Merge branch 'master' into codeflash/optimize-_get_db_span_description-mg9vzvxu

Author: misrasaurabh1

.github/workflows/ci.yml

@@ -27,34 +27,12 @@ jobs:
       - uses: actions/[email protected]
       - uses: actions/setup-python@v6
         with:
-          python-version: 3.12
+          python-version: 3.14
 
       - run: |
           pip install tox
           tox -e linters
 
-  check-ci-config:
-    name: Check CI config
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-
-    steps:
-      - uses: actions/[email protected]
-        with:
-          ref: ${{ github.event.pull_request.head.sha }}
-          fetch-depth: 0
-      - uses: actions/setup-python@v6
-        with:
-          python-version: 3.12
-
-      - name: Detect unexpected changes to tox.ini or CI
-        run: |
-          pip install -e .
-          pip install -r scripts/populate_tox/requirements.txt
-          python scripts/populate_tox/populate_tox.py --fail-on-changes
-          pip install -r scripts/split_tox_gh_actions/requirements.txt
-          python scripts/split_tox_gh_actions/split_tox_gh_actions.py --fail-on-changes
-
   build_lambda_layer:
     name: Build Package
     runs-on: ubuntu-latest

.github/workflows/codeql-analysis.yml

@@ -52,7 +52,7 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v3
+      uses: github/codeql-action/init@v4
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -63,7 +63,7 @@ jobs:
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@v3
+      uses: github/codeql-action/autobuild@v4
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 https://docs.github.com/en/actions/reference/workflow-syntax-for-github-actions
@@ -77,4 +77,4 @@ jobs:
     #   make release
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v3
+      uses: github/codeql-action/analyze@v4

.github/workflows/test-integrations-ai.yml

@@ -58,6 +58,14 @@ jobs:
         run: |
           set -x # print commands that are executed
           ./scripts/runtox.sh "py${{ matrix.python-version }}-cohere"
+      - name: Test google_genai
+        run: |
+          set -x # print commands that are executed
+          ./scripts/runtox.sh "py${{ matrix.python-version }}-google_genai"
+      - name: Test huggingface_hub
+        run: |
+          set -x # print commands that are executed
+          ./scripts/runtox.sh "py${{ matrix.python-version }}-huggingface_hub"
       - name: Test langchain-base
         run: |
           set -x # print commands that are executed
@@ -66,6 +74,14 @@ jobs:
         run: |
           set -x # print commands that are executed
           ./scripts/runtox.sh "py${{ matrix.python-version }}-langchain-notiktoken"
+      - name: Test langgraph
+        run: |
+          set -x # print commands that are executed
+          ./scripts/runtox.sh "py${{ matrix.python-version }}-langgraph"
+      - name: Test litellm
+        run: |
+          set -x # print commands that are executed
+          ./scripts/runtox.sh "py${{ matrix.python-version }}-litellm"
       - name: Test openai-base
         run: |
           set -x # print commands that are executed
@@ -74,18 +90,10 @@ jobs:
         run: |
           set -x # print commands that are executed
           ./scripts/runtox.sh "py${{ matrix.python-version }}-openai-notiktoken"
-      - name: Test langgraph
-        run: |
-          set -x # print commands that are executed
-          ./scripts/runtox.sh "py${{ matrix.python-version }}-langgraph"
       - name: Test openai_agents
         run: |
           set -x # print commands that are executed
           ./scripts/runtox.sh "py${{ matrix.python-version }}-openai_agents"
-      - name: Test huggingface_hub
-        run: |
-          set -x # print commands that are executed
-          ./scripts/runtox.sh "py${{ matrix.python-version }}-huggingface_hub"
       - name: Generate coverage XML (Python 3.6)
         if: ${{ !cancelled() && matrix.python-version == '3.6' }}
         run: |

CHANGELOG.md

@@ -1,5 +1,61 @@
 # Changelog
 
+## 2.41.0
+
+### Various fixes & improvements
+
+- feat: Add `concurrent.futures` patch to threading integration (#4770) by @alexander-alderman-webb
+  
+  The SDK now makes sure to automatically preserve span relationships when using `ThreadPoolExecutor`.
+- chore: Remove old metrics code (#4899) by @sentrivana
+
+  Removed all code related to the deprecated experimental metrics feature (`sentry_sdk.metrics`).
+- ref: Remove "experimental" from log function name (#4901) by @sentrivana
+- fix(ai): Add mapping for gen_ai message roles (#4884) by @shellmayr
+- feat(metrics): Add trace metrics behind an experiments flag (#4898) by @k-fish
+
+## 2.40.0
+
+### Various fixes & improvements
+
+- Add LiteLLM integration (#4864) by @constantinius
+  Once you've enabled the [new LiteLLM integration](https://docs.sentry.io/platforms/python/integrations/litellm/), you can use the Sentry AI Agents Monitoring, a Sentry dashboard that helps you understand what's going on with your AI requests:
+  
+  ```python
+  import sentry_sdk
+  from sentry_sdk.integrations.litellm import LiteLLMIntegration
+  sentry_sdk.init(
+      dsn="<your-dsn>",
+      # Set traces_sample_rate to 1.0 to capture 100%
+      # of transactions for tracing.
+      traces_sample_rate=1.0,
+      # Add data like inputs and responses;
+      # see https://docs.sentry.io/platforms/python/data-management/data-collected/ for more info
+      send_default_pii=True,
+      integrations=[
+          LiteLLMIntegration(),
+      ],
+  )
+  ```
+
+- Litestar: Copy request info to prevent cookies mutation (#4883) by @alexander-alderman-webb
+- Add tracing to `DramatiqIntegration` (#4571) by @Igreh
+- Also emit spans for MCP tool calls done by the LLM (#4875) by @constantinius
+- Option to not trace HTTP requests based on status codes (#4869) by @alexander-alderman-webb
+  You can now disable transactions for incoming requests with specific HTTP status codes. The [new `trace_ignore_status_codes` option](https://docs.sentry.io/platforms/python/configuration/options/#trace_ignore_status_codes) accepts a `set` of status codes as integers. If a transaction wraps a request that results in one of the provided status codes, the transaction will be unsampled.
+    
+  ```python
+  import sentry_sdk
+  
+  sentry_sdk.init(
+      trace_ignore_status_codes={301, 302, 303, *range(305, 400), 404},
+  )
+  ```
+
+- Move `_set_agent_data` call to `ai_client_span` function (#4876) by @constantinius
+- Add script to determine lowest supported versions (#4867) by @sentrivana
+- Update `CONTRIBUTING.md` (#4870) by @sentrivana
+
 ## 2.39.0
 
 ### Various fixes & improvements

docs/conf.py

@@ -31,7 +31,7 @@
 copyright = "2019-{}, Sentry Team and Contributors".format(datetime.now().year)
 author = "Sentry Team and Contributors"
 
-release = "2.39.0"
+release = "2.41.0"
 version = ".".join(release.split(".")[:2])  # The short X.Y version.
 
 

pyproject.toml

@@ -118,6 +118,10 @@ ignore_missing_imports = true
 module = "langgraph.*"
 ignore_missing_imports = true
 
+[[tool.mypy.overrides]]
+module = "google.genai.*"
+ignore_missing_imports = true
+
 [[tool.mypy.overrides]]
 module = "executing.*"
 ignore_missing_imports = true
@@ -179,6 +183,10 @@ ignore_missing_imports = true
 module = "agents.*"
 ignore_missing_imports = true
 
+[[tool.mypy.overrides]]
+module = "dramatiq.*"
+ignore_missing_imports = true
+
 #
 # Tool: Ruff (linting and formatting)
 #

scripts/populate_tox/README.md

@@ -14,25 +14,24 @@ combination of hardcoded and generated entries.
 
 The `populate_tox.py` script fills out the auto-generated part of that template.
 It does this by querying PyPI for each framework's package and its metadata and
-then determining which versions make sense to test to get good coverage.
+then determining which versions it makes sense to test to get good coverage.
 
 By default, the lowest supported and latest version of a framework are always
 tested, with a number of releases in between:
 - If the package has majors, we pick the highest version of each major.
 - If the package doesn't have multiple majors, we pick two versions in between
   lowest and highest.
 
-#### Caveats
+Each test suite requires at least some configuration to be added to
+`TEST_SUITE_CONFIG` in `scripts/populate_tox/config.py`. If you're adding a new
+integration, check out the [Add a new test suite](#add-a-new-test-suite) section.
 
-- Make sure the integration name is the same everywhere. If it consists of
-  multiple words, use an underscore instead of a hyphen.
+## Test suite config
 
-## Defining constraints
-
-The `TEST_SUITE_CONFIG` dictionary defines, for each integration test suite,
-the main package (framework, library) to test with; any additional test
-dependencies, optionally gated behind specific conditions; and optionally
-the Python versions to test on.
+The `TEST_SUITE_CONFIG` dictionary in `scripts/populate_tox/config.py` defines,
+for each integration test suite, the main package (framework, library) to test
+with; any additional test dependencies, optionally gated behind specific
+conditions; and optionally the Python versions to test on.
 
 Constraints are defined using the format specified below. The following sections
 describe each key.
@@ -58,7 +57,7 @@ in [packaging.specifiers](https://packaging.pypa.io/en/stable/specifiers.html).
 
 ### `package`
 
-The name of the third party package as it's listed on PyPI. The script will
+The name of the third-party package as it's listed on PyPI. The script will
 be picking different versions of this package to test.
 
 This key is mandatory.
@@ -69,15 +68,15 @@ The test dependencies of the test suite. They're defined as a dictionary of
 `rule: [package1, package2, ...]` key-value pairs. All packages
 in the package list of a rule will be installed as long as the rule applies.
 
-`rule`s are predefined. Each `rule` must be one of the following:
+Each `rule` must be one of the following:
   - `*`: packages will be always installed
   - a version specifier on the main package (e.g. `<=0.32`): packages will only
     be installed if the main package falls into the version bounds specified
   - specific Python version(s) in the form `py3.8,py3.9`: packages will only be
     installed if the Python version matches one from the list
 
 Rules can be used to specify version bounds on older versions of the main
-package's dependencies, for example. If e.g. Flask tests generally need
+package's dependencies, for example. If Flask tests generally need
 Werkzeug and don't care about its version, but Flask older than 3.0 needs
 a specific Werkzeug version to work, you can say:
 
@@ -176,7 +175,7 @@ be expressed like so:
 ### `integration_name`
 
 Sometimes, the name of the test suite doesn't match the name of the integration.
-For example, we have the `openai_base` and `openai_notiktoken` test suites, both
+For example, we have the `openai-base` and `openai-notiktoken` test suites, both
 of which are actually testing the `openai` integration. If this is the case, you
 can use the `integration_name` key to define the name of the integration. If not
 provided, it will default to the name of the test suite.
@@ -193,6 +192,11 @@ greater than 2, as the oldest and latest supported versions will always be
 picked. Additionally, if there is a recent prerelease, it'll also always be
 picked (this doesn't count towards `num_versions`).
 
+For instance, `num_versions` set to `2` will only test the first supported and
+the last release of the package. `num_versions` equal to `3` will test the first
+supported, the last release, and one release in between; `num_versions` set to `4`
+will test an additional release in between. In all these cases, if there is
+a recent prerelease, it'll be picked as well in addition to the picked versions.
 
 ## How-Tos
 
@@ -202,9 +206,10 @@ picked (this doesn't count towards `num_versions`).
    in `integrations/__init__.py`. This should be the lowest version of the
    framework that we can guarantee works with the SDK. If you've just added the
    integration, you should generally set this to the latest version of the framework
-   at the time.
+   at the time, unless you've verified the integration works for earlier versions
+   as well.
 2. Add the integration and any constraints to `TEST_SUITE_CONFIG`. See the
-   "Defining constraints" section for the format.
+   [Test suite config](#test-suite-config) section for the format.
 3. Add the integration to one of the groups in the `GROUPS` dictionary in
    `scripts/split_tox_gh_actions/split_tox_gh_actions.py`.
 4. Run `scripts/generate-test-files.sh` and commit the changes.

scripts/populate_tox/config.py

@@ -1,7 +1,6 @@
 # The TEST_SUITE_CONFIG dictionary defines, for each integration test suite,
-# the main package (framework, library) to test with; any additional test
-# dependencies, optionally gated behind specific conditions; and optionally
-# the Python versions to test on.
+# at least the main package (framework, library) to test with. Additional
+# test dependencies, Python versions to test on, etc. can also be defined here.
 #
 # See scripts/populate_tox/README.md for more info on the format and examples.
 
@@ -143,6 +142,13 @@
         "package": "gql[all]",
         "num_versions": 2,
     },
+    "google_genai": {
+        "package": "google-genai",
+        "deps": {
+            "*": ["pytest-asyncio"],
+        },
+        "python": ">=3.9",
+    },
     "graphene": {
         "package": "graphene",
         "deps": {
@@ -183,9 +189,8 @@
     "huggingface_hub": {
         "package": "huggingface_hub",
         "deps": {
-            "*": ["responses"],
+            "*": ["responses", "pytest-httpx"],
         },
-        "include": "<1.0",
     },
     "langchain-base": {
         "package": "langchain",
@@ -214,6 +219,9 @@
         "package": "launchdarkly-server-sdk",
         "num_versions": 2,
     },
+    "litellm": {
+        "package": "litellm",
+    },
     "litestar": {
         "package": "litestar",
         "deps": {
@@ -232,7 +240,10 @@
             "*": ["pytest-asyncio", "tiktoken"],
             "<1.55": ["httpx<0.28"],
         },
-        "python": ">=3.8",
+        "python": {
+            ">0.0,<2.3": ">=3.8",
+            ">=2.3": ">=3.9",
+        },
     },
     "openai-notiktoken": {
         "package": "openai",
@@ -241,7 +252,10 @@
             "*": ["pytest-asyncio"],
             "<1.55": ["httpx<0.28"],
         },
-        "python": ">=3.8",
+        "python": {
+            ">0.0,<2.3": ">=3.8",
+            ">=2.3": ">=3.9",
+        },
     },
     "openai_agents": {
         "package": "openai-agents",