b1469cca0e54566977b02", size = 68109, upload-time = "2025-10-18T13:46:42.958Z" },
+]
+
+[package.optional-dependencies]
+standard = [
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "httptools" },
+    { name = "python-dotenv" },
+    { name = "pyyaml" },
+    { name = "uvloop", marker = "platform_python_implementation != 'PyPy' and sys_platform != 'cygwin' and sys_platform != 'win32'" },
+    { name = "watchfiles" },
+    { name = "websockets" },
+]
+
+[[package]]
+name = "uvloop"
+version = "0.22.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/06/f0/18d39dbd1971d6d62c4629cc7fa67f74821b0dc1f5a77af43719de7936a7/uvloop-0.22.1.tar.gz", hash = "sha256:6c84bae345b9147082b17371e3dd5d42775bddce91f885499017f4607fdaf39f", size = 2443250, upload-time = "2025-10-16T22:17:19.342Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/3d/ff/7f72e8170be527b4977b033239a83a68d5c881cc4775fca255c677f7ac5d/uvloop-0.22.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:fe94b4564e865d968414598eea1a6de60adba0c040ba4ed05ac1300de402cd42", size = 1359936, upload-time = "2025-10-16T22:16:29.436Z" },
+    { url = "https://files.pythonhosted.org/packages/c3/c6/e5d433f88fd54d81ef4be58b2b7b0cea13c442454a1db703a1eea0db1a59/uvloop-0.22.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:51eb9bd88391483410daad430813d982010f9c9c89512321f5b60e2cddbdddd6", size = 752769, upload-time = "2025-10-16T22:16:30.493Z" },
+    { url = "https://files.pythonhosted.org/packages/24/68/a6ac446820273e71aa762fa21cdcc09861edd3536ff47c5cd3b7afb10eeb/uvloop-0.22.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:700e674a166ca5778255e0e1dc4e9d79ab2acc57b9171b79e65feba7184b3370", size = 4317413, upload-time = "2025-10-16T22:16:31.644Z" },
+    { url = "https://files.pythonhosted.org/packages/5f/6f/e62b4dfc7ad6518e7eff2516f680d02a0f6eb62c0c212e152ca708a0085e/uvloop-0.22.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7b5b1ac819a3f946d3b2ee07f09149578ae76066d70b44df3fa990add49a82e4", size = 4426307, upload-time = "2025-10-16T22:16:32.917Z" },
+    { url = "https://files.pythonhosted.org/packages/90/60/97362554ac21e20e81bcef1150cb2a7e4ffdaf8ea1e5b2e8bf7a053caa18/uvloop-0.22.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:e047cc068570bac9866237739607d1313b9253c3051ad84738cbb095be0537b2", size = 4131970, upload-time = "2025-10-16T22:16:34.015Z" },
+    { url = "https://files.pythonhosted.org/packages/99/39/6b3f7d234ba3964c428a6e40006340f53ba37993f46ed6e111c6e9141d18/uvloop-0.22.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:512fec6815e2dd45161054592441ef76c830eddaad55c8aa30952e6fe1ed07c0", size = 4296343, upload-time = "2025-10-16T22:16:35.149Z" },
+    { url = "https://files.pythonhosted.org/packages/89/8c/182a2a593195bfd39842ea68ebc084e20c850806117213f5a299dfc513d9/uvloop-0.22.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:561577354eb94200d75aca23fbde86ee11be36b00e52a4eaf8f50fb0c86b7705", size = 1358611, upload-time = "2025-10-16T22:16:36.833Z" },
+    { url = "https://files.pythonhosted.org/packages/d2/14/e301ee96a6dc95224b6f1162cd3312f6d1217be3907b79173b06785f2fe7/uvloop-0.22.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:1cdf5192ab3e674ca26da2eada35b288d2fa49fdd0f357a19f0e7c4e7d5077c8", size = 751811, upload-time = "2025-10-16T22:16:38.275Z" },
+    { url = "https://files.pythonhosted.org/packages/b7/02/654426ce265ac19e2980bfd9ea6590ca96a56f10c76e63801a2df01c0486/uvloop-0.22.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6e2ea3d6190a2968f4a14a23019d3b16870dd2190cd69c8180f7c632d21de68d", size = 4288562, upload-time = "2025-10-16T22:16:39.375Z" },
+    { url = "https://files.pythonhosted.org/packages/15/c0/0be24758891ef825f2065cd5db8741aaddabe3e248ee6acc5e8a80f04005/uvloop-0.22.1-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0530a5fbad9c9e4ee3f2b33b148c6a64d47bbad8000ea63704fa8260f4cf728e", size = 4366890, upload-time = "2025-10-16T22:16:40.547Z" },
+    { url = "https://files.pythonhosted.org/packages/d2/53/8369e5219a5855869bcee5f4d317f6da0e2c669aecf0ef7d371e3d084449/uvloop-0.22.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:bc5ef13bbc10b5335792360623cc378d52d7e62c2de64660616478c32cd0598e", size = 4119472, upload-time = "2025-10-16T22:16:41.694Z" },
+    { url = "https://files.pythonhosted.org/packages/f8/ba/d69adbe699b768f6b29a5eec7b47dd610bd17a69de51b251126a801369ea/uvloop-0.22.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:1f38ec5e3f18c8a10ded09742f7fb8de0108796eb673f30ce7762ce1b8550cad", size = 4239051, upload-time = "2025-10-16T22:16:43.224Z" },
+    { url = "https://files.pythonhosted.org/packages/90/cd/b62bdeaa429758aee8de8b00ac0dd26593a9de93d302bff3d21439e9791d/uvloop-0.22.1-cp314-cp314-macosx_10_13_universal2.whl", hash = "sha256:3879b88423ec7e97cd4eba2a443aa26ed4e59b45e6b76aabf13fe2f27023a142", size = 1362067, upload-time = "2025-10-16T22:16:44.503Z" },
+    { url = "https://files.pythonhosted.org/packages/0d/f8/a132124dfda0777e489ca86732e85e69afcd1ff7686647000050ba670689/uvloop-0.22.1-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:4baa86acedf1d62115c1dc6ad1e17134476688f08c6efd8a2ab076e815665c74", size = 752423, upload-time = "2025-10-16T22:16:45.968Z" },
+    { url = "https://files.pythonhosted.org/packages/a3/94/94af78c156f88da4b3a733773ad5ba0b164393e357cc4bd0ab2e2677a7d6/uvloop-0.22.1-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:297c27d8003520596236bdb2335e6b3f649480bd09e00d1e3a99144b691d2a35", size = 4272437, upload-time = "2025-10-16T22:16:47.451Z" },
+    { url = "https://files.pythonhosted.org/packages/b5/35/60249e9fd07b32c665192cec7af29e06c7cd96fa1d08b84f012a56a0b38e/uvloop-0.22.1-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c1955d5a1dd43198244d47664a5858082a3239766a839b2102a269aaff7a4e25", size = 4292101, upload-time = "2025-10-16T22:16:49.318Z" },
+    { url = "https://files.pythonhosted.org/packages/02/62/67d382dfcb25d0a98ce73c11ed1a6fba5037a1a1d533dcbb7cab033a2636/uvloop-0.22.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:b31dc2fccbd42adc73bc4e7cdbae4fc5086cf378979e53ca5d0301838c5682c6", size = 4114158, upload-time = "2025-10-16T22:16:50.517Z" },
+    { url = "https://files.pythonhosted.org/packages/f0/7a/f1171b4a882a5d13c8b7576f348acfe6074d72eaf52cccef752f748d4a9f/uvloop-0.22.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:93f617675b2d03af4e72a5333ef89450dfaa5321303ede6e67ba9c9d26878079", size = 4177360, upload-time = "2025-10-16T22:16:52.646Z" },
+    { url = "https://files.pythonhosted.org/packages/79/7b/b01414f31546caf0919da80ad57cbfe24c56b151d12af68cee1b04922ca8/uvloop-0.22.1-cp314-cp314t-macosx_10_13_universal2.whl", hash = "sha256:37554f70528f60cad66945b885eb01f1bb514f132d92b6eeed1c90fd54ed6289", size = 1454790, upload-time = "2025-10-16T22:16:54.355Z" },
+    { url = "https://files.pythonhosted.org/packages/d4/31/0bb232318dd838cad3fa8fb0c68c8b40e1145b32025581975e18b11fab40/uvloop-0.22.1-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:b76324e2dc033a0b2f435f33eb88ff9913c156ef78e153fb210e03c13da746b3", size = 796783, upload-time = "2025-10-16T22:16:55.906Z" },
+    { url = "https://files.pythonhosted.org/packages/42/38/c9b09f3271a7a723a5de69f8e237ab8e7803183131bc57c890db0b6bb872/uvloop-0.22.1-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:badb4d8e58ee08dad957002027830d5c3b06aea446a6a3744483c2b3b745345c", size = 4647548, upload-time = "2025-10-16T22:16:57.008Z" },
+    { url = "https://files.pythonhosted.org/packages/c1/37/945b4ca0ac27e3dc4952642d4c900edd030b3da6c9634875af6e13ae80e5/uvloop-0.22.1-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b91328c72635f6f9e0282e4a57da7470c7350ab1c9f48546c0f2866205349d21", size = 4467065, upload-time = "2025-10-16T22:16:58.206Z" },
+    { url = "https://files.pythonhosted.org/packages/97/cc/48d232f33d60e2e2e0b42f4e73455b146b76ebe216487e862700457fbf3c/uvloop-0.22.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:daf620c2995d193449393d6c62131b3fbd40a63bf7b307a1527856ace637fe88", size = 4328384, upload-time = "2025-10-16T22:16:59.36Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/16/c1fd27e9549f3c4baf1dc9c20c456cd2f822dbf8de9f463824b0c0357e06/uvloop-0.22.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:6cde23eeda1a25c75b2e07d39970f3374105d5eafbaab2a4482be82f272d5a5e", size = 4296730, upload-time = "2025-10-16T22:17:00.744Z" },
+]
+
+[[package]]
+name = "watchfiles"
+version = "1.1.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "anyio" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/c2/c9/8869df9b2a2d6c59d79220a4db37679e74f807c559ffe5265e08b227a210/watchfiles-1.1.1.tar.gz", hash = "sha256:a173cb5c16c4f40ab19cecf48a534c409f7ea983ab8fed0741304a1c0a31b3f2", size = 94440, upload-time = "2025-10-14T15:06:21.08Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/74/d5/f039e7e3c639d9b1d09b07ea412a6806d38123f0508e5f9b48a87b0a76cc/watchfiles-1.1.1-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:8c89f9f2f740a6b7dcc753140dd5e1ab9215966f7a3530d0c0705c83b401bd7d", size = 404745, upload-time = "2025-10-14T15:04:46.731Z" },
+    { url = "https://files.pythonhosted.org/packages/a5/96/a881a13aa1349827490dab2d363c8039527060cfcc2c92cc6d13d1b1049e/watchfiles-1.1.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:bd404be08018c37350f0d6e34676bd1e2889990117a2b90070b3007f172d0610", size = 391769, upload-time = "2025-10-14T15:04:48.003Z" },
+    { url = "https://files.pythonhosted.org/packages/4b/5b/d3b460364aeb8da471c1989238ea0e56bec24b6042a68046adf3d9ddb01c/watchfiles-1.1.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8526e8f916bb5b9a0a777c8317c23ce65de259422bba5b31325a6fa6029d33af", size = 449374, upload-time = "2025-10-14T15:04:49.179Z" },
+    { url = "https://files.pythonhosted.org/packages/b9/44/5769cb62d4ed055cb17417c0a109a92f007114a4e07f30812a73a4efdb11/watchfiles-1.1.1-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:2edc3553362b1c38d9f06242416a5d8e9fe235c204a4072e988ce2e5bb1f69f6", size = 459485, upload-time = "2025-10-14T15:04:50.155Z" },
+    { url = "https://files.pythonhosted.org/packages/19/0c/286b6301ded2eccd4ffd0041a1b726afda999926cf720aab63adb68a1e36/watchfiles-1.1.1-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:30f7da3fb3f2844259cba4720c3fc7138eb0f7b659c38f3bfa65084c7fc7abce", size = 488813, upload-time = "2025-10-14T15:04:51.059Z" },
+    { url = "https://files.pythonhosted.org/packages/c7/2b/8530ed41112dd4a22f4dcfdb5ccf6a1baad1ff6eed8dc5a5f09e7e8c41c7/watchfiles-1.1.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f8979280bdafff686ba5e4d8f97840f929a87ed9cdf133cbbd42f7766774d2aa", size = 594816, upload-time = "2025-10-14T15:04:52.031Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/d2/f5f9fb49489f184f18470d4f99f4e862a4b3e9ac2865688eb2099e3d837a/watchfiles-1.1.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:dcc5c24523771db3a294c77d94771abcfcb82a0e0ee8efd910c37c59ec1b31bb", size = 475186, upload-time = "2025-10-14T15:04:53.064Z" },
+    { url = "https://files.pythonhosted.org/packages/cf/68/5707da262a119fb06fbe214d82dd1fe4a6f4af32d2d14de368d0349eb52a/watchfiles-1.1.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1db5d7ae38ff20153d542460752ff397fcf5c96090c1230803713cf3147a6803", size = 456812, upload-time = "2025-10-14T15:04:55.174Z" },
+    { url = "https://files.pythonhosted.org/packages/66/ab/3cbb8756323e8f9b6f9acb9ef4ec26d42b2109bce830cc1f3468df20511d/watchfiles-1.1.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:28475ddbde92df1874b6c5c8aaeb24ad5be47a11f87cde5a28ef3835932e3e94", size = 630196, upload-time = "2025-10-14T15:04:56.22Z" },
+    { url = "https://files.pythonhosted.org/packages/78/46/7152ec29b8335f80167928944a94955015a345440f524d2dfe63fc2f437b/watchfiles-1.1.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:36193ed342f5b9842edd3532729a2ad55c4160ffcfa3700e0d54be496b70dd43", size = 622657, upload-time = "2025-10-14T15:04:57.521Z" },
+    { url = "https://files.pythonhosted.org/packages/0a/bf/95895e78dd75efe9a7f31733607f384b42eb5feb54bd2eb6ed57cc2e94f4/watchfiles-1.1.1-cp312-cp312-win32.whl", hash = "sha256:859e43a1951717cc8de7f4c77674a6d389b106361585951d9e69572823f311d9", size = 272042, upload-time = "2025-10-14T15:04:59.046Z" },
+    { url = "https://files.pythonhosted.org/packages/87/0a/90eb755f568de2688cb220171c4191df932232c20946966c27a59c400850/watchfiles-1.1.1-cp312-cp312-win_amd64.whl", hash = "sha256:91d4c9a823a8c987cce8fa2690923b069966dabb196dd8d137ea2cede885fde9", size = 288410, upload-time = "2025-10-14T15:05:00.081Z" },
+    { url = "https://files.pythonhosted.org/packages/36/76/f322701530586922fbd6723c4f91ace21364924822a8772c549483abed13/watchfiles-1.1.1-cp312-cp312-win_arm64.whl", hash = "sha256:a625815d4a2bdca61953dbba5a39d60164451ef34c88d751f6c368c3ea73d404", size = 278209, upload-time = "2025-10-14T15:05:01.168Z" },
+    { url = "https://files.pythonhosted.org/packages/bb/f4/f750b29225fe77139f7ae5de89d4949f5a99f934c65a1f1c0b248f26f747/watchfiles-1.1.1-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:130e4876309e8686a5e37dba7d5e9bc77e6ed908266996ca26572437a5271e18", size = 404321, upload-time = "2025-10-14T15:05:02.063Z" },
+    { url = "https://files.pythonhosted.org/packages/2b/f9/f07a295cde762644aa4c4bb0f88921d2d141af45e735b965fb2e87858328/watchfiles-1.1.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:5f3bde70f157f84ece3765b42b4a52c6ac1a50334903c6eaf765362f6ccca88a", size = 391783, upload-time = "2025-10-14T15:05:03.052Z" },
+    { url = "https://files.pythonhosted.org/packages/bc/11/fc2502457e0bea39a5c958d86d2cb69e407a4d00b85735ca724bfa6e0d1a/watchfiles-1.1.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:14e0b1fe858430fc0251737ef3824c54027bedb8c37c38114488b8e131cf8219", size = 449279, upload-time = "2025-10-14T15:05:04.004Z" },
+    { url = "https://files.pythonhosted.org/packages/e3/1f/d66bc15ea0b728df3ed96a539c777acfcad0eb78555ad9efcaa1274688f0/watchfiles-1.1.1-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:f27db948078f3823a6bb3b465180db8ebecf26dd5dae6f6180bd87383b6b4428", size = 459405, upload-time = "2025-10-14T15:05:04.942Z" },
+    { url = "https://files.pythonhosted.org/packages/be/90/9f4a65c0aec3ccf032703e6db02d89a157462fbb2cf20dd415128251cac0/watchfiles-1.1.1-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:059098c3a429f62fc98e8ec62b982230ef2c8df68c79e826e37b895bc359a9c0", size = 488976, upload-time = "2025-10-14T15:05:05.905Z" },
+    { url = "https://files.pythonhosted.org/packages/37/57/ee347af605d867f712be7029bb94c8c071732a4b44792e3176fa3c612d39/watchfiles-1.1.1-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:bfb5862016acc9b869bb57284e6cb35fdf8e22fe59f7548858e2f971d045f150", size = 595506, upload-time = "2025-10-14T15:05:06.906Z" },
+    { url = "https://files.pythonhosted.org/packages/a8/78/cc5ab0b86c122047f75e8fc471c67a04dee395daf847d3e59381996c8707/watchfiles-1.1.1-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:319b27255aacd9923b8a276bb14d21a5f7ff82564c744235fc5eae58d95422ae", size = 474936, upload-time = "2025-10-14T15:05:07.906Z" },
+    { url = "https://files.pythonhosted.org/packages/62/da/def65b170a3815af7bd40a3e7010bf6ab53089ef1b75d05dd5385b87cf08/watchfiles-1.1.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c755367e51db90e75b19454b680903631d41f9e3607fbd941d296a020c2d752d", size = 456147, upload-time = "2025-10-14T15:05:09.138Z" },
+    { url = "https://files.pythonhosted.org/packages/57/99/da6573ba71166e82d288d4df0839128004c67d2778d3b566c138695f5c0b/watchfiles-1.1.1-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:c22c776292a23bfc7237a98f791b9ad3144b02116ff10d820829ce62dff46d0b", size = 630007, upload-time = "2025-10-14T15:05:10.117Z" },
+    { url = "https://files.pythonhosted.org/packages/a8/51/7439c4dd39511368849eb1e53279cd3454b4a4dbace80bab88feeb83c6b5/watchfiles-1.1.1-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:3a476189be23c3686bc2f4321dd501cb329c0a0469e77b7b534ee10129ae6374", size = 622280, upload-time = "2025-10-14T15:05:11.146Z" },
+    { url = "https://files.pythonhosted.org/packages/95/9c/8ed97d4bba5db6fdcdb2b298d3898f2dd5c20f6b73aee04eabe56c59677e/watchfiles-1.1.1-cp313-cp313-win32.whl", hash = "sha256:bf0a91bfb5574a2f7fc223cf95eeea79abfefa404bf1ea5e339c0c1560ae99a0", size = 272056, upload-time = "2025-10-14T15:05:12.156Z" },
+    { url = "https://files.pythonhosted.org/packages/1f/f3/c14e28429f744a260d8ceae18bf58c1d5fa56b50d006a7a9f80e1882cb0d/watchfiles-1.1.1-cp313-cp313-win_amd64.whl", hash = "sha256:52e06553899e11e8074503c8e716d574adeeb7e68913115c4b3653c53f9bae42", size = 288162, upload-time = "2025-10-14T15:05:13.208Z" },
+    { url = "https://files.pythonhosted.org/packages/dc/61/fe0e56c40d5cd29523e398d31153218718c5786b5e636d9ae8ae79453d27/watchfiles-1.1.1-cp313-cp313-win_arm64.whl", hash = "sha256:ac3cc5759570cd02662b15fbcd9d917f7ecd47efe0d6b40474eafd246f91ea18", size = 277909, upload-time = "2025-10-14T15:05:14.49Z" },
+    { url = "https://files.pythonhosted.org/packages/79/42/e0a7d749626f1e28c7108a99fb9bf524b501bbbeb9b261ceecde644d5a07/watchfiles-1.1.1-cp313-cp313t-macosx_10_12_x86_64.whl", hash = "sha256:563b116874a9a7ce6f96f87cd0b94f7faf92d08d0021e837796f0a14318ef8da", size = 403389, upload-time = "2025-10-14T15:05:15.777Z" },
+    { url = "https://files.pythonhosted.org/packages/15/49/08732f90ce0fbbc13913f9f215c689cfc9ced345fb1bcd8829a50007cc8d/watchfiles-1.1.1-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:3ad9fe1dae4ab4212d8c91e80b832425e24f421703b5a42ef2e4a1e215aff051", size = 389964, upload-time = "2025-10-14T15:05:16.85Z" },
+    { url = "https://files.pythonhosted.org/packages/27/0d/7c315d4bd5f2538910491a0393c56bf70d333d51bc5b34bee8e68e8cea19/watchfiles-1.1.1-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ce70f96a46b894b36eba678f153f052967a0d06d5b5a19b336ab0dbbd029f73e", size = 448114, upload-time = "2025-10-14T15:05:17.876Z" },
+    { url = "https://files.pythonhosted.org/packages/c3/24/9e096de47a4d11bc4df41e9d1e61776393eac4cb6eb11b3e23315b78b2cc/watchfiles-1.1.1-cp313-cp313t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:cb467c999c2eff23a6417e58d75e5828716f42ed8289fe6b77a7e5a91036ca70", size = 460264, upload-time = "2025-10-14T15:05:18.962Z" },
+    { url = "https://files.pythonhosted.org/packages/cc/0f/e8dea6375f1d3ba5fcb0b3583e2b493e77379834c74fd5a22d66d85d6540/watchfiles-1.1.1-cp313-cp313t-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:836398932192dae4146c8f6f737d74baeac8b70ce14831a239bdb1ca882fc261", size = 487877, upload-time = "2025-10-14T15:05:20.094Z" },
+    { url = "https://files.pythonhosted.org/packages/ac/5b/df24cfc6424a12deb41503b64d42fbea6b8cb357ec62ca84a5a3476f654a/watchfiles-1.1.1-cp313-cp313t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:743185e7372b7bc7c389e1badcc606931a827112fbbd37f14c537320fca08620", size = 595176, upload-time = "2025-10-14T15:05:21.134Z" },
+    { url = "https://files.pythonhosted.org/packages/8f/b5/853b6757f7347de4e9b37e8cc3289283fb983cba1ab4d2d7144694871d9c/watchfiles-1.1.1-cp313-cp313t-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:afaeff7696e0ad9f02cbb8f56365ff4686ab205fcf9c4c5b6fdfaaa16549dd04", size = 473577, upload-time = "2025-10-14T15:05:22.306Z" },
+    { url = "https://files.pythonhosted.org/packages/e1/f7/0a4467be0a56e80447c8529c9fce5b38eab4f513cb3d9bf82e7392a5696b/watchfiles-1.1.1-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3f7eb7da0eb23aa2ba036d4f616d46906013a68caf61b7fdbe42fc8b25132e77", size = 455425, upload-time = "2025-10-14T15:05:23.348Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/e0/82583485ea00137ddf69bc84a2db88bd92ab4a6e3c405e5fb878ead8d0e7/watchfiles-1.1.1-cp313-cp313t-musllinux_1_1_aarch64.whl", hash = "sha256:831a62658609f0e5c64178211c942ace999517f5770fe9436be4c2faeba0c0ef", size = 628826, upload-time = "2025-10-14T15:05:24.398Z" },
+    { url = "https://files.pythonhosted.org/packages/28/9a/a785356fccf9fae84c0cc90570f11702ae9571036fb25932f1242c82191c/watchfiles-1.1.1-cp313-cp313t-musllinux_1_1_x86_64.whl", hash = "sha256:f9a2ae5c91cecc9edd47e041a930490c31c3afb1f5e6d71de3dc671bfaca02bf", size = 622208, upload-time = "2025-10-14T15:05:25.45Z" },
+    { url = "https://files.pythonhosted.org/packages/c3/f4/0872229324ef69b2c3edec35e84bd57a1289e7d3fe74588048ed8947a323/watchfiles-1.1.1-cp314-cp314-macosx_10_12_x86_64.whl", hash = "sha256:d1715143123baeeaeadec0528bb7441103979a1d5f6fd0e1f915383fea7ea6d5", size = 404315, upload-time = "2025-10-14T15:05:26.501Z" },
+    { url = "https://files.pythonhosted.org/packages/7b/22/16d5331eaed1cb107b873f6ae1b69e9ced582fcf0c59a50cd84f403b1c32/watchfiles-1.1.1-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:39574d6370c4579d7f5d0ad940ce5b20db0e4117444e39b6d8f99db5676c52fd", size = 390869, upload-time = "2025-10-14T15:05:27.649Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/7e/5643bfff5acb6539b18483128fdc0ef2cccc94a5b8fbda130c823e8ed636/watchfiles-1.1.1-cp314-cp314-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7365b92c2e69ee952902e8f70f3ba6360d0d596d9299d55d7d386df84b6941fb", size = 449919, upload-time = "2025-10-14T15:05:28.701Z" },
+    { url = "https://files.pythonhosted.org/packages/51/2e/c410993ba5025a9f9357c376f48976ef0e1b1aefb73b97a5ae01a5972755/watchfiles-1.1.1-cp314-cp314-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:bfff9740c69c0e4ed32416f013f3c45e2ae42ccedd1167ef2d805c000b6c71a5", size = 460845, upload-time = "2025-10-14T15:05:30.064Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/a4/2df3b404469122e8680f0fcd06079317e48db58a2da2950fb45020947734/watchfiles-1.1.1-cp314-cp314-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b27cf2eb1dda37b2089e3907d8ea92922b673c0c427886d4edc6b94d8dfe5db3", size = 489027, upload-time = "2025-10-14T15:05:31.064Z" },
+    { url = "https://files.pythonhosted.org/packages/ea/84/4587ba5b1f267167ee715b7f66e6382cca6938e0a4b870adad93e44747e6/watchfiles-1.1.1-cp314-cp314-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:526e86aced14a65a5b0ec50827c745597c782ff46b571dbfe46192ab9e0b3c33", size = 595615, upload-time = "2025-10-14T15:05:32.074Z" },
+    { url = "https://files.pythonhosted.org/packages/6a/0f/c6988c91d06e93cd0bb3d4a808bcf32375ca1904609835c3031799e3ecae/watchfiles-1.1.1-cp314-cp314-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:04e78dd0b6352db95507fd8cb46f39d185cf8c74e4cf1e4fbad1d3df96faf510", size = 474836, upload-time = "2025-10-14T15:05:33.209Z" },
+    { url = "https://files.pythonhosted.org/packages/b4/36/ded8aebea91919485b7bbabbd14f5f359326cb5ec218cd67074d1e426d74/watchfiles-1.1.1-cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5c85794a4cfa094714fb9c08d4a218375b2b95b8ed1666e8677c349906246c05", size = 455099, upload-time = "2025-10-14T15:05:34.189Z" },
+    { url = "https://files.pythonhosted.org/packages/98/e0/8c9bdba88af756a2fce230dd365fab2baf927ba42cd47521ee7498fd5211/watchfiles-1.1.1-cp314-cp314-musllinux_1_1_aarch64.whl", hash = "sha256:74d5012b7630714b66be7b7b7a78855ef7ad58e8650c73afc4c076a1f480a8d6", size = 630626, upload-time = "2025-10-14T15:05:35.216Z" },
+    { url = "https://files.pythonhosted.org/packages/2a/84/a95db05354bf2d19e438520d92a8ca475e578c647f78f53197f5a2f17aaf/watchfiles-1.1.1-cp314-cp314-musllinux_1_1_x86_64.whl", hash = "sha256:8fbe85cb3201c7d380d3d0b90e63d520f15d6afe217165d7f98c9c649654db81", size = 622519, upload-time = "2025-10-14T15:05:36.259Z" },
+    { url = "https://files.pythonhosted.org/packages/1d/ce/d8acdc8de545de995c339be67711e474c77d643555a9bb74a9334252bd55/watchfiles-1.1.1-cp314-cp314-win32.whl", hash = "sha256:3fa0b59c92278b5a7800d3ee7733da9d096d4aabcfabb9a928918bd276ef9b9b", size = 272078, upload-time = "2025-10-14T15:05:37.63Z" },
+    { url = "https://files.pythonhosted.org/packages/c4/c9/a74487f72d0451524be827e8edec251da0cc1fcf111646a511ae752e1a3d/watchfiles-1.1.1-cp314-cp314-win_amd64.whl", hash = "sha256:c2047d0b6cea13b3316bdbafbfa0c4228ae593d995030fda39089d36e64fc03a", size = 287664, upload-time = "2025-10-14T15:05:38.95Z" },
+    { url = "https://files.pythonhosted.org/packages/df/b8/8ac000702cdd496cdce998c6f4ee0ca1f15977bba51bdf07d872ebdfc34c/watchfiles-1.1.1-cp314-cp314-win_arm64.whl", hash = "sha256:842178b126593addc05acf6fce960d28bc5fae7afbaa2c6c1b3a7b9460e5be02", size = 277154, upload-time = "2025-10-14T15:05:39.954Z" },
+    { url = "https://files.pythonhosted.org/packages/47/a8/e3af2184707c29f0f14b1963c0aace6529f9d1b8582d5b99f31bbf42f59e/watchfiles-1.1.1-cp314-cp314t-macosx_10_12_x86_64.whl", hash = "sha256:88863fbbc1a7312972f1c511f202eb30866370ebb8493aef2812b9ff28156a21", size = 403820, upload-time = "2025-10-14T15:05:40.932Z" },
+    { url = "https://files.pythonhosted.org/packages/c0/ec/e47e307c2f4bd75f9f9e8afbe3876679b18e1bcec449beca132a1c5ffb2d/watchfiles-1.1.1-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:55c7475190662e202c08c6c0f4d9e345a29367438cf8e8037f3155e10a88d5a5", size = 390510, upload-time = "2025-10-14T15:05:41.945Z" },
+    { url = "https://files.pythonhosted.org/packages/d5/a0/ad235642118090f66e7b2f18fd5c42082418404a79205cdfca50b6309c13/watchfiles-1.1.1-cp314-cp314t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3f53fa183d53a1d7a8852277c92b967ae99c2d4dcee2bfacff8868e6e30b15f7", size = 448408, upload-time = "2025-10-14T15:05:43.385Z" },
+    { url = "https://files.pythonhosted.org/packages/df/85/97fa10fd5ff3332ae17e7e40e20784e419e28521549780869f1413742e9d/watchfiles-1.1.1-cp314-cp314t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:6aae418a8b323732fa89721d86f39ec8f092fc2af67f4217a2b07fd3e93c6101", size = 458968, upload-time = "2025-10-14T15:05:44.404Z" },
+    { url = "https://files.pythonhosted.org/packages/47/c2/9059c2e8966ea5ce678166617a7f75ecba6164375f3b288e50a40dc6d489/watchfiles-1.1.1-cp314-cp314t-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f096076119da54a6080e8920cbdaac3dbee667eb91dcc5e5b78840b87415bd44", size = 488096, upload-time = "2025-10-14T15:05:45.398Z" },
+    { url = "https://files.pythonhosted.org/packages/94/44/d90a9ec8ac309bc26db808a13e7bfc0e4e78b6fc051078a554e132e80160/watchfiles-1.1.1-cp314-cp314t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:00485f441d183717038ed2e887a7c868154f216877653121068107b227a2f64c", size = 596040, upload-time = "2025-10-14T15:05:46.502Z" },
+    { url = "https://files.pythonhosted.org/packages/95/68/4e3479b20ca305cfc561db3ed207a8a1c745ee32bf24f2026a129d0ddb6e/watchfiles-1.1.1-cp314-cp314t-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a55f3e9e493158d7bfdb60a1165035f1cf7d320914e7b7ea83fe22c6023b58fc", size = 473847, upload-time = "2025-10-14T15:05:47.484Z" },
+    { url = "https://files.pythonhosted.org/packages/4f/55/2af26693fd15165c4ff7857e38330e1b61ab8c37d15dc79118cdba115b7a/watchfiles-1.1.1-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8c91ed27800188c2ae96d16e3149f199d62f86c7af5f5f4d2c61a3ed8cd3666c", size = 455072, upload-time = "2025-10-14T15:05:48.928Z" },
+    { url = "https://files.pythonhosted.org/packages/66/1d/d0d200b10c9311ec25d2273f8aad8c3ef7cc7ea11808022501811208a750/watchfiles-1.1.1-cp314-cp314t-musllinux_1_1_aarch64.whl", hash = "sha256:311ff15a0bae3714ffb603e6ba6dbfba4065ab60865d15a6ec544133bdb21099", size = 629104, upload-time = "2025-10-14T15:05:49.908Z" },
+    { url = "https://files.pythonhosted.org/packages/e3/bd/fa9bb053192491b3867ba07d2343d9f2252e00811567d30ae8d0f78136fe/watchfiles-1.1.1-cp314-cp314t-musllinux_1_1_x86_64.whl", hash = "sha256:a916a2932da8f8ab582f242c065f5c81bed3462849ca79ee357dd9551b0e9b01", size = 622112, upload-time = "2025-10-14T15:05:50.941Z" },
+]
+
+[[package]]
+name = "websockets"
+version = "15.0.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/21/e6/26d09fab466b7ca9c7737474c52be4f76a40301b08362eb2dbc19dcc16c1/websockets-15.0.1.tar.gz", hash = "sha256:82544de02076bafba038ce055ee6412d68da13ab47f0c60cab827346de828dee", size = 177016, upload-time = "2025-03-05T20:03:41.606Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/51/6b/4545a0d843594f5d0771e86463606a3988b5a09ca5123136f8a76580dd63/websockets-15.0.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:3e90baa811a5d73f3ca0bcbf32064d663ed81318ab225ee4f427ad4e26e5aff3", size = 175437, upload-time = "2025-03-05T20:02:16.706Z" },
+    { url = "https://files.pythonhosted.org/packages/f4/71/809a0f5f6a06522af902e0f2ea2757f71ead94610010cf570ab5c98e99ed/websockets-15.0.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:592f1a9fe869c778694f0aa806ba0374e97648ab57936f092fd9d87f8bc03665", size = 173096, upload-time = "2025-03-05T20:02:18.832Z" },
+    { url = "https://files.pythonhosted.org/packages/3d/69/1a681dd6f02180916f116894181eab8b2e25b31e484c5d0eae637ec01f7c/websockets-15.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:0701bc3cfcb9164d04a14b149fd74be7347a530ad3bbf15ab2c678a2cd3dd9a2", size = 173332, upload-time = "2025-03-05T20:02:20.187Z" },
+    { url = "https://files.pythonhosted.org/packages/a6/02/0073b3952f5bce97eafbb35757f8d0d54812b6174ed8dd952aa08429bcc3/websockets-15.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e8b56bdcdb4505c8078cb6c7157d9811a85790f2f2b3632c7d1462ab5783d215", size = 183152, upload-time = "2025-03-05T20:02:22.286Z" },
+    { url = "https://files.pythonhosted.org/packages/74/45/c205c8480eafd114b428284840da0b1be9ffd0e4f87338dc95dc6ff961a1/websockets-15.0.1-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0af68c55afbd5f07986df82831c7bff04846928ea8d1fd7f30052638788bc9b5", size = 182096, upload-time = "2025-03-05T20:02:24.368Z" },
+    { url = "https://files.pythonhosted.org/packages/14/8f/aa61f528fba38578ec553c145857a181384c72b98156f858ca5c8e82d9d3/websockets-15.0.1-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:64dee438fed052b52e4f98f76c5790513235efaa1ef7f3f2192c392cd7c91b65", size = 182523, upload-time = "2025-03-05T20:02:25.669Z" },
+    { url = "https://files.pythonhosted.org/packages/ec/6d/0267396610add5bc0d0d3e77f546d4cd287200804fe02323797de77dbce9/websockets-15.0.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:d5f6b181bb38171a8ad1d6aa58a67a6aa9d4b38d0f8c5f496b9e42561dfc62fe", size = 182790, upload-time = "2025-03-05T20:02:26.99Z" },
+    { url = "https://files.pythonhosted.org/packages/02/05/c68c5adbf679cf610ae2f74a9b871ae84564462955d991178f95a1ddb7dd/websockets-15.0.1-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:5d54b09eba2bada6011aea5375542a157637b91029687eb4fdb2dab11059c1b4", size = 182165, upload-time = "2025-03-05T20:02:30.291Z" },
+    { url = "https://files.pythonhosted.org/packages/29/93/bb672df7b2f5faac89761cb5fa34f5cec45a4026c383a4b5761c6cea5c16/websockets-15.0.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:3be571a8b5afed347da347bfcf27ba12b069d9d7f42cb8c7028b5e98bbb12597", size = 182160, upload-time = "2025-03-05T20:02:31.634Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/83/de1f7709376dc3ca9b7eeb4b9a07b4526b14876b6d372a4dc62312bebee0/websockets-15.0.1-cp312-cp312-win32.whl", hash = "sha256:c338ffa0520bdb12fbc527265235639fb76e7bc7faafbb93f6ba80d9c06578a9", size = 176395, upload-time = "2025-03-05T20:02:33.017Z" },
+    { url = "https://files.pythonhosted.org/packages/7d/71/abf2ebc3bbfa40f391ce1428c7168fb20582d0ff57019b69ea20fa698043/websockets-15.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:fcd5cf9e305d7b8338754470cf69cf81f420459dbae8a3b40cee57417f4614a7", size = 176841, upload-time = "2025-03-05T20:02:34.498Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/9f/51f0cf64471a9d2b4d0fc6c534f323b664e7095640c34562f5182e5a7195/websockets-15.0.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:ee443ef070bb3b6ed74514f5efaa37a252af57c90eb33b956d35c8e9c10a1931", size = 175440, upload-time = "2025-03-05T20:02:36.695Z" },
+    { url = "https://files.pythonhosted.org/packages/8a/05/aa116ec9943c718905997412c5989f7ed671bc0188ee2ba89520e8765d7b/websockets-15.0.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:5a939de6b7b4e18ca683218320fc67ea886038265fd1ed30173f5ce3f8e85675", size = 173098, upload-time = "2025-03-05T20:02:37.985Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/0b/33cef55ff24f2d92924923c99926dcce78e7bd922d649467f0eda8368923/websockets-15.0.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:746ee8dba912cd6fc889a8147168991d50ed70447bf18bcda7039f7d2e3d9151", size = 173329, upload-time = "2025-03-05T20:02:39.298Z" },
+    { url = "https://files.pythonhosted.org/packages/31/1d/063b25dcc01faa8fada1469bdf769de3768b7044eac9d41f734fd7b6ad6d/websockets-15.0.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:595b6c3969023ecf9041b2936ac3827e4623bfa3ccf007575f04c5a6aa318c22", size = 183111, upload-time = "2025-03-05T20:02:40.595Z" },
+    { url = "https://files.pythonhosted.org/packages/93/53/9a87ee494a51bf63e4ec9241c1ccc4f7c2f45fff85d5bde2ff74fcb68b9e/websockets-15.0.1-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3c714d2fc58b5ca3e285461a4cc0c9a66bd0e24c5da9911e30158286c9b5be7f", size = 182054, upload-time = "2025-03-05T20:02:41.926Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/b2/83a6ddf56cdcbad4e3d841fcc55d6ba7d19aeb89c50f24dd7e859ec0805f/websockets-15.0.1-cp313-cp313-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0f3c1e2ab208db911594ae5b4f79addeb3501604a165019dd221c0bdcabe4db8", size = 182496, upload-time = "2025-03-05T20:02:43.304Z" },
+    { url = "https://files.pythonhosted.org/packages/98/41/e7038944ed0abf34c45aa4635ba28136f06052e08fc2168520bb8b25149f/websockets-15.0.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:229cf1d3ca6c1804400b0a9790dc66528e08a6a1feec0d5040e8b9eb14422375", size = 182829, upload-time = "2025-03-05T20:02:48.812Z" },
+    { url = "https://files.pythonhosted.org/packages/e0/17/de15b6158680c7623c6ef0db361da965ab25d813ae54fcfeae2e5b9ef910/websockets-15.0.1-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:756c56e867a90fb00177d530dca4b097dd753cde348448a1012ed6c5131f8b7d", size = 182217, upload-time = "2025-03-05T20:02:50.14Z" },
+    { url = "https://files.pythonhosted.org/packages/33/2b/1f168cb6041853eef0362fb9554c3824367c5560cbdaad89ac40f8c2edfc/websockets-15.0.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:558d023b3df0bffe50a04e710bc87742de35060580a293c2a984299ed83bc4e4", size = 182195, upload-time = "2025-03-05T20:02:51.561Z" },
+    { url = "https://files.pythonhosted.org/packages/86/eb/20b6cdf273913d0ad05a6a14aed4b9a85591c18a987a3d47f20fa13dcc47/websockets-15.0.1-cp313-cp313-win32.whl", hash = "sha256:ba9e56e8ceeeedb2e080147ba85ffcd5cd0711b89576b83784d8605a7df455fa", size = 176393, upload-time = "2025-03-05T20:02:53.814Z" },
+    { url = "https://files.pythonhosted.org/packages/1b/6c/c65773d6cab416a64d191d6ee8a8b1c68a09970ea6909d16965d26bfed1e/websockets-15.0.1-cp313-cp313-win_amd64.whl", hash = "sha256:e09473f095a819042ecb2ab9465aee615bd9c2028e4ef7d933600a8401c79561", size = 176837, upload-time = "2025-03-05T20:02:55.237Z" },
+    { url = "https://files.pythonhosted.org/packages/fa/a8/5b41e0da817d64113292ab1f8247140aac61cbf6cfd085d6a0fa77f4984f/websockets-15.0.1-py3-none-any.whl", hash = "sha256:f7a866fbc1e97b5c617ee4116daaa09b722101d4a3c170c787450ba409f9736f", size = 169743, upload-time = "2025-03-05T20:03:39.41Z" },
+]
@@ -10,9 +10,23 @@ from posthog.contexts import (
    tag as inner_tag,
    set_context_session as inner_set_context_session,
    identify_context as inner_identify_context,
+    set_capture_exception_code_variables_context as inner_set_capture_exception_code_variables_context,
+    set_code_variables_mask_patterns_context as inner_set_code_variables_mask_patterns_context,
+    set_code_variables_ignore_patterns_context as inner_set_code_variables_ignore_patterns_context,
+)
+from posthog.exception_utils import (
+    DEFAULT_CODE_VARIABLES_IGNORE_PATTERNS,
+    DEFAULT_CODE_VARIABLES_MASK_PATTERNS,
+)
+from posthog.feature_flags import (
+    InconclusiveMatchError as InconclusiveMatchError,
+    RequiresServerEvaluation as RequiresServerEvaluation,
+)
+from posthog.types import (
+    FeatureFlag,
+    FlagsAndPayloads,
+    FeatureFlagResult as FeatureFlagResult,
 )
-from posthog.feature_flags import InconclusiveMatchError, RequiresServerEvaluation
-from posthog.types import FeatureFlag, FlagsAndPayloads, FeatureFlagResult
 from posthog.version import VERSION

 __version__ = VERSION
@@ -20,13 +34,14 @@ __version__ = VERSION
 """Context management."""


-def new_context(fresh=False, capture_exceptions=True):
+def new_context(fresh=False, capture_exceptions=True, client=None):
    """
    Create a new context scope that will be active for the duration of the with block.

    Args:
        fresh: Whether to start with a fresh context (default: False)
        capture_exceptions: Whether to capture exceptions raised within the context (default: True)
+        client: Optional Posthog client instance to use for this context (default: None)

    Examples:
        ```python
@@ -39,7 +54,9 @@ def new_context(fresh=False, capture_exceptions=True):
    Category:
        Contexts
    """
-    return inner_new_context(fresh=fresh, capture_exceptions=capture_exceptions)
+    return inner_new_context(
+        fresh=fresh, capture_exceptions=capture_exceptions, client=client
+    )


 def scoped(fresh=False, capture_exceptions=True):
@@ -103,6 +120,27 @@ def identify_context(distinct_id: str):
    return inner_identify_context(distinct_id)


+def set_capture_exception_code_variables_context(enabled: bool):
+    """
+    Set whether code variables are captured for the current context.
+    """
+    return inner_set_capture_exception_code_variables_context(enabled)
+
+
+def set_code_variables_mask_patterns_context(mask_patterns: list):
+    """
+    Variable names matching these patterns will be masked with *** when capturing code variables.
+    """
+    return inner_set_code_variables_mask_patterns_context(mask_patterns)
+
+
+def set_code_variables_ignore_patterns_context(ignore_patterns: list):
+    """
+    Variable names matching these patterns will be ignored completely when capturing code variables.
+    """
+    return inner_set_code_variables_ignore_patterns_context(ignore_patterns)
+
+
 def tag(name: str, value: Any):
    """
    Add a tag to the current context.
@@ -150,6 +188,10 @@ enable_local_evaluation = True  # type: bool

 default_client = None  # type: Optional[Client]

+capture_exception_code_variables = False
+code_variables_mask_patterns = DEFAULT_CODE_VARIABLES_MASK_PATTERNS
+code_variables_ignore_patterns = DEFAULT_CODE_VARIABLES_IGNORE_PATTERNS
+

 # NOTE - this and following functions take unpacked kwargs because we needed to make
 # it impossible to write `posthog.capture(distinct-id, event-name)` - basically, to enforce
@@ -744,6 +786,9 @@ def setup() -> Client:
            enable_exception_autocapture=enable_exception_autocapture,
            log_captured_exceptions=log_captured_exceptions,
            enable_local_evaluation=enable_local_evaluation,
+            capture_exception_code_variables=capture_exception_code_variables,
+            code_variables_mask_patterns=code_variables_mask_patterns,
+            code_variables_ignore_patterns=code_variables_ignore_patterns,
        )

    # always set incase user changes it
@@ -14,14 +14,9 @@ from posthog import setup
 from posthog.ai.types import StreamingContentBlock, TokenUsage, ToolInProgress
 from posthog.ai.utils import (
    call_llm_and_track_usage_async,
-    extract_available_tool_calls,
-    get_model_params,
-    merge_system_prompt,
    merge_usage_stats,
-    with_privacy_mode,
 )
 from posthog.ai.anthropic.anthropic_converter import (
-    format_anthropic_streaming_content,
    extract_anthropic_usage_from_event,
    handle_anthropic_content_block_start,
    handle_anthropic_text_delta,
@@ -220,66 +215,34 @@ class AsyncWrappedMessages(AsyncMessages):
        content_blocks: List[StreamingContentBlock],
        accumulated_content: str,
    ):
-        if posthog_trace_id is None:
-            posthog_trace_id = str(uuid.uuid4())
+        from posthog.ai.types import StreamingEventData
+        from posthog.ai.anthropic.anthropic_converter import (
+            format_anthropic_streaming_input,
+            format_anthropic_streaming_output_complete,
+        )
+        from posthog.ai.utils import capture_streaming_event

-        # Format output using converter
-        formatted_content = format_anthropic_streaming_content(content_blocks)
-        formatted_output = []
+        # Prepare standardized event data
+        formatted_input = format_anthropic_streaming_input(kwargs)
+        sanitized_input = sanitize_anthropic(formatted_input)

-        if formatted_content:
-            formatted_output = [{"role": "assistant", "content": formatted_content}]
-        else:
-            # Fallback to accumulated content if no blocks
-            formatted_output = [
-                {
-                    "role": "assistant",
-                    "content": [{"type": "text", "text": accumulated_content}],
-                }
-            ]
-
-        event_properties = {
-            "$ai_provider": "anthropic",
-            "$ai_model": kwargs.get("model"),
-            "$ai_model_parameters": get_model_params(kwargs),
-            "$ai_input": with_privacy_mode(
-                self._client._ph_client,
-                posthog_privacy_mode,
-                sanitize_anthropic(merge_system_prompt(kwargs, "anthropic")),
+        event_data = StreamingEventData(
+            provider="anthropic",
+            model=kwargs.get("model", "unknown"),
+            base_url=str(self._client.base_url),
+            kwargs=kwargs,
+            formatted_input=sanitized_input,
+            formatted_output=format_anthropic_streaming_output_complete(
+                content_blocks, accumulated_content
            ),
-            "$ai_output_choices": with_privacy_mode(
-                self._client._ph_client,
-                posthog_privacy_mode,
-                formatted_output,
-            ),
-            "$ai_http_status": 200,
-            "$ai_input_tokens": usage_stats.get("input_tokens", 0),
-            "$ai_output_tokens": usage_stats.get("output_tokens", 0),
-            "$ai_cache_read_input_tokens": usage_stats.get(
-                "cache_read_input_tokens", 0
-            ),
-            "$ai_cache_creation_input_tokens": usage_stats.get(
-                "cache_creation_input_tokens", 0
-            ),
-            "$ai_latency": latency,
-            "$ai_trace_id": posthog_trace_id,
-            "$ai_base_url": str(self._client.base_url),
-            **(posthog_properties or {}),
-        }
+            usage_stats=usage_stats,
+            latency=latency,
+            distinct_id=posthog_distinct_id,
+            trace_id=posthog_trace_id,
+            properties=posthog_properties,
+            privacy_mode=posthog_privacy_mode,
+            groups=posthog_groups,
+        )

-        # Add tools if available
-        available_tools = extract_available_tool_calls("anthropic", kwargs)
-
-        if available_tools:
-            event_properties["$ai_tools"] = available_tools
-
-        if posthog_distinct_id is None:
-            event_properties["$process_person_profile"] = False
-
-        if hasattr(self._client._ph_client, "capture"):
-            self._client._ph_client.capture(
-                distinct_id=posthog_distinct_id or posthog_trace_id,
-                event="$ai_generation",
-                properties=event_properties,
-                groups=posthog_groups,
-            )
+        # Use the common capture function
+        capture_streaming_event(self._client._ph_client, event_data)
@@ -163,6 +163,32 @@ def format_anthropic_streaming_content(
    return formatted


+def extract_anthropic_web_search_count(response: Any) -> int:
+    """
+    Extract web search count from Anthropic response.
+
+    Anthropic provides exact web search counts via usage.server_tool_use.web_search_requests.
+
+    Args:
+        response: The response from Anthropic API
+
+    Returns:
+        Number of web search requests (0 if none)
+    """
+    if not hasattr(response, "usage"):
+        return 0
+
+    if not hasattr(response.usage, "server_tool_use"):
+        return 0
+
+    server_tool_use = response.usage.server_tool_use
+
+    if hasattr(server_tool_use, "web_search_requests"):
+        return max(0, int(getattr(server_tool_use, "web_search_requests", 0)))
+
+    return 0
+
+
 def extract_anthropic_usage_from_response(response: Any) -> TokenUsage:
    """
    Extract usage from a full Anthropic response (non-streaming).
@@ -191,6 +217,10 @@ def extract_anthropic_usage_from_response(response: Any) -> TokenUsage:
        if cache_creation and cache_creation > 0:
            result["cache_creation_input_tokens"] = cache_creation

+    web_search_count = extract_anthropic_web_search_count(response)
+    if web_search_count > 0:
+        result["web_search_count"] = web_search_count
+
    return result


@@ -222,6 +252,16 @@ def extract_anthropic_usage_from_event(event: Any) -> TokenUsage:
    if hasattr(event, "usage") and event.usage:
        usage["output_tokens"] = getattr(event.usage, "output_tokens", 0)

+        # Extract web search count from usage
+        if hasattr(event.usage, "server_tool_use"):
+            server_tool_use = event.usage.server_tool_use
+            if hasattr(server_tool_use, "web_search_requests"):
+                web_search_count = int(
+                    getattr(server_tool_use, "web_search_requests", 0)
+                )
+                if web_search_count > 0:
+                    usage["web_search_count"] = web_search_count
+
    return usage


@@ -338,6 +338,61 @@ def format_gemini_input(contents: Any) -> List[FormattedMessage]:
    return [_format_object_message(contents)]


+def extract_gemini_web_search_count(response: Any) -> int:
+    """
+    Extract web search count from Gemini response.
+
+    Gemini bills per request that uses grounding, not per query.
+    Returns 1 if grounding_metadata is present with actual search data, 0 otherwise.
+
+    Args:
+        response: The response from Gemini API
+
+    Returns:
+        1 if web search/grounding was used, 0 otherwise
+    """
+
+    # Check for grounding_metadata in candidates
+    if hasattr(response, "candidates"):
+        for candidate in response.candidates:
+            if (
+                hasattr(candidate, "grounding_metadata")
+                and candidate.grounding_metadata
+            ):
+                grounding_metadata = candidate.grounding_metadata
+
+                # Check if web_search_queries exists and is non-empty
+                if hasattr(grounding_metadata, "web_search_queries"):
+                    queries = grounding_metadata.web_search_queries
+
+                    if queries is not None and len(queries) > 0:
+                        return 1
+
+                # Check if grounding_chunks exists and is non-empty
+                if hasattr(grounding_metadata, "grounding_chunks"):
+                    chunks = grounding_metadata.grounding_chunks
+
+                    if chunks is not None and len(chunks) > 0:
+                        return 1
+
+            # Also check for google_search or grounding in function call names
+            if hasattr(candidate, "content") and candidate.content:
+                if hasattr(candidate.content, "parts") and candidate.content.parts:
+                    for part in candidate.content.parts:
+                        if hasattr(part, "function_call") and part.function_call:
+                            function_name = getattr(
+                                part.function_call, "name", ""
+                            ).lower()
+
+                            if (
+                                "google_search" in function_name
+                                or "grounding" in function_name
+                            ):
+                                return 1
+
+    return 0
+
+
 def _extract_usage_from_metadata(metadata: Any) -> TokenUsage:
    """
    Common logic to extract usage from Gemini metadata.
@@ -382,7 +437,14 @@ def extract_gemini_usage_from_response(response: Any) -> TokenUsage:
    if not hasattr(response, "usage_metadata") or not response.usage_metadata:
        return TokenUsage(input_tokens=0, output_tokens=0)

-    return _extract_usage_from_metadata(response.usage_metadata)
+    usage = _extract_usage_from_metadata(response.usage_metadata)
+
+    # Add web search count if present
+    web_search_count = extract_gemini_web_search_count(response)
+    if web_search_count > 0:
+        usage["web_search_count"] = web_search_count
+
+    return usage


 def extract_gemini_usage_from_chunk(chunk: Any) -> TokenUsage:
@@ -398,11 +460,19 @@ def extract_gemini_usage_from_chunk(chunk: Any) -> TokenUsage:

    usage: TokenUsage = TokenUsage()

+    # Extract web search count from the chunk before checking for usage_metadata
+    # Web search indicators can appear on any chunk, not just those with usage data
+    web_search_count = extract_gemini_web_search_count(chunk)
+    if web_search_count > 0:
+        usage["web_search_count"] = web_search_count
+
    if not hasattr(chunk, "usage_metadata") or not chunk.usage_metadata:
        return usage

-    # Use the shared helper to extract usage
-    usage = _extract_usage_from_metadata(chunk.usage_metadata)
+    usage_from_metadata = _extract_usage_from_metadata(chunk.usage_metadata)
+
+    # Merge the usage from metadata with any web search count we found
+    usage.update(usage_from_metadata)

    return usage

@@ -1,8 +1,8 @@
 try:
-    import langchain  # noqa: F401
+    import langchain_core  # noqa: F401
 except ImportError:
    raise ModuleNotFoundError(
-        "Please install LangChain to use this feature: 'pip install langchain'"
+        "Please install LangChain to use this feature: 'pip install langchain-core'"
    )

 import json
@@ -20,8 +20,14 @@ from typing import (
 )
 from uuid import UUID

-from langchain.callbacks.base import BaseCallbackHandler
-from langchain.schema.agent import AgentAction, AgentFinish
+try:
+    # LangChain 1.0+ and modern 0.x with langchain-core
+    from langchain_core.callbacks.base import BaseCallbackHandler
+    from langchain_core.agents import AgentAction, AgentFinish
+except (ImportError, ModuleNotFoundError):
+    # Fallback for older LangChain versions
+    from langchain.callbacks.base import BaseCallbackHandler
+    from langchain.schema.agent import AgentAction, AgentFinish
 from langchain_core.documents import Document
 from langchain_core.messages import (
    AIMessage,
@@ -73,6 +79,8 @@ class GenerationMetadata(SpanMetadata):
    """Base URL of the provider's API used in the run."""
    tools: Optional[List[Dict[str, Any]]] = None
    """Tools provided to the model."""
+    posthog_properties: Optional[Dict[str, Any]] = None
+    """PostHog properties of the run."""


 RunMetadata = Union[SpanMetadata, GenerationMetadata]
@@ -414,6 +422,8 @@ class CallbackHandler(BaseCallbackHandler):
                generation.model = model
            if provider := metadata.get("ls_provider"):
                generation.provider = provider
+
+            generation.posthog_properties = metadata.get("posthog_properties")
        try:
            base_url = serialized["kwargs"]["openai_api_base"]
            if base_url is not None:
@@ -486,6 +496,7 @@ class CallbackHandler(BaseCallbackHandler):
            "$ai_latency": run.latency,
            "$ai_span_name": run.name,
            "$ai_span_id": run_id,
+            "$ai_framework": "langchain",
        }
        if parent_run_id is not None:
            event_properties["$ai_parent_id"] = parent_run_id
@@ -556,8 +567,12 @@ class CallbackHandler(BaseCallbackHandler):
            "$ai_http_status": 200,
            "$ai_latency": run.latency,
            "$ai_base_url": run.base_url,
+            "$ai_framework": "langchain",
        }

+        if isinstance(run.posthog_properties, dict):
+            event_properties.update(run.posthog_properties)
+
        if run.tools:
            event_properties["$ai_tools"] = run.tools

@@ -567,7 +582,7 @@ class CallbackHandler(BaseCallbackHandler):
            event_properties["$ai_is_error"] = True
        else:
            # Add usage
-            usage = _parse_usage(output)
+            usage = _parse_usage(output, run.provider, run.model)
            event_properties["$ai_input_tokens"] = usage.input_tokens
            event_properties["$ai_output_tokens"] = usage.output_tokens
            event_properties["$ai_cache_creation_input_tokens"] = (
@@ -688,6 +703,8 @@ class ModelUsage:

 def _parse_usage_model(
    usage: Union[BaseModel, dict],
+    provider: Optional[str] = None,
+    model: Optional[str] = None,
 ) -> ModelUsage:
    if isinstance(usage, BaseModel):
        usage = usage.__dict__
@@ -750,15 +767,36 @@ def _parse_usage_model(
        "cache_read": "cache_read_tokens",
        "reasoning": "reasoning_tokens",
    }
-    return ModelUsage(
+    normalized_usage = ModelUsage(
        **{
            dataclass_key: parsed_usage.get(mapped_key) or 0
            for mapped_key, dataclass_key in field_mapping.items()
        },
    )
+    # For Anthropic providers, LangChain reports input_tokens as the sum of input and cache read tokens.
+    # Our cost calculation expects them to be separate for Anthropic, so we subtract cache tokens.
+    # For other providers (OpenAI, etc.), input_tokens already includes cache tokens as expected.
+    # Match logic consistent with plugin-server: exact match on provider OR substring match on model
+    is_anthropic = False
+    if provider and provider.lower() == "anthropic":
+        is_anthropic = True
+    elif model and "anthropic" in model.lower():
+        is_anthropic = True
+
+    if (
+        is_anthropic
+        and normalized_usage.input_tokens
+        and normalized_usage.cache_read_tokens
+    ):
+        normalized_usage.input_tokens = max(
+            normalized_usage.input_tokens - normalized_usage.cache_read_tokens, 0
+        )
+    return normalized_usage


-def _parse_usage(response: LLMResult) -> ModelUsage:
+def _parse_usage(
+    response: LLMResult, provider: Optional[str] = None, model: Optional[str] = None
+) -> ModelUsage:
    # langchain-anthropic uses the usage field
    llm_usage_keys = ["token_usage", "usage"]
    llm_usage: ModelUsage = ModelUsage(
@@ -772,13 +810,15 @@ def _parse_usage(response: LLMResult) -> ModelUsage:
    if response.llm_output is not None:
        for key in llm_usage_keys:
            if response.llm_output.get(key):
-                llm_usage = _parse_usage_model(response.llm_output[key])
+                llm_usage = _parse_usage_model(
+                    response.llm_output[key], provider, model
+                )
                break

    if hasattr(response, "generations"):
        for generation in response.generations:
            if "usage" in generation:
-                llm_usage = _parse_usage_model(generation["usage"])
+                llm_usage = _parse_usage_model(generation["usage"], provider, model)
                break

            for generation_chunk in generation:
@@ -786,7 +826,9 @@ def _parse_usage(response: LLMResult) -> ModelUsage:
                    "usage_metadata" in generation_chunk.generation_info
                ):
                    llm_usage = _parse_usage_model(
-                        generation_chunk.generation_info["usage_metadata"]
+                        generation_chunk.generation_info["usage_metadata"],
+                        provider,
+                        model,
                    )
                    break

@@ -813,7 +855,7 @@ def _parse_usage(response: LLMResult) -> ModelUsage:
                    bedrock_anthropic_usage or bedrock_titan_usage or ollama_usage
                )
                if chunk_usage:
-                    llm_usage = _parse_usage_model(chunk_usage)
+                    llm_usage = _parse_usage_model(chunk_usage, provider, model)
                    break

    return llm_usage
@@ -213,6 +213,15 @@ class WrappedResponses:
            **(posthog_properties or {}),
        }

+        # Add web search count if present
+        web_search_count = usage_stats.get("web_search_count")
+        if (
+            web_search_count is not None
+            and isinstance(web_search_count, int)
+            and web_search_count > 0
+        ):
+            event_properties["$ai_web_search_count"] = web_search_count
+
        if available_tool_calls:
            event_properties["$ai_tools"] = available_tool_calls

@@ -444,6 +453,16 @@ class WrappedCompletions:
            **(posthog_properties or {}),
        }

+        # Add web search count if present
+        web_search_count = usage_stats.get("web_search_count")
+
+        if (
+            web_search_count is not None
+            and isinstance(web_search_count, int)
+            and web_search_count > 0
+        ):
+            event_properties["$ai_web_search_count"] = web_search_count
+
        if available_tool_calls:
            event_properties["$ai_tools"] = available_tool_calls

@@ -255,6 +255,113 @@ def format_openai_streaming_content(
    return formatted


+def extract_openai_web_search_count(response: Any) -> int:
+    """
+    Extract web search count from OpenAI response.
+
+    Uses a two-tier detection strategy:
+    1. Priority 1 (exact count): Check for output[].type == "web_search_call" (Responses API)
+    2. Priority 2 (binary detection): Check for various web search indicators:
+       - Root-level citations, search_results, or usage.search_context_size (Perplexity)
+       - Annotations with type "url_citation" in choices/output (including delta for streaming)
+
+    Args:
+        response: The response from OpenAI API
+
+    Returns:
+        Number of web search requests (exact count or binary 1/0)
+    """
+
+    # Priority 1: Check for exact count in Responses API output
+    if hasattr(response, "output"):
+        web_search_count = 0
+
+        for item in response.output:
+            if hasattr(item, "type") and item.type == "web_search_call":
+                web_search_count += 1
+
+        web_search_count = max(0, web_search_count)
+
+        if web_search_count > 0:
+            return web_search_count
+
+    # Priority 2: Binary detection (returns 1 or 0)
+
+    # Check root-level indicators (Perplexity)
+    if hasattr(response, "citations"):
+        citations = getattr(response, "citations")
+
+        if citations and len(citations) > 0:
+            return 1
+
+    if hasattr(response, "search_results"):
+        search_results = getattr(response, "search_results")
+
+        if search_results and len(search_results) > 0:
+            return 1
+
+    if hasattr(response, "usage") and hasattr(response.usage, "search_context_size"):
+        if response.usage.search_context_size:
+            return 1
+
+    # Check for url_citation annotations in choices (Chat Completions)
+    if hasattr(response, "choices"):
+        for choice in response.choices:
+            # Check message.annotations (non-streaming or final chunk)
+            if hasattr(choice, "message") and hasattr(choice.message, "annotations"):
+                annotations = choice.message.annotations
+
+                if annotations:
+                    for annotation in annotations:
+                        # Support both dict and object formats
+                        annotation_type = (
+                            annotation.get("type")
+                            if isinstance(annotation, dict)
+                            else getattr(annotation, "type", None)
+                        )
+
+                        if annotation_type == "url_citation":
+                            return 1
+
+            # Check delta.annotations (streaming chunks)
+            if hasattr(choice, "delta") and hasattr(choice.delta, "annotations"):
+                annotations = choice.delta.annotations
+
+                if annotations:
+                    for annotation in annotations:
+                        # Support both dict and object formats
+                        annotation_type = (
+                            annotation.get("type")
+                            if isinstance(annotation, dict)
+                            else getattr(annotation, "type", None)
+                        )
+
+                        if annotation_type == "url_citation":
+                            return 1
+
+    # Check for url_citation annotations in output (Responses API)
+    if hasattr(response, "output"):
+        for item in response.output:
+            if hasattr(item, "content") and isinstance(item.content, list):
+                for content_item in item.content:
+                    if hasattr(content_item, "annotations"):
+                        annotations = content_item.annotations
+
+                        if annotations:
+                            for annotation in annotations:
+                                # Support both dict and object formats
+                                annotation_type = (
+                                    annotation.get("type")
+                                    if isinstance(annotation, dict)
+                                    else getattr(annotation, "type", None)
+                                )
+
+                                if annotation_type == "url_citation":
+                                    return 1
+
+    return 0
+
+
 def extract_openai_usage_from_response(response: Any) -> TokenUsage:
    """
    Extract usage statistics from a full OpenAI response (non-streaming).
@@ -312,6 +419,10 @@ def extract_openai_usage_from_response(response: Any) -> TokenUsage:
    if reasoning_tokens > 0:
        result["reasoning_tokens"] = reasoning_tokens

+    web_search_count = extract_openai_web_search_count(response)
+    if web_search_count > 0:
+        result["web_search_count"] = web_search_count
+
    return result


@@ -334,6 +445,13 @@ def extract_openai_usage_from_chunk(
    usage: TokenUsage = TokenUsage()

    if provider_type == "chat":
+        # Extract web search count from the chunk before checking for usage
+        # Web search indicators (citations, annotations) can appear on any chunk,
+        # not just those with usage data
+        web_search_count = extract_openai_web_search_count(chunk)
+        if web_search_count > 0:
+            usage["web_search_count"] = web_search_count
+
        if not hasattr(chunk, "usage") or not chunk.usage:
            return usage

@@ -386,6 +504,12 @@ def extract_openai_usage_from_chunk(
                        response_usage.output_tokens_details.reasoning_tokens
                    )

+                # Extract web search count from the complete response
+                if hasattr(chunk, "response"):
+                    web_search_count = extract_openai_web_search_count(chunk.response)
+                    if web_search_count > 0:
+                        usage["web_search_count"] = web_search_count
+
    return usage


@@ -63,6 +63,7 @@ class TokenUsage(TypedDict, total=False):
    cache_read_input_tokens: Optional[int]
    cache_creation_input_tokens: Optional[int]
    reasoning_tokens: Optional[int]
+    web_search_count: Optional[int]


 class ProviderResponse(TypedDict, total=False):
@@ -53,6 +53,12 @@ def merge_usage_stats(
        if source_reasoning is not None:
            current = target.get("reasoning_tokens") or 0
            target["reasoning_tokens"] = current + source_reasoning
+
+        source_web_search = source.get("web_search_count")
+        if source_web_search is not None:
+            current = target.get("web_search_count") or 0
+            target["web_search_count"] = max(current, source_web_search)
+
    elif mode == "cumulative":
        # Replace with latest values (already cumulative)
        if source.get("input_tokens") is not None:
@@ -67,6 +73,9 @@ def merge_usage_stats(
            ]
        if source.get("reasoning_tokens") is not None:
            target["reasoning_tokens"] = source["reasoning_tokens"]
+        if source.get("web_search_count") is not None:
+            target["web_search_count"] = source["web_search_count"]
+
    else:
        raise ValueError(f"Invalid mode: {mode}. Must be 'incremental' or 'cumulative'")

@@ -311,6 +320,10 @@ def call_llm_and_track_usage(
        if reasoning is not None and reasoning > 0:
            event_properties["$ai_reasoning_tokens"] = reasoning

+        web_search_count = usage.get("web_search_count")
+        if web_search_count is not None and web_search_count > 0:
+            event_properties["$ai_web_search_count"] = web_search_count
+
        if posthog_distinct_id is None:
            event_properties["$process_person_profile"] = False

@@ -414,6 +427,14 @@ async def call_llm_and_track_usage_async(
        if cache_creation is not None and cache_creation > 0:
            event_properties["$ai_cache_creation_input_tokens"] = cache_creation

+        reasoning = usage.get("reasoning_tokens")
+        if reasoning is not None and reasoning > 0:
+            event_properties["$ai_reasoning_tokens"] = reasoning
+
+        web_search_count = usage.get("web_search_count")
+        if web_search_count is not None and web_search_count > 0:
+            event_properties["$ai_web_search_count"] = web_search_count
+
        if posthog_distinct_id is None:
            event_properties["$process_person_profile"] = False

@@ -535,6 +556,15 @@ def capture_streaming_event(
            if value is not None and isinstance(value, int) and value > 0:
                event_properties[f"$ai_{field}"] = value

+    # Add web search count if present (all providers)
+    web_search_count = event_data["usage_stats"].get("web_search_count")
+    if (
+        web_search_count is not None
+        and isinstance(web_search_count, int)
+        and web_search_count > 0
+    ):
+        event_properties["$ai_web_search_count"] = web_search_count
+
    # Handle provider-specific fields
    if (
        event_data["provider"] == "openai"
@@ -3,7 +3,7 @@ import logging
 import os
 import sys
 from datetime import datetime, timedelta
-from typing import Any, Callable, Dict, Optional, Union
+from typing import Any, Dict, Optional, Union
 from typing_extensions import Unpack
 from uuid import uuid4

@@ -19,6 +19,9 @@ from posthog.exception_utils import (
    handle_in_app,
    exception_is_already_captured,
    mark_exception_as_captured,
+    try_attach_code_variables_to_frames,
+    DEFAULT_CODE_VARIABLES_MASK_PATTERNS,
+    DEFAULT_CODE_VARIABLES_IGNORE_PATTERNS,
 )
 from posthog.feature_flags import (
    InconclusiveMatchError,
@@ -39,6 +42,9 @@ from posthog.contexts import (
    _get_current_context,
    get_context_distinct_id,
    get_context_session_id,
+    get_capture_exception_code_variables_context,
+    get_code_variables_mask_patterns_context,
+    get_code_variables_ignore_patterns_context,
    new_context,
 )
 from posthog.types import (
@@ -60,7 +66,6 @@ from posthog.utils import (
    SizeLimitedDict,
    clean,
    guess_timezone,
-    remove_trailing_slash,
    system_context,
 )
 from posthog.version import VERSION
@@ -179,6 +184,9 @@ class Client(object):
        before_send=None,
        flag_fallback_cache_url=None,
        enable_local_evaluation=True,
+        capture_exception_code_variables=False,
+        code_variables_mask_patterns=None,
+        code_variables_ignore_patterns=None,
    ):
        """
        Initialize a new PostHog client instance.
@@ -234,6 +242,18 @@ class Client(object):
        self.privacy_mode = privacy_mode
        self.enable_local_evaluation = enable_local_evaluation

+        self.capture_exception_code_variables = capture_exception_code_variables
+        self.code_variables_mask_patterns = (
+            code_variables_mask_patterns
+            if code_variables_mask_patterns is not None
+            else DEFAULT_CODE_VARIABLES_MASK_PATTERNS
+        )
+        self.code_variables_ignore_patterns = (
+            code_variables_ignore_patterns
+            if code_variables_ignore_patterns is not None
+            else DEFAULT_CODE_VARIABLES_IGNORE_PATTERNS
+        )
+
        if project_root is None:
            try:
                project_root = os.getcwd()
@@ -275,8 +295,9 @@ class Client(object):
            # to call flush().
            if send:
                atexit.register(self.join)
-            for n in range(thread):
-                self.consumers = []
+
+            self.consumers = []
+            for _ in range(thread):
                consumer = Consumer(
                    self.queue,
                    self.api_key,
@@ -705,21 +726,7 @@ class Client(object):
        Examples:
            ```python
            # Set with distinct id
-            posthog.capture(
-                'event_name',
-                distinct_id='user-distinct-id',
-                properties={
-                    '$set': {'name': 'Max Hedgehog'},
-                    '$set_once': {'initial_url': '/blog'}
-                }
-            )
-            ```
-            ```python
-            # Set using context
-            from posthog import new_context, identify_context
-            with new_context():
-                identify_context('user-distinct-id')
-                posthog.capture('event_name')
+            posthog.set(distinct_id='user123', properties={'name': 'Max Hedgehog'})
            ```

        Category:
@@ -980,6 +987,34 @@ class Client(object):
                **properties,
            }

+            context_enabled = get_capture_exception_code_variables_context()
+            context_mask = get_code_variables_mask_patterns_context()
+            context_ignore = get_code_variables_ignore_patterns_context()
+
+            enabled = (
+                context_enabled
+                if context_enabled is not None
+                else self.capture_exception_code_variables
+            )
+            mask_patterns = (
+                context_mask
+                if context_mask is not None
+                else self.code_variables_mask_patterns
+            )
+            ignore_patterns = (
+                context_ignore
+                if context_ignore is not None
+                else self.code_variables_ignore_patterns
+            )
+
+            if enabled:
+                try_attach_code_variables_to_frames(
+                    all_exceptions_with_trace_and_in_app,
+                    exc_info,
+                    mask_patterns=mask_patterns,
+                    ignore_patterns=ignore_patterns,
+                )
+
            if self.log_captured_exceptions:
                self.log.exception(exception, extra=kwargs)

@@ -22,6 +22,9 @@ class ContextScope:
        self.session_id: Optional[str] = None
        self.distinct_id: Optional[str] = None
        self.tags: Dict[str, Any] = {}
+        self.capture_exception_code_variables: Optional[bool] = None
+        self.code_variables_mask_patterns: Optional[list] = None
+        self.code_variables_ignore_patterns: Optional[list] = None

    def set_session_id(self, session_id: str):
        self.session_id = session_id
@@ -32,6 +35,15 @@ class ContextScope:
    def add_tag(self, key: str, value: Any):
        self.tags[key] = value

+    def set_capture_exception_code_variables(self, enabled: bool):
+        self.capture_exception_code_variables = enabled
+
+    def set_code_variables_mask_patterns(self, mask_patterns: list):
+        self.code_variables_mask_patterns = mask_patterns
+
+    def set_code_variables_ignore_patterns(self, ignore_patterns: list):
+        self.code_variables_ignore_patterns = ignore_patterns
+
    def get_parent(self):
        return self.parent

@@ -59,6 +71,27 @@ class ContextScope:
            tags.update(new_tags)
        return tags

+    def get_capture_exception_code_variables(self) -> Optional[bool]:
+        if self.capture_exception_code_variables is not None:
+            return self.capture_exception_code_variables
+        if self.parent is not None and not self.fresh:
+            return self.parent.get_capture_exception_code_variables()
+        return None
+
+    def get_code_variables_mask_patterns(self) -> Optional[list]:
+        if self.code_variables_mask_patterns is not None:
+            return self.code_variables_mask_patterns
+        if self.parent is not None and not self.fresh:
+            return self.parent.get_code_variables_mask_patterns()
+        return None
+
+    def get_code_variables_ignore_patterns(self) -> Optional[list]:
+        if self.code_variables_ignore_patterns is not None:
+            return self.code_variables_ignore_patterns
+        if self.parent is not None and not self.fresh:
+            return self.parent.get_code_variables_ignore_patterns()
+        return None
+

 _context_stack: contextvars.ContextVar[Optional[ContextScope]] = contextvars.ContextVar(
    "posthog_context_stack", default=None
@@ -243,6 +276,54 @@ def get_context_distinct_id() -> Optional[str]:
    return None


+def set_capture_exception_code_variables_context(enabled: bool) -> None:
+    """
+    Set whether code variables are captured for the current context.
+    """
+    current_context = _get_current_context()
+    if current_context:
+        current_context.set_capture_exception_code_variables(enabled)
+
+
+def set_code_variables_mask_patterns_context(mask_patterns: list) -> None:
+    """
+    Variable names matching these patterns will be masked with *** when capturing code variables.
+    """
+    current_context = _get_current_context()
+    if current_context:
+        current_context.set_code_variables_mask_patterns(mask_patterns)
+
+
+def set_code_variables_ignore_patterns_context(ignore_patterns: list) -> None:
+    """
+    Variable names matching these patterns will be ignored completely when capturing code variables.
+    """
+    current_context = _get_current_context()
+    if current_context:
+        current_context.set_code_variables_ignore_patterns(ignore_patterns)
+
+
+def get_capture_exception_code_variables_context() -> Optional[bool]:
+    current_context = _get_current_context()
+    if current_context:
+        return current_context.get_capture_exception_code_variables()
+    return None
+
+
+def get_code_variables_mask_patterns_context() -> Optional[list]:
+    current_context = _get_current_context()
+    if current_context:
+        return current_context.get_code_variables_mask_patterns()
+    return None
+
+
+def get_code_variables_ignore_patterns_context() -> Optional[list]:
+    current_context = _get_current_context()
+    if current_context:
+        return current_context.get_code_variables_ignore_patterns()
+    return None
+
+
 F = TypeVar("F", bound=Callable[..., Any])


@@ -5,6 +5,7 @@
 # 💖open source (under MIT License)
 # We want to keep payloads as similar to Sentry as possible for easy interoperability

+import json
 import linecache
 import os
 import re
@@ -26,6 +27,7 @@ from typing import (  # noqa: F401
    Union,
    cast,
    TYPE_CHECKING,
+    Pattern,
 )

 from posthog.args import ExcInfo, ExceptionArg  # noqa: F401
@@ -40,6 +42,42 @@ except ImportError:

 DEFAULT_MAX_VALUE_LENGTH = 1024

+DEFAULT_CODE_VARIABLES_MASK_PATTERNS = [
+    r"(?i).*password.*",
+    r"(?i).*secret.*",
+    r"(?i).*passwd.*",
+    r"(?i).*pwd.*",
+    r"(?i).*api_key.*",
+    r"(?i).*apikey.*",
+    r"(?i).*auth.*",
+    r"(?i).*credentials.*",
+    r"(?i).*privatekey.*",
+    r"(?i).*private_key.*",
+    r"(?i).*token.*",
+]
+
+DEFAULT_CODE_VARIABLES_IGNORE_PATTERNS = [r"^__.*"]
+
+CODE_VARIABLES_REDACTED_VALUE = "$$_posthog_redacted_based_on_masking_rules_$$"
+
+DEFAULT_TOTAL_VARIABLES_SIZE_LIMIT = 20 * 1024
+
+
+class VariableSizeLimiter:
+    def __init__(self, max_size=DEFAULT_TOTAL_VARIABLES_SIZE_LIMIT):
+        self.max_size = max_size
+        self.current_size = 0
+
+    def can_add(self, size):
+        return self.current_size + size <= self.max_size
+
+    def add(self, size):
+        self.current_size += size
+
+    def get_remaining_space(self):
+        return self.max_size - self.current_size
+
+
 LogLevelStr = Literal["fatal", "critical", "error", "warning", "info", "debug"]

 Event = TypedDict(
@@ -884,3 +922,168 @@ def strip_string(value, max_length=None):
            "rem": [["!limit", "x", max_length - 3, max_length]],
        },
    )
+
+
+def _compile_patterns(patterns):
+    compiled = []
+    for pattern in patterns:
+        try:
+            compiled.append(re.compile(pattern))
+        except Exception:
+            pass
+    return compiled
+
+
+def _pattern_matches(name, patterns):
+    for pattern in patterns:
+        if pattern.search(name):
+            return True
+    return False
+
+
+def _serialize_variable_value(value, limiter, max_length=1024):
+    try:
+        if value is None:
+            result = "None"
+        elif isinstance(value, bool):
+            result = str(value)
+        elif isinstance(value, (int, float)):
+            result_size = len(str(value))
+            if not limiter.can_add(result_size):
+                return None
+            limiter.add(result_size)
+            return value
+        elif isinstance(value, str):
+            result = value
+        else:
+            result = json.dumps(value)
+
+        if len(result) > max_length:
+            result = result[: max_length - 3] + "..."
+
+        result_size = len(result)
+        if not limiter.can_add(result_size):
+            return None
+        limiter.add(result_size)
+
+        return result
+    except Exception:
+        try:
+            result = repr(value)
+            if len(result) > max_length:
+                result = result[: max_length - 3] + "..."
+
+            result_size = len(result)
+            if not limiter.can_add(result_size):
+                return None
+            limiter.add(result_size)
+            return result
+        except Exception:
+            try:
+                fallback = f"<{type(value).__name__}>"
+                fallback_size = len(fallback)
+                if not limiter.can_add(fallback_size):
+                    return None
+                limiter.add(fallback_size)
+                return fallback
+            except Exception:
+                fallback = "<unserializable object>"
+                fallback_size = len(fallback)
+                if not limiter.can_add(fallback_size):
+                    return None
+                limiter.add(fallback_size)
+                return fallback
+
+
+def _is_simple_type(value):
+    return isinstance(value, (type(None), bool, int, float, str))
+
+
+def serialize_code_variables(
+    frame, limiter, mask_patterns=None, ignore_patterns=None, max_length=1024
+):
+    if mask_patterns is None:
+        mask_patterns = []
+    if ignore_patterns is None:
+        ignore_patterns = []
+
+    compiled_mask = _compile_patterns(mask_patterns)
+    compiled_ignore = _compile_patterns(ignore_patterns)
+
+    try:
+        local_vars = frame.f_locals.copy()
+    except Exception:
+        return {}
+
+    simple_vars = {}
+    complex_vars = {}
+
+    for name, value in local_vars.items():
+        if _pattern_matches(name, compiled_ignore):
+            continue
+
+        if _is_simple_type(value):
+            simple_vars[name] = value
+        else:
+            complex_vars[name] = value
+
+    result = {}
+
+    all_vars = {**simple_vars, **complex_vars}
+    ordered_names = list(sorted(simple_vars.keys())) + list(sorted(complex_vars.keys()))
+
+    for name in ordered_names:
+        value = all_vars[name]
+
+        if _pattern_matches(name, compiled_mask):
+            redacted_value = CODE_VARIABLES_REDACTED_VALUE
+            redacted_size = len(redacted_value)
+            if not limiter.can_add(redacted_size):
+                break
+            limiter.add(redacted_size)
+            result[name] = redacted_value
+        else:
+            serialized = _serialize_variable_value(value, limiter, max_length)
+            if serialized is None:
+                break
+            result[name] = serialized
+
+    return result
+
+
+def try_attach_code_variables_to_frames(
+    all_exceptions, exc_info, mask_patterns, ignore_patterns
+):
+    exc_type, exc_value, traceback = exc_info
+
+    if traceback is None:
+        return
+
+    tb_frames = list(iter_stacks(traceback))
+
+    if not tb_frames:
+        return
+
+    limiter = VariableSizeLimiter()
+
+    for exception in all_exceptions:
+        stacktrace = exception.get("stacktrace")
+        if not stacktrace or "frames" not in stacktrace:
+            continue
+
+        serialized_frames = stacktrace["frames"]
+
+        for serialized_frame, tb_item in zip(serialized_frames, tb_frames):
+            if not serialized_frame.get("in_app"):
+                continue
+
+            variables = serialize_code_variables(
+                tb_item.tb_frame,
+                limiter,
+                mask_patterns=mask_patterns,
+                ignore_patterns=ignore_patterns,
+                max_length=1024,
+            )
+
+            if variables:
+                serialized_frame["code_variables"] = variables
@@ -3,13 +3,19 @@ from posthog import contexts
 from posthog.client import Client

 try:
-    from asgiref.sync import iscoroutinefunction
+    from asgiref.sync import iscoroutinefunction, markcoroutinefunction
 except ImportError:
-    # Fallback for older Django versions
+    # Fallback for older Django versions without asgiref
    import asyncio

    iscoroutinefunction = asyncio.iscoroutinefunction

+    # No-op fallback for markcoroutinefunction
+    # Older Django versions without asgiref typically don't support async middleware anyway
+    def markcoroutinefunction(func):
+        return func
+
+
 if TYPE_CHECKING:
    from django.http import HttpRequest, HttpResponse  # noqa: F401
    from typing import Callable, Dict, Any, Optional, Union, Awaitable  # noqa: F401
@@ -39,26 +45,24 @@ class PosthogContextMiddleware:
    See the context documentation for more information. The extracted distinct ID and session ID, if found, are used to
    associate all events captured in the middleware context with the same distinct ID and session as currently active on the
    frontend. See the documentation for `set_context_session` and `identify_context` for more details.
+
+    This middleware is hybrid-capable: it supports both WSGI (sync) and ASGI (async) Django applications. The middleware
+    detects at initialization whether the next middleware in the chain is async or sync, and adapts its behavior accordingly.
+    This ensures compatibility with both pure sync and pure async middleware chains, as well as mixed chains in ASGI mode.
    """

-    # Django middleware capability flags
    sync_capable = True
    async_capable = True

    def __init__(self, get_response):
        # type: (Union[Callable[[HttpRequest], HttpResponse], Callable[[HttpRequest], Awaitable[HttpResponse]]]) -> None
+        self.get_response = get_response
        self._is_coroutine = iscoroutinefunction(get_response)
-        self._async_get_response = None  # type: Optional[Callable[[HttpRequest], Awaitable[HttpResponse]]]
-        self._sync_get_response = None  # type: Optional[Callable[[HttpRequest], HttpResponse]]

+        # Mark this instance as a coroutine function if get_response is async
+        # This is required for Django to correctly detect async middleware
        if self._is_coroutine:
-            self._async_get_response = cast(
-                "Callable[[HttpRequest], Awaitable[HttpResponse]]", get_response
-            )
-        else:
-            self._sync_get_response = cast(
-                "Callable[[HttpRequest], HttpResponse]", get_response
-            )
+            markcoroutinefunction(self)

        from django.conf import settings

@@ -108,9 +112,18 @@ class PosthogContextMiddleware:

    def extract_tags(self, request):
        # type: (HttpRequest) -> Dict[str, Any]
-        tags = {}
+        """Extract tags from request in sync context."""
+        user_id, user_email = self.extract_request_user(request)
+        return self._build_tags(request, user_id, user_email)

-        (user_id, user_email) = self.extract_request_user(request)
+    def _build_tags(self, request, user_id, user_email):
+        # type: (HttpRequest, Optional[str], Optional[str]) -> Dict[str, Any]
+        """
+        Build tags dict from request and user info.
+
+        Centralized tag extraction logic used by both sync and async paths.
+        """
+        tags = {}

        # Extract session ID from X-POSTHOG-SESSION-ID header
        session_id = request.headers.get("X-POSTHOG-SESSION-ID")
@@ -162,59 +175,145 @@ class PosthogContextMiddleware:
        return tags

    def extract_request_user(self, request):
+        # type: (HttpRequest) -> tuple[Optional[str], Optional[str]]
+        """Extract user ID and email from request in sync context."""
+        user = getattr(request, "user", None)
+        return self._resolve_user_details(user)
+
+    async def aextract_tags(self, request):
+        # type: (HttpRequest) -> Dict[str, Any]
+        """
+        Async version of extract_tags for use in async request handling.
+
+        Uses await request.auser() instead of request.user to avoid
+        SynchronousOnlyOperation in async context.
+
+        Follows Django's naming convention for async methods (auser, asave, etc.).
+        """
+        user_id, user_email = await self.aextract_request_user(request)
+        return self._build_tags(request, user_id, user_email)
+
+    async def aextract_request_user(self, request):
+        # type: (HttpRequest) -> tuple[Optional[str], Optional[str]]
+        """
+        Async version of extract_request_user for use in async request handling.
+
+        Uses await request.auser() instead of request.user to avoid
+        SynchronousOnlyOperation in async context.
+
+        Follows Django's naming convention for async methods (auser, asave, etc.).
+        """
+        auser = getattr(request, "auser", None)
+        if callable(auser):
+            try:
+                user = await auser()
+                return self._resolve_user_details(user)
+            except Exception:
+                # If auser() fails, return empty - don't break the request
+                # Real errors (permissions, broken auth) will be logged by Django
+                return None, None
+
+        # Fallback for test requests without auser
+        return None, None
+
+    def _resolve_user_details(self, user):
+        # type: (Any) -> tuple[Optional[str], Optional[str]]
+        """
+        Extract user ID and email from a user object.
+
+        Handles both authenticated and unauthenticated users, as well as
+        legacy Django where is_authenticated was a method.
+        """
        user_id = None
        email = None

-        user = getattr(request, "user", None)
+        if user is None:
+            return user_id, email

-        if user and getattr(user, "is_authenticated", False):
-            try:
-                user_id = str(user.pk)
-            except Exception:
-                pass
+        # Handle is_authenticated (property in modern Django, method in legacy)
+        is_authenticated = getattr(user, "is_authenticated", False)
+        if callable(is_authenticated):
+            is_authenticated = is_authenticated()

-            try:
-                email = str(user.email)
-            except Exception:
-                pass
+        if not is_authenticated:
+            return user_id, email
+
+        # Extract user primary key
+        user_pk = getattr(user, "pk", None)
+        if user_pk is not None:
+            user_id = str(user_pk)
+
+        # Extract user email
+        user_email = getattr(user, "email", None)
+        if user_email:
+            email = str(user_email)

        return user_id, email

    def __call__(self, request):
-        # type: (HttpRequest) -> HttpResponse
-        # Purely defensive around django's internal sync/async handling - this should be unreachable, but if it's reached, we may
-        # as well return something semi-meaningful
+        # type: (HttpRequest) -> Union[HttpResponse, Awaitable[HttpResponse]]
+        """
+        Unified entry point for both sync and async request handling.
+
+        When sync_capable and async_capable are both True, Django passes requests
+        without conversion. This method detects the mode and routes accordingly.
+        """
        if self._is_coroutine:
-            raise RuntimeError(
-                "PosthogContextMiddleware received sync call but get_response is async"
-            )
+            return self.__acall__(request)
+        else:
+            # Synchronous path
+            if self.request_filter and not self.request_filter(request):
+                return self.get_response(request)

-        if self.request_filter and not self.request_filter(request):
-            assert self._sync_get_response is not None
-            return self._sync_get_response(request)
+            with contexts.new_context(self.capture_exceptions, client=self.client):
+                for k, v in self.extract_tags(request).items():
+                    contexts.tag(k, v)

-        with contexts.new_context(self.capture_exceptions, client=self.client):
-            for k, v in self.extract_tags(request).items():
-                contexts.tag(k, v)
-
-            assert self._sync_get_response is not None
-            return self._sync_get_response(request)
+                return self.get_response(request)

    async def __acall__(self, request):
-        # type: (HttpRequest) -> HttpResponse
+        # type: (HttpRequest) -> Awaitable[HttpResponse]
+        """
+        Asynchronous entry point for async request handling.
+
+        This method is called when the middleware chain is async.
+        Uses aextract_tags() which calls request.auser() to avoid
+        SynchronousOnlyOperation when accessing user in async context.
+        """
        if self.request_filter and not self.request_filter(request):
-            if self._async_get_response is not None:
-                return await self._async_get_response(request)
-            else:
-                assert self._sync_get_response is not None
-                return self._sync_get_response(request)
+            return await self.get_response(request)

        with contexts.new_context(self.capture_exceptions, client=self.client):
-            for k, v in self.extract_tags(request).items():
+            for k, v in (await self.aextract_tags(request)).items():
                contexts.tag(k, v)

-            if self._async_get_response is not None:
-                return await self._async_get_response(request)
-            else:
-                assert self._sync_get_response is not None
-                return self._sync_get_response(request)
+            return await self.get_response(request)
+
+    def process_exception(self, request, exception):
+        # type: (HttpRequest, Exception) -> None
+        """
+        Process exceptions from views and downstream middleware.
+
+        Django calls this WHILE still inside the context created by __call__,
+        so request tags have already been extracted and set. This method just
+        needs to capture the exception directly.
+
+        Django converts view exceptions into responses before they propagate through
+        the middleware stack, so the context manager in __call__/__acall__ never sees them.
+
+        Note: Django's process_exception is always synchronous, even for async views.
+        """
+        if self.request_filter and not self.request_filter(request):
+            return
+
+        if not self.capture_exceptions:
+            return
+
+        # Context and tags already set by __call__ or __acall__
+        # Just capture the exception
+        if self.client:
+            self.client.capture_exception(exception)
+        else:
+            from posthog import capture_exception
+
+            capture_exception(exception)
@@ -1,4 +1,3 @@
-import os
 from unittest.mock import patch

 import pytest
@@ -1034,3 +1033,233 @@ def test_async_streaming_with_tool_calls(mock_client, mock_anthropic_stream_with
        assert props["$ai_output_tokens"] == 25
        assert props["$ai_cache_read_input_tokens"] == 5
        assert props["$ai_cache_creation_input_tokens"] == 0
+
+
+def test_web_search_count(mock_client):
+    """Test that web search count is properly tracked from Anthropic responses."""
+
+    # Create a mock usage with web search
+    class MockServerToolUse:
+        def __init__(self):
+            self.web_search_requests = 3
+
+    class MockUsageWithWebSearch:
+        def __init__(self):
+            self.input_tokens = 100
+            self.output_tokens = 50
+            self.cache_read_input_tokens = 0
+            self.cache_creation_input_tokens = 0
+            self.server_tool_use = MockServerToolUse()
+
+    class MockResponseWithWebSearch:
+        def __init__(self):
+            self.content = [MockContent(text="Search results show...")]
+            self.model = "claude-3-opus-20240229"
+            self.usage = MockUsageWithWebSearch()
+
+    mock_response = MockResponseWithWebSearch()
+
+    with patch("anthropic.resources.Messages.create", return_value=mock_response):
+        client = Anthropic(api_key="test-key", posthog_client=mock_client)
+        response = client.messages.create(
+            model="claude-3-opus-20240229",
+            messages=[{"role": "user", "content": "Search for recent news"}],
+            posthog_distinct_id="test-id",
+        )
+
+        assert response == mock_response
+        assert mock_client.capture.call_count == 1
+
+        call_args = mock_client.capture.call_args[1]
+        props = call_args["properties"]
+
+        # Verify web search count is captured
+        assert props["$ai_web_search_count"] == 3
+        assert props["$ai_input_tokens"] == 100
+        assert props["$ai_output_tokens"] == 50
+
+
+@pytest.fixture
+def mock_anthropic_stream_with_web_search():
+    """Mock stream events for web search."""
+
+    class MockServerToolUse:
+        def __init__(self):
+            self.web_search_requests = 2
+
+    class MockMessage:
+        def __init__(self):
+            self.usage = MockUsage(
+                input_tokens=50,
+                cache_creation_input_tokens=0,
+                cache_read_input_tokens=5,
+            )
+
+    def stream_generator():
+        # Message start with usage
+        event = MockStreamEvent("message_start")
+        event.message = MockMessage()
+        yield event
+
+        # Text block start
+        event = MockStreamEvent("content_block_start")
+        event.content_block = MockContentBlock("text")
+        event.index = 0
+        yield event
+
+        # Text delta
+        event = MockStreamEvent("content_block_delta")
+        event.delta = MockDelta(text="Here are the search results...")
+        event.index = 0
+        yield event
+
+        # Text block stop
+        event = MockStreamEvent("content_block_stop")
+        event.index = 0
+        yield event
+
+        # Message delta with final usage including web search
+        event = MockStreamEvent("message_delta")
+        usage = MockUsage(output_tokens=25)
+        usage.server_tool_use = MockServerToolUse()
+        event.usage = usage
+        yield event
+
+        # Message stop
+        event = MockStreamEvent("message_stop")
+        yield event
+
+    return stream_generator()
+
+
+def test_streaming_with_web_search(mock_client, mock_anthropic_stream_with_web_search):
+    """Test that web search count is properly captured in streaming mode."""
+    with patch(
+        "anthropic.resources.Messages.create",
+        return_value=mock_anthropic_stream_with_web_search,
+    ):
+        client = Anthropic(api_key="test-key", posthog_client=mock_client)
+        response = client.messages.create(
+            model="claude-3-opus-20240229",
+            messages=[{"role": "user", "content": "Search for recent news"}],
+            stream=True,
+            posthog_distinct_id="test-id",
+        )
+
+        # Consume the stream - this triggers the finally block synchronously
+        list(response)
+
+        # Capture happens synchronously when generator is exhausted
+        assert mock_client.capture.call_count == 1
+
+        call_args = mock_client.capture.call_args[1]
+        props = call_args["properties"]
+
+        # Verify web search count is captured
+        assert props["$ai_web_search_count"] == 2
+        assert props["$ai_input_tokens"] == 50
+        assert props["$ai_output_tokens"] == 25
+
+
+def test_async_with_web_search(mock_client):
+    """Test that web search count is properly tracked in async non-streaming mode."""
+    import asyncio
+
+    # Create a mock usage with web search
+    class MockServerToolUse:
+        def __init__(self):
+            self.web_search_requests = 3
+
+    class MockUsageWithWebSearch:
+        def __init__(self):
+            self.input_tokens = 100
+            self.output_tokens = 50
+            self.cache_read_input_tokens = 0
+            self.cache_creation_input_tokens = 0
+            self.server_tool_use = MockServerToolUse()
+
+    class MockResponseWithWebSearch:
+        def __init__(self):
+            self.content = [MockContent(text="Search results show...")]
+            self.model = "claude-3-opus-20240229"
+            self.usage = MockUsageWithWebSearch()
+
+    mock_response = MockResponseWithWebSearch()
+
+    async def mock_async_create(**kwargs):
+        return mock_response
+
+    with patch(
+        "anthropic.resources.AsyncMessages.create",
+        side_effect=mock_async_create,
+    ):
+        async_client = AsyncAnthropic(api_key="test-key", posthog_client=mock_client)
+
+        async def run_test():
+            response = await async_client.messages.create(
+                model="claude-3-opus-20240229",
+                messages=[{"role": "user", "content": "Search for recent news"}],
+                posthog_distinct_id="test-id",
+            )
+            return response
+
+        # asyncio.run() waits for all async operations to complete
+        response = asyncio.run(run_test())
+
+        assert response == mock_response
+        assert mock_client.capture.call_count == 1
+
+        call_args = mock_client.capture.call_args[1]
+        props = call_args["properties"]
+
+        # Verify web search count is captured
+        assert props["$ai_web_search_count"] == 3
+        assert props["$ai_input_tokens"] == 100
+        assert props["$ai_output_tokens"] == 50
+
+
+def test_async_streaming_with_web_search(
+    mock_client, mock_anthropic_stream_with_web_search
+):
+    """Test that web search count is properly captured in async streaming mode."""
+    import asyncio
+
+    async def mock_async_generator():
+        # Convert regular generator to async generator
+        for event in mock_anthropic_stream_with_web_search:
+            yield event
+
+    async def mock_async_create(**kwargs):
+        # Return the async generator (to be awaited by the implementation)
+        return mock_async_generator()
+
+    with patch(
+        "anthropic.resources.AsyncMessages.create",
+        side_effect=mock_async_create,
+    ):
+        async_client = AsyncAnthropic(api_key="test-key", posthog_client=mock_client)
+
+        async def run_test():
+            response = await async_client.messages.create(
+                model="claude-3-opus-20240229",
+                messages=[{"role": "user", "content": "Search for recent news"}],
+                stream=True,
+                posthog_distinct_id="test-id",
+            )
+
+            # Consume the async stream
+            [event async for event in response]
+
+        # asyncio.run() waits for all async operations to complete
+        asyncio.run(run_test())
+
+        # Capture completes before asyncio.run() returns
+        assert mock_client.capture.call_count == 1
+
+        call_args = mock_client.capture.call_args[1]
+        props = call_args["properties"]
+
+        # Verify web search count is captured
+        assert props["$ai_web_search_count"] == 2
+        assert props["$ai_input_tokens"] == 50
+        assert props["$ai_output_tokens"] == 25
@@ -837,3 +837,262 @@ def test_streaming_cache_and_reasoning_tokens(mock_client, mock_google_genai_cli
    assert props["$ai_output_tokens"] == 10
    assert props["$ai_cache_read_input_tokens"] == 30
    assert props["$ai_reasoning_tokens"] == 5
+
+
+def test_web_search_grounding(mock_client, mock_google_genai_client):
+    """Test web search detection via grounding_metadata."""
+
+    # Create mock response with grounding metadata
+    mock_response = MagicMock()
+
+    # Mock usage metadata
+    mock_usage = MagicMock()
+    mock_usage.prompt_token_count = 60
+    mock_usage.candidates_token_count = 40
+    mock_usage.cached_content_token_count = 0
+    mock_usage.thoughts_token_count = 0
+    mock_response.usage_metadata = mock_usage
+
+    # Mock grounding metadata
+    mock_grounding_chunk = MagicMock()
+    mock_grounding_chunk.uri = "https://example.com"
+
+    mock_grounding_metadata = MagicMock()
+    mock_grounding_metadata.grounding_chunks = [mock_grounding_chunk]
+
+    # Mock text part
+    mock_text_part = MagicMock()
+    mock_text_part.text = "According to search results..."
+    type(mock_text_part).text = mock_text_part.text
+
+    # Mock content with parts
+    mock_content = MagicMock()
+    mock_content.parts = [mock_text_part]
+
+    # Mock candidate with grounding metadata
+    mock_candidate = MagicMock()
+    mock_candidate.content = mock_content
+    mock_candidate.grounding_metadata = mock_grounding_metadata
+    type(mock_candidate).grounding_metadata = mock_candidate.grounding_metadata
+
+    mock_response.candidates = [mock_candidate]
+    mock_response.text = "According to search results..."
+
+    # Mock the generate_content method
+    mock_google_genai_client.models.generate_content.return_value = mock_response
+
+    client = Client(api_key="test-key", posthog_client=mock_client)
+    response = client.models.generate_content(
+        model="gemini-2.5-flash",
+        contents="What's the latest news?",
+        posthog_distinct_id="test-id",
+    )
+
+    assert response == mock_response
+    assert mock_client.capture.call_count == 1
+
+    call_args = mock_client.capture.call_args[1]
+    props = call_args["properties"]
+
+    # Verify web search count is detected (binary for grounding)
+    assert props["$ai_web_search_count"] == 1
+    assert props["$ai_input_tokens"] == 60
+    assert props["$ai_output_tokens"] == 40
+
+
+def test_streaming_with_web_search(mock_client, mock_google_genai_client):
+    """Test that web search count is properly captured in streaming mode."""
+
+    def mock_streaming_response():
+        # Create chunk 1 with grounding metadata
+        mock_chunk1 = MagicMock()
+        mock_chunk1.text = "According to "
+
+        mock_usage1 = MagicMock()
+        mock_usage1.prompt_token_count = 30
+        mock_usage1.candidates_token_count = 5
+        mock_usage1.cached_content_token_count = 0
+        mock_usage1.thoughts_token_count = 0
+        mock_chunk1.usage_metadata = mock_usage1
+
+        # Add grounding metadata to first chunk
+        mock_grounding_chunk = MagicMock()
+        mock_grounding_chunk.uri = "https://example.com"
+
+        mock_grounding_metadata = MagicMock()
+        mock_grounding_metadata.grounding_chunks = [mock_grounding_chunk]
+
+        mock_candidate1 = MagicMock()
+        mock_candidate1.grounding_metadata = mock_grounding_metadata
+        type(mock_candidate1).grounding_metadata = mock_candidate1.grounding_metadata
+
+        mock_chunk1.candidates = [mock_candidate1]
+
+        # Create chunk 2
+        mock_chunk2 = MagicMock()
+        mock_chunk2.text = "search results..."
+
+        mock_usage2 = MagicMock()
+        mock_usage2.prompt_token_count = 30
+        mock_usage2.candidates_token_count = 15
+        mock_usage2.cached_content_token_count = 0
+        mock_usage2.thoughts_token_count = 0
+        mock_chunk2.usage_metadata = mock_usage2
+
+        mock_candidate2 = MagicMock()
+        mock_chunk2.candidates = [mock_candidate2]
+
+        yield mock_chunk1
+        yield mock_chunk2
+
+    # Mock the generate_content_stream method
+    mock_google_genai_client.models.generate_content_stream.return_value = (
+        mock_streaming_response()
+    )
+
+    client = Client(api_key="test-key", posthog_client=mock_client)
+
+    response = client.models.generate_content_stream(
+        model="gemini-2.5-flash",
+        contents="What's the latest news?",
+        posthog_distinct_id="test-id",
+    )
+
+    chunks = list(response)
+    assert len(chunks) == 2
+    assert mock_client.capture.call_count == 1
+
+    call_args = mock_client.capture.call_args[1]
+    props = call_args["properties"]
+
+    # Verify web search count is detected (binary for grounding)
+    assert props["$ai_web_search_count"] == 1
+    assert props["$ai_input_tokens"] == 30
+    assert props["$ai_output_tokens"] == 15
+
+
+def test_empty_grounding_metadata_no_web_search(mock_client, mock_google_genai_client):
+    """Test that empty grounding_metadata (all null fields) does not count as web search."""
+
+    # Create mock response with empty grounding metadata (all null fields)
+    mock_response = MagicMock()
+
+    # Mock usage metadata
+    mock_usage = MagicMock()
+    mock_usage.prompt_token_count = 10
+    mock_usage.candidates_token_count = 10
+    mock_usage.cached_content_token_count = 0
+    mock_usage.thoughts_token_count = 0
+    mock_response.usage_metadata = mock_usage
+
+    # Mock empty grounding metadata (all fields are None)
+    mock_grounding_metadata = MagicMock()
+    mock_grounding_metadata.web_search_queries = None
+    mock_grounding_metadata.grounding_chunks = None
+    mock_grounding_metadata.grounding_supports = None
+    mock_grounding_metadata.retrieval_metadata = None
+    mock_grounding_metadata.retrieval_queries = None
+    mock_grounding_metadata.search_entry_point = None
+
+    # Mock text part
+    mock_text_part = MagicMock()
+    mock_text_part.text = "Hey there! How can I help you today?"
+    type(mock_text_part).text = mock_text_part.text
+
+    # Mock content with parts
+    mock_content = MagicMock()
+    mock_content.parts = [mock_text_part]
+
+    # Mock candidate with empty grounding metadata
+    mock_candidate = MagicMock()
+    mock_candidate.content = mock_content
+    mock_candidate.grounding_metadata = mock_grounding_metadata
+    type(mock_candidate).grounding_metadata = mock_candidate.grounding_metadata
+
+    mock_response.candidates = [mock_candidate]
+    mock_response.text = "Hey there! How can I help you today?"
+
+    # Mock the generate_content method
+    mock_google_genai_client.models.generate_content.return_value = mock_response
+
+    client = Client(api_key="test-key", posthog_client=mock_client)
+
+    response = client.models.generate_content(
+        model="gemini-2.5-flash",
+        contents="Hello",
+        posthog_distinct_id="test-id",
+    )
+
+    assert response == mock_response
+    assert mock_client.capture.call_count == 1
+
+    call_args = mock_client.capture.call_args[1]
+    props = call_args["properties"]
+
+    # Verify web search count is 0 (not present in properties when 0)
+    assert "$ai_web_search_count" not in props
+    assert props["$ai_input_tokens"] == 10
+    assert props["$ai_output_tokens"] == 10
+
+
+def test_empty_array_grounding_metadata_no_web_search(
+    mock_client, mock_google_genai_client
+):
+    """Test that grounding_metadata with empty arrays does not count as web search."""
+
+    # Create mock response with grounding metadata having empty arrays
+    mock_response = MagicMock()
+
+    # Mock usage metadata
+    mock_usage = MagicMock()
+    mock_usage.prompt_token_count = 15
+    mock_usage.candidates_token_count = 12
+    mock_usage.cached_content_token_count = 0
+    mock_usage.thoughts_token_count = 0
+    mock_response.usage_metadata = mock_usage
+
+    # Mock grounding metadata with empty arrays
+    mock_grounding_metadata = MagicMock()
+    mock_grounding_metadata.web_search_queries = []
+    mock_grounding_metadata.grounding_chunks = []
+    mock_grounding_metadata.grounding_supports = []
+
+    # Mock text part
+    mock_text_part = MagicMock()
+    mock_text_part.text = "I can help with that."
+    type(mock_text_part).text = mock_text_part.text
+
+    # Mock content with parts
+    mock_content = MagicMock()
+    mock_content.parts = [mock_text_part]
+
+    # Mock candidate with grounding metadata containing empty arrays
+    mock_candidate = MagicMock()
+    mock_candidate.content = mock_content
+    mock_candidate.grounding_metadata = mock_grounding_metadata
+    type(mock_candidate).grounding_metadata = mock_candidate.grounding_metadata
+
+    mock_response.candidates = [mock_candidate]
+    mock_response.text = "I can help with that."
+
+    # Mock the generate_content method
+    mock_google_genai_client.models.generate_content.return_value = mock_response
+
+    client = Client(api_key="test-key", posthog_client=mock_client)
+
+    response = client.models.generate_content(
+        model="gemini-2.5-flash",
+        contents="What can you do?",
+        posthog_distinct_id="test-id",
+    )
+
+    assert response == mock_response
+    assert mock_client.capture.call_count == 1
+
+    call_args = mock_client.capture.call_args[1]
+    props = call_args["properties"]
+
+    # Verify web search count is 0 (not present in properties when 0)
+    assert "$ai_web_search_count" not in props
+    assert props["$ai_input_tokens"] == 15
+    assert props["$ai_output_tokens"] == 12
@@ -1,5 +1,5 @@
 import pytest

-pytest.importorskip("langchain")
+pytest.importorskip("langchain_core")
 pytest.importorskip("langchain_community")
 pytest.importorskip("langgraph")
@@ -113,6 +113,7 @@ def test_metadata_capture(mock_client):
        base_url="https://us.posthog.com",
        name="test",
        end_time=None,
+        posthog_properties=None,
    )
    assert callbacks._runs[run_id] == expected
    with patch("time.time", return_value=1234567891):
@@ -204,6 +205,7 @@ def test_basic_chat_chain(mock_client, stream):
    # Generation is second
    assert generation_args["event"] == "$ai_generation"
    assert "distinct_id" in generation_args
+    assert generation_props["$ai_framework"] == "langchain"
    assert "$ai_model" in generation_props
    assert "$ai_provider" in generation_props
    assert generation_props["$ai_input"] == [
@@ -1123,9 +1125,9 @@ def test_anthropic_chain(mock_client):
    )
    chain = prompt | ChatAnthropic(
        api_key=ANTHROPIC_API_KEY,
-        model="claude-3-opus-20240229",
+        model="claude-sonnet-4-5-20250929",
        temperature=0,
-        max_tokens=1,
+        max_tokens=1024,
    )
    callbacks = CallbackHandler(
        mock_client,
@@ -1148,12 +1150,12 @@ def test_anthropic_chain(mock_client):
    assert gen_args["event"] == "$ai_generation"
    assert gen_props["$ai_trace_id"] == "test-trace-id"
    assert gen_props["$ai_provider"] == "anthropic"
-    assert gen_props["$ai_model"] == "claude-3-opus-20240229"
+    assert gen_props["$ai_model"] == "claude-sonnet-4-5-20250929"
    assert gen_props["foo"] == "bar"

    assert gen_props["$ai_model_parameters"] == {
        "temperature": 0.0,
-        "max_tokens": 1,
+        "max_tokens": 1024,
        "streaming": False,
    }
    assert gen_props["$ai_input"] == [
@@ -1169,7 +1171,7 @@ def test_anthropic_chain(mock_client):
        <= approximate_latency
    )
    assert gen_props["$ai_input_tokens"] == 17
-    assert gen_props["$ai_output_tokens"] == 1
+    assert gen_props["$ai_output_tokens"] == 4

    assert trace_args["event"] == "$ai_trace"
    assert trace_props["$ai_input_state"] == {}
@@ -1186,9 +1188,9 @@ async def test_async_anthropic_streaming(mock_client):
    )
    chain = prompt | ChatAnthropic(
        api_key=ANTHROPIC_API_KEY,
-        model="claude-3-opus-20240229",
+        model="claude-sonnet-4-5-20250929",
        temperature=0,
-        max_tokens=1,
+        max_tokens=1024,
        streaming=True,
        stream_usage=True,
    )
@@ -1268,6 +1270,7 @@ def test_metadata_tools(mock_client):
        name="test",
        tools=tools,
        end_time=None,
+        posthog_properties=None,
    )
    assert callbacks._runs[run_id] == expected
    with patch("time.time", return_value=1234567891):
@@ -1564,9 +1567,9 @@ def test_anthropic_cache_write_and_read_tokens(mock_client):
            AIMessage(
                content="Using cached analysis to provide quick response.",
                usage_metadata={
-                    "input_tokens": 200,
+                    "input_tokens": 1200,
                    "output_tokens": 30,
-                    "total_tokens": 1030,
+                    "total_tokens": 1230,
                    "cache_read_input_tokens": 800,  # Anthropic cache read
                },
            )
@@ -1583,13 +1586,58 @@ def test_anthropic_cache_write_and_read_tokens(mock_client):
    generation_props = generation_args["properties"]

    assert generation_args["event"] == "$ai_generation"
-    assert generation_props["$ai_input_tokens"] == 200
+    assert (
+        generation_props["$ai_input_tokens"] == 1200
+    )  # No provider metadata, no subtraction
    assert generation_props["$ai_output_tokens"] == 30
    assert generation_props["$ai_cache_creation_input_tokens"] == 0
    assert generation_props["$ai_cache_read_input_tokens"] == 800
    assert generation_props["$ai_reasoning_tokens"] == 0


+def test_anthropic_provider_subtracts_cache_tokens(mock_client):
+    """Test that Anthropic provider correctly subtracts cache tokens from input tokens."""
+    from langchain_core.outputs import LLMResult, ChatGeneration
+    from langchain_core.messages import AIMessage
+    from uuid import uuid4
+
+    cb = CallbackHandler(mock_client)
+    run_id = uuid4()
+
+    # Set up with Anthropic provider
+    cb._set_llm_metadata(
+        serialized={},
+        run_id=run_id,
+        messages=[{"role": "user", "content": "test"}],
+        metadata={"ls_provider": "anthropic", "ls_model_name": "claude-3-sonnet"},
+    )
+
+    # Response with cache tokens: 1200 input (includes 800 cached)
+    response = LLMResult(
+        generations=[
+            [
+                ChatGeneration(
+                    message=AIMessage(content="Response"),
+                    generation_info={
+                        "usage_metadata": {
+                            "input_tokens": 1200,
+                            "output_tokens": 50,
+                            "cache_read_input_tokens": 800,
+                        }
+                    },
+                )
+            ]
+        ],
+        llm_output={},
+    )
+
+    cb._pop_run_and_capture_generation(run_id, None, response)
+
+    generation_args = mock_client.capture.call_args_list[0][1]
+    assert generation_args["properties"]["$ai_input_tokens"] == 400  # 1200 - 800
+    assert generation_args["properties"]["$ai_cache_read_input_tokens"] == 800
+
+
 def test_openai_cache_read_tokens(mock_client):
    """Test that OpenAI cache read tokens are captured correctly."""
    prompt = ChatPromptTemplate.from_messages(
@@ -1625,7 +1673,7 @@ def test_openai_cache_read_tokens(mock_client):
    generation_props = generation_args["properties"]

    assert generation_args["event"] == "$ai_generation"
-    assert generation_props["$ai_input_tokens"] == 150
+    assert generation_props["$ai_input_tokens"] == 150  # No subtraction for OpenAI
    assert generation_props["$ai_output_tokens"] == 40
    assert generation_props["$ai_cache_read_input_tokens"] == 100
    assert generation_props["$ai_cache_creation_input_tokens"] == 0
@@ -1707,7 +1755,7 @@ def test_combined_reasoning_and_cache_tokens(mock_client):
    generation_props = generation_args["properties"]

    assert generation_args["event"] == "$ai_generation"
-    assert generation_props["$ai_input_tokens"] == 500
+    assert generation_props["$ai_input_tokens"] == 500  # No subtraction for OpenAI
    assert generation_props["$ai_output_tokens"] == 100
    assert generation_props["$ai_cache_read_input_tokens"] == 300
    assert generation_props["$ai_cache_creation_input_tokens"] == 0
@@ -1715,7 +1763,7 @@ def test_combined_reasoning_and_cache_tokens(mock_client):


@pytest.mark.skipif(not OPENAI_API_KEY, reason="OPENAI_API_KEY is not set")
-def test_openai_reasoning_tokens(mock_client):
+def test_openai_reasoning_tokens_o4_mini(mock_client):
    model = ChatOpenAI(
        api_key=OPENAI_API_KEY, model="o4-mini", max_completion_tokens=10
    )
@@ -1876,3 +1924,429 @@ def test_tool_definition(mock_client):
    assert props["$ai_latency"] == 1.0
    # Verify that tools are captured in the $ai_tools property
    assert props["$ai_tools"] == tools
+
+
+def test_cache_read_tokens_subtraction_from_input_tokens(mock_client):
+    """Test that cache_read_tokens are properly subtracted from input_tokens.
+
+    This tests the logic in callbacks.py lines 757-758:
+        if normalized_usage.input_tokens and normalized_usage.cache_read_tokens:
+            normalized_usage.input_tokens = max(normalized_usage.input_tokens - normalized_usage.cache_read_tokens, 0)
+    """
+    prompt = ChatPromptTemplate.from_messages(
+        [("user", "Use the cached prompt for this request")]
+    )
+
+    # Scenario 1: input_tokens includes cache_read_tokens (typical case)
+    # input_tokens=150 includes 100 cache_read tokens, so actual input is 50
+    model = FakeMessagesListChatModel(
+        responses=[
+            AIMessage(
+                content="Response using cached prompt context.",
+                usage_metadata={
+                    "input_tokens": 150,  # Total includes cache reads
+                    "output_tokens": 40,
+                    "total_tokens": 190,
+                    "cache_read_input_tokens": 100,  # 100 tokens read from cache
+                },
+            )
+        ]
+    )
+
+    callbacks = [CallbackHandler(mock_client)]
+    chain = prompt | model
+    result = chain.invoke({}, config={"callbacks": callbacks})
+
+    assert result.content == "Response using cached prompt context."
+    assert mock_client.capture.call_count == 3
+
+    generation_args = mock_client.capture.call_args_list[1][1]
+    generation_props = generation_args["properties"]
+
+    assert generation_args["event"] == "$ai_generation"
+    # Input tokens not reduced without provider metadata
+    assert generation_props["$ai_input_tokens"] == 150
+    assert generation_props["$ai_output_tokens"] == 40
+    assert generation_props["$ai_cache_read_input_tokens"] == 100
+
+
+def test_cache_read_tokens_subtraction_prevents_negative(mock_client):
+    """Test that cache_read_tokens subtraction doesn't result in negative input_tokens.
+
+    This tests the max(..., 0) part of the logic in callbacks.py lines 757-758.
+    """
+    prompt = ChatPromptTemplate.from_messages(
+        [("user", "Edge case with large cache read")]
+    )
+
+    # Edge case: cache_read_tokens >= input_tokens
+    # This could happen in some API responses where accounting differs
+    model = FakeMessagesListChatModel(
+        responses=[
+            AIMessage(
+                content="Response with edge case token counts.",
+                usage_metadata={
+                    "input_tokens": 80,
+                    "output_tokens": 20,
+                    "total_tokens": 100,
+                    "cache_read_input_tokens": 100,  # More than input_tokens
+                },
+            )
+        ]
+    )
+
+    callbacks = [CallbackHandler(mock_client)]
+    chain = prompt | model
+    result = chain.invoke({}, config={"callbacks": callbacks})
+
+    assert result.content == "Response with edge case token counts."
+    assert mock_client.capture.call_count == 3
+
+    generation_args = mock_client.capture.call_args_list[1][1]
+    generation_props = generation_args["properties"]
+
+    assert generation_args["event"] == "$ai_generation"
+    # Input tokens not reduced without provider metadata
+    assert generation_props["$ai_input_tokens"] == 80
+    assert generation_props["$ai_output_tokens"] == 20
+    assert generation_props["$ai_cache_read_input_tokens"] == 100
+
+
+def test_no_cache_read_tokens_no_subtraction(mock_client):
+    """Test that when there are no cache_read_tokens, input_tokens remain unchanged.
+
+    This tests the conditional check before the subtraction in callbacks.py line 757.
+    """
+    prompt = ChatPromptTemplate.from_messages(
+        [("user", "Normal request without cache")]
+    )
+
+    # No cache usage - input_tokens should remain as-is
+    model = FakeMessagesListChatModel(
+        responses=[
+            AIMessage(
+                content="Response without cache.",
+                usage_metadata={
+                    "input_tokens": 100,
+                    "output_tokens": 30,
+                    "total_tokens": 130,
+                    # No cache_read_input_tokens
+                },
+            )
+        ]
+    )
+
+    callbacks = [CallbackHandler(mock_client)]
+    chain = prompt | model
+    result = chain.invoke({}, config={"callbacks": callbacks})
+
+    assert result.content == "Response without cache."
+    assert mock_client.capture.call_count == 3
+
+    generation_args = mock_client.capture.call_args_list[1][1]
+    generation_props = generation_args["properties"]
+
+    assert generation_args["event"] == "$ai_generation"
+    # Input tokens should remain unchanged at 100
+    assert generation_props["$ai_input_tokens"] == 100
+    assert generation_props["$ai_output_tokens"] == 30
+    assert generation_props["$ai_cache_read_input_tokens"] == 0
+
+
+def test_zero_input_tokens_with_cache_read(mock_client):
+    """Test edge case where input_tokens is 0 but cache_read_tokens exist.
+
+    This tests the falsy check in the conditional (line 757).
+    """
+    prompt = ChatPromptTemplate.from_messages([("user", "Edge case query")])
+
+    # Edge case: input_tokens is 0 (falsy), should skip subtraction
+    model = FakeMessagesListChatModel(
+        responses=[
+            AIMessage(
+                content="Response.",
+                usage_metadata={
+                    "input_tokens": 0,
+                    "output_tokens": 10,
+                    "total_tokens": 10,
+                    "cache_read_input_tokens": 50,
+                },
+            )
+        ]
+    )
+
+    callbacks = [CallbackHandler(mock_client)]
+    chain = prompt | model
+    result = chain.invoke({}, config={"callbacks": callbacks})
+
+    assert result.content == "Response."
+    assert mock_client.capture.call_count == 3
+
+    generation_args = mock_client.capture.call_args_list[1][1]
+    generation_props = generation_args["properties"]
+
+    assert generation_args["event"] == "$ai_generation"
+    # Input tokens should remain 0 (no subtraction because input_tokens is falsy)
+    assert generation_props["$ai_input_tokens"] == 0
+    assert generation_props["$ai_output_tokens"] == 10
+    assert generation_props["$ai_cache_read_input_tokens"] == 50
+
+
+def test_cache_write_tokens_not_subtracted_from_input(mock_client):
+    """Test that cache_creation_input_tokens (cache write) do NOT affect input_tokens.
+
+    Only cache_read_tokens should be subtracted from input_tokens, not cache_write_tokens.
+    """
+    prompt = ChatPromptTemplate.from_messages([("user", "Create cache")])
+
+    # Cache creation without cache read
+    model = FakeMessagesListChatModel(
+        responses=[
+            AIMessage(
+                content="Creating cache.",
+                usage_metadata={
+                    "input_tokens": 1000,
+                    "output_tokens": 20,
+                    "total_tokens": 1020,
+                    "cache_creation_input_tokens": 800,  # Cache write, not read
+                },
+            )
+        ]
+    )
+
+    callbacks = [CallbackHandler(mock_client)]
+    chain = prompt | model
+    result = chain.invoke({}, config={"callbacks": callbacks})
+
+    assert result.content == "Creating cache."
+    assert mock_client.capture.call_count == 3
+
+    generation_args = mock_client.capture.call_args_list[1][1]
+    generation_props = generation_args["properties"]
+
+    assert generation_args["event"] == "$ai_generation"
+    # Input tokens should NOT be reduced by cache_creation_input_tokens
+    assert generation_props["$ai_input_tokens"] == 1000
+    assert generation_props["$ai_output_tokens"] == 20
+    assert generation_props["$ai_cache_creation_input_tokens"] == 800
+    assert generation_props["$ai_cache_read_input_tokens"] == 0
+
+
+def test_agent_action_and_finish_imports():
+    """
+    Regression test for LangChain 1.0+ compatibility (Issue #362).
+    Verifies that AgentAction and AgentFinish can be imported and used.
+    This test ensures the imports work with both LangChain 0.x and 1.0+.
+    """
+    # Import the types that caused the compatibility issue
+    try:
+        from langchain_core.agents import AgentAction, AgentFinish
+    except (ImportError, ModuleNotFoundError):
+        from langchain.schema.agent import AgentAction, AgentFinish  # type: ignore
+
+    # Verify they're available in the callbacks module
+    from posthog.ai.langchain.callbacks import CallbackHandler
+
+    # Test on_agent_action with mock data
+    mock_client = MagicMock()
+    callbacks = CallbackHandler(mock_client)
+    run_id = uuid.uuid4()
+    parent_run_id = uuid.uuid4()
+
+    # Create mock AgentAction
+    action = AgentAction(tool="test_tool", tool_input="test_input", log="test_log")
+
+    # Should not raise an exception
+    callbacks.on_agent_action(action, run_id=run_id, parent_run_id=parent_run_id)
+
+    # Verify parent was set
+    assert run_id in callbacks._parent_tree
+    assert callbacks._parent_tree[run_id] == parent_run_id
+
+    # Test on_agent_finish with mock data
+    finish = AgentFinish(return_values={"output": "test_output"}, log="finish_log")
+
+    # Should not raise an exception
+    callbacks.on_agent_finish(finish, run_id=run_id, parent_run_id=parent_run_id)
+
+    # Verify capture was called
+    assert mock_client.capture.call_count == 1
+    call_args = mock_client.capture.call_args[1]
+    assert call_args["event"] == "$ai_span"
+
+
+def test_posthog_properties_field_in_generation_metadata(mock_client):
+    """Test that posthog_properties is properly stored in GenerationMetadata."""
+    callbacks = CallbackHandler(mock_client)
+    run_id = uuid.uuid4()
+
+    # Test with billable=True
+    with patch("time.time", return_value=1234567890):
+        callbacks._set_llm_metadata(
+            {"kwargs": {"openai_api_base": "https://api.openai.com"}},
+            run_id,
+            messages=[{"role": "user", "content": "Test message"}],
+            invocation_params={"temperature": 0.5},
+            metadata={
+                "ls_model_name": "gpt-4o",
+                "ls_provider": "openai",
+                "posthog_properties": {"$ai_billable": True},
+            },
+            name="test",
+        )
+
+    expected = GenerationMetadata(
+        model="gpt-4o",
+        input=[{"role": "user", "content": "Test message"}],
+        start_time=1234567890,
+        model_params={"temperature": 0.5},
+        provider="openai",
+        base_url="https://api.openai.com",
+        name="test",
+        posthog_properties={"$ai_billable": True},
+        end_time=None,
+    )
+    assert callbacks._runs[run_id] == expected
+    assert callbacks._runs[run_id].posthog_properties == {"$ai_billable": True}
+
+    callbacks._pop_run_metadata(run_id)
+
+    # Test with billable=False (explicit)
+    run_id2 = uuid.uuid4()
+    with patch("time.time", return_value=1234567890):
+        callbacks._set_llm_metadata(
+            {"kwargs": {"openai_api_base": "https://api.openai.com"}},
+            run_id2,
+            messages=[{"role": "user", "content": "Test message"}],
+            invocation_params={"temperature": 0.5},
+            metadata={
+                "ls_model_name": "gpt-4o",
+                "ls_provider": "openai",
+                "posthog_properties": {"$ai_billable": False},
+            },
+            name="test",
+        )
+
+    assert callbacks._runs[run_id2].posthog_properties == {"$ai_billable": False}
+    callbacks._pop_run_metadata(run_id2)
+
+    # Test when posthog_properties not provided
+    run_id3 = uuid.uuid4()
+    with patch("time.time", return_value=1234567890):
+        callbacks._set_llm_metadata(
+            {"kwargs": {"openai_api_base": "https://api.openai.com"}},
+            run_id3,
+            messages=[{"role": "user", "content": "Test message"}],
+            invocation_params={"temperature": 0.5},
+            metadata={"ls_model_name": "gpt-4o", "ls_provider": "openai"},
+            name="test",
+        )
+
+    assert callbacks._runs[run_id3].posthog_properties is None
+
+
+def test_billable_property_in_generation_event(mock_client):
+    """Test that the billable property is captured in the $ai_generation event."""
+    callbacks = CallbackHandler(mock_client)
+
+    # We need to test the _set_llm_metadata directly since FakeMessagesListChatModel
+    # doesn't support metadata in the same way as real models
+    run_id = uuid.uuid4()
+    with patch("time.time", return_value=1234567890):
+        callbacks._set_llm_metadata(
+            {},
+            run_id,
+            messages=[{"role": "user", "content": "Test"}],
+            metadata={
+                "posthog_properties": {"$ai_billable": True},
+                "ls_model_name": "test-model",
+            },
+            invocation_params={},
+        )
+
+    mock_response = MagicMock()
+    mock_response.generations = [[MagicMock()]]
+
+    with patch("time.time", return_value=1234567891):
+        run = callbacks._pop_run_metadata(run_id)
+
+    callbacks._capture_generation(
+        trace_id=run_id,
+        run_id=run_id,
+        run=run,
+        output=mock_response,
+        parent_run_id=None,
+    )
+
+    assert mock_client.capture.call_count == 1
+    call_args = mock_client.capture.call_args[1]
+    props = call_args["properties"]
+
+    assert call_args["event"] == "$ai_generation"
+    assert props["$ai_billable"] is True
+
+
+def test_billable_defaults_to_false_in_event(mock_client):
+    """Test that $ai_billable is not present when not specified."""
+    prompt = ChatPromptTemplate.from_messages([("user", "Test query")])
+    model = FakeMessagesListChatModel(
+        responses=[AIMessage(content="Test response")],
+    )
+
+    callbacks = [CallbackHandler(mock_client)]
+    chain = prompt | model
+    chain.invoke({}, config={"callbacks": callbacks})
+
+    generation_call = None
+    for call in mock_client.capture.call_args_list:
+        if call[1]["event"] == "$ai_generation":
+            generation_call = call
+            break
+
+    assert generation_call is not None
+    props = generation_call[1]["properties"]
+    assert "$ai_billable" not in props
+
+
+def test_billable_with_real_chain(mock_client):
+    """Test billable tracking through a complete chain execution with mocked metadata."""
+    callbacks = CallbackHandler(mock_client)
+    run_id = uuid.uuid4()
+
+    with patch("time.time", return_value=1000.0):
+        callbacks._set_llm_metadata(
+            {},
+            run_id,
+            messages=[{"role": "user", "content": "What's the weather?"}],
+            metadata={
+                "ls_model_name": "fake-model",
+                "ls_provider": "fake",
+                "posthog_properties": {"$ai_billable": True},
+            },
+            invocation_params={"temperature": 0.7},
+        )
+
+    assert callbacks._runs[run_id].posthog_properties == {"$ai_billable": True}
+
+    mock_response = MagicMock()
+    mock_response.generations = [[MagicMock()]]
+
+    with patch("time.time", return_value=1001.0):
+        run = callbacks._pop_run_metadata(run_id)
+
+    callbacks._capture_generation(
+        trace_id=run_id,
+        run_id=run_id,
+        run=run,
+        output=mock_response,
+        parent_run_id=None,
+    )
+
+    assert mock_client.capture.call_count == 1
+    call_args = mock_client.capture.call_args[1]
+    props = call_args["properties"]
+
+    assert call_args["event"] == "$ai_generation"
+    assert props["$ai_billable"] is True
+    assert props["$ai_model"] == "fake-model"
+    assert props["$ai_provider"] == "fake"
@@ -1339,3 +1339,340 @@ def test_tool_definition(mock_client, mock_openai_response):
        assert isinstance(props["$ai_latency"], float)
        # Verify that tools are captured in the $ai_tools property
        assert props["$ai_tools"] == tools
+
+
+def test_web_search_perplexity_style(mock_client):
+    """Test web search detection via annotations (Perplexity-style)."""
+
+    class MockAnnotation:
+        def __init__(self):
+            self.type = "url_citation"
+
+    class MockMessage:
+        def __init__(self):
+            self.role = "assistant"
+            self.content = "Based on recent search results..."
+            self.annotations = [MockAnnotation(), MockAnnotation()]
+
+    class MockChoice:
+        def __init__(self):
+            self.message = MockMessage()
+
+    class MockUsage:
+        def __init__(self):
+            self.prompt_tokens = 50
+            self.completion_tokens = 30
+
+    class MockResponseWithAnnotations:
+        def __init__(self):
+            self.choices = [MockChoice()]
+            self.usage = MockUsage()
+            self.model = "gpt-4-turbo"
+
+    mock_response = MockResponseWithAnnotations()
+
+    with patch("openai.resources.chat.Completions.create", return_value=mock_response):
+        client = OpenAI(api_key="test-key", posthog_client=mock_client)
+        response = client.chat.completions.create(
+            model="gpt-4-turbo",
+            messages=[{"role": "user", "content": "What's happening in tech?"}],
+            posthog_distinct_id="test-id",
+        )
+
+        assert response == mock_response
+        assert mock_client.capture.call_count == 1
+
+        call_args = mock_client.capture.call_args[1]
+        props = call_args["properties"]
+
+        # Verify web search count is detected (binary detection)
+        assert props["$ai_web_search_count"] == 1
+
+
+def test_web_search_responses_api(mock_client):
+    """Test exact web search count from Responses API."""
+
+    class MockWebSearchItem:
+        def __init__(self):
+            self.type = "web_search_call"
+
+    class MockMessageItem:
+        def __init__(self):
+            self.type = "message"
+            self.role = "assistant"
+            self.content = "Here are the results..."
+
+    class MockUsage:
+        def __init__(self):
+            self.input_tokens = 100
+            self.output_tokens = 75
+
+    class MockResponsesAPIResponse:
+        def __init__(self):
+            self.output = [MockWebSearchItem(), MockWebSearchItem(), MockMessageItem()]
+            self.usage = MockUsage()
+            self.model = "gpt-4o"
+
+    mock_response = MockResponsesAPIResponse()
+
+    with patch(
+        "openai.resources.responses.Responses.create", return_value=mock_response
+    ):
+        # Manually call the tracking since we're testing the converter logic
+        from posthog.ai.utils import call_llm_and_track_usage
+
+        def mock_create_call(**kwargs):
+            return mock_response
+
+        result = call_llm_and_track_usage(
+            posthog_distinct_id="test-id",
+            ph_client=mock_client,
+            provider="openai",
+            posthog_trace_id=None,
+            posthog_properties=None,
+            posthog_privacy_mode=False,
+            posthog_groups=None,
+            base_url="https://api.openai.com/v1",
+            call_method=mock_create_call,
+            model="gpt-4o",
+            messages=[{"role": "user", "content": "Search query"}],
+        )
+
+        assert result == mock_response
+        assert mock_client.capture.call_count == 1
+
+        call_args = mock_client.capture.call_args[1]
+        props = call_args["properties"]
+
+        # Verify exact web search count
+        assert props["$ai_web_search_count"] == 2
+
+
+@pytest.fixture
+def streaming_web_search_chunks():
+    """Streaming chunks with web search indicators (Perplexity-style)."""
+    return [
+        ChatCompletionChunk(
+            id="chunk1",
+            model="gpt-4",
+            object="chat.completion.chunk",
+            created=1234567890,
+            choices=[
+                ChoiceChunk(
+                    index=0,
+                    delta=ChoiceDelta(
+                        role="assistant",
+                        content="Based on my search, ",
+                    ),
+                    finish_reason=None,
+                )
+            ],
+        ),
+        ChatCompletionChunk(
+            id="chunk2",
+            model="gpt-4",
+            object="chat.completion.chunk",
+            created=1234567891,
+            choices=[
+                ChoiceChunk(
+                    index=0,
+                    delta=ChoiceDelta(
+                        content="here are the latest news...",
+                    ),
+                    finish_reason=None,
+                )
+            ],
+        ),
+        ChatCompletionChunk(
+            id="chunk3",
+            model="gpt-4",
+            object="chat.completion.chunk",
+            created=1234567892,
+            choices=[
+                ChoiceChunk(
+                    index=0,
+                    delta=ChoiceDelta(),
+                    finish_reason="stop",
+                )
+            ],
+            usage=CompletionUsage(
+                prompt_tokens=20,
+                completion_tokens=15,
+                total_tokens=35,
+            ),
+        ),
+    ]
+
+
+def test_streaming_with_web_search(mock_client, streaming_web_search_chunks):
+    """Test that web search count is properly captured in streaming mode."""
+
+    # Add citations attribute to the last chunk to indicate web search was used
+    streaming_web_search_chunks[-1].citations = ["https://example.com/news"]
+
+    with patch("openai.resources.chat.completions.Completions.create") as mock_create:
+        mock_create.return_value = streaming_web_search_chunks
+
+        client = OpenAI(api_key="test-key", posthog_client=mock_client)
+        response_generator = client.chat.completions.create(
+            model="gpt-4",
+            messages=[{"role": "user", "content": "Search for recent news"}],
+            stream=True,
+            posthog_distinct_id="test-id",
+        )
+
+        # Consume the generator to trigger the event capture
+        chunks = list(response_generator)
+
+        # Verify the chunks were returned correctly
+        assert len(chunks) == 3
+        assert mock_client.capture.call_count == 1
+
+        call_args = mock_client.capture.call_args[1]
+        props = call_args["properties"]
+
+        # Verify web search count is captured (binary detection = 1)
+        assert props["$ai_web_search_count"] == 1
+        assert props["$ai_input_tokens"] == 20
+        assert props["$ai_output_tokens"] == 15
+
+
+def test_streaming_with_web_search_on_non_usage_chunk(
+    mock_client, streaming_web_search_chunks
+):
+    """Test that web search count is captured even when citations appear on chunks without usage data."""
+
+    # Add citations attribute to the FIRST chunk (which has no usage data)
+    # This tests the fix for the bug where web search indicators on non-usage chunks were ignored
+    streaming_web_search_chunks[0].citations = ["https://example.com/news"]
+
+    with patch("openai.resources.chat.completions.Completions.create") as mock_create:
+        mock_create.return_value = streaming_web_search_chunks
+
+        client = OpenAI(api_key="test-key", posthog_client=mock_client)
+        response_generator = client.chat.completions.create(
+            model="gpt-4",
+            messages=[{"role": "user", "content": "Search for recent news"}],
+            stream=True,
+            posthog_distinct_id="test-id",
+        )
+
+        # Consume the generator to trigger the event capture
+        chunks = list(response_generator)
+
+        # Verify the chunks were returned correctly
+        assert len(chunks) == 3
+        assert mock_client.capture.call_count == 1
+
+        call_args = mock_client.capture.call_args[1]
+        props = call_args["properties"]
+
+        # Verify web search count is captured even though citations were on first chunk
+        assert props["$ai_web_search_count"] == 1
+        assert props["$ai_input_tokens"] == 20
+        assert props["$ai_output_tokens"] == 15
+
+
+@pytest.mark.asyncio
+async def test_async_chat_with_web_search(mock_client):
+    """Test that web search count is properly tracked in async non-streaming mode."""
+
+    # Create mock response with citations (Perplexity-style)
+    mock_response = ChatCompletion(
+        id="chatcmpl-test",
+        model="gpt-4",
+        object="chat.completion",
+        created=1234567890,
+        choices=[
+            Choice(
+                index=0,
+                message=ChatCompletionMessage(
+                    role="assistant",
+                    content="Here are the search results...",
+                ),
+                finish_reason="stop",
+            )
+        ],
+        usage=CompletionUsage(
+            prompt_tokens=20,
+            completion_tokens=15,
+            total_tokens=35,
+        ),
+    )
+
+    # Add citations attribute to indicate web search
+    mock_response.citations = ["https://example.com/result1"]
+
+    async def mock_create(self, **kwargs):
+        return mock_response
+
+    with patch(
+        "openai.resources.chat.completions.AsyncCompletions.create", new=mock_create
+    ):
+        client = AsyncOpenAI(api_key="test-key", posthog_client=mock_client)
+
+        response = await client.chat.completions.create(
+            model="gpt-4",
+            messages=[{"role": "user", "content": "Search for recent news"}],
+            posthog_distinct_id="test-id",
+        )
+
+    assert response == mock_response
+    assert mock_client.capture.call_count == 1
+
+    call_args = mock_client.capture.call_args[1]
+    props = call_args["properties"]
+
+    # Verify web search count is captured (binary detection = 1)
+    assert props["$ai_web_search_count"] == 1
+    assert props["$ai_input_tokens"] == 20
+    assert props["$ai_output_tokens"] == 15
+
+
+@pytest.mark.asyncio
+async def test_async_chat_streaming_with_web_search(
+    mock_client, streaming_web_search_chunks
+):
+    """Test that web search count is properly captured in async streaming mode."""
+
+    # Add citations attribute to the last chunk to indicate web search was used
+    streaming_web_search_chunks[-1].citations = ["https://example.com/news"]
+
+    captured_kwargs = {}
+
+    async def mock_create(self, **kwargs):
+        captured_kwargs["kwargs"] = kwargs
+
+        async def chunk_iterable():
+            for chunk in streaming_web_search_chunks:
+                yield chunk
+
+        return chunk_iterable()
+
+    with patch(
+        "openai.resources.chat.completions.AsyncCompletions.create", new=mock_create
+    ):
+        client = AsyncOpenAI(api_key="test-key", posthog_client=mock_client)
+
+        response_stream = await client.chat.completions.create(
+            model="gpt-4",
+            messages=[{"role": "user", "content": "Search for recent news"}],
+            stream=True,
+            posthog_distinct_id="test-id",
+        )
+
+        chunks = []
+        async for chunk in response_stream:
+            chunks.append(chunk)
+
+    # Verify the chunks were returned correctly
+    assert len(chunks) == 3
+    assert mock_client.capture.call_count == 1
+
+    call_args = mock_client.capture.call_args[1]
+    props = call_args["properties"]
+
+    # Verify web search count is captured (binary detection = 1)
+    assert props["$ai_web_search_count"] == 1
+    assert props["$ai_input_tokens"] == 20
+    assert props["$ai_output_tokens"] == 15
@@ -4,7 +4,21 @@ from posthog.contexts import (
    get_context_distinct_id,
 )
 import unittest
-from unittest.mock import Mock
+from unittest.mock import Mock, patch
+import asyncio
+
+# Configure Django settings before importing middleware
+import django
+from django.conf import settings
+
+if not settings.configured:
+    settings.configure(
+        DEBUG=True,
+        SECRET_KEY="test-secret-key",
+        INSTALLED_APPS=[],
+        MIDDLEWARE=[],
+    )
+    django.setup()

 from posthog.integrations.django import PosthogContextMiddleware

@@ -38,14 +52,33 @@ class TestPosthogContextMiddleware(unittest.TestCase):
        request_filter=None,
        tag_map=None,
        capture_exceptions=True,
+        get_response=None,
    ):
-        """Helper to create middleware instance without calling __init__"""
-        middleware = PosthogContextMiddleware.__new__(PosthogContextMiddleware)
-        middleware.get_response = Mock()
-        middleware.extra_tags = extra_tags
-        middleware.request_filter = request_filter
-        middleware.tag_map = tag_map
-        middleware.capture_exceptions = capture_exceptions
+        """Helper to create middleware instance with mock Django settings"""
+        if get_response is None:
+            get_response = Mock()
+
+        with patch("django.conf.settings") as mock_settings:
+            # Configure mock settings
+            mock_settings.POSTHOG_MW_EXTRA_TAGS = extra_tags
+            mock_settings.POSTHOG_MW_REQUEST_FILTER = request_filter
+            mock_settings.POSTHOG_MW_TAG_MAP = tag_map
+            mock_settings.POSTHOG_MW_CAPTURE_EXCEPTIONS = capture_exceptions
+            mock_settings.POSTHOG_MW_CLIENT = None
+
+            # Make hasattr work correctly
+            def mock_hasattr(obj, name):
+                return name in [
+                    "POSTHOG_MW_EXTRA_TAGS",
+                    "POSTHOG_MW_REQUEST_FILTER",
+                    "POSTHOG_MW_TAG_MAP",
+                    "POSTHOG_MW_CAPTURE_EXCEPTIONS",
+                    "POSTHOG_MW_CLIENT",
+                ]
+
+            with patch("builtins.hasattr", side_effect=mock_hasattr):
+                middleware = PosthogContextMiddleware(get_response)
+
        return middleware

    def test_extract_tags_basic(self):
@@ -168,6 +201,573 @@ class TestPosthogContextMiddleware(unittest.TestCase):

        self.assertEqual(tags["$request_method"], "PATCH")

+    def test_process_exception_called_during_view_exception(self):
+        """
+        Unit test verifying process_exception captures exceptions per Django's contract.
+
+        Since this is a library test (no Django runtime), we simulate how Django
+        would invoke our middleware in production:
+        1. Middleware.__call__ creates context with request tags
+        2. View raises exception inside get_response
+        3. Django's BaseHandler catches it, calls process_exception, returns error response
+        4. Exception never propagates to middleware's context manager
+
+        We manually call process_exception to simulate Django's behavior - this is
+        the only way to test the hook without a full Django integration test.
+        """
+        mock_client = Mock()
+        view_exception = ValueError("View raised this error")
+        error_response = Mock(status_code=500)
+
+        def mock_get_response(request):
+            # Simulate Django's exception handling: catches view exception,
+            # calls process_exception hook if it exists, returns error response
+            if hasattr(middleware, "process_exception"):
+                middleware.process_exception(request, view_exception)
+            return error_response
+
+        middleware = self.create_middleware(get_response=mock_get_response)
+        middleware.client = mock_client
+
+        request = MockRequest(
+            headers={"X-POSTHOG-DISTINCT-ID": "test-user"},
+            method="POST",
+            path="/api/endpoint",
+        )
+        response = middleware(request)
+
+        self.assertEqual(response.status_code, 500)
+        mock_client.capture_exception.assert_called_once_with(view_exception)
+
+    def test_process_exception_respects_capture_exceptions_false(self):
+        """Verify process_exception respects capture_exceptions=False setting"""
+        mock_client = Mock()
+        view_exception = ValueError("Should not be captured")
+
+        def mock_get_response(request):
+            if hasattr(middleware, "process_exception"):
+                middleware.process_exception(request, view_exception)
+            return Mock(status_code=500)
+
+        middleware = self.create_middleware(
+            capture_exceptions=False, get_response=mock_get_response
+        )
+        middleware.client = mock_client
+
+        request = MockRequest()
+        middleware(request)
+
+        mock_client.capture_exception.assert_not_called()
+
+    def test_process_exception_respects_request_filter(self):
+        """Verify process_exception respects request_filter setting"""
+        mock_client = Mock()
+        view_exception = ValueError("Should be filtered")
+
+        def mock_get_response(request):
+            if hasattr(middleware, "process_exception"):
+                middleware.process_exception(request, view_exception)
+            return Mock(status_code=500)
+
+        middleware = self.create_middleware(
+            request_filter=lambda req: False,
+            capture_exceptions=True,
+            get_response=mock_get_response,
+        )
+        middleware.client = mock_client
+
+        request = MockRequest()
+        middleware(request)
+
+        mock_client.capture_exception.assert_not_called()
+
+
+class TestPosthogContextMiddlewareSync(unittest.TestCase):
+    """Test synchronous middleware behavior"""
+
+    def test_sync_middleware_call(self):
+        """Test that sync middleware correctly processes requests"""
+        mock_response = Mock()
+        get_response = Mock(return_value=mock_response)
+
+        # Create middleware with sync get_response
+        middleware = PosthogContextMiddleware(get_response)
+
+        # Verify sync mode detected
+        self.assertFalse(middleware._is_coroutine)
+
+        request = MockRequest(
+            headers={"X-POSTHOG-SESSION-ID": "test-session"},
+            method="GET",
+            path="/test",
+        )
+
+        with new_context():
+            response = middleware(request)
+
+            # Verify response returned
+            self.assertEqual(response, mock_response)
+            get_response.assert_called_once_with(request)
+
+    def test_sync_middleware_with_filter(self):
+        """Test sync middleware respects request filter"""
+        mock_response = Mock()
+        get_response = Mock(return_value=mock_response)
+
+        # Create middleware with request filter that filters all requests
+        def request_filter(req):
+            return False
+
+        middleware = PosthogContextMiddleware.__new__(PosthogContextMiddleware)
+        middleware.get_response = get_response
+        middleware._is_coroutine = False
+        middleware.request_filter = request_filter
+        middleware.capture_exceptions = True
+        middleware.client = None
+
+        request = MockRequest()
+
+        # Should skip context creation and return response directly
+        response = middleware(request)
+        self.assertEqual(response, mock_response)
+        get_response.assert_called_once_with(request)
+
+    def test_view_exceptions_only_captured_via_process_exception(self):
+        """
+        Demonstrates that process_exception is required to capture view exceptions.
+
+        In production Django, view exceptions don't propagate to middleware's context
+        manager because Django's BaseHandler catches them first and converts them to
+        error responses. Django provides the exception via process_exception hook instead.
+
+        This unit test proves:
+        1. Context manager in __call__ never sees view exceptions (Django intercepts)
+        2. Only process_exception can capture them
+        3. Without process_exception, exceptions are silently lost (v6.7.5 regression)
+
+        We manually call process_exception to verify the hook works - in production,
+        Django's BaseHandler would call it when a view raises.
+        """
+        mock_client = Mock()
+        get_response = Mock(return_value=Mock(status_code=500))
+
+        middleware = PosthogContextMiddleware(get_response)
+        middleware.client = mock_client
+
+        def get_response_simulating_django(request):
+            # Simulates Django behavior: view exception converted to error response,
+            # never propagates to middleware's context manager
+            return Mock(status_code=500)
+
+        middleware._sync_get_response = get_response_simulating_django
+
+        request = MockRequest()
+
+        response = middleware(request)
+        self.assertEqual(response.status_code, 500)
+
+        # Context manager didn't capture anything - exception was intercepted by Django
+        mock_client.capture_exception.assert_not_called()
+
+        # Verify process_exception hook exists and captures exceptions when called
+        if hasattr(middleware, "process_exception"):
+            exception = ValueError("View error")
+            middleware.process_exception(request, exception)
+            mock_client.capture_exception.assert_called_once_with(exception)
+        else:
+            self.fail(
+                "process_exception missing - view exceptions will not be captured!"
+            )
+
+
+class TestPosthogContextMiddlewareAsync(unittest.TestCase):
+    """Test asynchronous middleware behavior"""
+
+    def test_async_middleware_detection(self):
+        """Test that async get_response is correctly detected"""
+
+        async def async_get_response(request):
+            return Mock()
+
+        middleware = PosthogContextMiddleware(async_get_response)
+
+        # Verify async mode detected
+        self.assertTrue(middleware._is_coroutine)
+
+    def test_async_middleware_call(self):
+        """Test that async middleware correctly processes requests"""
+
+        async def run_test():
+            mock_response = Mock()
+
+            async def async_get_response(request):
+                return mock_response
+
+            middleware = PosthogContextMiddleware(async_get_response)
+
+            request = MockRequest(
+                headers={"X-POSTHOG-SESSION-ID": "async-session"},
+                method="POST",
+                path="/async-test",
+            )
+
+            with new_context():
+                # Call should return the coroutine from __acall__
+                result = middleware(request)
+
+                # Verify it's a coroutine
+                self.assertTrue(asyncio.iscoroutine(result))
+
+                # Await the result
+                response = await result
+                self.assertEqual(response, mock_response)
+
+        asyncio.run(run_test())
+
+    def test_async_middleware_with_filter(self):
+        """Test async middleware respects request filter"""
+
+        async def run_test():
+            mock_response = Mock()
+
+            async def async_get_response(request):
+                return mock_response
+
+            # Properly initialize middleware
+            middleware = PosthogContextMiddleware(async_get_response)
+            # Override request filter after initialization
+            middleware.request_filter = lambda req: False
+
+            request = MockRequest()
+
+            # Should skip context creation and return response directly
+            result = middleware(request)
+            response = await result
+            self.assertEqual(response, mock_response)
+
+        asyncio.run(run_test())
+
+    def test_async_middleware_context_propagation(self):
+        """Test that async middleware properly propagates context"""
+
+        async def run_test():
+            mock_response = Mock()
+
+            async def async_get_response(request):
+                # Verify context is available during async processing
+                session_id = get_context_session_id()
+                self.assertEqual(session_id, "async-session-123")
+                return mock_response
+
+            middleware = PosthogContextMiddleware(async_get_response)
+
+            request = MockRequest(
+                headers={"X-POSTHOG-SESSION-ID": "async-session-123"},
+                method="GET",
+            )
+
+            with new_context():
+                result = middleware(request)
+                await result
+
+        asyncio.run(run_test())
+
+    def test_async_middleware_exception_capture(self):
+        """Test that async middleware captures exceptions during request processing"""
+
+        async def run_test():
+            mock_client = Mock()
+
+            # Make async_get_response raise an exception
+            async def raise_exception(request):
+                raise ValueError("Async test exception")
+
+            # Properly initialize middleware
+            middleware = PosthogContextMiddleware(raise_exception)
+            middleware.client = mock_client  # Override with mock client
+
+            request = MockRequest()
+
+            # Should capture exception and re-raise
+            with self.assertRaises(ValueError):
+                result = middleware(request)
+                await result
+
+            # Verify exception was captured by middleware
+            mock_client.capture_exception.assert_called_once()
+            captured_exception = mock_client.capture_exception.call_args[0][0]
+            self.assertIsInstance(captured_exception, ValueError)
+            self.assertEqual(str(captured_exception), "Async test exception")
+
+        asyncio.run(run_test())
+
+    def test_async_middleware_with_authenticated_user(self):
+        """
+        Test that async middleware correctly extracts user info in async context.
+
+        Django's request.user is a SimpleLazyObject that defers DB access.
+        In async context, accessing it directly raises SynchronousOnlyOperation.
+        The middleware should use request.auser() instead.
+
+        This tests the fix for issue #355.
+        """
+
+        async def run_test():
+            mock_response = Mock()
+            mock_user = Mock()
+            mock_user.is_authenticated = True
+            mock_user.pk = 123
+            mock_user.email = "test@example.com"
+
+            async def async_get_response(request):
+                # Verify user info was extracted and set as distinct_id
+                distinct_id = get_context_distinct_id()
+                self.assertEqual(distinct_id, "123")
+                return mock_response
+
+            middleware = PosthogContextMiddleware(async_get_response)
+            middleware.client = Mock()
+
+            request = MockRequest(
+                headers={"X-POSTHOG-SESSION-ID": "test-session"}, method="GET"
+            )
+
+            # Mock auser() to return authenticated user
+            async def mock_auser():
+                return mock_user
+
+            request.auser = mock_auser
+
+            with new_context():
+                result = middleware(request)
+                response = await result
+                self.assertEqual(response, mock_response)
+
+        asyncio.run(run_test())
+
+    def test_async_middleware_with_unauthenticated_user(self):
+        """
+        Test that async middleware handles unauthenticated users correctly.
+        """
+
+        async def run_test():
+            mock_response = Mock()
+            mock_user = Mock()
+            mock_user.is_authenticated = False  # Not authenticated
+
+            async def async_get_response(request):
+                # Verify no distinct_id was set (no user)
+                distinct_id = get_context_distinct_id()
+                self.assertIsNone(distinct_id)
+                return mock_response
+
+            middleware = PosthogContextMiddleware(async_get_response)
+            middleware.client = Mock()
+
+            request = MockRequest(
+                headers={"X-POSTHOG-SESSION-ID": "test-session"}, method="GET"
+            )
+
+            async def mock_auser():
+                return mock_user
+
+            request.auser = mock_auser
+
+            with new_context():
+                result = middleware(request)
+                response = await result
+                self.assertEqual(response, mock_response)
+
+        asyncio.run(run_test())
+
+    def test_async_middleware_without_user_attribute(self):
+        """
+        Test that async middleware handles requests without user attribute (no auth middleware).
+        """
+
+        async def run_test():
+            mock_response = Mock()
+
+            async def async_get_response(request):
+                return mock_response
+
+            middleware = PosthogContextMiddleware(async_get_response)
+            middleware.client = Mock()
+
+            # Request without auser method (no auth middleware)
+            request = MockRequest(
+                headers={"X-POSTHOG-SESSION-ID": "test-session"}, method="GET"
+            )
+
+            with new_context():
+                result = middleware(request)
+                response = await result
+                self.assertEqual(response, mock_response)
+
+        asyncio.run(run_test())
+
+    def test_async_middleware_with_extra_tags(self):
+        """
+        Test that async middleware works with extra_tags callback.
+        """
+
+        async def run_test():
+            mock_response = Mock()
+
+            def extra_tags_callback(request):
+                # Simple sync callback - should work
+                return {"custom_tag": "custom_value"}
+
+            async def async_get_response(request):
+                return mock_response
+
+            middleware = PosthogContextMiddleware(async_get_response)
+            middleware.extra_tags = extra_tags_callback
+            middleware.client = Mock()
+
+            request = MockRequest(
+                headers={"X-POSTHOG-SESSION-ID": "test-session"}, method="GET"
+            )
+
+            # Mock auser for no user
+            async def mock_auser():
+                return None
+
+            request.auser = mock_auser
+
+            with new_context():
+                result = middleware(request)
+                response = await result
+                self.assertEqual(response, mock_response)
+
+        asyncio.run(run_test())
+
+    def test_async_middleware_with_tag_map(self):
+        """
+        Test that async middleware works with tag_map callback.
+        """
+
+        async def run_test():
+            mock_response = Mock()
+
+            def tag_map_callback(tags):
+                # Simple sync callback - should work
+                tags["mapped"] = "yes"
+                return tags
+
+            async def async_get_response(request):
+                return mock_response
+
+            middleware = PosthogContextMiddleware(async_get_response)
+            middleware.tag_map = tag_map_callback
+            middleware.client = Mock()
+
+            request = MockRequest(
+                headers={"X-POSTHOG-SESSION-ID": "test-session"}, method="GET"
+            )
+
+            # Mock auser for no user
+            async def mock_auser():
+                return None
+
+            request.auser = mock_auser
+
+            with new_context():
+                result = middleware(request)
+                response = await result
+                self.assertEqual(response, mock_response)
+
+        asyncio.run(run_test())
+
+    def test_async_middleware_user_extraction_with_all_headers(self):
+        """
+        Test async middleware extracts all request info correctly.
+        """
+
+        async def run_test():
+            mock_response = Mock()
+            mock_user = Mock()
+            mock_user.is_authenticated = True
+            mock_user.pk = 456
+            mock_user.email = "async@test.com"
+
+            async def async_get_response(request):
+                # Verify all context was set correctly
+                distinct_id = get_context_distinct_id()
+                session_id = get_context_session_id()
+                self.assertEqual(distinct_id, "456")
+                self.assertEqual(session_id, "async-sess-123")
+                return mock_response
+
+            middleware = PosthogContextMiddleware(async_get_response)
+            middleware.client = Mock()
+
+            request = MockRequest(
+                headers={
+                    "X-POSTHOG-SESSION-ID": "async-sess-123",
+                    "X-Forwarded-For": "192.168.1.1",
+                    "User-Agent": "TestAgent/1.0",
+                },
+                method="POST",
+                path="/api/test",
+            )
+
+            async def mock_auser():
+                return mock_user
+
+            request.auser = mock_auser
+
+            with new_context():
+                result = middleware(request)
+                response = await result
+                self.assertEqual(response, mock_response)
+
+        asyncio.run(run_test())
+
+
+class TestPosthogContextMiddlewareHybrid(unittest.TestCase):
+    """Test hybrid middleware behavior with mixed sync/async chains"""
+
+    def test_hybrid_flags_set(self):
+        """Test that both capability flags are set"""
+        self.assertTrue(PosthogContextMiddleware.sync_capable)
+        self.assertTrue(PosthogContextMiddleware.async_capable)
+
+    def test_sync_to_async_routing(self):
+        """Test that __call__ routes to __acall__ when async"""
+
+        async def run_test():
+            async def async_get_response(request):
+                return Mock()
+
+            middleware = PosthogContextMiddleware(async_get_response)
+
+            # Verify routing happens
+            request = MockRequest()
+            result = middleware(request)
+
+            # Should be a coroutine from __acall__
+            self.assertTrue(asyncio.iscoroutine(result))
+            await result  # Clean up
+
+        asyncio.run(run_test())
+
+    def test_sync_path_direct_return(self):
+        """Test that sync path returns directly without coroutine"""
+        mock_response = Mock()
+
+        def sync_get_response(request):
+            return mock_response
+
+        middleware = PosthogContextMiddleware(sync_get_response)
+
+        request = MockRequest()
+        result = middleware(request)
+
+        # Should NOT be a coroutine
+        self.assertFalse(asyncio.iscoroutine(result))
+        self.assertEqual(result, mock_response)
+

 if __name__ == "__main__":
    unittest.main()
@@ -32,3 +32,377 @@ def test_excepthook(tmpdir):
        b'"$exception_list": [{"mechanism": {"type": "generic", "handled": true}, "module": null, "type": "ZeroDivisionError", "value": "division by zero", "stacktrace": {"frames": [{"platform": "python", "filename": "app.py", "abs_path"'
        in output
    )
+
+
+def test_code_variables_capture(tmpdir):
+    app = tmpdir.join("app.py")
+    app.write(
+        dedent(
+            """
+    import os
+    from posthog import Posthog
+    
+    class UnserializableObject:
+        pass
+    
+    posthog = Posthog(
+        'phc_x', 
+        host='https://eu.i.posthog.com', 
+        debug=True, 
+        enable_exception_autocapture=True,
+        capture_exception_code_variables=True,
+        project_root=os.path.dirname(os.path.abspath(__file__))
+    )
+    
+    def trigger_error():
+        my_string = "hello world"
+        my_number = 42
+        my_bool = True
+        my_dict = {"name": "test", "value": 123}
+        my_obj = UnserializableObject()
+        my_password = "secret123"  # Should be masked by default
+        __should_be_ignored = "hidden"  # Should be ignored by default
+        
+        1/0  # Trigger exception
+    
+    def intermediate_function():
+        request_id = "abc-123"
+        user_count = 100
+        is_active = True
+        
+        trigger_error()
+    
+    def process_data():
+        batch_size = 50
+        retry_count = 3
+        
+        intermediate_function()
+    
+    process_data()
+    """
+        )
+    )
+
+    with pytest.raises(subprocess.CalledProcessError) as excinfo:
+        subprocess.check_output([sys.executable, str(app)], stderr=subprocess.STDOUT)
+
+    output = excinfo.value.output
+
+    assert b"ZeroDivisionError" in output
+    assert b"code_variables" in output
+
+    # Variables from trigger_error frame
+    assert b"'my_string': 'hello world'" in output
+    assert b"'my_number': 42" in output
+    assert b"'my_bool': 'True'" in output
+    assert b'"my_dict": "{\\"name\\": \\"test\\", \\"value\\": 123}"' in output
+    assert b"<__main__.UnserializableObject object at" in output
+    assert b"'my_password': '$$_posthog_redacted_based_on_masking_rules_$$'" in output
+    assert b"'__should_be_ignored':" not in output
+
+    # Variables from intermediate_function frame
+    assert b"'request_id': 'abc-123'" in output
+    assert b"'user_count': 100" in output
+    assert b"'is_active': 'True'" in output
+
+    # Variables from process_data frame
+    assert b"'batch_size': 50" in output
+    assert b"'retry_count': 3" in output
+
+
+def test_code_variables_context_override(tmpdir):
+    app = tmpdir.join("app.py")
+    app.write(
+        dedent(
+            """
+    import os
+    import posthog
+    from posthog import Posthog
+    
+    posthog_client = Posthog(
+        'phc_x', 
+        host='https://eu.i.posthog.com', 
+        debug=True, 
+        enable_exception_autocapture=True,
+        capture_exception_code_variables=False,
+        project_root=os.path.dirname(os.path.abspath(__file__))
+    )
+    
+    def process_data():
+        bank = "should_be_masked"
+        __dunder_var = "should_be_visible"
+        
+        1/0
+    
+    with posthog.new_context(client=posthog_client):
+        posthog.set_capture_exception_code_variables_context(True)
+        posthog.set_code_variables_mask_patterns_context([r"(?i).*bank.*"])
+        posthog.set_code_variables_ignore_patterns_context([])
+        
+        process_data()
+    """
+        )
+    )
+
+    with pytest.raises(subprocess.CalledProcessError) as excinfo:
+        subprocess.check_output([sys.executable, str(app)], stderr=subprocess.STDOUT)
+
+    output = excinfo.value.output
+
+    assert b"ZeroDivisionError" in output
+    assert b"code_variables" in output
+    assert b"'bank': '$$_posthog_redacted_based_on_masking_rules_$$'" in output
+    assert b"'__dunder_var': 'should_be_visible'" in output
+
+
+def test_code_variables_size_limiter(tmpdir):
+    app = tmpdir.join("app.py")
+    app.write(
+        dedent(
+            """
+    import os
+    from posthog import Posthog
+    
+    posthog = Posthog(
+        'phc_x', 
+        host='https://eu.i.posthog.com', 
+        debug=True, 
+        enable_exception_autocapture=True,
+        capture_exception_code_variables=True,
+        project_root=os.path.dirname(os.path.abspath(__file__))
+    )
+    
+    def trigger_error():
+        var_a = "a" * 2000
+        var_b = "b" * 2000
+        var_c = "c" * 2000
+        var_d = "d" * 2000
+        var_e = "e" * 2000
+        var_f = "f" * 2000
+        var_g = "g" * 2000
+        
+        1/0
+    
+    def intermediate_function():
+        var_h = "h" * 2000
+        var_i = "i" * 2000
+        var_j = "j" * 2000
+        var_k = "k" * 2000
+        var_l = "l" * 2000
+        var_m = "m" * 2000
+        var_n = "n" * 2000
+        
+        trigger_error()
+    
+    def process_data():
+        var_o = "o" * 2000
+        var_p = "p" * 2000
+        var_q = "q" * 2000
+        var_r = "r" * 2000
+        var_s = "s" * 2000
+        var_t = "t" * 2000
+        var_u = "u" * 2000
+        
+        intermediate_function()
+    
+    process_data()
+    """
+        )
+    )
+
+    with pytest.raises(subprocess.CalledProcessError) as excinfo:
+        subprocess.check_output([sys.executable, str(app)], stderr=subprocess.STDOUT)
+
+    output = excinfo.value.output.decode("utf-8")
+
+    assert "ZeroDivisionError" in output
+    assert "code_variables" in output
+
+    captured_vars = []
+    for var_name in [
+        "var_a",
+        "var_b",
+        "var_c",
+        "var_d",
+        "var_e",
+        "var_f",
+        "var_g",
+        "var_h",
+        "var_i",
+        "var_j",
+        "var_k",
+        "var_l",
+        "var_m",
+        "var_n",
+        "var_o",
+        "var_p",
+        "var_q",
+        "var_r",
+        "var_s",
+        "var_t",
+        "var_u",
+    ]:
+        if f"'{var_name}'" in output:
+            captured_vars.append(var_name)
+
+    assert len(captured_vars) > 0
+    assert len(captured_vars) < 21
+
+
+def test_code_variables_disabled_capture(tmpdir):
+    app = tmpdir.join("app.py")
+    app.write(
+        dedent(
+            """
+    import os
+    from posthog import Posthog
+    
+    posthog = Posthog(
+        'phc_x', 
+        host='https://eu.i.posthog.com', 
+        debug=True, 
+        enable_exception_autocapture=True,
+        capture_exception_code_variables=False,
+        project_root=os.path.dirname(os.path.abspath(__file__))
+    )
+    
+    def trigger_error():
+        my_string = "hello world"
+        my_number = 42
+        my_bool = True
+        
+        1/0
+    
+    trigger_error()
+    """
+        )
+    )
+
+    with pytest.raises(subprocess.CalledProcessError) as excinfo:
+        subprocess.check_output([sys.executable, str(app)], stderr=subprocess.STDOUT)
+
+    output = excinfo.value.output.decode("utf-8")
+
+    assert "ZeroDivisionError" in output
+    assert "'code_variables':" not in output
+    assert '"code_variables":' not in output
+    assert "'my_string'" not in output
+    assert "'my_number'" not in output
+
+
+def test_code_variables_enabled_then_disabled_in_context(tmpdir):
+    app = tmpdir.join("app.py")
+    app.write(
+        dedent(
+            """
+    import os
+    import posthog
+    from posthog import Posthog
+    
+    posthog_client = Posthog(
+        'phc_x', 
+        host='https://eu.i.posthog.com', 
+        debug=True, 
+        enable_exception_autocapture=True,
+        capture_exception_code_variables=True,
+        project_root=os.path.dirname(os.path.abspath(__file__))
+    )
+    
+    def process_data():
+        my_var = "should not be captured"
+        important_value = 123
+        
+        1/0
+    
+    with posthog.new_context(client=posthog_client):
+        posthog.set_capture_exception_code_variables_context(False)
+        
+        process_data()
+    """
+        )
+    )
+
+    with pytest.raises(subprocess.CalledProcessError) as excinfo:
+        subprocess.check_output([sys.executable, str(app)], stderr=subprocess.STDOUT)
+
+    output = excinfo.value.output.decode("utf-8")
+
+    assert "ZeroDivisionError" in output
+    assert "'code_variables':" not in output
+    assert '"code_variables":' not in output
+    assert "'my_var'" not in output
+    assert "'important_value'" not in output
+
+
+def test_code_variables_repr_fallback(tmpdir):
+    app = tmpdir.join("app.py")
+    app.write(
+        dedent(
+            """
+    import os
+    import re
+    from datetime import datetime, timedelta
+    from decimal import Decimal
+    from fractions import Fraction
+    from posthog import Posthog
+    
+    class CustomReprClass:
+        def __repr__(self):
+            return '<CustomReprClass: custom representation>'
+    
+    posthog = Posthog(
+        'phc_x', 
+        host='https://eu.i.posthog.com', 
+        debug=True, 
+        enable_exception_autocapture=True,
+        capture_exception_code_variables=True,
+        project_root=os.path.dirname(os.path.abspath(__file__))
+    )
+    
+    def trigger_error():
+        my_regex = re.compile(r'\\d+')
+        my_datetime = datetime(2024, 1, 15, 10, 30, 45)
+        my_timedelta = timedelta(days=5, hours=3)
+        my_decimal = Decimal('123.456')
+        my_fraction = Fraction(3, 4)
+        my_set = {1, 2, 3}
+        my_frozenset = frozenset([4, 5, 6])
+        my_bytes = b'hello bytes'
+        my_bytearray = bytearray(b'mutable bytes')
+        my_memoryview = memoryview(b'memory view')
+        my_complex = complex(3, 4)
+        my_range = range(10)
+        my_custom = CustomReprClass()
+        my_lambda = lambda x: x * 2
+        my_function = trigger_error
+        
+        1/0
+    
+    trigger_error()
+    """
+        )
+    )
+
+    with pytest.raises(subprocess.CalledProcessError) as excinfo:
+        subprocess.check_output([sys.executable, str(app)], stderr=subprocess.STDOUT)
+
+    output = excinfo.value.output.decode("utf-8")
+
+    assert "ZeroDivisionError" in output
+    assert "code_variables" in output
+
+    assert "re.compile(" in output and "\\\\d+" in output
+    assert "datetime.datetime(2024, 1, 15, 10, 30, 45)" in output
+    assert "datetime.timedelta(days=5, seconds=10800)" in output
+    assert "Decimal('123.456')" in output
+    assert "Fraction(3, 4)" in output
+    assert "{1, 2, 3}" in output
+    assert "frozenset({4, 5, 6})" in output
+    assert "b'hello bytes'" in output
+    assert "bytearray(b'mutable bytes')" in output
+    assert "<memory at" in output
+    assert "(3+4j)" in output
+    assert "range(0, 10)" in output
+    assert "<CustomReprClass: custom representation>" in output
+    assert "<lambda>" in output
+    assert "<function trigger_error at" in output
@@ -1,4 +1,4 @@
-VERSION = "6.7.9"
+VERSION = "7.0.1"

 if __name__ == "__main__":
    print(VERSION, end="")  # noqa: T201
@@ -10,14 +10,13 @@ authors = [{ name = "PostHog", email = "hey@posthog.com" }]
 maintainers = [{ name = "PostHog", email = "hey@posthog.com" }]
 license = { text = "MIT" }
 readme = "README.md"
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 classifiers = [
    "Development Status :: 5 - Production/Stable",
    "Intended Audience :: Developers",
    "Operating System :: OS Independent",
    "License :: OSI Approved :: MIT License",
    "Programming Language :: Python",
-    "Programming Language :: Python :: 3.9",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
@@ -66,13 +65,13 @@ test = [
    "pytest-timeout",
    "pytest-asyncio",
    "django",
-    "openai",
-    "anthropic",
-    "langgraph>=0.4.8",
-    "langchain-core>=0.3.65",
-    "langchain-community>=0.3.25",
-    "langchain-openai>=0.3.22",
-    "langchain-anthropic>=0.3.15",
+    "openai>=2.0",
+    "anthropic>=0.72",
+    "langgraph>=1.0",
+    "langchain-core>=1.0",
+    "langchain-community>=0.4",
+    "langchain-openai>=1.0",
+    "langchain-anthropic>=1.0",
    "google-genai",
    "pydantic",
    "parameterized>=0.8.1",
@@ -96,3 +95,5 @@ version = { attr = "posthog.version.VERSION" }
 [tool.pytest.ini_options]
 asyncio_mode = "auto"
 asyncio_default_fixture_loop_scope = "function"
+testpaths = ["posthog/test"]
+norecursedirs = ["integration_tests"]
@@ -2,7 +2,7 @@
  "id": "posthog-python",
  "hogRef": "0.3",
  "info": {
-    "version": "6.7.7",
+    "version": "7.0.0",
    "id": "posthog-python",
    "title": "PostHog Python SDK",
    "description": "Integrate PostHog into any python application.",
@@ -503,6 +503,24 @@
              "description": "",
              "isOptional": false,
              "type": "bool"
+            },
+            {
+              "name": "capture_exception_code_variables",
+              "description": "",
+              "isOptional": false,
+              "type": "bool"
+            },
+            {
+              "name": "code_variables_mask_patterns",
+              "description": "",
+              "isOptional": false,
+              "type": "any"
+            },
+            {
+              "name": "code_variables_ignore_patterns",
+              "description": "",
+              "isOptional": false,
+              "type": "any"
            }
          ],
          "showDocs": true,
@@ -1478,12 +1496,7 @@
            {
              "id": "example_1",
              "name": "Set with distinct id",
-              "code": "# Set with distinct id\nposthog.capture(\n    'event_name',\n    distinct_id='user-distinct-id',\n    properties={\n        '$set': {'name': 'Max Hedgehog'},\n        '$set_once': {'initial_url': '/blog'}\n    }\n)"
-            },
-            {
-              "id": "example_2",
-              "name": "Set using context",
-              "code": "# Set using context\nfrom posthog import new_context, identify_context\nwith new_context():\n    identify_context('user-distinct-id')\n    posthog.capture('event_name')"
+              "code": "# Set with distinct id\nposthog.set(distinct_id='user123', properties={'name': 'Max Hedgehog'})"
            }
          ]
        },
@@ -2138,6 +2151,12 @@
              "description": "Whether to capture exceptions raised within the context (default: True)",
              "isOptional": false,
              "type": "bool"
+            },
+            {
+              "name": "client",
+              "description": "Optional Posthog client instance to use for this context (default: None)",
+              "isOptional": false,
+              "type": "any"
            }
          ],
          "showDocs": true,
@@ -2216,6 +2235,69 @@
            }
          ]
        },
+        {
+          "id": "set_capture_exception_code_variables_context",
+          "title": "set_capture_exception_code_variables_context",
+          "description": "Set whether code variables are captured for the current context.",
+          "details": "",
+          "category": null,
+          "params": [
+            {
+              "name": "enabled",
+              "description": "",
+              "isOptional": true,
+              "type": "bool"
+            }
+          ],
+          "showDocs": true,
+          "releaseTag": "public",
+          "returnType": {
+            "id": "return_type",
+            "name": "None"
+          }
+        },
+        {
+          "id": "set_code_variables_ignore_patterns_context",
+          "title": "set_code_variables_ignore_patterns_context",
+          "description": "Variable names matching these patterns will be ignored completely when capturing code variables.",
+          "details": "",
+          "category": null,
+          "params": [
+            {
+              "name": "ignore_patterns",
+              "description": "",
+              "isOptional": true,
+              "type": "list"
+            }
+          ],
+          "showDocs": true,
+          "releaseTag": "public",
+          "returnType": {
+            "id": "return_type",
+            "name": "None"
+          }
+        },
+        {
+          "id": "set_code_variables_mask_patterns_context",
+          "title": "set_code_variables_mask_patterns_context",
+          "description": "Variable names matching these patterns will be masked with *** when capturing code variables.",
+          "details": "",
+          "category": null,
+          "params": [
+            {
+              "name": "mask_patterns",
+              "description": "",
+              "isOptional": true,
+              "type": "list"
+            }
+          ],
+          "showDocs": true,
+          "releaseTag": "public",
+          "returnType": {
+            "id": "return_type",
+            "name": "None"
+          }
+        },
        {
          "id": "set_context_session",
          "title": "set_context_session",
@@ -14,7 +14,7 @@ long_description = """
 PostHog is developer-friendly, self-hosted product analytics.
 posthog-python is the python package.

-This package requires Python 3.9 or higher.
+This package requires Python 3.10 or higher.
 """

 # Minimal setup.py for backward compatibility
@@ -47,7 +47,7 @@ long_description = """
 PostHog is developer-friendly, self-hosted product analytics.
 posthog-python is the python package.

-This package requires Python 3.9 or higher.
+This package requires Python 3.10 or higher.
 """

 # Minimal setup.py for backward compatibility
Author	SHA1	Message	Date
Aleksander BłaszkiewiczandGitHub	f75c5efeec	feat: use repr in code variables (#372 )	2025-11-15 13:43:55 +01:00
Tue HaulundandGitHub	65785b892e	fix: avoid overwriting consumer list when using more than one consumer (#370 ) fix: avoid overwriting consumer list when using more than one consumer thread	2025-11-12 13:05:05 +01:00
github-actions[bot]	6dde2bf9e5	Update generated references	2025-11-11 18:13:36 +00:00
Carlos MarchalandGitHub	48203364a9	chore(llma): update SDKs (#367 )	2025-11-11 18:12:33 +00:00
github-actions[bot]	805c308841	Update generated references	2025-11-11 17:57:26 +00:00
Alessandro PogliaghiandGitHub	898654a174	feat(ph-ai): PostHog properties dict in GenerationMetadata (#366 )	2025-11-11 17:56:32 +00:00
github-actions[bot]	499d54570c	Update generated references	2025-11-11 08:57:51 +00:00
Carlos MarchalandGitHub	6c815dffc3	fix(llma): Langchain cache token double subtraction for non-Anthropic providers (#369 )	2025-11-11 09:56:57 +01:00
Julian BezandGitHub	3a1b8e49cd	fix: add ruff check to CI and fix all lint errors (#360 ) - Add 'Lint with ruff' step to CI workflow (was only running format check) - Fix F401: Add explicit re-exports for public API types in __init__.py - Fix F811: Rename duplicate test_openai_reasoning_tokens to test_openai_reasoning_tokens_o4_mini - Fix E731: Convert lambda to def function in test_middleware.py - Fix unused imports in client.py and test files (auto-fixed) Without ruff check in CI, lint errors were accumulating on master undetected.	2025-11-10 12:45:52 +01:00
github-actions[bot]	f3e5d7132f	Update generated references	2025-11-07 15:57:55 +00:00
Aleksander BłaszkiewiczandGitHub	88f606994c	fix: code variables without client (#368 ) * fix: pass variables from init to client * chore: version+changelog	2025-11-07 16:57:01 +01:00
Luke BeltonandGitHub	a155e1dfd6	fix docstring for `set` (#364 )	2025-11-06 16:02:49 +00:00
github-actions[bot]	f648a5dfd7	Update generated references	2025-11-06 15:13:17 +00:00
Aleksander BłaszkiewiczandGitHub	e309bd7149	feat: add code variables capture (#365 ) * feat: add code variables capture * feat: bump version and add changelog	2025-11-06 16:12:17 +01:00
github-actions[bot]	0cfd678857	Update generated references	2025-11-04 19:44:04 +00:00
Radu RaiceaandGitHub	3d8825fc67	feat(llma): send number of web searches (#359 ) * feat(llma): send number of web searches * feat(llma): add more tests * chore(llma): bump version * fix(llma): feedback * fix(llma): fix Gemini * fix(llma): fix OpenAI's Chat Completions streaming	2025-11-04 19:43:11 +00:00
github-actions[bot]	3e52e7feda	Update generated references	2025-11-03 12:29:46 +00:00
Julian BezandGitHub	98e322695d	fix(django): handle request.user in async middleware context (#358 )	2025-11-03 12:28:57 +00:00
github-actions[bot]	700c922baf	Update generated references	2025-11-02 18:58:55 +00:00
Georgiy Tarasov GitHub Radu Raicea Andrew Maguire	69293f5198	fix(llma): cache cost calculation in the LangChain callback (#346 ) * fix(llma): cache cost calculation in the LangChain callback * fix: format * Update posthog/ai/langchain/callbacks.py Co-authored-by: Radu Raicea <radu@raicea.com> * Bump version to 6.7.13 Master has already released 6.7.12 with other fixes, so this PR will be 6.7.13 --------- Co-authored-by: Radu Raicea <radu@raicea.com> Co-authored-by: Andrew Maguire <andrewm4894@gmail.com>	2025-11-02 18:58:04 +00:00
github-actions[bot]	46589f93d5	Update generated references	2025-11-02 17:10:28 +00:00
Andrew MaguireandGitHub	57546d29e6	fix(llma): LangChain 1.0+ compatibility for CallbackHandler (#363 ) * fix: Add LangChain 1.0+ compatibility for CallbackHandler imports - Use try/except to import from langchain_core first (LangChain 1.0+) - Fall back to legacy langchain imports for older versions - Maintains backward compatibility with LangChain 0.x - All existing tests pass (45 passed) Fixes #362 * test: Add regression test for AgentAction/AgentFinish imports - Tests that AgentAction and AgentFinish can be imported - Tests on_agent_action and on_agent_finish callbacks with mock data - Ensures compatibility with both LangChain 0.x and 1.0+ - Catches the import issue that was previously only tested with API keys This addresses a test coverage gap identified during code review. * chore: Add CHANGELOG entry for LangChain 1.0+ compatibility fix * fix: Remove unused type: ignore comments for mypy The type: ignore comments were only needed when the except block executes, but CI runs with LangChain 1.0+ so the try block succeeds. Mypy flags these as unused-ignore errors. * chore: bump version to 6.7.12 for langchain 1.0 compatibility	2025-11-02 17:09:33 +00:00
Julian BezandGitHub	50b0c7170a	fix(django): restore process_exception to capture view exceptions (#350 ) Restores the process_exception method that was removed in v6.7.5 (PR #328), which broke exception capture from Django views and downstream middleware. Django converts view exceptions into responses before they propagate through the middleware stack's __call__ method, so the context manager's exception handler never sees them. Django provides these exceptions via the process_exception hook instead. Changes: - Add process_exception method to capture exceptions from views and downstream middleware with proper request context and tags - Add tests verifying process_exception behavior and settings (capture_exceptions, request_filter)	2025-10-29 10:40:08 +00:00
github-actions[bot]	f719c3dadf	Update generated references	2025-10-28 13:06:45 +00:00
Andrew MaguireandGitHub	105090a6ba	chore: bump version to 6.7.11 for AI framework feature (#354 ) Update version and changelog for PR #347	2025-10-28 13:05:50 +00:00
Andrew Maguire GitHub Claude	edfadcc6a8	feat(ai): Add `$ai_framework` property for framework integrations (#347 ) * Add $ai_lib_metadata to AI integrations Adds framework identification metadata to all AI events for easier filtering and analytics. Each integration now includes a $ai_lib_metadata property with schema version and framework name. - LangChain: Hardcoded to "langchain" - Native wrappers (Anthropic, OpenAI, Gemini): Uses provider name - Ready for future frameworks (pydantic-ai, crewai, llamaindex) This enables PostHog queries to easily distinguish between: - Direct SDK wrapper usage - Framework-mediated usage (LangChain, etc.) - Different framework types 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * Add \$ai_lib_metadata to sync/async paths and tests - Added \$ai_lib_metadata to call_llm_and_track_usage (sync) - Added \$ai_lib_metadata to call_llm_and_track_usage_async (async) - Added test assertion in test_basic_completion - Placed metadata at end of properties for consistency All tests pass successfully. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * Refactor: use unified utility function for $ai_lib_metadata Creates a single `get_ai_lib_metadata(framework)` utility function to generate the $ai_lib_metadata object, replacing inline implementations across the codebase. Changes: - Add get_ai_lib_metadata() utility to utils.py - Update LangChain callbacks to use utility function - Update call_llm_and_track_usage() to use utility function - Update call_llm_and_track_usage_async() to use utility function - Update capture_streaming_event() to use utility function Benefits: - Consistency across all integrations - Single source of truth for metadata structure - Easier to extend with version detection later 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * Add $ai_lib_metadata assertions to provider tests Add missing $ai_lib_metadata assertions to Anthropic, Gemini, and LangChain tests to match the validation already present in OpenAI tests. Each test now verifies the metadata field contains the correct schema version and framework name. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * Simplify to $ai_framework property, only for actual frameworks Changes: - Replace complex $ai_lib_metadata object with simple $ai_framework string - Only include $ai_framework when using actual framework (LangChain) - Remove $ai_framework from direct provider calls (OpenAI, Anthropic, Gemini) - Update all tests to reflect new behavior Before: {"schema": "v1", "frameworks": [{"name": "langchain"}]} After: "langchain" (only when using LangChain framework) This eliminates wasteful redundancy where framework=provider for direct calls. --------- Co-authored-by: Claude <noreply@anthropic.com>	2025-10-28 09:59:20 +00:00
Julian BezandGitHub	13184e2e16	chore: standardize workflow extensions to .yml (#349 ) Rename workflow files from .yaml to .yml for consistency with existing workflows (ci.yml, call-flags-project-board.yml). This resolves naming confusion and standardizes all GitHub Actions workflow files to use the .yml extension.	2025-10-24 14:17:27 +00:00
webjunkieandgithub-actions[bot]	1b8642331f	Update generated references	2025-10-24 14:16:57 +00:00
Julian BezandGitHub	6af129f414	fix(django): make middleware truly hybrid-compatible with sync and async Django stacks (#348 ) Address code review feedback and critical issues from PR #328. Changes: - Keep __call__ as sync method that conditionally routes to __acall__ for async paths - Use markcoroutinefunction() to properly mark instances when async is detected - Detect async/sync at init time via iscoroutinefunction(get_response) - Remove process_exception method - it was non-functional (Django doesn't call it on new-style middleware without MiddlewareMixin) - Fix markcoroutinefunction fallback to be a simple no-op instead of accessing private API - Exception capture works correctly via contexts.new_context() which has built-in exception handling - Add comprehensive test coverage for sync, async, and hybrid middleware behavior - Add async exception capture tests - Refactor tests to use proper middleware initialization This implementation follows Django's recommended hybrid middleware pattern where both sync_capable and async_capable are True, allowing Django to pass requests without conversion while the middleware adapts based on the detected mode. The sync path behavior is identical to version 6.7.4 (pre-async), ensuring perfect backward compatibility for WSGI deployments. Addresses #329 Related to #328	2025-10-24 15:50:21 +02:00