1.128.0

Bumps
[phonenumbers](https://github.com/daviddrysdale/python-phonenumbers)
from 8.13.50 to 9.0.2.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="73ef5e664b"><code>73ef5e6</code></a>
Prep for 9.0.2 release</li>
<li><a
href="528a98bc75"><code>528a98b</code></a>
Generated files for metadata</li>
<li><a
href="28f5958abd"><code>28f5958</code></a>
Merge metadata changes from upstream 9.0.2</li>
<li><a
href="25ae49c160"><code>25ae49c</code></a>
Prep for 9.0.1 release</li>
<li><a
href="b8a1459cef"><code>b8a1459</code></a>
Generated files for metadata</li>
<li><a
href="f6cd233359"><code>f6cd233</code></a>
Merge metadata changes from upstream 9.0.1</li>
<li><a
href="c46f1049ba"><code>c46f104</code></a>
Prep for 9.0.0 release</li>
<li><a
href="d542ec2abc"><code>d542ec2</code></a>
Generated files for metadata</li>
<li><a
href="a4da80e252"><code>a4da80e</code></a>
Merge metadata changes from upstream 9.0.0</li>
<li><a
href="45c822e887"><code>45c822e</code></a>
Prep for 8.13.55 release</li>
<li>Additional commits viewable in <a
href="https://github.com/daviddrysdale/python-phonenumbers/compare/v8.13.50...v9.0.2">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=phonenumbers&package-manager=pip&previous-version=8.13.50&new-version=9.0.2)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.ci/before_build_wheel.sh

@@ -0,0 +1,10 @@
+#!/bin/sh
+set -xeu
+
+# On 32-bit Linux platforms, we need libatomic1 to use rustup
+if command -v yum &> /dev/null; then
+   yum install -y libatomic
+fi
+
+# Install a Rust toolchain
+curl https://sh.rustup.rs -sSf | sh -s -- --default-toolchain 1.82.0 -y --profile minimal

.ci/scripts/check_lockfile.py

@@ -11,12 +11,12 @@ with open("poetry.lock", "rb") as f:
 
 try:
     lock_version = lockfile["metadata"]["lock-version"]
-    assert lock_version == "2.0"
+    assert lock_version == "2.1"
 except Exception:
     print(
         """\
-    Lockfile is not version 2.0. You probably need to upgrade poetry on your local box
-    and re-run `poetry lock --no-update`. See the Poetry cheat sheet at
+    Lockfile is not version 2.1. You probably need to upgrade poetry on your local box
+    and re-run `poetry lock`. See the Poetry cheat sheet at
     https://element-hq.github.io/synapse/develop/development/dependencies.html
     """
     )

.github/workflows/docker.yml

@@ -18,22 +18,22 @@ jobs:
     steps:
       - name: Set up QEMU
         id: qemu
-        uses: docker/setup-qemu-action@v3
+        uses: docker/setup-qemu-action@29109295f81e9208d7d86ff1c6c12d2833863392 # v3.6.0
         with:
           platforms: arm64
 
       - name: Set up Docker Buildx
         id: buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
 
       - name: Inspect builder
         run: docker buildx inspect
 
       - name: Install Cosign
-        uses: sigstore/cosign-installer@v3.8.1
+        uses: sigstore/cosign-installer@d7d6bc7722e3daa8354c50bcb52f4837da5e9b6a # v3.8.1
 
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Extract version from pyproject.toml
         # Note: explicitly requesting bash will mean bash is invoked with `-eo pipefail`, see
@@ -43,13 +43,13 @@ jobs:
           echo "SYNAPSE_VERSION=$(grep "^version" pyproject.toml | sed -E 's/version\s*=\s*["]([^"]*)["]/\1/')" >> $GITHUB_ENV
 
       - name: Log in to DockerHub
-        uses: docker/login-action@v3
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Log in to GHCR
-        uses: docker/login-action@v3
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
         with:
           registry: ghcr.io
           username: ${{ github.repository_owner }}
@@ -57,7 +57,7 @@ jobs:
 
       - name: Calculate docker image tag
         id: set-tag
-        uses: docker/metadata-action@master
+        uses: docker/metadata-action@902fa8ec7d6ecbf8d84d538b9b233a880e428804 # v5.7.0
         with:
           images: |
             docker.io/matrixdotorg/synapse
@@ -72,7 +72,7 @@ jobs:
 
       - name: Build and push all platforms
         id: build-and-push
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
         with:
           push: true
           labels: |

.github/workflows/docs-pr-netlify.yaml

@@ -14,7 +14,7 @@ jobs:
       # There's a 'download artifact' action, but it hasn't been updated for the workflow_run action
       # (https://github.com/actions/download-artifact/issues/60) so instead we get this mess:
       - name: 📥 Download artifact
-        uses: dawidd6/action-download-artifact@20319c5641d495c8a52e688b7dc5fada6c3a9fbc # v8
+        uses: dawidd6/action-download-artifact@07ab29fd4a977ae4d2b275087cf67563dfdf0295 # v9
         with:
           workflow: docs-pr.yaml
           run_id: ${{ github.event.workflow_run.id }}
@@ -22,7 +22,7 @@ jobs:
           path: book
 
       - name: 📤 Deploy to Netlify
-        uses: matrix-org/netlify-pr-preview@v3
+        uses: matrix-org/netlify-pr-preview@9805cd123fc9a7e421e35340a05e1ebc5dee46b5 # v3
         with:
           path: book
           owner: ${{ github.event.workflow_run.head_repository.owner.login }}

.github/workflows/docs-pr.yaml

@@ -13,7 +13,7 @@ jobs:
     name: GitHub Pages
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           # Fetch all history so that the schema_versions script works.
           fetch-depth: 0
@@ -24,7 +24,7 @@ jobs:
           mdbook-version: '0.4.17'
 
       - name: Setup python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
         with:
           python-version: "3.x"
 
@@ -39,7 +39,7 @@ jobs:
           cp book/welcome_and_overview.html book/index.html
 
       - name: Upload Artifact
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         with:
           name: book
           path: book
@@ -50,7 +50,7 @@ jobs:
     name: Check links in documentation
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Setup mdbook
         uses: peaceiris/actions-mdbook@ee69d230fe19748b7abf22df32acaa93833fad08 # v2.0.0

.github/workflows/docs.yaml

@@ -50,7 +50,7 @@ jobs:
     needs:
       - pre
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           # Fetch all history so that the schema_versions script works.
           fetch-depth: 0
@@ -64,7 +64,7 @@ jobs:
         run: echo 'window.SYNAPSE_VERSION = "${{ needs.pre.outputs.branch-version }}";' > ./docs/website_files/version.js
 
       - name: Setup python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
         with:
           python-version: "3.x"
 

.github/workflows/fix_lint.yaml

@@ -13,21 +13,22 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@master
+        uses: dtolnay/rust-toolchain@56f84321dbccf38fb67ce29ab63e4754056677e0 # master (rust 1.85.1)
         with:
           # We use nightly so that `fmt` correctly groups together imports, and
           # clippy correctly fixes up the benchmarks.
           toolchain: nightly-2022-12-01
           components: clippy, rustfmt
-      - uses: Swatinem/rust-cache@v2
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
 
       - name: Setup Poetry
-        uses: matrix-org/setup-python-poetry@v1
+        uses: matrix-org/setup-python-poetry@5bbf6603c5c930615ec8a29f1b5d7d258d905aa4 # v2.0.0
         with:
           install-project: "false"
+          poetry-version: "2.1.1"
 
       - name: Run ruff check
         continue-on-error: true
@@ -43,6 +44,6 @@ jobs:
       - run: cargo fmt
         continue-on-error: true
 
-      - uses: stefanzweifel/git-auto-commit-action@v5
+      - uses: stefanzweifel/git-auto-commit-action@e348103e9026cc0eee72ae06630dbe30c8bf7a79 # v5.1.0
         with:
           commit_message: "Attempt to fix linting"

.github/workflows/latest_deps.yml

@@ -39,17 +39,17 @@ jobs:
     if: needs.check_repo.outputs.should_run_workflow == 'true'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@stable
-      - uses: Swatinem/rust-cache@v2
+        uses: dtolnay/rust-toolchain@fcf085fcb4b4b8f63f96906cd713eb52181b5ea4 # stable (rust 1.85.1)
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
 
       # The dev dependencies aren't exposed in the wheel metadata (at least with current
       # poetry-core versions), so we install with poetry.
-      - uses: matrix-org/setup-python-poetry@v1
+      - uses: matrix-org/setup-python-poetry@5bbf6603c5c930615ec8a29f1b5d7d258d905aa4 # v2.0.0
         with:
           python-version: "3.x"
-          poetry-version: "1.3.2"
+          poetry-version: "2.1.1"
           extras: "all"
       # Dump installed versions for debugging.
       - run: poetry run pip list > before.txt
@@ -72,11 +72,11 @@ jobs:
             postgres-version: "14"
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@stable
-      - uses: Swatinem/rust-cache@v2
+        uses: dtolnay/rust-toolchain@fcf085fcb4b4b8f63f96906cd713eb52181b5ea4 # stable (rust 1.85.1)
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
 
       - run: sudo apt-get -qq install xmlsec1
       - name: Set up PostgreSQL ${{ matrix.postgres-version }}
@@ -86,7 +86,7 @@ jobs:
             -e POSTGRES_PASSWORD=postgres \
             -e POSTGRES_INITDB_ARGS="--lc-collate C --lc-ctype C --encoding UTF8" \
             postgres:${{ matrix.postgres-version }}
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
         with:
           python-version: "3.x"
       - run: pip install .[all,test]
@@ -145,11 +145,11 @@ jobs:
       BLACKLIST: ${{ matrix.workers && 'synapse-blacklist-with-workers' }}
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@stable
-      - uses: Swatinem/rust-cache@v2
+        uses: dtolnay/rust-toolchain@fcf085fcb4b4b8f63f96906cd713eb52181b5ea4 # stable (rust 1.85.1)
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
 
       - name: Ensure sytest runs `pip install`
         # Delete the lockfile so sytest will `pip install` rather than `poetry install`
@@ -164,7 +164,7 @@ jobs:
         if: ${{ always() }}
         run: /sytest/scripts/tap_to_gha.pl /logs/results.tap
       - name: Upload SyTest logs
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         if: ${{ always() }}
         with:
           name: Sytest Logs - ${{ job.status }} - (${{ join(matrix.*, ', ') }})
@@ -192,15 +192,15 @@ jobs:
             database: Postgres
 
     steps:
-      - name: Run actions/checkout@v4 for synapse
-        uses: actions/checkout@v4
+      - name: Check out synapse codebase
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           path: synapse
 
       - name: Prepare Complement's Prerequisites
         run: synapse/.ci/scripts/setup_complement_prerequisites.sh
 
-      - uses: actions/setup-go@v5
+      - uses: actions/setup-go@0aaccfd150d50ccaeb58ebd88d36e91967a5f35b # v5.4.0
         with:
           cache-dependency-path: complement/go.sum
           go-version-file: complement/go.mod
@@ -225,7 +225,7 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - uses: JasonEtco/create-an-issue@1b14a70e4d8dc185e5cc76d3bec9eab20257b2c5 # v2.9.2
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/poetry_lockfile.yaml

@@ -16,8 +16,8 @@ jobs:
     name: "Check locked dependencies have sdists"
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
         with:
           python-version: '3.x'
       - run: pip install tomli

.github/workflows/push_complement_image.yml

@@ -33,29 +33,29 @@ jobs:
       packages: write
     steps:
       - name: Checkout specific branch (debug build)
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         if: github.event_name == 'workflow_dispatch'
         with:
           ref: ${{ inputs.branch }}
       - name: Checkout clean copy of develop (scheduled build)
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         if: github.event_name == 'schedule'
         with:
           ref: develop
       - name: Checkout clean copy of master (on-push)
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         if: github.event_name == 'push'
         with:
           ref: master
       - name: Login to registry
-        uses: docker/login-action@v3
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
       - name: Work out labels for complement image
         id: meta
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@902fa8ec7d6ecbf8d84d538b9b233a880e428804 # v5.7.0
         with:
           images: ghcr.io/${{ github.repository }}/complement-synapse
           tags: |

.github/workflows/release-artifacts.yml

@@ -27,8 +27,8 @@ jobs:
     name: "Calculate list of debian distros"
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
         with:
           python-version: '3.x'
       - id: set-distros
@@ -55,18 +55,18 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           path: src
 
       - name: Set up Docker Buildx
         id: buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
         with:
           install: true
 
       - name: Set up docker layer caching
-        uses: actions/cache@v4
+        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
         with:
           path: /tmp/.buildx-cache
           key: ${{ runner.os }}-buildx-${{ github.sha }}
@@ -74,7 +74,7 @@ jobs:
             ${{ runner.os }}-buildx-
 
       - name: Set up python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
         with:
           python-version: '3.x'
 
@@ -101,7 +101,7 @@ jobs:
           echo "ARTIFACT_NAME=${DISTRO#*:}" >> "$GITHUB_OUTPUT"
 
       - name: Upload debs as artifacts
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         with:
           name: debs-${{ steps.artifact-name.outputs.ARTIFACT_NAME }}
           path: debs/*
@@ -130,20 +130,20 @@ jobs:
             arch: aarch64
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
         with:
           # setup-python@v4 doesn't impose a default python version. Need to use 3.x
           # here, because `python` on osx points to Python 2.7.
           python-version: "3.x"
 
       - name: Install cibuildwheel
-        run: python -m pip install cibuildwheel==2.19.1
+        run: python -m pip install cibuildwheel==2.23.0
 
       - name: Set up QEMU to emulate aarch64
         if: matrix.arch == 'aarch64'
-        uses: docker/setup-qemu-action@v3
+        uses: docker/setup-qemu-action@29109295f81e9208d7d86ff1c6c12d2833863392 # v3.6.0
         with:
           platforms: arm64
 
@@ -165,7 +165,7 @@ jobs:
           CARGO_NET_GIT_FETCH_WITH_CLI: true
           CIBW_ENVIRONMENT_PASS_LINUX: CARGO_NET_GIT_FETCH_WITH_CLI
 
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         with:
           name: Wheel-${{ matrix.os }}-${{ matrix.arch }}
           path: ./wheelhouse/*.whl
@@ -176,8 +176,8 @@ jobs:
     if: ${{ !startsWith(github.ref, 'refs/pull/') }}
 
     steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
         with:
           python-version: '3.10'
 
@@ -186,7 +186,7 @@ jobs:
       - name: Build sdist
         run: python -m build --sdist
 
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         with:
           name: Sdist
           path: dist/*.tar.gz
@@ -203,7 +203,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Download all workflow run artifacts
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@95815c38cf2ff2164869cbab79da8d1f422bc89e # v4.2.1
       - name: Build a tarball for the debs
         # We need to merge all the debs uploads into one folder, then compress
         # that.
@@ -213,7 +213,7 @@ jobs:
           tar -cvJf debs.tar.xz debs
       - name: Attach to release
         # Pinned to work around https://github.com/softprops/action-gh-release/issues/445
-        uses: softprops/action-gh-release@v0.1.15
+        uses: softprops/action-gh-release@de2c0eb89ae2a093876385947365aca7b0e5f844 # v0.1.15
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:

.github/workflows/tests.yml

@@ -23,7 +23,7 @@ jobs:
       linting: ${{ !startsWith(github.ref, 'refs/pull/') || steps.filter.outputs.linting }}
       linting_readme: ${{ !startsWith(github.ref, 'refs/pull/') || steps.filter.outputs.linting_readme }}
     steps:
-    - uses: dorny/paths-filter@v3
+    - uses: dorny/paths-filter@de90cc6fb38fc0963ad72b210f1f284cd68cea36 # v3.0.2
       id: filter
       # We only check on PRs
       if: startsWith(github.ref, 'refs/pull/')
@@ -83,14 +83,14 @@ jobs:
     if: ${{ needs.changes.outputs.linting == 'true' }}
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@1.66.0
-      - uses: Swatinem/rust-cache@v2
-      - uses: matrix-org/setup-python-poetry@v1
+        uses: dtolnay/rust-toolchain@e05ebb0e73db581a4877c6ce762e29fe1e0b5073 # 1.66.0
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
+      - uses: matrix-org/setup-python-poetry@5bbf6603c5c930615ec8a29f1b5d7d258d905aa4 # v2.0.0
         with:
           python-version: "3.x"
-          poetry-version: "1.3.2"
+          poetry-version: "2.1.1"
           extras: "all"
       - run: poetry run scripts-dev/generate_sample_config.sh --check
       - run: poetry run scripts-dev/config-lint.sh
@@ -101,8 +101,8 @@ jobs:
     if: ${{ needs.changes.outputs.linting == 'true' }}
 
     steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
         with:
           python-version: "3.x"
       - run: "pip install 'click==8.1.1' 'GitPython>=3.1.20'"
@@ -111,8 +111,8 @@ jobs:
   check-lockfile:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
         with:
           python-version: "3.x"
       - run: .ci/scripts/check_lockfile.py
@@ -124,11 +124,12 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Setup Poetry
-        uses: matrix-org/setup-python-poetry@v1
+        uses: matrix-org/setup-python-poetry@5bbf6603c5c930615ec8a29f1b5d7d258d905aa4 # v2.0.0
         with:
+          poetry-version: "2.1.1"
           install-project: "false"
 
       - name: Run ruff check
@@ -145,14 +146,14 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@1.66.0
-      - uses: Swatinem/rust-cache@v2
+        uses: dtolnay/rust-toolchain@e05ebb0e73db581a4877c6ce762e29fe1e0b5073 # 1.66.0
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
 
       - name: Setup Poetry
-        uses: matrix-org/setup-python-poetry@v1
+        uses: matrix-org/setup-python-poetry@5bbf6603c5c930615ec8a29f1b5d7d258d905aa4 # v2.0.0
         with:
           # We want to make use of type hints in optional dependencies too.
           extras: all
@@ -161,11 +162,12 @@ jobs:
           # https://github.com/matrix-org/synapse/pull/15376#issuecomment-1498983775
           # To make CI green, err towards caution and install the project.
           install-project: "true"
+          poetry-version: "2.1.1"
 
       # Cribbed from
       # https://github.com/AustinScola/mypy-cache-github-action/blob/85ea4f2972abed39b33bd02c36e341b28ca59213/src/restore.ts#L10-L17
       - name: Restore/persist mypy's cache
-        uses: actions/cache@v4
+        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
         with:
           path: |
             .mypy_cache
@@ -178,7 +180,7 @@ jobs:
   lint-crlf:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - name: Check line endings
         run: scripts-dev/check_line_terminators.sh
 
@@ -186,11 +188,11 @@ jobs:
     if: ${{ (github.base_ref == 'develop'  || contains(github.base_ref, 'release-')) && github.actor != 'dependabot[bot]' }}
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           ref: ${{ github.event.pull_request.head.sha }}
           fetch-depth: 0
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
         with:
           python-version: "3.x"
       - run: "pip install 'towncrier>=18.6.0rc1'"
@@ -204,15 +206,15 @@ jobs:
     if: ${{ needs.changes.outputs.linting == 'true' }}
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           ref: ${{ github.event.pull_request.head.sha }}
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@1.66.0
-      - uses: Swatinem/rust-cache@v2
-      - uses: matrix-org/setup-python-poetry@v1
+        uses: dtolnay/rust-toolchain@e05ebb0e73db581a4877c6ce762e29fe1e0b5073 # 1.66.0
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
+      - uses: matrix-org/setup-python-poetry@5bbf6603c5c930615ec8a29f1b5d7d258d905aa4 # v2.0.0
         with:
-          poetry-version: "1.3.2"
+          poetry-version: "2.1.1"
           extras: "all"
       - run: poetry run scripts-dev/check_pydantic_models.py
 
@@ -222,13 +224,13 @@ jobs:
     if: ${{ needs.changes.outputs.rust == 'true' }}
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@1.66.0
+        uses: dtolnay/rust-toolchain@e05ebb0e73db581a4877c6ce762e29fe1e0b5073 # 1.66.0
         with:
             components: clippy
-      - uses: Swatinem/rust-cache@v2
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
 
       - run: cargo clippy -- -D warnings
 
@@ -240,14 +242,14 @@ jobs:
     if: ${{ needs.changes.outputs.rust == 'true' }}
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@master
+        uses: dtolnay/rust-toolchain@56f84321dbccf38fb67ce29ab63e4754056677e0 # master (rust 1.85.1)
         with:
             toolchain: nightly-2022-12-01
             components: clippy
-      - uses: Swatinem/rust-cache@v2
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
 
       - run: cargo clippy --all-features -- -D warnings
 
@@ -257,15 +259,15 @@ jobs:
     if: ${{ needs.changes.outputs.rust == 'true' }}
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@master
+        uses: dtolnay/rust-toolchain@56f84321dbccf38fb67ce29ab63e4754056677e0 # master (rust 1.85.1)
         with:
           # We use nightly so that it correctly groups together imports
           toolchain: nightly-2022-12-01
           components: rustfmt
-      - uses: Swatinem/rust-cache@v2
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
 
       - run: cargo fmt --check
 
@@ -276,8 +278,8 @@ jobs:
     needs: changes
     if: ${{ needs.changes.outputs.linting_readme == 'true' }}
     steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
         with:
           python-version: "3.x"
       - run: "pip install rstcheck"
@@ -301,7 +303,7 @@ jobs:
       - lint-readme
     runs-on: ubuntu-latest
     steps:
-      - uses: matrix-org/done-action@v3
+      - uses: matrix-org/done-action@3409aa904e8a2aaf2220f09bc954d3d0b0a2ee67 # v3
         with:
           needs: ${{ toJSON(needs) }}
 
@@ -324,8 +326,8 @@ jobs:
     needs: linting-done
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
         with:
           python-version: "3.x"
       - id: get-matrix
@@ -345,7 +347,7 @@ jobs:
         job:  ${{ fromJson(needs.calculate-test-jobs.outputs.trial_test_matrix) }}
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - run: sudo apt-get -qq install xmlsec1
       - name: Set up PostgreSQL ${{ matrix.job.postgres-version }}
         if: ${{ matrix.job.postgres-version }}
@@ -360,13 +362,13 @@ jobs:
             postgres:${{ matrix.job.postgres-version }}
 
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@1.66.0
-      - uses: Swatinem/rust-cache@v2
+        uses: dtolnay/rust-toolchain@e05ebb0e73db581a4877c6ce762e29fe1e0b5073 # 1.66.0
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
 
-      - uses: matrix-org/setup-python-poetry@v1
+      - uses: matrix-org/setup-python-poetry@5bbf6603c5c930615ec8a29f1b5d7d258d905aa4 # v2.0.0
         with:
           python-version: ${{ matrix.job.python-version }}
-          poetry-version: "1.3.2"
+          poetry-version: "2.1.1"
           extras: ${{ matrix.job.extras }}
       - name: Await PostgreSQL
         if: ${{ matrix.job.postgres-version }}
@@ -399,11 +401,11 @@ jobs:
       - changes
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@1.66.0
-      - uses: Swatinem/rust-cache@v2
+        uses: dtolnay/rust-toolchain@e05ebb0e73db581a4877c6ce762e29fe1e0b5073 # 1.66.0
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
 
       # There aren't wheels for some of the older deps, so we need to install
       # their build dependencies
@@ -412,7 +414,7 @@ jobs:
           sudo apt-get -qq install build-essential libffi-dev python3-dev \
             libxml2-dev libxslt-dev xmlsec1 zlib1g-dev libjpeg-dev libwebp-dev
 
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
         with:
           python-version: '3.9'
 
@@ -462,13 +464,13 @@ jobs:
         extras: ["all"]
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       # Install libs necessary for PyPy to build binary wheels for dependencies
       - run: sudo apt-get -qq install xmlsec1 libxml2-dev libxslt-dev
-      - uses: matrix-org/setup-python-poetry@v1
+      - uses: matrix-org/setup-python-poetry@5bbf6603c5c930615ec8a29f1b5d7d258d905aa4 # v2.0.0
         with:
           python-version: ${{ matrix.python-version }}
-          poetry-version: "1.3.2"
+          poetry-version: "2.1.1"
           extras: ${{ matrix.extras }}
       - run: poetry run trial --jobs=2 tests
       - name: Dump logs
@@ -512,13 +514,13 @@ jobs:
         job: ${{ fromJson(needs.calculate-test-jobs.outputs.sytest_test_matrix) }}
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - name: Prepare test blacklist
         run: cat sytest-blacklist .ci/worker-blacklist > synapse-blacklist-with-workers
 
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@1.66.0
-      - uses: Swatinem/rust-cache@v2
+        uses: dtolnay/rust-toolchain@e05ebb0e73db581a4877c6ce762e29fe1e0b5073 # 1.66.0
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
 
       - name: Run SyTest
         run: /bootstrap.sh synapse
@@ -527,7 +529,7 @@ jobs:
         if: ${{ always() }}
         run: /sytest/scripts/tap_to_gha.pl /logs/results.tap
       - name: Upload SyTest logs
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         if: ${{ always() }}
         with:
           name: Sytest Logs - ${{ job.status }} - (${{ join(matrix.job.*, ', ') }})
@@ -557,11 +559,11 @@ jobs:
           --health-retries 5
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - run: sudo apt-get -qq install xmlsec1 postgresql-client
-      - uses: matrix-org/setup-python-poetry@v1
+      - uses: matrix-org/setup-python-poetry@5bbf6603c5c930615ec8a29f1b5d7d258d905aa4 # v2.0.0
         with:
-          poetry-version: "1.3.2"
+          poetry-version: "2.1.1"
           extras: "postgres"
       - run: .ci/scripts/test_export_data_command.sh
         env:
@@ -601,7 +603,7 @@ jobs:
           --health-retries 5
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - name: Add PostgreSQL apt repository
         # We need a version of pg_dump that can handle the version of
         # PostgreSQL being tested against. The Ubuntu package repository lags
@@ -612,10 +614,10 @@ jobs:
           wget --quiet -O - https://www.postgresql.org/media/keys/ACCC4CF8.asc | sudo apt-key add -
           sudo apt-get update
       - run: sudo apt-get -qq install xmlsec1 postgresql-client
-      - uses: matrix-org/setup-python-poetry@v1
+      - uses: matrix-org/setup-python-poetry@5bbf6603c5c930615ec8a29f1b5d7d258d905aa4 # v2.0.0
         with:
           python-version: ${{ matrix.python-version }}
-          poetry-version: "1.3.2"
+          poetry-version: "2.1.1"
           extras: "postgres"
       - run: .ci/scripts/test_synapse_port_db.sh
         id: run_tester_script
@@ -625,7 +627,7 @@ jobs:
           PGPASSWORD: postgres
           PGDATABASE: postgres
       - name: "Upload schema differences"
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         if: ${{ failure() && !cancelled() && steps.run_tester_script.outcome == 'failure' }}
         with:
           name: Schema dumps
@@ -655,19 +657,19 @@ jobs:
             database: Postgres
 
     steps:
-      - name: Run actions/checkout@v4 for synapse
-        uses: actions/checkout@v4
+      - name: Checkout synapse codebase
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           path: synapse
 
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@1.66.0
-      - uses: Swatinem/rust-cache@v2
+        uses: dtolnay/rust-toolchain@e05ebb0e73db581a4877c6ce762e29fe1e0b5073 # 1.66.0
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
 
       - name: Prepare Complement's Prerequisites
         run: synapse/.ci/scripts/setup_complement_prerequisites.sh
 
-      - uses: actions/setup-go@v5
+      - uses: actions/setup-go@0aaccfd150d50ccaeb58ebd88d36e91967a5f35b # v5.4.0
         with:
           cache-dependency-path: complement/go.sum
           go-version-file: complement/go.mod
@@ -690,11 +692,11 @@ jobs:
       - changes
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@1.66.0
-      - uses: Swatinem/rust-cache@v2
+        uses: dtolnay/rust-toolchain@e05ebb0e73db581a4877c6ce762e29fe1e0b5073 # 1.66.0
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
 
       - run: cargo test
 
@@ -708,13 +710,13 @@ jobs:
       - changes
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@master
+        uses: dtolnay/rust-toolchain@56f84321dbccf38fb67ce29ab63e4754056677e0 # master (rust 1.85.1)
         with:
             toolchain: nightly-2022-12-01
-      - uses: Swatinem/rust-cache@v2
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
 
       - run: cargo bench --no-run
 
@@ -733,7 +735,7 @@ jobs:
       - linting-done
     runs-on: ubuntu-latest
     steps:
-      - uses: matrix-org/done-action@v3
+      - uses: matrix-org/done-action@3409aa904e8a2aaf2220f09bc954d3d0b0a2ee67 # v3
         with:
           needs: ${{ toJSON(needs) }}
 

.github/workflows/triage-incoming.yml

@@ -6,7 +6,7 @@ on:
 
 jobs:
   triage:
-    uses: matrix-org/backend-meta/.github/workflows/triage-incoming.yml@v2
+    uses: matrix-org/backend-meta/.github/workflows/triage-incoming.yml@18beaf3c8e536108bd04d18e6c3dc40ba3931e28 # v2.0.3
     with:
       project_id: 'PVT_kwDOAIB0Bs4AFDdZ'
       content_id: ${{ github.event.issue.node_id }}

.github/workflows/triage_labelled.yml

@@ -11,7 +11,7 @@ jobs:
     if: >
       contains(github.event.issue.labels.*.name, 'X-Needs-Info')
     steps:
-      - uses: actions/add-to-project@main
+      - uses: actions/add-to-project@280af8ae1f83a494cfad2cb10f02f6d13529caa9 # main (v1.0.2 + 10 commits)
         id: add_project
         with:
           project-url: "https://github.com/orgs/matrix-org/projects/67"

.github/workflows/twisted_trunk.yml

@@ -40,16 +40,17 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@stable
-      - uses: Swatinem/rust-cache@v2
+        uses: dtolnay/rust-toolchain@fcf085fcb4b4b8f63f96906cd713eb52181b5ea4 # stable (rust 1.85.1)
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
 
-      - uses: matrix-org/setup-python-poetry@v1
+      - uses: matrix-org/setup-python-poetry@5bbf6603c5c930615ec8a29f1b5d7d258d905aa4 # v2.0.0
         with:
           python-version: "3.x"
           extras: "all"
+          poetry-version: "2.1.1"
       - run: |
           poetry remove twisted
           poetry add --extras tls git+https://github.com/twisted/twisted.git#${{ inputs.twisted_ref || 'trunk' }}
@@ -64,17 +65,18 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - run: sudo apt-get -qq install xmlsec1
 
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@stable
-      - uses: Swatinem/rust-cache@v2
+        uses: dtolnay/rust-toolchain@fcf085fcb4b4b8f63f96906cd713eb52181b5ea4 # stable (rust 1.85.1)
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
 
-      - uses: matrix-org/setup-python-poetry@v1
+      - uses: matrix-org/setup-python-poetry@5bbf6603c5c930615ec8a29f1b5d7d258d905aa4 # v2.0.0
         with:
           python-version: "3.x"
           extras: "all test"
+          poetry-version: "2.1.1"
       - run: |
           poetry remove twisted
           poetry add --extras tls git+https://github.com/twisted/twisted.git#trunk
@@ -108,11 +110,11 @@ jobs:
         - ${{ github.workspace }}:/src
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Install Rust
-        uses: dtolnay/rust-toolchain@stable
-      - uses: Swatinem/rust-cache@v2
+        uses: dtolnay/rust-toolchain@fcf085fcb4b4b8f63f96906cd713eb52181b5ea4 # stable (rust 1.85.1)
+      - uses: Swatinem/rust-cache@9d47c6ad4b02e050fd481d890b2ea34778fd09d6 # v2.7.8
 
       - name: Patch dependencies
         # Note: The poetry commands want to create a virtualenv in /src/.venv/,
@@ -136,7 +138,7 @@ jobs:
         if: ${{ always() }}
         run: /sytest/scripts/tap_to_gha.pl /logs/results.tap
       - name: Upload SyTest logs
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         if: ${{ always() }}
         with:
           name: Sytest Logs - ${{ job.status }} - (${{ join(matrix.*, ', ') }})
@@ -164,14 +166,14 @@ jobs:
 
     steps:
       - name: Run actions/checkout@v4 for synapse
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           path: synapse
 
       - name: Prepare Complement's Prerequisites
         run: synapse/.ci/scripts/setup_complement_prerequisites.sh
 
-      - uses: actions/setup-go@v5
+      - uses: actions/setup-go@0aaccfd150d50ccaeb58ebd88d36e91967a5f35b # v5.4.0
         with:
           cache-dependency-path: complement/go.sum
           go-version-file: complement/go.mod
@@ -181,11 +183,11 @@ jobs:
         run: |
           set -x
           DEBIAN_FRONTEND=noninteractive sudo apt-get install -yqq python3 pipx
-          pipx install poetry==1.3.2
+          pipx install poetry==2.1.1
 
           poetry remove -n twisted
           poetry add -n --extras tls git+https://github.com/twisted/twisted.git#trunk
-          poetry lock --no-update
+          poetry lock
         working-directory: synapse
 
       - run: |
@@ -206,7 +208,7 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - uses: JasonEtco/create-an-issue@1b14a70e4d8dc185e5cc76d3bec9eab20257b2c5 # v2.9.2
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

CHANGES.md

@@ -1,10 +1,183 @@
+# Synapse 1.128.0 (2025-04-08)
+
+No significant changes since 1.128.0rc1.
+
+
+
+
+# Synapse 1.128.0rc1 (2025-04-01)
+
+### Features
+
+- Add an access token introspection cache to make Matrix Authentication Service integration ([MSC3861](https://github.com/matrix-org/matrix-doc/pull/3861)) more efficient. ([\#18231](https://github.com/element-hq/synapse/issues/18231))
+- Add background job to clear unreferenced state groups. ([\#18254](https://github.com/element-hq/synapse/issues/18254))
+- Hashes of media files are now tracked by Synapse. Media quarantines will now apply to all files with the same hash. ([\#18277](https://github.com/element-hq/synapse/issues/18277), [\#18302](https://github.com/element-hq/synapse/issues/18302), [\#18296](https://github.com/element-hq/synapse/issues/18296))
+
+### Bugfixes
+
+- Add index to sliding sync ([MSC4186](https://github.com/matrix-org/matrix-doc/pull/4186)) membership snapshot table, to fix a performance issue. ([\#18074](https://github.com/element-hq/synapse/issues/18074))
+
+### Updates to the Docker image
+
+- Specify the architecture of installed packages via an APT config option, which is more reliable than appending package names with `:{arch}`. ([\#18271](https://github.com/element-hq/synapse/issues/18271))
+- Always specify base image debian versions with a build argument. ([\#18272](https://github.com/element-hq/synapse/issues/18272))
+- Allow passing arguments to `start_for_complement.sh` (to be sent to `configure_workers_and_start.py`). ([\#18273](https://github.com/element-hq/synapse/issues/18273))
+- Make some improvements to the `prefix-log` script in the workers image. ([\#18274](https://github.com/element-hq/synapse/issues/18274))
+- Use `uv pip` to install `supervisor` in the worker image. ([\#18275](https://github.com/element-hq/synapse/issues/18275))
+- Avoid needing to download & use `rsync` in a build layer. ([\#18287](https://github.com/element-hq/synapse/issues/18287))
+
+### Improved Documentation
+
+- Fix how to obtain access token and change naming from riot to element ([\#18225](https://github.com/element-hq/synapse/issues/18225))
+- Correct a small typo in the SSO mapping providers documentation. ([\#18276](https://github.com/element-hq/synapse/issues/18276))
+- Add docs for how to clear out the Poetry wheel cache. ([\#18283](https://github.com/element-hq/synapse/issues/18283))
+
+### Internal Changes
+
+- Add a column `participant` to `room_memberships` table. ([\#18068](https://github.com/element-hq/synapse/issues/18068))
+- Update Poetry to 2.1.1, including updating the lock file version. ([\#18251](https://github.com/element-hq/synapse/issues/18251))
+- Pin GitHub Actions dependencies by commit hash. ([\#18255](https://github.com/element-hq/synapse/issues/18255))
+- Add DB delta to remove the old state group deletion job. ([\#18284](https://github.com/element-hq/synapse/issues/18284))
+
+
+
+### Updates to locked dependencies
+
+* Bump actions/add-to-project from f5473ace9aeee8b97717b281e26980aa5097023f to 280af8ae1f83a494cfad2cb10f02f6d13529caa9. ([\#18303](https://github.com/element-hq/synapse/issues/18303))
+* Bump actions/cache from 4.2.2 to 4.2.3. ([\#18266](https://github.com/element-hq/synapse/issues/18266))
+* Bump actions/download-artifact from 4.2.0 to 4.2.1. ([\#18268](https://github.com/element-hq/synapse/issues/18268))
+* Bump actions/setup-python from 5.4.0 to 5.5.0. ([\#18298](https://github.com/element-hq/synapse/issues/18298))
+* Bump actions/upload-artifact from 4.6.1 to 4.6.2. ([\#18304](https://github.com/element-hq/synapse/issues/18304))
+* Bump authlib from 1.4.1 to 1.5.1. ([\#18306](https://github.com/element-hq/synapse/issues/18306))
+* Bump dawidd6/action-download-artifact from 8 to 9. ([\#18204](https://github.com/element-hq/synapse/issues/18204))
+* Bump jinja2 from 3.1.5 to 3.1.6. ([\#18223](https://github.com/element-hq/synapse/issues/18223))
+* Bump log from 0.4.26 to 0.4.27. ([\#18267](https://github.com/element-hq/synapse/issues/18267))
+* Bump phonenumbers from 8.13.50 to 9.0.2. ([\#18299](https://github.com/element-hq/synapse/issues/18299))
+* Bump pygithub from 2.5.0 to 2.6.1. ([\#18243](https://github.com/element-hq/synapse/issues/18243))
+* Bump pyo3-log from 0.12.1 to 0.12.2. ([\#18269](https://github.com/element-hq/synapse/issues/18269))
+
+# Synapse 1.127.1 (2025-03-26)
+
+## Security
+- Fix [CVE-2025-30355](https://www.cve.org/CVERecord?id=CVE-2025-30355) / [GHSA-v56r-hwv5-mxg6](https://github.com/element-hq/synapse/security/advisories/GHSA-v56r-hwv5-mxg6). **High severity vulnerability affecting federation. The vulnerability has been exploited in the wild.**
+
+
+
+# Synapse 1.127.0 (2025-03-25)
+
+No significant changes since 1.127.0rc1.
+
+
+
+
+# Synapse 1.127.0rc1 (2025-03-18)
+
+### Features
+
+- Update [MSC4140](https://github.com/matrix-org/matrix-spec-proposals/pull/4140) implementation to no longer cancel a user's own delayed state events with an event type & state key that match a more recent state event sent by that user. ([\#17810](https://github.com/element-hq/synapse/issues/17810))
+
+### Improved Documentation
+
+- Fixed a minor typo in the Synapse documentation. Contributed by @karuto12. ([\#18224](https://github.com/element-hq/synapse/issues/18224))
+
+### Internal Changes
+
+- Remove undocumented `SYNAPSE_USE_FROZEN_DICTS` environment variable. ([\#18123](https://github.com/element-hq/synapse/issues/18123))
+- Fix detection of workflow failures in the release script. ([\#18211](https://github.com/element-hq/synapse/issues/18211))
+- Add caching support to media endpoints. ([\#18235](https://github.com/element-hq/synapse/issues/18235))
+
+
+
+### Updates to locked dependencies
+
+* Bump anyhow from 1.0.96 to 1.0.97. ([\#18201](https://github.com/element-hq/synapse/issues/18201))
+* Bump bcrypt from 4.2.1 to 4.3.0. ([\#18207](https://github.com/element-hq/synapse/issues/18207))
+* Bump bytes from 1.10.0 to 1.10.1. ([\#18227](https://github.com/element-hq/synapse/issues/18227))
+* Bump http from 1.2.0 to 1.3.1. ([\#18245](https://github.com/element-hq/synapse/issues/18245))
+* Bump sentry-sdk from 2.19.2 to 2.22.0. ([\#18205](https://github.com/element-hq/synapse/issues/18205))
+* Bump serde from 1.0.218 to 1.0.219. ([\#18228](https://github.com/element-hq/synapse/issues/18228))
+* Bump serde_json from 1.0.139 to 1.0.140. ([\#18202](https://github.com/element-hq/synapse/issues/18202))
+* Bump ulid from 1.2.0 to 1.2.1. ([\#18246](https://github.com/element-hq/synapse/issues/18246))
+
+# Synapse 1.126.0 (2025-03-11)
+Administrators using the Debian/Ubuntu packages from `packages.matrix.org`, please check
+[the relevant section in the upgrade notes](https://github.com/element-hq/synapse/blob/release-v1.126/docs/upgrade.md#change-of-signing-key-expiry-date-for-the-debianubuntu-package-repository)
+as we have recently updated the expiry date on the repository's GPG signing key. The old version of the key will expire on `2025-03-15`.
+
+No significant changes since 1.126.0rc3.
+
+
+
+
+# Synapse 1.126.0rc3 (2025-03-07)
+
+### Bugfixes
+
+- Revert the background job to clear unreferenced state groups (that was introduced in v1.126.0rc1), due to [a suspected issue](https://github.com/element-hq/synapse/issues/18217) that causes increased disk usage. ([\#18222](https://github.com/element-hq/synapse/issues/18222))
+
+
+
+
+# Synapse 1.126.0rc2 (2025-03-05)
+
+
+### Internal Changes
+
+- Fix wheel building configuration in CI by installing libatomic1. ([\#18212](https://github.com/element-hq/synapse/issues/18212), [\#18213](https://github.com/element-hq/synapse/issues/18213))
+
+# Synapse 1.126.0rc1 (2025-03-04)
+
+Synapse 1.126.0rc1 was not fully released due to an error in CI.
+
+### Features
+
+- Define ratelimit configuration for delayed event management. ([\#18019](https://github.com/element-hq/synapse/issues/18019))
+- Add `form_secret_path` config option. ([\#18090](https://github.com/element-hq/synapse/issues/18090))
+- Add the `--no-secrets-in-config` command line option. ([\#18092](https://github.com/element-hq/synapse/issues/18092))
+- Add background job to clear unreferenced state groups. ([\#18154](https://github.com/element-hq/synapse/issues/18154))
+- Add support for specifying/overriding `id_token_signing_alg_values_supported` for an OpenID identity provider. ([\#18177](https://github.com/element-hq/synapse/issues/18177))
+- Add `worker_replication_secret_path` config option. ([\#18191](https://github.com/element-hq/synapse/issues/18191))
+- Add support for specifying/overriding `redirect_uri` in the authorization and token requests against an OpenID identity provider. ([\#18197](https://github.com/element-hq/synapse/issues/18197))
+
+### Bugfixes
+
+- Make sure we advertise registration as disabled when [MSC3861](https://github.com/matrix-org/matrix-spec-proposals/pull/3861) is enabled. ([\#17661](https://github.com/element-hq/synapse/issues/17661))
+- Prevent suspended users from sending encrypted messages. ([\#18157](https://github.com/element-hq/synapse/issues/18157))
+- Cleanup deleted state group references. ([\#18165](https://github.com/element-hq/synapse/issues/18165))
+- Fix [MSC4108 QR-code login](https://github.com/matrix-org/matrix-spec-proposals/pull/4108) not working with some reverse-proxy setups. ([\#18178](https://github.com/element-hq/synapse/issues/18178))
+- Support device IDs that can't be represented in a scope when delegating auth to Matrix Authentication Service 0.15.0+. ([\#18174](https://github.com/element-hq/synapse/issues/18174))
+
+### Updates to the Docker image
+
+- Speed up the building of the Docker image. ([\#18038](https://github.com/element-hq/synapse/issues/18038))
+
+### Improved Documentation
+
+- Move incorrectly placed version indicator in User Event Redaction Admin API docs. ([\#18152](https://github.com/element-hq/synapse/issues/18152))
+- Document suspension Admin API. ([\#18162](https://github.com/element-hq/synapse/issues/18162))
+
+### Deprecations and Removals
+
+- Disable room list publication by default. ([\#18175](https://github.com/element-hq/synapse/issues/18175))
+
+### Updates to locked dependencies
+
+* Bump anyhow from 1.0.95 to 1.0.96. ([\#18187](https://github.com/element-hq/synapse/issues/18187))
+* Bump authlib from 1.4.0 to 1.4.1. ([\#18190](https://github.com/element-hq/synapse/issues/18190))
+* Bump click from 8.1.7 to 8.1.8. ([\#18189](https://github.com/element-hq/synapse/issues/18189))
+* Bump log from 0.4.25 to 0.4.26. ([\#18184](https://github.com/element-hq/synapse/issues/18184))
+* Bump pyo3-log from 0.12.0 to 0.12.1. ([\#18046](https://github.com/element-hq/synapse/issues/18046))
+* Bump serde from 1.0.217 to 1.0.218. ([\#18183](https://github.com/element-hq/synapse/issues/18183))
+* Bump serde_json from 1.0.138 to 1.0.139. ([\#18186](https://github.com/element-hq/synapse/issues/18186))
+* Bump sigstore/cosign-installer from 3.8.0 to 3.8.1. ([\#18185](https://github.com/element-hq/synapse/issues/18185))
+* Bump types-psycopg2 from 2.9.21.20241019 to 2.9.21.20250121. ([\#18188](https://github.com/element-hq/synapse/issues/18188))
+
+
 # Synapse 1.125.0 (2025-02-25)
 
 No significant changes since 1.125.0rc1.
 
 
-
-
 # Synapse 1.125.0rc1 (2025-02-18)
 
 ### Features

Cargo.lock

@@ -13,9 +13,9 @@ dependencies = [
 
 [[package]]
 name = "anyhow"
-version = "1.0.96"
+version = "1.0.97"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6b964d184e89d9b6b67dd2715bc8e74cf3107fb2b529990c90cf517326150bf4"
+checksum = "dcfed56ad506cb2c684a14971b8861fdc3baaaae314b9e5f9bb532cbe3ba7a4f"
 
 [[package]]
 name = "arc-swap"
@@ -67,9 +67,9 @@ checksum = "79296716171880943b8470b5f8d03aa55eb2e645a4874bdbb28adb49162e012c"
 
 [[package]]
 name = "bytes"
-version = "1.10.0"
+version = "1.10.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f61dac84819c6588b558454b194026eb1f09c293b9036ae9b159e74e73ab6cf9"
+checksum = "d71b6127be86fdcfddb610f7182ac57211d4b18a3e9c82eb2d17662f2227ad6a"
 
 [[package]]
 name = "cfg-if"
@@ -173,9 +173,9 @@ checksum = "7f24254aa9a54b5c858eaee2f5bccdb46aaf0e486a595ed5fd8f86ba55232a70"
 
 [[package]]
 name = "http"
-version = "1.2.0"
+version = "1.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f16ca2af56261c99fba8bac40a10251ce8188205a4c448fbb745a2e4daa76fea"
+checksum = "f4a85d31aea989eead29a3aaf9e1115a180df8282431156e533de47660892565"
 dependencies = [
  "bytes",
  "fnv",
@@ -223,9 +223,9 @@ checksum = "ae743338b92ff9146ce83992f766a31066a91a8c84a45e0e9f21e7cf6de6d346"
 
 [[package]]
 name = "log"
-version = "0.4.26"
+version = "0.4.27"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "30bde2b3dc3671ae49d8e2e9f044c7c005836e7a023ee57cffa25ab82764bb9e"
+checksum = "13dc2df351e3202783a1fe0d44375f7295ffb4049267b0f3018346dc122a1d94"
 
 [[package]]
 name = "memchr"
@@ -277,9 +277,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3"
-version = "0.23.4"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "57fe09249128b3173d092de9523eaa75136bf7ba85e0d69eca241c7939c933cc"
+checksum = "7778bffd85cf38175ac1f545509665d0b9b92a198ca7941f131f85f7a4f9a872"
 dependencies = [
  "anyhow",
  "cfg-if",
@@ -296,9 +296,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-build-config"
-version = "0.23.4"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1cd3927b5a78757a0d71aa9dff669f903b1eb64b54142a9bd9f757f8fde65fd7"
+checksum = "94f6cbe86ef3bf18998d9df6e0f3fc1050a8c5efa409bf712e661a4366e010fb"
 dependencies = [
  "once_cell",
  "target-lexicon",
@@ -306,9 +306,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-ffi"
-version = "0.23.4"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dab6bb2102bd8f991e7749f130a70d05dd557613e39ed2deeee8e9ca0c4d548d"
+checksum = "e9f1b4c431c0bb1c8fb0a338709859eed0d030ff6daa34368d3b152a63dfdd8d"
 dependencies = [
  "libc",
  "pyo3-build-config",
@@ -316,9 +316,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-log"
-version = "0.12.1"
+version = "0.12.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "be5bb22b77965a7b5394e9aae9897a0607b51df5167561ffc3b02643b4200bc7"
+checksum = "4b78e4983ba15bc62833a0e0941d965bc03690163f1127864f1408db25063466"
 dependencies = [
  "arc-swap",
  "log",
@@ -327,9 +327,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-macros"
-version = "0.23.4"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "91871864b353fd5ffcb3f91f2f703a22a9797c91b9ab497b1acac7b07ae509c7"
+checksum = "fbc2201328f63c4710f68abdf653c89d8dbc2858b88c5d88b0ff38a75288a9da"
 dependencies = [
  "proc-macro2",
  "pyo3-macros-backend",
@@ -339,9 +339,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-macros-backend"
-version = "0.23.4"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "43abc3b80bc20f3facd86cd3c60beed58c3e2aa26213f3cda368de39c60a27e4"
+checksum = "fca6726ad0f3da9c9de093d6f116a93c1a38e417ed73bf138472cf4064f72028"
 dependencies = [
  "heck",
  "proc-macro2",
@@ -437,18 +437,18 @@ checksum = "f3cb5ba0dc43242ce17de99c180e96db90b235b8a9fdc9543c96d2209116bd9f"
 
 [[package]]
 name = "serde"
-version = "1.0.218"
+version = "1.0.219"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e8dfc9d19bdbf6d17e22319da49161d5d0108e4188e8b680aef6299eed22df60"
+checksum = "5f0e2c6ed6606019b4e29e69dbaba95b11854410e5347d525002456dbbb786b6"
 dependencies = [
  "serde_derive",
 ]
 
 [[package]]
 name = "serde_derive"
-version = "1.0.218"
+version = "1.0.219"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f09503e191f4e797cb8aac08e9a4a4695c5edf6a2e70e376d961ddd5c969f82b"
+checksum = "5b0276cf7f2c73365f7157c8123c21cd9a50fbbd844757af28ca1f5925fc2a00"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -457,9 +457,9 @@ dependencies = [
 
 [[package]]
 name = "serde_json"
-version = "1.0.139"
+version = "1.0.140"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "44f86c3acccc9c65b153fe1b85a3be07fe5515274ec9f0653b4a0875731c72a6"
+checksum = "20068b6e96dc6c9bd23e01df8827e6c7e1f2fddd43c21810382803c136b99373"
 dependencies = [
  "itoa",
  "memchr",
@@ -544,9 +544,9 @@ checksum = "42ff0bf0c66b8238c6f3b578df37d0b7848e55df8577b3f74f92a69acceeb825"
 
 [[package]]
 name = "ulid"
-version = "1.2.0"
+version = "1.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ab82fc73182c29b02e2926a6df32f2241dbadb5cfc111fd595515b3598f46bb3"
+checksum = "470dbf6591da1b39d43c14523b2b469c86879a53e8b758c8e090a470fe7b1fbe"
 dependencies = [
  "rand",
  "web-time",

changelog.d/17661.bugfix

@@ -1 +0,0 @@
-Make sure we advertise registration as disabled when MSC3861 is enabled.

changelog.d/18019.feature

@@ -1 +0,0 @@
-Define ratelimit configuration for delayed event management.

changelog.d/18038.docker

@@ -1 +0,0 @@
-Speed up the building of the Docker image.

changelog.d/18046.misc

@@ -1 +0,0 @@
-Bump pyo3-log from 0.12.0 to 0.12.1.

changelog.d/18090.feature

@@ -1 +0,0 @@
-Add `form_secret_path` config option.

changelog.d/18092.feature

@@ -1 +0,0 @@
-Add the `--no-secrets-in-config` command line option.

changelog.d/18152.doc

@@ -1 +0,0 @@
-Move incorrectly placed version indicator in User Event Redaction Admin API docs.

changelog.d/18154.feature

@@ -1 +0,0 @@
-Add background job to clear unreferenced state groups.

changelog.d/18157.bugfix

@@ -1 +0,0 @@
-Prevent suspended users from sending encrypted messages.

changelog.d/18162.misc

@@ -1 +0,0 @@
-Document suspension Admin API.

changelog.d/18165.bugfix

@@ -1 +0,0 @@
-Cleanup deleted state group references.

changelog.d/18174.misc

@@ -1 +0,0 @@
-Support device IDs that can't be represented in a scope when delegating auth to Matrix Authentication Service 0.15.0+.

changelog.d/18175.misc

@@ -1 +0,0 @@
-Disable room list publication by default.

changelog.d/18177.feature

@@ -1 +0,0 @@
-Add support for specifying/overriding `id_token_signing_alg_values_supported` for an OpenID identity provider.

changelog.d/18178.bugfix

@@ -1 +0,0 @@
-Fix MSC4108 QR-code login not working with some reverse-proxy setups.

changelog.d/18191.feature

@@ -1 +0,0 @@
-Add `worker_replication_secret_path` config option.

changelog.d/18197.feature

@@ -1 +0,0 @@
-Add support for specifying/overriding `redirect_uri` in the authorization and token requests against an OpenID identity provider.

debian/build_virtualenv

@@ -35,7 +35,7 @@ TEMP_VENV="$(mktemp -d)"
 python3 -m venv "$TEMP_VENV"
 source "$TEMP_VENV/bin/activate"
 pip install -U pip
-pip install poetry==1.3.2
+pip install poetry==2.1.1 poetry-plugin-export==1.9.0
 poetry export \
     --extras all \
     --extras test \

debian/changelog

@@ -1,3 +1,58 @@
+matrix-synapse-py3 (1.128.0) stable; urgency=medium
+
+  * New Synapse release 1.128.0.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 08 Apr 2025 14:09:54 +0100
+
+matrix-synapse-py3 (1.128.0~rc1) stable; urgency=medium
+
+  * Update Poetry to 2.1.1.
+  * New synapse release 1.128.0rc1.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 01 Apr 2025 14:35:33 +0000
+
+matrix-synapse-py3 (1.127.1) stable; urgency=medium
+
+  * New Synapse release 1.127.1.
+
+ -- Synapse Packaging team <packages@matrix.org>  Wed, 26 Mar 2025 21:07:31 +0000
+
+matrix-synapse-py3 (1.127.0) stable; urgency=medium
+
+  * New Synapse release 1.127.0.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 25 Mar 2025 12:04:15 +0000
+
+matrix-synapse-py3 (1.127.0~rc1) stable; urgency=medium
+
+  * New Synapse release 1.127.0rc1.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 18 Mar 2025 13:30:05 +0000
+
+matrix-synapse-py3 (1.126.0) stable; urgency=medium
+
+  * New Synapse release 1.126.0.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 11 Mar 2025 13:11:29 +0000
+
+matrix-synapse-py3 (1.126.0~rc3) stable; urgency=medium
+
+  * New Synapse release 1.126.0rc3.
+
+ -- Synapse Packaging team <packages@matrix.org>  Fri, 07 Mar 2025 15:45:05 +0000
+
+matrix-synapse-py3 (1.126.0~rc2) stable; urgency=medium
+
+  * New Synapse release 1.126.0rc2.
+
+ -- Synapse Packaging team <packages@matrix.org>  Wed, 05 Mar 2025 14:29:12 +0000
+
+matrix-synapse-py3 (1.126.0~rc1) stable; urgency=medium
+
+  * New Synapse release 1.126.0rc1.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 04 Mar 2025 13:11:51 +0000
+
 matrix-synapse-py3 (1.125.0) stable; urgency=medium
 
   * New Synapse release 1.125.0.

docker/Dockerfile

@@ -22,7 +22,7 @@
 
 ARG DEBIAN_VERSION=bookworm
 ARG PYTHON_VERSION=3.12
-ARG POETRY_VERSION=1.8.3
+ARG POETRY_VERSION=2.1.1
 
 ###
 ### Stage 0: generate requirements.txt
@@ -56,7 +56,7 @@ ENV UV_LINK_MODE=copy
 ARG POETRY_VERSION
 RUN --mount=type=cache,target=/root/.cache/uv \
   if [ -z "$TEST_ONLY_IGNORE_POETRY_LOCKFILE" ]; then \
-    uvx --with poetry-plugin-export==1.8.0 \
+    uvx --with poetry-plugin-export==1.9.0 \
         poetry@${POETRY_VERSION} export --extras all -o /synapse/requirements.txt ${TEST_ONLY_SKIP_DEP_HASH_VERIFICATION:+--without-hashes}; \
   else \
     touch /synapse/requirements.txt; \
@@ -134,7 +134,6 @@ RUN \
   --mount=type=cache,target=/var/cache/apt,sharing=locked \
   --mount=type=cache,target=/var/lib/apt,sharing=locked \
   apt-get update -qq && \
-  apt-get install -y --no-install-recommends rsync && \
   apt-cache depends --recurse --no-recommends --no-suggests --no-conflicts --no-breaks --no-replaces --no-enhances --no-pre-depends \
       curl \
       gosu \
@@ -148,14 +147,10 @@ RUN \
   for arch in arm64 amd64; do \
     mkdir -p /tmp/debs-${arch} && \
     cd /tmp/debs-${arch} && \
-    apt-get download $(sed "s/$/:${arch}/" /tmp/pkg-list); \
+    apt-get -o APT::Architecture="${arch}" download $(cat /tmp/pkg-list); \
   done
 
 # Extract the debs for each architecture
-# On the runtime image, /lib is a symlink to /usr/lib, so we need to copy the
-# libraries to the right place, else the `COPY` won't work.
-# On amd64, we'll also have a /lib64 folder with ld-linux-x86-64.so.2, which is
-# already present in the runtime image.
 RUN \
   for arch in arm64 amd64; do \
     mkdir -p /install-${arch}/var/lib/dpkg/status.d/ && \
@@ -165,8 +160,6 @@ RUN \
       dpkg --ctrl-tarfile $deb | tar -Ox ./control > /install-${arch}/var/lib/dpkg/status.d/${package_name}; \
       dpkg --extract $deb /install-${arch}; \
     done; \
-    rsync -avr /install-${arch}/lib/ /install-${arch}/usr/lib; \
-    rm -rf /install-${arch}/lib /install-${arch}/lib64; \
   done
 
 
@@ -183,7 +176,14 @@ LABEL org.opencontainers.image.documentation='https://github.com/element-hq/syna
 LABEL org.opencontainers.image.source='https://github.com/element-hq/synapse.git'
 LABEL org.opencontainers.image.licenses='AGPL-3.0-or-later'
 
-COPY --from=runtime-deps /install-${TARGETARCH} /
+# On the runtime image, /lib is a symlink to /usr/lib, so we need to copy the
+# libraries to the right place, else the `COPY` won't work.
+# On amd64, we'll also have a /lib64 folder with ld-linux-x86-64.so.2, which is
+# already present in the runtime image.
+COPY --from=runtime-deps /install-${TARGETARCH}/lib /usr/lib
+COPY --from=runtime-deps /install-${TARGETARCH}/etc /etc
+COPY --from=runtime-deps /install-${TARGETARCH}/usr /usr
+COPY --from=runtime-deps /install-${TARGETARCH}/var /var
 COPY --from=builder /install /usr/local
 COPY ./docker/start.py /start.py
 COPY ./docker/conf /conf

docker/Dockerfile-workers

@@ -2,12 +2,13 @@
 
 ARG SYNAPSE_VERSION=latest
 ARG FROM=matrixdotorg/synapse:$SYNAPSE_VERSION
+ARG DEBIAN_VERSION=bookworm
 
 # first of all, we create a base image with an nginx which we can copy into the
 # target image. For repeated rebuilds, this is much faster than apt installing
 # each time.
 
-FROM docker.io/library/debian:bookworm-slim AS deps_base
+FROM docker.io/library/debian:${DEBIAN_VERSION}-slim AS deps_base
     RUN \
        --mount=type=cache,target=/var/cache/apt,sharing=locked \
        --mount=type=cache,target=/var/lib/apt,sharing=locked \
@@ -21,15 +22,20 @@ FROM docker.io/library/debian:bookworm-slim AS deps_base
 # which makes it much easier to copy (but we need to make sure we use an image
 # based on the same debian version as the synapse image, to make sure we get
 # the expected version of libc.
-FROM docker.io/library/redis:7-bookworm AS redis_base
+FROM docker.io/library/redis:7-${DEBIAN_VERSION} AS redis_base
 
 # now build the final image, based on the the regular Synapse docker image
 FROM $FROM
 
-    # Install supervisord with pip instead of apt, to avoid installing a second
+    # Install supervisord with uv pip instead of apt, to avoid installing a second
     # copy of python.
-    RUN --mount=type=cache,target=/root/.cache/pip \
-        pip install supervisor~=4.2
+    # --link-mode=copy silences a warning as uv isn't able to do hardlinks between its cache
+    # (mounted as --mount=type=cache) and the target directory.
+    RUN \
+         --mount=type=bind,from=ghcr.io/astral-sh/uv:0.6.8,source=/uv,target=/uv \
+         --mount=type=cache,target=/root/.cache/uv \
+        /uv pip install --link-mode=copy --prefix="/usr/local" supervisor~=4.2
+
     RUN mkdir -p /etc/supervisor/conf.d
 
     # Copy over redis and nginx

docker/complement/Dockerfile

@@ -9,6 +9,9 @@
 ARG SYNAPSE_VERSION=latest
 # This is an intermediate image, to be built locally (not pulled from a registry).
 ARG FROM=matrixdotorg/synapse-workers:$SYNAPSE_VERSION
+ARG DEBIAN_VERSION=bookworm
+
+FROM docker.io/library/postgres:13-${DEBIAN_VERSION} AS postgres_base
 
 FROM $FROM
 # First of all, we copy postgres server from the official postgres image,
@@ -20,8 +23,8 @@ FROM $FROM
 # the same debian version as Synapse's docker image (so the versions of the
 # shared libraries match).
 RUN adduser --system --uid 999 postgres --home /var/lib/postgresql
-COPY --from=docker.io/library/postgres:13-bookworm /usr/lib/postgresql /usr/lib/postgresql
-COPY --from=docker.io/library/postgres:13-bookworm /usr/share/postgresql /usr/share/postgresql
+COPY --from=postgres_base /usr/lib/postgresql /usr/lib/postgresql
+COPY --from=postgres_base /usr/share/postgresql /usr/share/postgresql
 RUN mkdir /var/run/postgresql && chown postgres /var/run/postgresql
 ENV PATH="${PATH}:/usr/lib/postgresql/13/bin"
 ENV PGDATA=/var/lib/postgresql/data

docker/complement/conf/start_for_complement.sh

@@ -5,12 +5,12 @@
 set -e
 
 echo "Complement Synapse launcher"
-echo "  Args: $@"
+echo "  Args: $*"
 echo "  Env: SYNAPSE_COMPLEMENT_DATABASE=$SYNAPSE_COMPLEMENT_DATABASE SYNAPSE_COMPLEMENT_USE_WORKERS=$SYNAPSE_COMPLEMENT_USE_WORKERS SYNAPSE_COMPLEMENT_USE_ASYNCIO_REACTOR=$SYNAPSE_COMPLEMENT_USE_ASYNCIO_REACTOR"
 
 function log {
     d=$(date +"%Y-%m-%d %H:%M:%S,%3N")
-    echo "$d $@"
+    echo "$d $*"
 }
 
 # Set the server name of the homeserver
@@ -131,4 +131,4 @@ export SYNAPSE_TLS_KEY=/conf/server.tls.key
 
 # Run the script that writes the necessary config files and starts supervisord, which in turn
 # starts everything else
-exec /configure_workers_and_start.py
+exec /configure_workers_and_start.py "$@"

docker/prefix-log

@@ -10,6 +10,9 @@
 # '-W interactive' is a `mawk` extension which disables buffering on stdout and sets line-buffered reads on
 # stdin. The effect is that the output is flushed after each line, rather than being batched, which helps reduce
 # confusion due to to interleaving of the different processes.
-exec 1> >(awk -W interactive '{print "'"${SUPERVISOR_PROCESS_NAME}"' | "$0 }' >&1)
-exec 2> >(awk -W interactive '{print "'"${SUPERVISOR_PROCESS_NAME}"' | "$0 }' >&2)
+prefixer() {
+    mawk -W interactive '{printf("%s | %s\n", ENVIRON["SUPERVISOR_PROCESS_NAME"], $0); fflush() }'
+}
+exec 1> >(prefixer)
+exec 2> >(prefixer >&2)
 exec "$@"

docs/admin_api/media_admin_api.md

@@ -46,6 +46,14 @@ to any local media, and any locally-cached copies of remote media.
 
 The media file itself (and any thumbnails) is not deleted from the server.
 
+Since Synapse 1.128.0, hashes of uploaded media are tracked. If this media
+is quarantined, Synapse will:
+
+ - Quarantine any media with a matching hash that has already been uploaded.
+ - Quarantine any future media.
+ - Quarantine any existing cached remote media.
+ - Quarantine any future remote media.
+
 ## Quarantining media by ID
 
 This API quarantines a single piece of local or remote media.

docs/development/dependencies.md

@@ -150,6 +150,28 @@ $ poetry shell
 $ poetry install --extras all
 ```
 
+If you want to go even further and remove the Poetry caches:
+
+```shell
+# Find your Poetry cache directory
+# Docs: https://github.com/python-poetry/poetry/blob/main/docs/configuration.md#cache-directory
+$ poetry config cache-dir
+
+# Remove packages from all cached repositories
+$ poetry cache clear --all .
+
+# Go completely nuclear and clear out everything Poetry cache related
+# including the wheel artifacts which is not covered by the above command
+# (see https://github.com/python-poetry/poetry/issues/10304)
+#
+# This is necessary in order to rebuild or fetch new wheels. For example, if you update
+# the `icu` library in on your system, you will need to rebuild the PyICU Python package
+# in order to incorporate the correct dynamically linked library locations otherwise you
+# will run into errors like: `ImportError: libicui18n.so.75: cannot open shared object file: No such file or directory`
+$ rm -rf $(poetry config cache-dir)
+```
+
+
 ## ...run a command in the `poetry` virtualenv?
 
 Use `poetry run cmd args` when you need the python virtualenv context.
@@ -187,7 +209,7 @@ useful.
 ## ...add a new dependency?
 
 Either:
-- manually update `pyproject.toml`; then `poetry lock --no-update`; or else
+- manually update `pyproject.toml`; then `poetry lock`; or else
 - `poetry add packagename`. See `poetry add --help`; note the `--dev`,
   `--extras` and `--optional` flags in particular.
 
@@ -202,12 +224,12 @@ poetry remove packagename
 ```
 
 ought to do the trick. Alternatively, manually update `pyproject.toml` and
-`poetry lock --no-update`. Include the updated `pyproject.toml` and `poetry.lock`
+`poetry lock`. Include the updated `pyproject.toml` and `poetry.lock`
 files in your commit.
 
 ## ...update the version range for an existing dependency?
 
-Best done by manually editing `pyproject.toml`, then `poetry lock --no-update`.
+Best done by manually editing `pyproject.toml`, then `poetry lock`.
 Include the updated `pyproject.toml` and `poetry.lock` in your commit.
 
 ## ...update a dependency in the locked environment?
@@ -233,7 +255,7 @@ poetry add packagename==1.2.3
 
 # Get poetry to recompute the content-hash of pyproject.toml without changing
 # the locked package versions.
-poetry lock --no-update
+poetry lock
 ```
 
 Either way, include the updated `poetry.lock` file in your commit.

docs/sso_mapping_providers.md

@@ -10,7 +10,7 @@ As an example, a SSO service may return the email address
 to turn that into a displayname when creating a Matrix user for this individual.
 It may choose `John Smith`, or `Smith, John [Example.com]` or any number of
 variations. As each Synapse configuration may want something different, this is
-where SAML mapping providers come into play.
+where SSO mapping providers come into play.
 
 SSO mapping providers are currently supported for OpenID and SAML SSO
 configurations. Please see the details below for how to implement your own.

docs/upgrade.md

@@ -137,6 +137,24 @@ room_list_publication_rules:
 
 [`room_list_publication_rules`]: usage/configuration/config_documentation.md#room_list_publication_rules
 
+## Change of signing key expiry date for the Debian/Ubuntu package repository
+
+Administrators using the Debian/Ubuntu packages from `packages.matrix.org`,
+please be aware that we have recently updated the expiry date on the repository's GPG signing key,
+but this change must be imported into your keyring.
+
+If you have the `matrix-org-archive-keyring` package installed and it updates before the current key expires, this should
+happen automatically.
+
+Otherwise, if you see an error similar to `The following signatures were invalid: EXPKEYSIG F473DD4473365DE1`, you
+will need to get a fresh copy of the keys. You can do so with:
+
+```sh
+sudo wget -O /usr/share/keyrings/matrix-org-archive-keyring.gpg https://packages.matrix.org/debian/matrix-org-archive-keyring.gpg
+```
+
+The old version of the key will expire on `2025-03-15`.
+
 # Upgrading to v1.122.0
 
 ## Dropping support for PostgreSQL 11 and 12

docs/usage/administration/admin_faq.md

@@ -160,7 +160,7 @@ Using the following curl command:
 ```console
 curl -H 'Authorization: Bearer <access-token>' -X DELETE https://matrix.org/_matrix/client/r0/directory/room/<room-alias>
 ```
-`<access-token>` - can be obtained in riot by looking in the riot settings, down the bottom is:
+`<access-token>` - can be obtained in element by looking in All settings, clicking Help & About and down the bottom is:
 Access Token:\<click to reveal\>
 
 `<room-alias>` - the room alias, eg. #my_room:matrix.org this possibly needs to be URL encoded also, for example  %23my_room%3Amatrix.org

docs/workers.md

@@ -255,7 +255,7 @@ information.
     ^/_matrix/client/(r0|v3|unstable)/keys/changes$
     ^/_matrix/client/(r0|v3|unstable)/keys/claim$
     ^/_matrix/client/(r0|v3|unstable)/room_keys/
-    ^/_matrix/client/(r0|v3|unstable)/keys/upload/
+    ^/_matrix/client/(r0|v3|unstable)/keys/upload$
 
     # Registration/login requests
     ^/_matrix/client/(api/v1|r0|v3|unstable)/login$

pyproject.toml

@@ -97,7 +97,7 @@ module-name = "synapse.synapse_rust"
 
 [tool.poetry]
 name = "matrix-synapse"
-version = "1.125.0"
+version = "1.128.0"
 description = "Homeserver for the Matrix decentralised comms protocol"
 authors = ["Matrix.org Team and Contributors <packages@matrix.org>"]
 license = "AGPL-3.0-or-later"
@@ -390,7 +390,7 @@ skip = "cp36* cp37* cp38* pp37* pp38* *-musllinux_i686 pp*aarch64 *-musllinux_aa
 #
 # We temporarily pin Rust to 1.82.0 to work around
 # https://github.com/element-hq/synapse/issues/17988
-before-all =  "curl https://sh.rustup.rs -sSf | sh -s -- --default-toolchain 1.82.0 -y --profile minimal"
+before-all =  "sh .ci/before_build_wheel.sh"
 environment= { PATH = "$PATH:$HOME/.cargo/bin" }
 
 # For some reason if we don't manually clean the build directory we

rust/Cargo.toml

@@ -30,7 +30,7 @@ http = "1.1.0"
 lazy_static = "1.4.0"
 log = "0.4.17"
 mime = "0.3.17"
-pyo3 = { version = "0.23.2", features = [
+pyo3 = { version = "0.23.5", features = [
     "macros",
     "anyhow",
     "abi3",

scripts-dev/release.py

@@ -592,7 +592,7 @@ def _wait_for_actions(gh_token: Optional[str]) -> None:
         if all(
             workflow["status"] != "in_progress" for workflow in resp["workflow_runs"]
         ):
-            success = (
+            success = all(
                 workflow["status"] == "completed" for workflow in resp["workflow_runs"]
             )
             if success:

synapse/_scripts/synapse_port_db.py

@@ -128,6 +128,7 @@ BOOLEAN_COLUMNS = {
     "pushers": ["enabled"],
     "redactions": ["have_censored"],
     "remote_media_cache": ["authenticated"],
+    "room_memberships": ["participant"],
     "room_stats_state": ["is_federatable"],
     "rooms": ["is_public", "has_auth_chain_index"],
     "sliding_sync_joined_rooms": ["is_encrypted"],
@@ -194,7 +195,7 @@ IGNORED_TABLES = {
     # Porting the auto generated sequence in this table is non-trivial.
     # None of the entries in this list are mandatory for Synapse to keep working.
     # If state group disk space is an issue after the port, the
-    # `delete_unreferenced_state_groups_bg_update` background task can be run again.
+    # `mark_unreferenced_state_groups_for_deletion_bg_update` background task can be run again.
     "state_groups_pending_deletion",
     # We don't port these tables, as they're a faff and we can regenerate
     # them anyway.
@@ -226,7 +227,7 @@ IGNORED_BACKGROUND_UPDATES = {
     # Reapplying this background update to the postgres database is unnecessary after
     # already having waited for the SQLite database to complete all running background
     # updates.
-    "delete_unreferenced_state_groups_bg_update",
+    "mark_unreferenced_state_groups_for_deletion_bg_update",
 }
 
 

synapse/api/auth/msc3861_delegated.py

@@ -19,6 +19,7 @@
 #
 #
 import logging
+from dataclasses import dataclass
 from typing import TYPE_CHECKING, Any, Callable, Dict, List, Optional
 from urllib.parse import urlencode
 
@@ -47,6 +48,7 @@ from synapse.logging.context import make_deferred_yieldable
 from synapse.types import Requester, UserID, create_requester
 from synapse.util import json_decoder
 from synapse.util.caches.cached_call import RetryOnExceptionCachedCall
+from synapse.util.caches.response_cache import ResponseCache
 
 if TYPE_CHECKING:
     from synapse.rest.admin.experimental_features import ExperimentalFeature
@@ -76,6 +78,61 @@ def scope_to_list(scope: str) -> List[str]:
     return scope.strip().split(" ")
 
 
+@dataclass
+class IntrospectionResult:
+    _inner: IntrospectionToken
+
+    # when we retrieved this token,
+    # in milliseconds since the Unix epoch
+    retrieved_at_ms: int
+
+    def is_active(self, now_ms: int) -> bool:
+        if not self._inner.get("active"):
+            return False
+
+        expires_in = self._inner.get("expires_in")
+        if expires_in is None:
+            return True
+        if not isinstance(expires_in, int):
+            raise InvalidClientTokenError("token `expires_in` is not an int")
+
+        absolute_expiry_ms = expires_in * 1000 + self.retrieved_at_ms
+        return now_ms < absolute_expiry_ms
+
+    def get_scope_list(self) -> List[str]:
+        value = self._inner.get("scope")
+        if not isinstance(value, str):
+            return []
+        return scope_to_list(value)
+
+    def get_sub(self) -> Optional[str]:
+        value = self._inner.get("sub")
+        if not isinstance(value, str):
+            return None
+        return value
+
+    def get_username(self) -> Optional[str]:
+        value = self._inner.get("username")
+        if not isinstance(value, str):
+            return None
+        return value
+
+    def get_name(self) -> Optional[str]:
+        value = self._inner.get("name")
+        if not isinstance(value, str):
+            return None
+        return value
+
+    def get_device_id(self) -> Optional[str]:
+        value = self._inner.get("device_id")
+        if value is not None and not isinstance(value, str):
+            raise AuthError(
+                500,
+                "Invalid device ID in introspection result",
+            )
+        return value
+
+
 class PrivateKeyJWTWithKid(PrivateKeyJWT):  # type: ignore[misc]
     """An implementation of the private_key_jwt client auth method that includes a kid header.
 
@@ -121,6 +178,31 @@ class MSC3861DelegatedAuth(BaseAuth):
         self._hostname = hs.hostname
         self._admin_token: Callable[[], Optional[str]] = self._config.admin_token
 
+        # # Token Introspection Cache
+        # This remembers what users/devices are represented by which access tokens,
+        # in order to reduce overall system load:
+        # - on Synapse (as requests are relatively expensive)
+        # - on the network
+        # - on MAS
+        #
+        # Since there is no invalidation mechanism currently,
+        # the entries expire after 2 minutes.
+        # This does mean tokens can be treated as valid by Synapse
+        # for longer than reality.
+        #
+        # Ideally, tokens should logically be invalidated in the following circumstances:
+        # - If a session logout happens.
+        #   In this case, MAS will delete the device within Synapse
+        #   anyway and this is good enough as an invalidation.
+        # - If the client refreshes their token in MAS.
+        #   In this case, the device still exists and it's not the end of the world for
+        #   the old access token to continue working for a short time.
+        self._introspection_cache: ResponseCache[str] = ResponseCache(
+            self._clock,
+            "token_introspection",
+            timeout_ms=120_000,
+        )
+
         self._issuer_metadata = RetryOnExceptionCachedCall[OpenIDProviderMetadata](
             self._load_metadata
         )
@@ -193,7 +275,7 @@ class MSC3861DelegatedAuth(BaseAuth):
         metadata = await self._issuer_metadata.get()
         return metadata.get("introspection_endpoint")
 
-    async def _introspect_token(self, token: str) -> IntrospectionToken:
+    async def _introspect_token(self, token: str) -> IntrospectionResult:
         """
         Send a token to the introspection endpoint and returns the introspection response
 
@@ -266,7 +348,9 @@ class MSC3861DelegatedAuth(BaseAuth):
                 "The introspection endpoint returned an invalid JSON response."
             )
 
-        return IntrospectionToken(**resp)
+        return IntrospectionResult(
+            IntrospectionToken(**resp), retrieved_at_ms=self._clock.time_msec()
+        )
 
     async def is_server_admin(self, requester: Requester) -> bool:
         return "urn:synapse:admin:*" in requester.scope
@@ -344,7 +428,9 @@ class MSC3861DelegatedAuth(BaseAuth):
             )
 
         try:
-            introspection_result = await self._introspect_token(token)
+            introspection_result = await self._introspection_cache.wrap(
+                token, self._introspect_token, token
+            )
         except Exception:
             logger.exception("Failed to introspect token")
             raise SynapseError(503, "Unable to introspect the access token")
@@ -353,11 +439,11 @@ class MSC3861DelegatedAuth(BaseAuth):
 
         # TODO: introspection verification should be more extensive, especially:
         #   - verify the audience
-        if not introspection_result.get("active"):
+        if not introspection_result.is_active(self._clock.time_msec()):
             raise InvalidClientTokenError("Token is not active")
 
         # Let's look at the scope
-        scope: List[str] = scope_to_list(introspection_result.get("scope", ""))
+        scope: List[str] = introspection_result.get_scope_list()
 
         # Determine type of user based on presence of particular scopes
         has_user_scope = SCOPE_MATRIX_API in scope
@@ -367,7 +453,7 @@ class MSC3861DelegatedAuth(BaseAuth):
             raise InvalidClientTokenError("No scope in token granting user rights")
 
         # Match via the sub claim
-        sub: Optional[str] = introspection_result.get("sub")
+        sub: Optional[str] = introspection_result.get_sub()
         if sub is None:
             raise InvalidClientTokenError(
                 "Invalid sub claim in the introspection result"
@@ -381,7 +467,7 @@ class MSC3861DelegatedAuth(BaseAuth):
             # or the external_id was never recorded
 
             # TODO: claim mapping should be configurable
-            username: Optional[str] = introspection_result.get("username")
+            username: Optional[str] = introspection_result.get_username()
             if username is None or not isinstance(username, str):
                 raise AuthError(
                     500,
@@ -399,7 +485,7 @@ class MSC3861DelegatedAuth(BaseAuth):
 
                 # TODO: claim mapping should be configurable
                 # If present, use the name claim as the displayname
-                name: Optional[str] = introspection_result.get("name")
+                name: Optional[str] = introspection_result.get_name()
 
                 await self.store.register_user(
                     user_id=user_id.to_string(), create_profile_with_displayname=name
@@ -414,15 +500,8 @@ class MSC3861DelegatedAuth(BaseAuth):
 
         # MAS 0.15+ will give us the device ID as an explicit value for compatibility sessions
         # If present, we get it from here, if not we get it in thee scope
-        device_id = introspection_result.get("device_id")
-        if device_id is not None:
-            # We got the device ID explicitly, just sanity check that it's a string
-            if not isinstance(device_id, str):
-                raise AuthError(
-                    500,
-                    "Invalid device ID in introspection result",
-                )
-        else:
+        device_id = introspection_result.get_device_id()
+        if device_id is None:
             # Find device_ids in scope
             # We only allow a single device_id in the scope, so we find them all in the
             # scope list, and raise if there are more than one. The OIDC server should be

synapse/api/constants.py

@@ -29,8 +29,13 @@ from typing import Final
 # the max size of a (canonical-json-encoded) event
 MAX_PDU_SIZE = 65536
 
-# the "depth" field on events is limited to 2**63 - 1
-MAX_DEPTH = 2**63 - 1
+# Max/min size of ints in canonical JSON
+CANONICALJSON_MAX_INT = (2**53) - 1
+CANONICALJSON_MIN_INT = -CANONICALJSON_MAX_INT
+
+# the "depth" field on events is limited to the same as what
+# canonicaljson accepts
+MAX_DEPTH = CANONICALJSON_MAX_INT
 
 # the maximum length for a room alias is 255 characters
 MAX_ALIAS_LENGTH = 255

synapse/events/__init__.py

@@ -22,7 +22,6 @@
 
 import abc
 import collections.abc
-import os
 from typing import (
     TYPE_CHECKING,
     Any,
@@ -48,21 +47,21 @@ from synapse.synapse_rust.events import EventInternalMetadata
 from synapse.types import JsonDict, StrCollection
 from synapse.util.caches import intern_dict
 from synapse.util.frozenutils import freeze
-from synapse.util.stringutils import strtobool
 
 if TYPE_CHECKING:
     from synapse.events.builder import EventBuilder
 
-# Whether we should use frozen_dict in FrozenEvent. Using frozen_dicts prevents
-# bugs where we accidentally share e.g. signature dicts. However, converting a
-# dict to frozen_dicts is expensive.
-#
-# NOTE: This is overridden by the configuration by the Synapse worker apps, but
-# for the sake of tests, it is set here while it cannot be configured on the
-# homeserver object itself.
 
-USE_FROZEN_DICTS = strtobool(os.environ.get("SYNAPSE_USE_FROZEN_DICTS", "0"))
+USE_FROZEN_DICTS = False
+"""
+Whether we should use frozen_dict in FrozenEvent. Using frozen_dicts prevents
+bugs where we accidentally share e.g. signature dicts. However, converting a
+dict to frozen_dicts is expensive.
 
+NOTE: This is overridden by the configuration by the Synapse worker apps, but
+for the sake of tests, it is set here because it cannot be configured on the
+homeserver object itself.
+"""
 
 T = TypeVar("T")
 

synapse/events/utils.py

@@ -40,6 +40,8 @@ import attr
 from canonicaljson import encode_canonical_json
 
 from synapse.api.constants import (
+    CANONICALJSON_MAX_INT,
+    CANONICALJSON_MIN_INT,
     MAX_PDU_SIZE,
     EventContentFields,
     EventTypes,
@@ -61,9 +63,6 @@ SPLIT_FIELD_REGEX = re.compile(r"\\*\.")
 # Find escaped characters, e.g. those with a \ in front of them.
 ESCAPE_SEQUENCE_PATTERN = re.compile(r"\\(.)")
 
-CANONICALJSON_MAX_INT = (2**53) - 1
-CANONICALJSON_MIN_INT = -CANONICALJSON_MAX_INT
-
 
 # Module API callback that allows adding fields to the unsigned section of
 # events that are sent to clients.

synapse/events/validator.py

@@ -86,9 +86,7 @@ class EventValidator:
 
         # Depending on the room version, ensure the data is spec compliant JSON.
         if event.room_version.strict_canonicaljson:
-            # Note that only the client controlled portion of the event is
-            # checked, since we trust the portions of the event we created.
-            validate_canonicaljson(event.content)
+            validate_canonicaljson(event.get_pdu_json())
 
         if event.type == EventTypes.Aliases:
             if "aliases" in event.content:

synapse/federation/federation_base.py

@@ -20,7 +20,7 @@
 #
 #
 import logging
-from typing import TYPE_CHECKING, Awaitable, Callable, Optional
+from typing import TYPE_CHECKING, Awaitable, Callable, List, Optional, Sequence
 
 from synapse.api.constants import MAX_DEPTH, EventContentFields, EventTypes, Membership
 from synapse.api.errors import Codes, SynapseError
@@ -29,6 +29,7 @@ from synapse.crypto.event_signing import check_event_content_hash
 from synapse.crypto.keyring import Keyring
 from synapse.events import EventBase, make_event_from_dict
 from synapse.events.utils import prune_event, validate_canonicaljson
+from synapse.federation.units import filter_pdus_for_valid_depth
 from synapse.http.servlet import assert_params_in_dict
 from synapse.logging.opentracing import log_kv, trace
 from synapse.types import JsonDict, get_domain_from_id
@@ -267,6 +268,15 @@ def _is_invite_via_3pid(event: EventBase) -> bool:
     )
 
 
+def parse_events_from_pdu_json(
+    pdus_json: Sequence[JsonDict], room_version: RoomVersion
+) -> List[EventBase]:
+    return [
+        event_from_pdu_json(pdu_json, room_version)
+        for pdu_json in filter_pdus_for_valid_depth(pdus_json)
+    ]
+
+
 def event_from_pdu_json(pdu_json: JsonDict, room_version: RoomVersion) -> EventBase:
     """Construct an EventBase from an event json received over federation
 

synapse/federation/federation_client.py

@@ -68,6 +68,7 @@ from synapse.federation.federation_base import (
     FederationBase,
     InvalidEventSignatureError,
     event_from_pdu_json,
+    parse_events_from_pdu_json,
 )
 from synapse.federation.transport.client import SendJoinResponse
 from synapse.http.client import is_unknown_endpoint
@@ -349,7 +350,7 @@ class FederationClient(FederationBase):
 
         room_version = await self.store.get_room_version(room_id)
 
-        pdus = [event_from_pdu_json(p, room_version) for p in transaction_data_pdus]
+        pdus = parse_events_from_pdu_json(transaction_data_pdus, room_version)
 
         # Check signatures and hash of pdus, removing any from the list that fail checks
         pdus[:] = await self._check_sigs_and_hash_for_pulled_events_and_fetch(
@@ -393,9 +394,7 @@ class FederationClient(FederationBase):
             transaction_data,
         )
 
-        pdu_list: List[EventBase] = [
-            event_from_pdu_json(p, room_version) for p in transaction_data["pdus"]
-        ]
+        pdu_list = parse_events_from_pdu_json(transaction_data["pdus"], room_version)
 
         if pdu_list and pdu_list[0]:
             pdu = pdu_list[0]
@@ -809,7 +808,7 @@ class FederationClient(FederationBase):
 
         room_version = await self.store.get_room_version(room_id)
 
-        auth_chain = [event_from_pdu_json(p, room_version) for p in res["auth_chain"]]
+        auth_chain = parse_events_from_pdu_json(res["auth_chain"], room_version)
 
         signed_auth = await self._check_sigs_and_hash_for_pulled_events_and_fetch(
             destination, auth_chain, room_version=room_version
@@ -1529,9 +1528,7 @@ class FederationClient(FederationBase):
 
             room_version = await self.store.get_room_version(room_id)
 
-            events = [
-                event_from_pdu_json(e, room_version) for e in content.get("events", [])
-            ]
+            events = parse_events_from_pdu_json(content.get("events", []), room_version)
 
             signed_events = await self._check_sigs_and_hash_for_pulled_events_and_fetch(
                 destination, events, room_version=room_version

synapse/federation/federation_server.py

@@ -66,7 +66,7 @@ from synapse.federation.federation_base import (
     event_from_pdu_json,
 )
 from synapse.federation.persistence import TransactionActions
-from synapse.federation.units import Edu, Transaction
+from synapse.federation.units import Edu, Transaction, serialize_and_filter_pdus
 from synapse.handlers.worker_lock import NEW_EVENT_DURING_PURGE_LOCK_NAME
 from synapse.http.servlet import assert_params_in_dict
 from synapse.logging.context import (
@@ -469,7 +469,12 @@ class FederationServer(FederationBase):
                 logger.info("Ignoring PDU: %s", e)
                 continue
 
-            event = event_from_pdu_json(p, room_version)
+            try:
+                event = event_from_pdu_json(p, room_version)
+            except SynapseError as e:
+                logger.info("Ignoring PDU for failing to deserialize: %s", e)
+                continue
+
             pdus_by_room.setdefault(room_id, []).append(event)
 
             if event.origin_server_ts > newest_pdu_ts:
@@ -636,8 +641,8 @@ class FederationServer(FederationBase):
         )
 
         return {
-            "pdus": [pdu.get_pdu_json() for pdu in pdus],
-            "auth_chain": [pdu.get_pdu_json() for pdu in auth_chain],
+            "pdus": serialize_and_filter_pdus(pdus),
+            "auth_chain": serialize_and_filter_pdus(auth_chain),
         }
 
     async def on_pdu_request(
@@ -761,8 +766,8 @@ class FederationServer(FederationBase):
         event_json = event.get_pdu_json(time_now)
         resp = {
             "event": event_json,
-            "state": [p.get_pdu_json(time_now) for p in state_events],
-            "auth_chain": [p.get_pdu_json(time_now) for p in auth_chain_events],
+            "state": serialize_and_filter_pdus(state_events, time_now),
+            "auth_chain": serialize_and_filter_pdus(auth_chain_events, time_now),
             "members_omitted": caller_supports_partial_state,
         }
 
@@ -1005,7 +1010,7 @@ class FederationServer(FederationBase):
 
             time_now = self._clock.time_msec()
             auth_pdus = await self.handler.on_event_auth(event_id)
-            res = {"auth_chain": [a.get_pdu_json(time_now) for a in auth_pdus]}
+            res = {"auth_chain": serialize_and_filter_pdus(auth_pdus, time_now)}
         return 200, res
 
     async def on_query_client_keys(
@@ -1090,7 +1095,7 @@ class FederationServer(FederationBase):
 
             time_now = self._clock.time_msec()
 
-        return {"events": [ev.get_pdu_json(time_now) for ev in missing_events]}
+        return {"events": serialize_and_filter_pdus(missing_events, time_now)}
 
     async def on_openid_userinfo(self, token: str) -> Optional[str]:
         ts_now_ms = self._clock.time_msec()

synapse/federation/units.py

@@ -24,10 +24,12 @@ server protocol.
 """
 
 import logging
-from typing import List, Optional
+from typing import List, Optional, Sequence
 
 import attr
 
+from synapse.api.constants import CANONICALJSON_MAX_INT, CANONICALJSON_MIN_INT
+from synapse.events import EventBase
 from synapse.types import JsonDict
 
 logger = logging.getLogger(__name__)
@@ -104,8 +106,28 @@ class Transaction:
         result = {
             "origin": self.origin,
             "origin_server_ts": self.origin_server_ts,
-            "pdus": self.pdus,
+            "pdus": filter_pdus_for_valid_depth(self.pdus),
         }
         if self.edus:
             result["edus"] = self.edus
         return result
+
+
+def filter_pdus_for_valid_depth(pdus: Sequence[JsonDict]) -> List[JsonDict]:
+    filtered_pdus = []
+    for pdu in pdus:
+        # Drop PDUs that have a depth that is outside of the range allowed
+        # by canonical json.
+        if (
+            "depth" in pdu
+            and CANONICALJSON_MIN_INT <= pdu["depth"] <= CANONICALJSON_MAX_INT
+        ):
+            filtered_pdus.append(pdu)
+
+    return filtered_pdus
+
+
+def serialize_and_filter_pdus(
+    pdus: Sequence[EventBase], time_now: Optional[int] = None
+) -> List[JsonDict]:
+    return filter_pdus_for_valid_depth([pdu.get_pdu_json(time_now) for pdu in pdus])

synapse/handlers/delayed_events.py

@@ -191,18 +191,36 @@ class DelayedEventsHandler:
 
     async def _handle_state_deltas(self, deltas: List[StateDelta]) -> None:
         """
-        Process current state deltas to cancel pending delayed events
+        Process current state deltas to cancel other users' pending delayed events
         that target the same state.
         """
         for delta in deltas:
+            if delta.event_id is None:
+                logger.debug(
+                    "Not handling delta for deleted state: %r %r",
+                    delta.event_type,
+                    delta.state_key,
+                )
+                continue
+
             logger.debug(
                 "Handling: %r %r, %s", delta.event_type, delta.state_key, delta.event_id
             )
 
+            event = await self._store.get_event(
+                delta.event_id, check_room_id=delta.room_id
+            )
+            sender = UserID.from_string(event.sender)
+
             next_send_ts = await self._store.cancel_delayed_state_events(
                 room_id=delta.room_id,
                 event_type=delta.event_type,
                 state_key=delta.state_key,
+                not_from_localpart=(
+                    sender.localpart
+                    if sender.domain == self._config.server.server_name
+                    else ""
+                ),
             )
 
             if self._next_send_ts_changed(next_send_ts):

synapse/handlers/message.py

@@ -1462,6 +1462,12 @@ class EventCreationHandler:
                     )
                     return prev_event
 
+            if not event.is_state() and event.type in [
+                EventTypes.Message,
+                EventTypes.Encrypted,
+            ]:
+                await self.store.set_room_participation(event.user_id, event.room_id)
+
             if event.internal_metadata.is_out_of_band_membership():
                 # the only sort of out-of-band-membership events we expect to see here are
                 # invite rejections and rescinded knocks that we have generated ourselves.

synapse/media/_base.py

@@ -118,6 +118,9 @@ DEFAULT_MAX_TIMEOUT_MS = 20_000
 # Maximum allowed timeout_ms for download and thumbnail requests
 MAXIMUM_ALLOWED_MAX_TIMEOUT_MS = 60_000
 
+# The ETag header value to use for immutable media. This can be anything.
+_IMMUTABLE_ETAG = "1"
+
 
 def respond_404(request: SynapseRequest) -> None:
     assert request.path is not None
@@ -224,12 +227,7 @@ def add_file_headers(
 
     request.setHeader(b"Content-Disposition", disposition.encode("ascii"))
 
-    # cache for at least a day.
-    # XXX: we might want to turn this off for data we don't want to
-    # recommend caching as it's sensitive or private - or at least
-    # select private. don't bother setting Expires as all our
-    # clients are smart enough to be happy with Cache-Control
-    request.setHeader(b"Cache-Control", b"public,max-age=86400,s-maxage=86400")
+    _add_cache_headers(request)
 
     if file_size is not None:
         request.setHeader(b"Content-Length", b"%d" % (file_size,))
@@ -240,6 +238,26 @@ def add_file_headers(
     request.setHeader(b"X-Robots-Tag", "noindex, nofollow, noarchive, noimageindex")
 
 
+def _add_cache_headers(request: Request) -> None:
+    """Adds the appropriate cache headers to the response"""
+
+    # Cache on the client for at least a day.
+    #
+    # We set this to "public,s-maxage=0,proxy-revalidate" to allow CDNs to cache
+    # the media, so long as they "revalidate" the media on every request. By
+    # revalidate, we mean send the request to Synapse with a `If-None-Match`
+    # header, to which Synapse can either respond with a 304 if the user is
+    # authenticated/authorized, or a 401/403 if they're not.
+    request.setHeader(
+        b"Cache-Control", b"public,max-age=86400,s-maxage=0,proxy-revalidate"
+    )
+
+    # Set an ETag header to allow requesters to use it in requests to check if
+    # the cache is still valid. Since media is immutable (though may be
+    # deleted), we just set this to a constant.
+    request.setHeader(b"ETag", _IMMUTABLE_ETAG)
+
+
 # separators as defined in RFC2616. SP and HT are handled separately.
 # see _can_encode_filename_as_token.
 _FILENAME_SEPARATOR_CHARS = {
@@ -336,13 +354,15 @@ async def respond_with_multipart_responder(
 
         from synapse.media.media_storage import MultipartFileConsumer
 
+        _add_cache_headers(request)
+
         # note that currently the json_object is just {}, this will change when linked media
         # is implemented
         multipart_consumer = MultipartFileConsumer(
             clock,
             request,
             media_type,
-            {},
+            {},  # Note: if we change this we need to change the returned ETag.
             disposition,
             media_length,
         )
@@ -419,6 +439,46 @@ async def respond_with_responder(
     finish_request(request)
 
 
+def respond_with_304(request: SynapseRequest) -> None:
+    request.setResponseCode(304)
+
+    # could alternatively use request.notifyFinish() and flip a flag when
+    # the Deferred fires, but since the flag is RIGHT THERE it seems like
+    # a waste.
+    if request._disconnected:
+        logger.warning(
+            "Not sending response to request %s, already disconnected.", request
+        )
+        return None
+
+    _add_cache_headers(request)
+
+    request.finish()
+
+
+def check_for_cached_entry_and_respond(request: SynapseRequest) -> bool:
+    """Check if the request has a conditional header that allows us to return a
+    304 Not Modified response, and if it does, return a 304 response.
+
+    This handles clients and intermediary proxies caching media.
+    This method assumes that the user has already been
+    authorised to request the media.
+
+    Returns True if we have responded."""
+
+    # We've checked the user has access to the media, so we now check if it
+    # is a "conditional request" and we can just return a `304 Not Modified`
+    # response. Since media is immutable (though may be deleted), we just
+    # check this is the expected constant.
+    etag = request.getHeader("If-None-Match")
+    if etag == _IMMUTABLE_ETAG:
+        # Return a `304 Not modified`.
+        respond_with_304(request)
+        return True
+
+    return False
+
+
 class Responder(ABC):
     """Represents a response that can be streamed to the requester.
 

synapse/media/media_repository.py

@@ -52,13 +52,18 @@ from synapse.media._base import (
     FileInfo,
     Responder,
     ThumbnailInfo,
+    check_for_cached_entry_and_respond,
     get_filename_from_headers,
     respond_404,
     respond_with_multipart_responder,
     respond_with_responder,
 )
 from synapse.media.filepath import MediaFilePaths
-from synapse.media.media_storage import MediaStorage
+from synapse.media.media_storage import (
+    MediaStorage,
+    SHA256TransparentIOReader,
+    SHA256TransparentIOWriter,
+)
 from synapse.media.storage_provider import StorageProviderWrapper
 from synapse.media.thumbnailer import Thumbnailer, ThumbnailError
 from synapse.media.url_previewer import UrlPreviewer
@@ -300,15 +305,26 @@ class MediaRepository:
             auth_user: The user_id of the uploader
         """
         file_info = FileInfo(server_name=None, file_id=media_id)
-        fname = await self.media_storage.store_file(content, file_info)
+        sha256reader = SHA256TransparentIOReader(content)
+        # This implements all of IO as it has a passthrough
+        fname = await self.media_storage.store_file(sha256reader.wrap(), file_info)
+        sha256 = sha256reader.hexdigest()
+        should_quarantine = await self.store.get_is_hash_quarantined(sha256)
         logger.info("Stored local media in file %r", fname)
 
+        if should_quarantine:
+            logger.warn(
+                "Media has been automatically quarantined as it matched existing quarantined media"
+            )
+
         await self.store.update_local_media(
             media_id=media_id,
             media_type=media_type,
             upload_name=upload_name,
             media_length=content_length,
             user_id=auth_user,
+            sha256=sha256,
+            quarantined_by="system" if should_quarantine else None,
         )
 
         try:
@@ -341,11 +357,19 @@ class MediaRepository:
         media_id = random_string(24)
 
         file_info = FileInfo(server_name=None, file_id=media_id)
-
-        fname = await self.media_storage.store_file(content, file_info)
+        # This implements all of IO as it has a passthrough
+        sha256reader = SHA256TransparentIOReader(content)
+        fname = await self.media_storage.store_file(sha256reader.wrap(), file_info)
+        sha256 = sha256reader.hexdigest()
+        should_quarantine = await self.store.get_is_hash_quarantined(sha256)
 
         logger.info("Stored local media in file %r", fname)
 
+        if should_quarantine:
+            logger.warn(
+                "Media has been automatically quarantined as it matched existing quarantined media"
+            )
+
         await self.store.store_local_media(
             media_id=media_id,
             media_type=media_type,
@@ -353,6 +377,9 @@ class MediaRepository:
             upload_name=upload_name,
             media_length=content_length,
             user_id=auth_user,
+            sha256=sha256,
+            # TODO: Better name?
+            quarantined_by="system" if should_quarantine else None,
         )
 
         try:
@@ -459,6 +486,11 @@ class MediaRepository:
 
         self.mark_recently_accessed(None, media_id)
 
+        # Once we've checked auth we can return early if the media is cached on
+        # the client
+        if check_for_cached_entry_and_respond(request):
+            return
+
         media_type = media_info.media_type
         if not media_type:
             media_type = "application/octet-stream"
@@ -538,6 +570,17 @@ class MediaRepository:
                 allow_authenticated,
             )
 
+        # Check if the media is cached on the client, if so return 304. We need
+        # to do this after we have fetched remote media, as we need it to do the
+        # auth.
+        if check_for_cached_entry_and_respond(request):
+            # We always need to use the responder.
+            if responder:
+                with responder:
+                    pass
+
+            return
+
         # We deliberately stream the file outside the lock
         if responder and media_info:
             upload_name = name if name else media_info.upload_name
@@ -739,11 +782,13 @@ class MediaRepository:
         file_info = FileInfo(server_name=server_name, file_id=file_id)
 
         async with self.media_storage.store_into_file(file_info) as (f, fname):
+            sha256writer = SHA256TransparentIOWriter(f)
             try:
                 length, headers = await self.client.download_media(
                     server_name,
                     media_id,
-                    output_stream=f,
+                    # This implements all of BinaryIO as it has a passthrough
+                    output_stream=sha256writer.wrap(),
                     max_size=self.max_upload_size,
                     max_timeout_ms=max_timeout_ms,
                     download_ratelimiter=download_ratelimiter,
@@ -808,6 +853,7 @@ class MediaRepository:
                 upload_name=upload_name,
                 media_length=length,
                 filesystem_id=file_id,
+                sha256=sha256writer.hexdigest(),
             )
 
         logger.info("Stored remote media in file %r", fname)
@@ -828,6 +874,7 @@ class MediaRepository:
             last_access_ts=time_now_ms,
             quarantined_by=None,
             authenticated=authenticated,
+            sha256=sha256writer.hexdigest(),
         )
 
     async def _federation_download_remote_file(
@@ -862,11 +909,13 @@ class MediaRepository:
         file_info = FileInfo(server_name=server_name, file_id=file_id)
 
         async with self.media_storage.store_into_file(file_info) as (f, fname):
+            sha256writer = SHA256TransparentIOWriter(f)
             try:
                 res = await self.client.federation_download_media(
                     server_name,
                     media_id,
-                    output_stream=f,
+                    # This implements all of BinaryIO as it has a passthrough
+                    output_stream=sha256writer.wrap(),
                     max_size=self.max_upload_size,
                     max_timeout_ms=max_timeout_ms,
                     download_ratelimiter=download_ratelimiter,
@@ -937,6 +986,7 @@ class MediaRepository:
                 upload_name=upload_name,
                 media_length=length,
                 filesystem_id=file_id,
+                sha256=sha256writer.hexdigest(),
             )
 
         logger.debug("Stored remote media in file %r", fname)
@@ -957,6 +1007,7 @@ class MediaRepository:
             last_access_ts=time_now_ms,
             quarantined_by=None,
             authenticated=authenticated,
+            sha256=sha256writer.hexdigest(),
         )
 
     def _get_thumbnail_requirements(

synapse/media/media_storage.py

@@ -19,6 +19,7 @@
 #
 #
 import contextlib
+import hashlib
 import json
 import logging
 import os
@@ -70,6 +71,88 @@ logger = logging.getLogger(__name__)
 CRLF = b"\r\n"
 
 
+class SHA256TransparentIOWriter:
+    """Will generate a SHA256 hash from a source stream transparently.
+
+    Args:
+        source: Source stream.
+    """
+
+    def __init__(self, source: BinaryIO):
+        self._hash = hashlib.sha256()
+        self._source = source
+
+    def write(self, buffer: Union[bytes, bytearray]) -> int:
+        """Wrapper for source.write()
+
+        Args:
+            buffer
+
+        Returns:
+            the value of source.write()
+        """
+        res = self._source.write(buffer)
+        self._hash.update(buffer)
+        return res
+
+    def hexdigest(self) -> str:
+        """The digest of the written or read value.
+
+        Returns:
+            The digest in hex formaat.
+        """
+        return self._hash.hexdigest()
+
+    def wrap(self) -> BinaryIO:
+        # This class implements a subset the IO interface and passes through everything else via __getattr__
+        return cast(BinaryIO, self)
+
+    # Passthrough any other calls
+    def __getattr__(self, attr_name: str) -> Any:
+        return getattr(self._source, attr_name)
+
+
+class SHA256TransparentIOReader:
+    """Will generate a SHA256 hash from a source stream transparently.
+
+    Args:
+        source: Source IO stream.
+    """
+
+    def __init__(self, source: IO):
+        self._hash = hashlib.sha256()
+        self._source = source
+
+    def read(self, n: int = -1) -> bytes:
+        """Wrapper for source.read()
+
+        Args:
+            n
+
+        Returns:
+            the value of source.read()
+        """
+        bytes = self._source.read(n)
+        self._hash.update(bytes)
+        return bytes
+
+    def hexdigest(self) -> str:
+        """The digest of the written or read value.
+
+        Returns:
+            The digest in hex formaat.
+        """
+        return self._hash.hexdigest()
+
+    def wrap(self) -> IO:
+        # This class implements a subset the IO interface and passes through everything else via __getattr__
+        return cast(IO, self)
+
+    # Passthrough any other calls
+    def __getattr__(self, attr_name: str) -> Any:
+        return getattr(self._source, attr_name)
+
+
 class MediaStorage:
     """Responsible for storing/fetching files from local sources.
 
@@ -107,7 +190,6 @@ class MediaStorage:
         Returns:
             the file path written to in the primary media store
         """
-
         async with self.store_into_file(file_info) as (f, fname):
             # Write to the main media repository
             await self.write_to_file(source, f)

synapse/media/thumbnailer.py

@@ -34,6 +34,7 @@ from synapse.logging.opentracing import trace
 from synapse.media._base import (
     FileInfo,
     ThumbnailInfo,
+    check_for_cached_entry_and_respond,
     respond_404,
     respond_with_file,
     respond_with_multipart_responder,
@@ -294,6 +295,11 @@ class ThumbnailProvider:
             if media_info.authenticated:
                 raise NotFoundError()
 
+        # Once we've checked auth we can return early if the media is cached on
+        # the client
+        if check_for_cached_entry_and_respond(request):
+            return
+
         thumbnail_infos = await self.store.get_local_media_thumbnails(media_id)
         await self._select_and_respond_with_thumbnail(
             request,
@@ -334,6 +340,11 @@ class ThumbnailProvider:
             if media_info.authenticated:
                 raise NotFoundError()
 
+        # Once we've checked auth we can return early if the media is cached on
+        # the client
+        if check_for_cached_entry_and_respond(request):
+            return
+
         thumbnail_infos = await self.store.get_local_media_thumbnails(media_id)
         for info in thumbnail_infos:
             t_w = info.width == desired_width
@@ -431,6 +442,10 @@ class ThumbnailProvider:
                 respond_404(request)
                 return
 
+        # Check if the media is cached on the client, if so return 304.
+        if check_for_cached_entry_and_respond(request):
+            return
+
         thumbnail_infos = await self.store.get_remote_media_thumbnails(
             server_name, media_id
         )
@@ -510,6 +525,10 @@ class ThumbnailProvider:
             if media_info.authenticated:
                 raise NotFoundError()
 
+        # Check if the media is cached on the client, if so return 304.
+        if check_for_cached_entry_and_respond(request):
+            return
+
         thumbnail_infos = await self.store.get_remote_media_thumbnails(
             server_name, media_id
         )

synapse/storage/controllers/purge_events.py

@@ -25,6 +25,7 @@ from typing import (
     TYPE_CHECKING,
     Collection,
     Mapping,
+    Optional,
     Set,
 )
 
@@ -52,7 +53,7 @@ class PurgeEventsStorageController:
             )
 
         self.stores.state.db_pool.updates.register_background_update_handler(
-            _BackgroundUpdates.DELETE_UNREFERENCED_STATE_GROUPS_BG_UPDATE,
+            _BackgroundUpdates.MARK_UNREFERENCED_STATE_GROUPS_FOR_DELETION_BG_UPDATE,
             self._background_delete_unrefereneced_state_groups,
         )
 
@@ -92,6 +93,69 @@ class PurgeEventsStorageController:
                 sg_to_delete
             )
 
+    async def _find_unreferenced_groups(
+        self,
+        state_groups: Collection[int],
+    ) -> Set[int]:
+        """Used when purging history to figure out which state groups can be
+        deleted.
+
+        Args:
+            state_groups: Set of state groups referenced by events
+                that are going to be deleted.
+
+        Returns:
+            The set of state groups that can be deleted.
+        """
+        # Set of events that we have found to be referenced by events
+        referenced_groups = set()
+
+        # Set of state groups we've already seen
+        state_groups_seen = set(state_groups)
+
+        # Set of state groups to handle next.
+        next_to_search = set(state_groups)
+        while next_to_search:
+            # We bound size of groups we're looking up at once, to stop the
+            # SQL query getting too big
+            if len(next_to_search) < 100:
+                current_search = next_to_search
+                next_to_search = set()
+            else:
+                current_search = set(itertools.islice(next_to_search, 100))
+                next_to_search -= current_search
+
+            referenced = await self.stores.main.get_referenced_state_groups(
+                current_search
+            )
+            referenced_groups |= referenced
+
+            # We don't continue iterating up the state group graphs for state
+            # groups that are referenced.
+            current_search -= referenced
+
+            edges = await self.stores.state.get_previous_state_groups(current_search)
+
+            prevs = set(edges.values())
+            # We don't bother re-handling groups we've already seen
+            prevs -= state_groups_seen
+            next_to_search |= prevs
+            state_groups_seen |= prevs
+
+            # We also check to see if anything referencing the state groups are
+            # also unreferenced. This helps ensure that we delete unreferenced
+            # state groups, if we don't then we will de-delta them when we
+            # delete the other state groups leading to increased DB usage.
+            next_edges = await self.stores.state.get_next_state_groups(current_search)
+            nexts = set(next_edges.keys())
+            nexts -= state_groups_seen
+            next_to_search |= nexts
+            state_groups_seen |= nexts
+
+        to_delete = state_groups_seen - referenced_groups
+
+        return to_delete
+
     @wrap_as_background_process("_delete_state_groups_loop")
     async def _delete_state_groups_loop(self) -> None:
         """Background task that deletes any state groups that may be pending
@@ -160,47 +224,47 @@ class PurgeEventsStorageController:
         """This background update will slowly delete any unreferenced state groups"""
 
         last_checked_state_group = progress.get("last_checked_state_group")
-        max_state_group = progress.get("max_state_group")
 
-        if last_checked_state_group is None or max_state_group is None:
+        if last_checked_state_group is None:
             # This is the first run.
-            last_checked_state_group = 0
-
-            max_state_group = await self.stores.state.db_pool.simple_select_one_onecol(
-                table="state_groups",
-                keyvalues={},
-                retcol="MAX(id)",
-                allow_none=True,
-                desc="get_max_state_group",
+            last_checked_state_group = (
+                await self.stores.state.db_pool.simple_select_one_onecol(
+                    table="state_groups",
+                    keyvalues={},
+                    retcol="MAX(id)",
+                    allow_none=True,
+                    desc="get_max_state_group",
+                )
             )
-            if max_state_group is None:
+            if last_checked_state_group is None:
                 # There are no state groups so the background process is finished.
                 await self.stores.state.db_pool.updates._end_background_update(
-                    _BackgroundUpdates.DELETE_UNREFERENCED_STATE_GROUPS_BG_UPDATE
+                    _BackgroundUpdates.MARK_UNREFERENCED_STATE_GROUPS_FOR_DELETION_BG_UPDATE
                 )
                 return batch_size
+            last_checked_state_group += 1
 
         (
             last_checked_state_group,
             final_batch,
         ) = await self._delete_unreferenced_state_groups_batch(
-            last_checked_state_group, batch_size, max_state_group
+            last_checked_state_group,
+            batch_size,
         )
 
         if not final_batch:
             # There are more state groups to check.
             progress = {
                 "last_checked_state_group": last_checked_state_group,
-                "max_state_group": max_state_group,
             }
             await self.stores.state.db_pool.updates._background_update_progress(
-                _BackgroundUpdates.DELETE_UNREFERENCED_STATE_GROUPS_BG_UPDATE,
+                _BackgroundUpdates.MARK_UNREFERENCED_STATE_GROUPS_FOR_DELETION_BG_UPDATE,
                 progress,
             )
         else:
             # This background process is finished.
             await self.stores.state.db_pool.updates._end_background_update(
-                _BackgroundUpdates.DELETE_UNREFERENCED_STATE_GROUPS_BG_UPDATE
+                _BackgroundUpdates.MARK_UNREFERENCED_STATE_GROUPS_FOR_DELETION_BG_UPDATE
             )
 
         return batch_size
@@ -209,11 +273,9 @@ class PurgeEventsStorageController:
         self,
         last_checked_state_group: int,
         batch_size: int,
-        max_state_group: int,
     ) -> tuple[int, bool]:
         """Looks for unreferenced state groups starting from the last state group
-        checked, and any state groups which would become unreferenced if a state group
-        was deleted, and marks them for deletion.
+        checked and marks them for deletion.
 
         Args:
             last_checked_state_group: The last state group that was checked.
@@ -223,35 +285,15 @@ class PurgeEventsStorageController:
             (last_checked_state_group, final_batch)
         """
 
-        # Look for state groups that can be cleaned up.
-        def get_next_state_groups_txn(txn: LoggingTransaction) -> Set[int]:
-            state_group_sql = "SELECT id FROM state_groups WHERE ? < id AND id <= ? ORDER BY id LIMIT ?"
-            txn.execute(
-                state_group_sql, (last_checked_state_group, max_state_group, batch_size)
-            )
-
-            next_set = {row[0] for row in txn}
-
-            return next_set
-
-        next_set = await self.stores.state.db_pool.runInteraction(
-            "get_next_state_groups", get_next_state_groups_txn
+        # Find all state groups that can be deleted if any of the original set are deleted.
+        (
+            to_delete,
+            last_checked_state_group,
+            final_batch,
+        ) = await self._find_unreferenced_groups_for_background_deletion(
+            last_checked_state_group, batch_size
         )
 
-        final_batch = False
-        if len(next_set) < batch_size:
-            final_batch = True
-        else:
-            last_checked_state_group = max(next_set)
-
-        if len(next_set) == 0:
-            return last_checked_state_group, final_batch
-
-        # Find all state groups that can be deleted if the original set is deleted.
-        # This set includes the original set, as well as any state groups that would
-        # become unreferenced upon deleting the original set.
-        to_delete = await self._find_unreferenced_groups(next_set)
-
         if len(to_delete) == 0:
             return last_checked_state_group, final_batch
 
@@ -261,65 +303,146 @@ class PurgeEventsStorageController:
 
         return last_checked_state_group, final_batch
 
-    async def _find_unreferenced_groups(
+    async def _find_unreferenced_groups_for_background_deletion(
         self,
-        state_groups: Collection[int],
-    ) -> Set[int]:
-        """Used when purging history to figure out which state groups can be
-        deleted.
+        last_checked_state_group: int,
+        batch_size: int,
+    ) -> tuple[Set[int], int, bool]:
+        """Used when deleting unreferenced state groups in the background to figure out
+        which state groups can be deleted.
+        To avoid increased DB usage due to de-deltaing state groups, this returns only
+        state groups which are free standing (ie. no shared edges with referenced groups) or
+        state groups which do not share edges which result in a future referenced group.
+
+        The following scenarios outline the possibilities based on state group data in
+        the DB.
+
+        ie. Free standing -> state groups 1-N would be returned:
+            SG_1
+            |
+            ...
+            |
+            SG_N
+
+        ie. Previous reference -> state groups 2-N would be returned:
+            SG_1 <- referenced by event
+            |
+            SG_2
+            |
+            ...
+            |
+            SG_N
+
+        ie. Future reference -> none of the following state groups would be returned:
+            SG_1
+            |
+            SG_2
+            |
+            ...
+            |
+            SG_N <- referenced by event
 
         Args:
-            state_groups: Set of state groups referenced by events
-                that are going to be deleted.
+            last_checked_state_group: The last state group that was checked.
+            batch_size: How many state groups to process in this iteration.
 
         Returns:
-            The set of state groups that can be deleted.
+            (to_delete, last_checked_state_group, final_batch)
         """
-        # Set of events that we have found to be referenced by events
-        referenced_groups = set()
 
-        # Set of state groups we've already seen
-        state_groups_seen = set(state_groups)
+        # If a state group's next edge is not pending deletion then we don't delete the state group.
+        # If there is no next edge or the next edges are all marked for deletion, then delete
+        # the state group.
+        # This holds since we walk backwards from the latest state groups, ensuring that
+        # we've already checked newer state groups for event references along the way.
+        def get_next_state_groups_marked_for_deletion_txn(
+            txn: LoggingTransaction,
+        ) -> tuple[dict[int, bool], dict[int, int]]:
+            state_group_sql = """
+                SELECT s.id, e.state_group, d.state_group
+                FROM (
+                    SELECT id FROM state_groups
+                    WHERE id < ? ORDER BY id DESC LIMIT ?
+                ) as s
+                LEFT JOIN state_group_edges AS e ON (s.id = e.prev_state_group)
+                LEFT JOIN state_groups_pending_deletion AS d ON (e.state_group = d.state_group)
+            """
+            txn.execute(state_group_sql, (last_checked_state_group, batch_size))
 
-        # Set of state groups to handle next.
-        next_to_search = set(state_groups)
-        while next_to_search:
-            # We bound size of groups we're looking up at once, to stop the
-            # SQL query getting too big
-            if len(next_to_search) < 100:
-                current_search = next_to_search
-                next_to_search = set()
-            else:
-                current_search = set(itertools.islice(next_to_search, 100))
-                next_to_search -= current_search
+            # Mapping from state group to whether we should delete it.
+            state_groups_to_deletion: dict[int, bool] = {}
 
-            referenced = await self.stores.main.get_referenced_state_groups(
-                current_search
-            )
-            referenced_groups |= referenced
+            # Mapping from state group to prev state group.
+            state_groups_to_prev: dict[int, int] = {}
 
-            # We don't continue iterating up the state group graphs for state
-            # groups that are referenced.
-            current_search -= referenced
+            for row in txn:
+                state_group = row[0]
+                next_edge = row[1]
+                pending_deletion = row[2]
 
-            edges = await self.stores.state.get_previous_state_groups(current_search)
+                if next_edge is not None:
+                    state_groups_to_prev[next_edge] = state_group
 
-            prevs = set(edges.values())
-            # We don't bother re-handling groups we've already seen
-            prevs -= state_groups_seen
-            next_to_search |= prevs
-            state_groups_seen |= prevs
+                if next_edge is not None and not pending_deletion:
+                    # We have found an edge not marked for deletion.
+                    # Check previous results to see if this group is part of a chain
+                    # within this batch that qualifies for deletion.
+                    # ie. batch contains:
+                    # SG_1 -> SG_2 -> SG_3
+                    # If SG_3 is a candidate for deletion, then SG_2 & SG_1 should also
+                    # be, even though they have edges which may not be marked for
+                    # deletion.
+                    # This relies on SQL results being sorted in DESC order to work.
+                    next_is_deletion_candidate = state_groups_to_deletion.get(next_edge)
+                    if (
+                        next_is_deletion_candidate is None
+                        or not next_is_deletion_candidate
+                    ):
+                        state_groups_to_deletion[state_group] = False
+                    else:
+                        state_groups_to_deletion.setdefault(state_group, True)
+                else:
+                    # This state group may be a candidate for deletion
+                    state_groups_to_deletion.setdefault(state_group, True)
 
-            # We also check to see if anything referencing the state groups are
-            # also unreferenced. This helps ensure that we delete unreferenced
-            # state groups, if we don't then we will de-delta them when we
-            # delete the other state groups leading to increased DB usage.
-            next_edges = await self.stores.state.get_next_state_groups(current_search)
-            nexts = set(next_edges.keys())
-            nexts -= state_groups_seen
-            next_to_search |= nexts
-            state_groups_seen |= nexts
+            return state_groups_to_deletion, state_groups_to_prev
 
-        to_delete = state_groups_seen - referenced_groups
+        (
+            state_groups_to_deletion,
+            state_group_edges,
+        ) = await self.stores.state.db_pool.runInteraction(
+            "get_next_state_groups_marked_for_deletion",
+            get_next_state_groups_marked_for_deletion_txn,
+        )
+        deletion_candidates = {
+            state_group
+            for state_group, deletion in state_groups_to_deletion.items()
+            if deletion
+        }
 
-        return to_delete
+        final_batch = False
+        state_groups = state_groups_to_deletion.keys()
+        if len(state_groups) < batch_size:
+            final_batch = True
+        else:
+            last_checked_state_group = min(state_groups)
+
+        if len(state_groups) == 0:
+            return set(), last_checked_state_group, final_batch
+
+        # Determine if any of the remaining state groups are directly referenced.
+        referenced = await self.stores.main.get_referenced_state_groups(
+            deletion_candidates
+        )
+
+        # Remove state groups from deletion_candidates which are directly referenced or share a
+        # future edge with a referenced state group within this batch.
+        def filter_reference_chains(group: Optional[int]) -> None:
+            while group is not None:
+                deletion_candidates.discard(group)
+                group = state_group_edges.get(group)
+
+        for referenced_group in referenced:
+            filter_reference_chains(referenced_group)
+
+        return deletion_candidates, last_checked_state_group, final_batch

synapse/storage/databases/main/delayed_events.py

@@ -424,25 +424,37 @@ class DelayedEventsStore(SQLBaseStore):
         room_id: str,
         event_type: str,
         state_key: str,
+        not_from_localpart: str,
     ) -> Optional[Timestamp]:
         """
         Cancels all matching delayed state events, i.e. remove them as long as they haven't been processed.
 
+        Args:
+            room_id: The room ID to match against.
+            event_type: The event type to match against.
+            state_key: The state key to match against.
+            not_from_localpart: The localpart of a user whose delayed events to not cancel.
+                If set to the empty string, any users' delayed events may be cancelled.
+
         Returns: The send time of the next delayed event to be sent, if any.
         """
 
         def cancel_delayed_state_events_txn(
             txn: LoggingTransaction,
         ) -> Optional[Timestamp]:
-            self.db_pool.simple_delete_txn(
-                txn,
-                table="delayed_events",
-                keyvalues={
-                    "room_id": room_id,
-                    "event_type": event_type,
-                    "state_key": state_key,
-                    "is_processed": False,
-                },
+            txn.execute(
+                """
+                DELETE FROM delayed_events
+                WHERE room_id = ? AND event_type = ? AND state_key = ?
+                    AND user_localpart <> ?
+                    AND NOT is_processed
+                """,
+                (
+                    room_id,
+                    event_type,
+                    state_key,
+                    not_from_localpart,
+                ),
             )
             return self._get_next_delayed_event_send_ts_txn(txn)
 

synapse/storage/databases/main/media_repository.py

@@ -19,6 +19,7 @@
 # [This file includes modifications made by New Vector Limited]
 #
 #
+import logging
 from enum import Enum
 from typing import (
     TYPE_CHECKING,
@@ -51,6 +52,8 @@ BG_UPDATE_REMOVE_MEDIA_REPO_INDEX_WITHOUT_METHOD_2 = (
     "media_repository_drop_index_wo_method_2"
 )
 
+logger = logging.getLogger(__name__)
+
 
 @attr.s(slots=True, frozen=True, auto_attribs=True)
 class LocalMedia:
@@ -65,6 +68,7 @@ class LocalMedia:
     safe_from_quarantine: bool
     user_id: Optional[str]
     authenticated: Optional[bool]
+    sha256: Optional[str]
 
 
 @attr.s(slots=True, frozen=True, auto_attribs=True)
@@ -79,6 +83,7 @@ class RemoteMedia:
     last_access_ts: int
     quarantined_by: Optional[str]
     authenticated: Optional[bool]
+    sha256: Optional[str]
 
 
 @attr.s(slots=True, frozen=True, auto_attribs=True)
@@ -154,6 +159,26 @@ class MediaRepositoryBackgroundUpdateStore(SQLBaseStore):
             unique=True,
         )
 
+        self.db_pool.updates.register_background_index_update(
+            update_name="local_media_repository_sha256_idx",
+            index_name="local_media_repository_sha256",
+            table="local_media_repository",
+            where_clause="sha256 IS NOT NULL",
+            columns=[
+                "sha256",
+            ],
+        )
+
+        self.db_pool.updates.register_background_index_update(
+            update_name="remote_media_cache_sha256_idx",
+            index_name="remote_media_cache_sha256",
+            table="remote_media_cache",
+            where_clause="sha256 IS NOT NULL",
+            columns=[
+                "sha256",
+            ],
+        )
+
         self.db_pool.updates.register_background_update_handler(
             BG_UPDATE_REMOVE_MEDIA_REPO_INDEX_WITHOUT_METHOD_2,
             self._drop_media_index_without_method,
@@ -221,6 +246,7 @@ class MediaRepositoryStore(MediaRepositoryBackgroundUpdateStore):
                 "safe_from_quarantine",
                 "user_id",
                 "authenticated",
+                "sha256",
             ),
             allow_none=True,
             desc="get_local_media",
@@ -239,6 +265,7 @@ class MediaRepositoryStore(MediaRepositoryBackgroundUpdateStore):
             safe_from_quarantine=row[7],
             user_id=row[8],
             authenticated=row[9],
+            sha256=row[10],
         )
 
     async def get_local_media_by_user_paginate(
@@ -295,7 +322,8 @@ class MediaRepositoryStore(MediaRepositoryBackgroundUpdateStore):
                     quarantined_by,
                     safe_from_quarantine,
                     user_id,
-                    authenticated
+                    authenticated,
+                    sha256
                 FROM local_media_repository
                 WHERE user_id = ?
                 ORDER BY {order_by_column} {order}, media_id ASC
@@ -320,6 +348,7 @@ class MediaRepositoryStore(MediaRepositoryBackgroundUpdateStore):
                     safe_from_quarantine=bool(row[8]),
                     user_id=row[9],
                     authenticated=row[10],
+                    sha256=row[11],
                 )
                 for row in txn
             ]
@@ -449,6 +478,8 @@ class MediaRepositoryStore(MediaRepositoryBackgroundUpdateStore):
         media_length: int,
         user_id: UserID,
         url_cache: Optional[str] = None,
+        sha256: Optional[str] = None,
+        quarantined_by: Optional[str] = None,
     ) -> None:
         if self.hs.config.media.enable_authenticated_media:
             authenticated = True
@@ -466,6 +497,8 @@ class MediaRepositoryStore(MediaRepositoryBackgroundUpdateStore):
                 "user_id": user_id.to_string(),
                 "url_cache": url_cache,
                 "authenticated": authenticated,
+                "sha256": sha256,
+                "quarantined_by": quarantined_by,
             },
             desc="store_local_media",
         )
@@ -477,20 +510,28 @@ class MediaRepositoryStore(MediaRepositoryBackgroundUpdateStore):
         upload_name: Optional[str],
         media_length: int,
         user_id: UserID,
+        sha256: str,
         url_cache: Optional[str] = None,
+        quarantined_by: Optional[str] = None,
     ) -> None:
+        updatevalues = {
+            "media_type": media_type,
+            "upload_name": upload_name,
+            "media_length": media_length,
+            "url_cache": url_cache,
+            "sha256": sha256,
+        }
+
+        # This should never be un-set by this function.
+        if quarantined_by is not None:
+            updatevalues["quarantined_by"] = quarantined_by
+
         await self.db_pool.simple_update_one(
             "local_media_repository",
             keyvalues={
-                "user_id": user_id.to_string(),
                 "media_id": media_id,
             },
-            updatevalues={
-                "media_type": media_type,
-                "upload_name": upload_name,
-                "media_length": media_length,
-                "url_cache": url_cache,
-            },
+            updatevalues=updatevalues,
             desc="update_local_media",
         )
 
@@ -657,6 +698,7 @@ class MediaRepositoryStore(MediaRepositoryBackgroundUpdateStore):
                 "last_access_ts",
                 "quarantined_by",
                 "authenticated",
+                "sha256",
             ),
             allow_none=True,
             desc="get_cached_remote_media",
@@ -674,6 +716,7 @@ class MediaRepositoryStore(MediaRepositoryBackgroundUpdateStore):
             last_access_ts=row[5],
             quarantined_by=row[6],
             authenticated=row[7],
+            sha256=row[8],
         )
 
     async def store_cached_remote_media(
@@ -685,6 +728,7 @@ class MediaRepositoryStore(MediaRepositoryBackgroundUpdateStore):
         time_now_ms: int,
         upload_name: Optional[str],
         filesystem_id: str,
+        sha256: Optional[str],
     ) -> None:
         if self.hs.config.media.enable_authenticated_media:
             authenticated = True
@@ -703,6 +747,7 @@ class MediaRepositoryStore(MediaRepositoryBackgroundUpdateStore):
                 "filesystem_id": filesystem_id,
                 "last_access_ts": time_now_ms,
                 "authenticated": authenticated,
+                "sha256": sha256,
             },
             desc="store_cached_remote_media",
         )
@@ -946,3 +991,46 @@ class MediaRepositoryStore(MediaRepositoryBackgroundUpdateStore):
         await self.db_pool.runInteraction(
             "delete_url_cache_media", _delete_url_cache_media_txn
         )
+
+    async def get_is_hash_quarantined(self, sha256: str) -> bool:
+        """Get whether a specific sha256 hash digest matches any quarantined media.
+
+        Returns:
+            None if the media_id doesn't exist.
+        """
+
+        # If we don't have the index yet, performance tanks, so we return False.
+        # In the background updates, remote_media_cache_sha256_idx is created
+        # after local_media_repository_sha256_idx, which is why we only need to
+        # check for the completion of the former.
+        if not await self.db_pool.updates.has_completed_background_update(
+            "remote_media_cache_sha256_idx"
+        ):
+            return False
+
+        def get_matching_media_txn(
+            txn: LoggingTransaction, table: str, sha256: str
+        ) -> bool:
+            # Return on first match
+            sql = """
+            SELECT 1
+            FROM local_media_repository
+            WHERE sha256 = ? AND quarantined_by IS NOT NULL
+
+            UNION ALL
+
+            SELECT 1
+            FROM remote_media_cache
+            WHERE sha256 = ? AND quarantined_by IS NOT NULL
+            LIMIT 1
+            """
+            txn.execute(sql, (sha256, sha256))
+            row = txn.fetchone()
+            return row is not None
+
+        return await self.db_pool.runInteraction(
+            "get_matching_media_txn",
+            get_matching_media_txn,
+            "local_media_repository",
+            sha256,
+        )

synapse/storage/databases/main/room.py

@@ -51,11 +51,15 @@ from synapse.api.room_versions import RoomVersion, RoomVersions
 from synapse.config.homeserver import HomeServerConfig
 from synapse.events import EventBase
 from synapse.replication.tcp.streams.partial_state import UnPartialStatedRoomStream
-from synapse.storage._base import db_to_json, make_in_list_sql_clause
+from synapse.storage._base import (
+    db_to_json,
+    make_in_list_sql_clause,
+)
 from synapse.storage.database import (
     DatabasePool,
     LoggingDatabaseConnection,
     LoggingTransaction,
+    make_tuple_in_list_sql_clause,
 )
 from synapse.storage.databases.main.cache import CacheInvalidationWorkerStore
 from synapse.storage.types import Cursor
@@ -1127,6 +1131,109 @@ class RoomWorkerStore(CacheInvalidationWorkerStore):
 
         return local_media_ids
 
+    def _quarantine_local_media_txn(
+        self,
+        txn: LoggingTransaction,
+        hashes: Set[str],
+        media_ids: Set[str],
+        quarantined_by: Optional[str],
+    ) -> int:
+        """Quarantine and unquarantine local media items.
+
+        Args:
+            txn (cursor)
+            hashes: A set of sha256 hashes for any media that should be quarantined
+            media_ids: A set of media IDs for any media that should be quarantined
+            quarantined_by: The ID of the user who initiated the quarantine request
+                If it is `None` media will be removed from quarantine
+        Returns:
+            The total number of media items quarantined
+        """
+        total_media_quarantined = 0
+
+        # Effectively a legacy path, update any media that was explicitly named.
+        if media_ids:
+            sql_many_clause_sql, sql_many_clause_args = make_in_list_sql_clause(
+                txn.database_engine, "media_id", media_ids
+            )
+            sql = f"""
+                UPDATE local_media_repository
+                SET quarantined_by = ?
+                WHERE {sql_many_clause_sql}"""
+
+            if quarantined_by is not None:
+                sql += " AND safe_from_quarantine = FALSE"
+
+            txn.execute(sql, [quarantined_by] + sql_many_clause_args)
+            # Note that a rowcount of -1 can be used to indicate no rows were affected.
+            total_media_quarantined += txn.rowcount if txn.rowcount > 0 else 0
+
+        # Update any media that was identified via hash.
+        if hashes:
+            sql_many_clause_sql, sql_many_clause_args = make_in_list_sql_clause(
+                txn.database_engine, "sha256", hashes
+            )
+            sql = f"""
+                UPDATE local_media_repository
+                SET quarantined_by = ?
+                WHERE {sql_many_clause_sql}"""
+
+            if quarantined_by is not None:
+                sql += " AND safe_from_quarantine = FALSE"
+
+            txn.execute(sql, [quarantined_by] + sql_many_clause_args)
+            total_media_quarantined += txn.rowcount if txn.rowcount > 0 else 0
+
+        return total_media_quarantined
+
+    def _quarantine_remote_media_txn(
+        self,
+        txn: LoggingTransaction,
+        hashes: Set[str],
+        media: Set[Tuple[str, str]],
+        quarantined_by: Optional[str],
+    ) -> int:
+        """Quarantine and unquarantine remote items
+
+        Args:
+            txn (cursor)
+            hashes: A set of sha256 hashes for any media that should be quarantined
+            media_ids: A set of tuples (media_origin, media_id) for any media that should be quarantined
+            quarantined_by: The ID of the user who initiated the quarantine request
+                If it is `None` media will be removed from quarantine
+        Returns:
+            The total number of media items quarantined
+        """
+        total_media_quarantined = 0
+
+        if media:
+            sql_in_list_clause, sql_args = make_tuple_in_list_sql_clause(
+                txn.database_engine,
+                ("media_origin", "media_id"),
+                media,
+            )
+            sql = f"""
+                UPDATE remote_media_cache
+                SET quarantined_by = ?
+                WHERE {sql_in_list_clause}"""
+
+            txn.execute(sql, [quarantined_by] + sql_args)
+            total_media_quarantined += txn.rowcount if txn.rowcount > 0 else 0
+
+        total_media_quarantined = 0
+        if hashes:
+            sql_many_clause_sql, sql_many_clause_args = make_in_list_sql_clause(
+                txn.database_engine, "sha256", hashes
+            )
+            sql = f"""
+                UPDATE remote_media_cache
+                SET quarantined_by = ?
+                WHERE {sql_many_clause_sql}"""
+            txn.execute(sql, [quarantined_by] + sql_many_clause_args)
+            total_media_quarantined += txn.rowcount if txn.rowcount > 0 else 0
+
+        return total_media_quarantined
+
     def _quarantine_media_txn(
         self,
         txn: LoggingTransaction,
@@ -1146,40 +1253,49 @@ class RoomWorkerStore(CacheInvalidationWorkerStore):
         Returns:
             The total number of media items quarantined
         """
+        hashes = set()
+        media_ids = set()
+        remote_media = set()
 
-        # Update all the tables to set the quarantined_by flag
-        sql = """
-            UPDATE local_media_repository
-            SET quarantined_by = ?
-            WHERE media_id = ?
-        """
-
-        # set quarantine
-        if quarantined_by is not None:
-            sql += "AND safe_from_quarantine = FALSE"
-            txn.executemany(
-                sql, [(quarantined_by, media_id) for media_id in local_mxcs]
+        # First, determine the hashes of the media we want to delete.
+        # We also want the media_ids for any media that lacks a hash.
+        if local_mxcs:
+            hash_sql_many_clause_sql, hash_sql_many_clause_args = (
+                make_in_list_sql_clause(txn.database_engine, "media_id", local_mxcs)
             )
-        # remove from quarantine
-        else:
-            txn.executemany(
-                sql, [(quarantined_by, media_id) for media_id in local_mxcs]
+            hash_sql = f"SELECT sha256, media_id FROM local_media_repository WHERE {hash_sql_many_clause_sql}"
+            if quarantined_by is not None:
+                hash_sql += " AND safe_from_quarantine = FALSE"
+
+            txn.execute(hash_sql, hash_sql_many_clause_args)
+            for sha256, media_id in txn:
+                if sha256:
+                    hashes.add(sha256)
+                else:
+                    media_ids.add(media_id)
+
+        # Do the same for remote media
+        if remote_mxcs:
+            hash_sql_in_list_clause, hash_sql_args = make_tuple_in_list_sql_clause(
+                txn.database_engine,
+                ("media_origin", "media_id"),
+                remote_mxcs,
             )
 
-        # Note that a rowcount of -1 can be used to indicate no rows were affected.
-        total_media_quarantined = txn.rowcount if txn.rowcount > 0 else 0
+            hash_sql = f"SELECT sha256, media_origin, media_id FROM remote_media_cache WHERE {hash_sql_in_list_clause}"
+            txn.execute(hash_sql, hash_sql_args)
+            for sha256, media_origin, media_id in txn:
+                if sha256:
+                    hashes.add(sha256)
+                else:
+                    remote_media.add((media_origin, media_id))
 
-        txn.executemany(
-            """
-                UPDATE remote_media_cache
-                SET quarantined_by = ?
-                WHERE media_origin = ? AND media_id = ?
-            """,
-            [(quarantined_by, origin, media_id) for origin, media_id in remote_mxcs],
+        count = self._quarantine_local_media_txn(txn, hashes, media_ids, quarantined_by)
+        count += self._quarantine_remote_media_txn(
+            txn, hashes, remote_media, quarantined_by
         )
-        total_media_quarantined += txn.rowcount if txn.rowcount > 0 else 0
 
-        return total_media_quarantined
+        return count
 
     async def block_room(self, room_id: str, user_id: str) -> None:
         """Marks the room as blocked.

synapse/storage/databases/main/roommember.py

@@ -79,6 +79,7 @@ logger = logging.getLogger(__name__)
 
 _MEMBERSHIP_PROFILE_UPDATE_NAME = "room_membership_profile_update"
 _CURRENT_STATE_MEMBERSHIP_UPDATE_NAME = "current_state_events_membership"
+_POPULATE_PARTICIPANT_BG_UPDATE_BATCH_SIZE = 1000
 
 
 @attr.s(frozen=True, slots=True, auto_attribs=True)
@@ -1606,6 +1607,66 @@ class RoomMemberWorkerStore(EventsWorkerStore, CacheInvalidationWorkerStore):
             from_ts,
         )
 
+    async def set_room_participation(self, user_id: str, room_id: str) -> None:
+        """
+        Record the provided user as participating in the given room
+
+        Args:
+            user_id: the user ID of the user
+            room_id: ID of the room to set the participant in
+        """
+
+        def _set_room_participation_txn(
+            txn: LoggingTransaction, user_id: str, room_id: str
+        ) -> None:
+            sql = """
+                UPDATE room_memberships
+                SET participant = true
+                WHERE (user_id, room_id) IN (
+                    SELECT user_id, room_id
+                    FROM room_memberships
+                    WHERE user_id = ?
+                    AND room_id = ?
+                    ORDER BY event_stream_ordering DESC
+                    LIMIT 1
+                )
+            """
+            txn.execute(sql, (user_id, room_id))
+
+        await self.db_pool.runInteraction(
+            "_set_room_participation_txn", _set_room_participation_txn, user_id, room_id
+        )
+
+    async def get_room_participation(self, user_id: str, room_id: str) -> bool:
+        """
+        Check whether a user is listed as a participant in a room
+
+        Args:
+            user_id: user ID of the user
+            room_id: ID of the room to check in
+        """
+
+        def _get_room_participation_txn(
+            txn: LoggingTransaction, user_id: str, room_id: str
+        ) -> bool:
+            sql = """
+                SELECT participant
+                FROM room_memberships
+                WHERE user_id = ?
+                AND room_id = ?
+                ORDER BY event_stream_ordering DESC
+                LIMIT 1
+            """
+            txn.execute(sql, (user_id, room_id))
+            res = txn.fetchone()
+            if res:
+                return res[0]
+            return False
+
+        return await self.db_pool.runInteraction(
+            "_get_room_participation_txn", _get_room_participation_txn, user_id, room_id
+        )
+
 
 class RoomMemberBackgroundUpdateStore(SQLBaseStore):
     def __init__(
@@ -1636,6 +1697,93 @@ class RoomMemberBackgroundUpdateStore(SQLBaseStore):
             columns=["user_id", "room_id"],
         )
 
+        self.db_pool.updates.register_background_update_handler(
+            "populate_participant_bg_update", self._populate_participant
+        )
+
+    async def _populate_participant(self, progress: JsonDict, batch_size: int) -> int:
+        """
+        Background update to populate column `participant` on `room_memberships` table
+
+        A 'participant' is someone who is currently joined to a room and has sent at least
+        one `m.room.message` or `m.room.encrypted` event.
+
+        This background update will set the `participant` column across all rows in
+        `room_memberships` based on the user's *current* join status, and if
+        they've *ever* sent a message or encrypted event. Therefore one should
+        never assume the `participant` column's value is based solely on whether
+        the user participated in a previous "session" (where a "session" is defined
+        as a period between the user joining and leaving). See
+        https://github.com/element-hq/synapse/pull/18068#discussion_r1931070291
+        for further detail.
+        """
+        stream_token = progress.get("last_stream_token", None)
+
+        def _get_max_stream_token_txn(txn: LoggingTransaction) -> int:
+            sql = """
+                SELECT event_stream_ordering from room_memberships
+                ORDER BY event_stream_ordering DESC
+                LIMIT 1;
+            """
+            txn.execute(sql)
+            res = txn.fetchone()
+            if not res or not res[0]:
+                return 0
+            return res[0]
+
+        def _background_populate_participant_txn(
+            txn: LoggingTransaction, stream_token: str
+        ) -> None:
+            sql = """
+                UPDATE room_memberships
+                SET participant = True
+                FROM (
+                    SELECT DISTINCT c.state_key, e.room_id
+                    FROM current_state_events AS c
+                    INNER JOIN events AS e ON c.room_id = e.room_id
+                    WHERE c.membership = 'join'
+                        AND c.state_key = e.sender
+                        AND (
+                            e.type = 'm.room.message'
+                            OR e.type = 'm.room.encrypted'
+                        )
+                ) AS subquery
+                WHERE room_memberships.user_id = subquery.state_key
+                    AND room_memberships.room_id = subquery.room_id
+                    AND room_memberships.event_stream_ordering <= ?
+                    AND room_memberships.event_stream_ordering > ?;
+            """
+            batch = int(stream_token) - _POPULATE_PARTICIPANT_BG_UPDATE_BATCH_SIZE
+            txn.execute(sql, (stream_token, batch))
+
+        if stream_token is None:
+            stream_token = await self.db_pool.runInteraction(
+                "_get_max_stream_token", _get_max_stream_token_txn
+            )
+
+        if stream_token < 0:
+            await self.db_pool.updates._end_background_update(
+                "populate_participant_bg_update"
+            )
+            return _POPULATE_PARTICIPANT_BG_UPDATE_BATCH_SIZE
+
+        await self.db_pool.runInteraction(
+            "_background_populate_participant_txn",
+            _background_populate_participant_txn,
+            stream_token,
+        )
+
+        progress["last_stream_token"] = (
+            stream_token - _POPULATE_PARTICIPANT_BG_UPDATE_BATCH_SIZE
+        )
+        await self.db_pool.runInteraction(
+            "populate_participant_bg_update",
+            self.db_pool.updates._background_update_progress_txn,
+            "populate_participant_bg_update",
+            progress,
+        )
+        return _POPULATE_PARTICIPANT_BG_UPDATE_BATCH_SIZE
+
     async def _background_add_membership_profile(
         self, progress: JsonDict, batch_size: int
     ) -> int:

synapse/storage/databases/main/sliding_sync.py

@@ -1,7 +1,7 @@
 #
 # This file is licensed under the Affero General Public License (AGPL) version 3.
 #
-# Copyright (C) 2023 New Vector, Ltd
+# Copyright (C) 2023, 2025 New Vector, Ltd
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU Affero General Public License as
@@ -61,6 +61,13 @@ class SlidingSyncStore(SQLBaseStore):
             columns=("required_state_id",),
         )
 
+        self.db_pool.updates.register_background_index_update(
+            update_name="sliding_sync_membership_snapshots_membership_event_id_idx",
+            index_name="sliding_sync_membership_snapshots_membership_event_id_idx",
+            table="sliding_sync_membership_snapshots",
+            columns=("membership_event_id",),
+        )
+
     async def get_latest_bump_stamp_for_room(
         self,
         room_id: str,

synapse/storage/schema/__init__.py

@@ -19,7 +19,7 @@
 #
 #
 
-SCHEMA_VERSION = 89  # remember to update the list below when updating
+SCHEMA_VERSION = 91  # remember to update the list below when updating
 """Represents the expectations made by the codebase about the database schema
 
 This should be incremented whenever the codebase changes its requirements on the
@@ -158,6 +158,9 @@ Changes in SCHEMA_VERSION = 88
 
 Changes in SCHEMA_VERSION = 89
     - Add `state_groups_pending_deletion` and `state_groups_persisting` tables.
+
+Changes in SCHEMA_VERSION = 90
+    - Add a column `participant` to `room_memberships` table
     - Add background update to delete unreferenced state groups.
 """
 

synapse/storage/schema/main/delta/89/01_sliding_sync_membership_snapshot_index.sql

@@ -0,0 +1,15 @@
+--
+-- This file is licensed under the Affero General Public License (AGPL) version 3.
+--
+-- Copyright (C) 2025 New Vector, Ltd
+--
+-- This program is free software: you can redistribute it and/or modify
+-- it under the terms of the GNU Affero General Public License as
+-- published by the Free Software Foundation, either version 3 of the
+-- License, or (at your option) any later version.
+--
+-- See the GNU Affero General Public License for more details:
+-- <https://www.gnu.org/licenses/agpl-3.0.html>.
+
+INSERT INTO background_updates (ordering, update_name, progress_json) VALUES
+    (8901, 'sliding_sync_membership_snapshots_membership_event_id_idx', '{}');

synapse/storage/schema/main/delta/90/01_add_column_participant_room_memberships_table.sql

@@ -0,0 +1,20 @@
+--
+-- This file is licensed under the Affero General Public License (AGPL) version 3.
+--
+-- Copyright (C) 2025 New Vector, Ltd
+--
+-- This program is free software: you can redistribute it and/or modify
+-- it under the terms of the GNU Affero General Public License as
+-- published by the Free Software Foundation, either version 3 of the
+-- License, or (at your option) any later version.
+--
+-- See the GNU Affero General Public License for more details:
+-- <https://www.gnu.org/licenses/agpl-3.0.html>.
+
+-- Add a column `participant` to `room_memberships` table to track whether a room member has sent
+-- a `m.room.message` or `m.room.encrypted` event into a room they are a member of
+ALTER TABLE room_memberships ADD COLUMN participant BOOLEAN DEFAULT FALSE;
+
+-- Add a background update to populate `participant` column
+INSERT INTO background_updates (ordering, update_name, progress_json) VALUES
+  (9001, 'populate_participant_bg_update', '{}');

synapse/storage/schema/main/delta/91/01_media_hash.sql

@@ -0,0 +1,28 @@
+--
+-- This file is licensed under the Affero General Public License (AGPL) version 3.
+--
+-- Copyright (C) 2025 New Vector, Ltd
+--
+-- This program is free software: you can redistribute it and/or modify
+-- it under the terms of the GNU Affero General Public License as
+-- published by the Free Software Foundation, either version 3 of the
+-- License, or (at your option) any later version.
+--
+-- See the GNU Affero General Public License for more details:
+-- <https://www.gnu.org/licenses/agpl-3.0.html>.
+
+-- Store the SHA256 content hash of media files.
+ALTER TABLE local_media_repository ADD COLUMN sha256 TEXT;
+ALTER TABLE remote_media_cache ADD COLUMN sha256 TEXT;
+
+-- Add a background updates to handle creating the new index.
+--
+-- Note that the ordering of the update is not following the usual scheme. This
+-- is because when upgrading from Synapse 1.127, this index is fairly important
+-- to have up quickly, so that it doesn't tank performance, which is why it is
+-- scheduled before other background updates in the 1.127 -> 1.128 upgrade
+INSERT INTO
+  background_updates (ordering, update_name, progress_json)
+VALUES
+  (8890, 'local_media_repository_sha256_idx', '{}'),
+  (8891, 'remote_media_cache_sha256_idx', '{}');

synapse/storage/schema/state/delta/90/02_delete_unreferenced_state_groups.sql

@@ -13,4 +13,4 @@
 
 -- Add a background update to delete any unreferenced state groups
 INSERT INTO background_updates (ordering, update_name, progress_json) VALUES
-  (8902, 'delete_unreferenced_state_groups_bg_update', '{}');
+  (9002, 'mark_unreferenced_state_groups_for_deletion_bg_update', '{}');

synapse/storage/schema/state/delta/90/03_remove_old_deletion_bg_update.sql

@@ -0,0 +1,15 @@
+--
+-- This file is licensed under the Affero General Public License (AGPL) version 3.
+--
+-- Copyright (C) 2025 New Vector, Ltd
+--
+-- This program is free software: you can redistribute it and/or modify
+-- it under the terms of the GNU Affero General Public License as
+-- published by the Free Software Foundation, either version 3 of the
+-- License, or (at your option) any later version.
+--
+-- See the GNU Affero General Public License for more details:
+-- <https://www.gnu.org/licenses/agpl-3.0.html>.
+
+-- Remove the old unreferenced state group deletion background update if it exists
+DELETE FROM background_updates WHERE update_name = 'delete_unreferenced_state_groups_bg_update';

synapse/types/storage/__init__.py

@@ -49,6 +49,6 @@ class _BackgroundUpdates:
         "sliding_sync_membership_snapshots_fix_forgotten_column_bg_update"
     )
 
-    DELETE_UNREFERENCED_STATE_GROUPS_BG_UPDATE = (
-        "delete_unreferenced_state_groups_bg_update"
+    MARK_UNREFERENCED_STATE_GROUPS_FOR_DELETION_BG_UPDATE = (
+        "mark_unreferenced_state_groups_for_deletion_bg_update"
     )

tests/federation/test_federation_media.py

@@ -147,6 +147,45 @@ class FederationMediaDownloadsTest(unittest.FederatingHomeserverTestCase):
         found_file = any(SMALL_PNG in field for field in stripped_bytes)
         self.assertTrue(found_file)
 
+    def test_federation_etag(self) -> None:
+        """Test that federation ETags work"""
+
+        content = io.BytesIO(b"file_to_stream")
+        content_uri = self.get_success(
+            self.media_repo.create_content(
+                "text/plain",
+                "test_upload",
+                content,
+                46,
+                UserID.from_string("@user_id:whatever.org"),
+            )
+        )
+
+        channel = self.make_signed_federation_request(
+            "GET",
+            f"/_matrix/federation/v1/media/download/{content_uri.media_id}",
+        )
+        self.pump()
+        self.assertEqual(200, channel.code)
+
+        # We expect exactly one ETag header.
+        etags = channel.headers.getRawHeaders("ETag")
+        self.assertIsNotNone(etags)
+        assert etags is not None  # For mypy
+        self.assertEqual(len(etags), 1)
+        etag = etags[0]
+
+        # Refetching with the etag should result in 304 and empty body.
+        channel = self.make_signed_federation_request(
+            "GET",
+            f"/_matrix/federation/v1/media/download/{content_uri.media_id}",
+            custom_headers=[("If-None-Match", etag)],
+        )
+        self.pump()
+        self.assertEqual(channel.code, 304)
+        self.assertEqual(channel.is_finished(), True)
+        self.assertNotIn("body", channel.result)
+
 
 class FederationThumbnailTest(unittest.FederatingHomeserverTestCase):
     def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None:

tests/handlers/test_oauth_delegation.py

@@ -539,6 +539,44 @@ class MSC3861OAuthDelegation(HomeserverTestCase):
         error = self.get_failure(self.auth.get_user_by_req(request), SynapseError)
         self.assertEqual(error.value.code, 503)
 
+    def test_cached_expired_introspection(self) -> None:
+        """The handler should raise an error if the introspection response gives
+        an expiry time, the introspection response is cached and then the entry is
+        re-requested after it has expired."""
+
+        self.http_client.request = introspection_mock = AsyncMock(
+            return_value=FakeResponse.json(
+                code=200,
+                payload={
+                    "active": True,
+                    "sub": SUBJECT,
+                    "scope": " ".join(
+                        [
+                            MATRIX_USER_SCOPE,
+                            f"{MATRIX_DEVICE_SCOPE_PREFIX}AABBCC",
+                        ]
+                    ),
+                    "username": USERNAME,
+                    "expires_in": 60,
+                },
+            )
+        )
+        request = Mock(args={})
+        request.args[b"access_token"] = [b"mockAccessToken"]
+        request.requestHeaders.getRawHeaders = mock_getRawHeaders()
+
+        # The first CS-API request causes a successful introspection
+        self.get_success(self.auth.get_user_by_req(request))
+        self.assertEqual(introspection_mock.call_count, 1)
+
+        # Sleep for 60 seconds so the token expires.
+        self.reactor.advance(60.0)
+
+        # Now the CS-API request fails because the token expired
+        self.get_failure(self.auth.get_user_by_req(request), InvalidClientTokenError)
+        # Ensure another introspection request was not sent
+        self.assertEqual(introspection_mock.call_count, 1)
+
     def make_device_keys(self, user_id: str, device_id: str) -> JsonDict:
         # We only generate a master key to simplify the test.
         master_signing_key = generate_signing_key(device_id)

tests/handlers/test_profile.py

@@ -369,6 +369,7 @@ class ProfileTestCase(unittest.HomeserverTestCase):
                 time_now_ms=self.clock.time_msec(),
                 upload_name=None,
                 filesystem_id="xyz",
+                sha256="abcdefg12345",
             )
         )
 

tests/media/test_media_retention.py

@@ -31,6 +31,9 @@ from synapse.rest.client import login, register, room
 from synapse.server import HomeServer
 from synapse.types import UserID
 from synapse.util import Clock
+from synapse.util.stringutils import (
+    random_string,
+)
 
 from tests import unittest
 from tests.unittest import override_config
@@ -65,7 +68,6 @@ class MediaRetentionTestCase(unittest.HomeserverTestCase):
         # quarantined media) into both the local store and the remote cache, plus
         # one additional local media that is marked as protected from quarantine.
         media_repository = hs.get_media_repository()
-        test_media_content = b"example string"
 
         def _create_media_and_set_attributes(
             last_accessed_ms: Optional[int],
@@ -73,12 +75,14 @@ class MediaRetentionTestCase(unittest.HomeserverTestCase):
             is_protected: Optional[bool] = False,
         ) -> MXCUri:
             # "Upload" some media to the local media store
+            # If the meda
+            random_content = bytes(random_string(24), "utf-8")
             mxc_uri: MXCUri = self.get_success(
                 media_repository.create_content(
                     media_type="text/plain",
                     upload_name=None,
-                    content=io.BytesIO(test_media_content),
-                    content_length=len(test_media_content),
+                    content=io.BytesIO(random_content),
+                    content_length=len(random_content),
                     auth_user=UserID.from_string(test_user_id),
                 )
             )
@@ -129,6 +133,7 @@ class MediaRetentionTestCase(unittest.HomeserverTestCase):
                     time_now_ms=clock.time_msec(),
                     upload_name="testfile.txt",
                     filesystem_id="abcdefg12345",
+                    sha256=random_string(24),
                 )
             )
 

tests/media/test_media_storage.py

@@ -42,6 +42,7 @@ from twisted.web.resource import Resource
 from synapse.api.errors import Codes, HttpResponseException
 from synapse.api.ratelimiting import Ratelimiter
 from synapse.events import EventBase
+from synapse.http.client import ByteWriteable
 from synapse.http.types import QueryParams
 from synapse.logging.context import make_deferred_yieldable
 from synapse.media._base import FileInfo, ThumbnailInfo
@@ -59,7 +60,7 @@ from synapse.util import Clock
 
 from tests import unittest
 from tests.server import FakeChannel
-from tests.test_utils import SMALL_CMYK_JPEG, SMALL_PNG
+from tests.test_utils import SMALL_CMYK_JPEG, SMALL_PNG, SMALL_PNG_SHA256
 from tests.unittest import override_config
 from tests.utils import default_config
 
@@ -1257,3 +1258,107 @@ class RemoteDownloadLimiterTestCase(unittest.HomeserverTestCase):
         )
         assert channel.code == 502
         assert channel.json_body["errcode"] == "M_TOO_LARGE"
+
+
+def read_body(
+    response: IResponse, stream: ByteWriteable, max_size: Optional[int]
+) -> Deferred:
+    d: Deferred = defer.Deferred()
+    stream.write(SMALL_PNG)
+    d.callback(len(SMALL_PNG))
+    return d
+
+
+class MediaHashesTestCase(unittest.HomeserverTestCase):
+    servlets = [
+        admin.register_servlets,
+        login.register_servlets,
+        media.register_servlets,
+    ]
+
+    def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None:
+        self.user = self.register_user("user", "pass")
+        self.tok = self.login("user", "pass")
+        self.store = hs.get_datastores().main
+        self.client = hs.get_federation_http_client()
+
+    def create_resource_dict(self) -> Dict[str, Resource]:
+        resources = super().create_resource_dict()
+        resources["/_matrix/media"] = self.hs.get_media_repository_resource()
+        return resources
+
+    def test_ensure_correct_sha256(self) -> None:
+        """Check that the hash does not change"""
+        media = self.helper.upload_media(SMALL_PNG, tok=self.tok, expect_code=200)
+        mxc = media.get("content_uri")
+        assert mxc
+        store_media = self.get_success(self.store.get_local_media(mxc[11:]))
+        assert store_media
+        self.assertEqual(
+            store_media.sha256,
+            SMALL_PNG_SHA256,
+        )
+
+    def test_ensure_multiple_correct_sha256(self) -> None:
+        """Check that two media items have the same hash."""
+        media_a = self.helper.upload_media(SMALL_PNG, tok=self.tok, expect_code=200)
+        mxc_a = media_a.get("content_uri")
+        assert mxc_a
+        store_media_a = self.get_success(self.store.get_local_media(mxc_a[11:]))
+        assert store_media_a
+
+        media_b = self.helper.upload_media(SMALL_PNG, tok=self.tok, expect_code=200)
+        mxc_b = media_b.get("content_uri")
+        assert mxc_b
+        store_media_b = self.get_success(self.store.get_local_media(mxc_b[11:]))
+        assert store_media_b
+
+        self.assertNotEqual(
+            store_media_a.media_id,
+            store_media_b.media_id,
+        )
+        self.assertEqual(
+            store_media_a.sha256,
+            store_media_b.sha256,
+        )
+
+    @override_config(
+        {
+            "enable_authenticated_media": False,
+        }
+    )
+    # mock actually reading file body
+    @patch(
+        "synapse.http.matrixfederationclient.read_body_with_max_size",
+        read_body,
+    )
+    def test_ensure_correct_sha256_federated(self) -> None:
+        """Check that federated media have the same hash."""
+
+        # Mock getting a file over federation
+        async def _send_request(*args: Any, **kwargs: Any) -> IResponse:
+            resp = MagicMock(spec=IResponse)
+            resp.code = 200
+            resp.length = 500
+            resp.headers = Headers({"Content-Type": ["application/octet-stream"]})
+            resp.phrase = b"OK"
+            return resp
+
+        self.client._send_request = _send_request  # type: ignore
+
+        # first request should go through
+        channel = self.make_request(
+            "GET",
+            "/_matrix/media/v3/download/remote.org/abc",
+            shorthand=False,
+            access_token=self.tok,
+        )
+        assert channel.code == 200
+        store_media = self.get_success(
+            self.store.get_cached_remote_media("remote.org", "abc")
+        )
+        assert store_media
+        self.assertEqual(
+            store_media.sha256,
+            SMALL_PNG_SHA256,
+        )

tests/rest/admin/test_admin.py

@@ -20,7 +20,7 @@
 #
 
 import urllib.parse
-from typing import Dict
+from typing import Dict, cast
 
 from parameterized import parameterized
 
@@ -32,6 +32,7 @@ from synapse.http.server import JsonResource
 from synapse.rest.admin import VersionServlet
 from synapse.rest.client import login, media, room
 from synapse.server import HomeServer
+from synapse.types import UserID
 from synapse.util import Clock
 
 from tests import unittest
@@ -227,10 +228,25 @@ class QuarantineMediaTestCase(unittest.HomeserverTestCase):
         # Upload some media
         response_1 = self.helper.upload_media(SMALL_PNG, tok=non_admin_user_tok)
         response_2 = self.helper.upload_media(SMALL_PNG, tok=non_admin_user_tok)
+        response_3 = self.helper.upload_media(SMALL_PNG, tok=non_admin_user_tok)
 
         # Extract media IDs
         server_and_media_id_1 = response_1["content_uri"][6:]
         server_and_media_id_2 = response_2["content_uri"][6:]
+        server_and_media_id_3 = response_3["content_uri"][6:]
+
+        # Remove the hash from the media to simulate historic media.
+        self.get_success(
+            self.hs.get_datastores().main.update_local_media(
+                media_id=server_and_media_id_3.split("/")[1],
+                media_type="image/png",
+                upload_name=None,
+                media_length=123,
+                user_id=UserID.from_string(non_admin_user),
+                # Hack to force some media to have no hash.
+                sha256=cast(str, None),
+            )
+        )
 
         # Quarantine all media by this user
         url = "/_synapse/admin/v1/user/%s/media/quarantine" % urllib.parse.quote(
@@ -244,12 +260,13 @@ class QuarantineMediaTestCase(unittest.HomeserverTestCase):
         self.pump(1.0)
         self.assertEqual(200, channel.code, msg=channel.json_body)
         self.assertEqual(
-            channel.json_body, {"num_quarantined": 2}, "Expected 2 quarantined items"
+            channel.json_body, {"num_quarantined": 3}, "Expected 3 quarantined items"
         )
 
         # Attempt to access each piece of media
         self._ensure_quarantined(admin_user_tok, server_and_media_id_1)
         self._ensure_quarantined(admin_user_tok, server_and_media_id_2)
+        self._ensure_quarantined(admin_user_tok, server_and_media_id_3)
 
     def test_cannot_quarantine_safe_media(self) -> None:
         self.register_user("user_admin", "pass", admin=True)

tests/rest/admin/test_media.py

@@ -35,7 +35,7 @@ from synapse.server import HomeServer
 from synapse.util import Clock
 
 from tests import unittest
-from tests.test_utils import SMALL_PNG
+from tests.test_utils import SMALL_CMYK_JPEG, SMALL_PNG
 from tests.unittest import override_config
 
 VALID_TIMESTAMP = 1609459200000  # 2021-01-01 in milliseconds
@@ -598,23 +598,27 @@ class DeleteMediaByDateSizeTestCase(_AdminMediaTests):
 
 
 class QuarantineMediaByIDTestCase(_AdminMediaTests):
+    def upload_media_and_return_media_id(self, data: bytes) -> str:
+        # Upload some media into the room
+        response = self.helper.upload_media(
+            data,
+            tok=self.admin_user_tok,
+            expect_code=200,
+        )
+        # Extract media ID from the response
+        server_and_media_id = response["content_uri"][6:]  # Cut off 'mxc://'
+        return server_and_media_id.split("/")[1]
+
     def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None:
         self.store = hs.get_datastores().main
         self.server_name = hs.hostname
 
         self.admin_user = self.register_user("admin", "pass", admin=True)
         self.admin_user_tok = self.login("admin", "pass")
-
-        # Upload some media into the room
-        response = self.helper.upload_media(
-            SMALL_PNG,
-            tok=self.admin_user_tok,
-            expect_code=200,
-        )
-        # Extract media ID from the response
-        server_and_media_id = response["content_uri"][6:]  # Cut off 'mxc://'
-        self.media_id = server_and_media_id.split("/")[1]
-
+        self.media_id = self.upload_media_and_return_media_id(SMALL_PNG)
+        self.media_id_2 = self.upload_media_and_return_media_id(SMALL_PNG)
+        self.media_id_3 = self.upload_media_and_return_media_id(SMALL_PNG)
+        self.media_id_other = self.upload_media_and_return_media_id(SMALL_CMYK_JPEG)
         self.url = "/_synapse/admin/v1/media/%s/%s/%s"
 
     @parameterized.expand(["quarantine", "unquarantine"])
@@ -686,6 +690,52 @@ class QuarantineMediaByIDTestCase(_AdminMediaTests):
         assert media_info is not None
         self.assertFalse(media_info.quarantined_by)
 
+    def test_quarantine_media_match_hash(self) -> None:
+        """
+        Tests that quarantining removes all media with the same hash
+        """
+
+        media_info = self.get_success(self.store.get_local_media(self.media_id))
+        assert media_info is not None
+        self.assertFalse(media_info.quarantined_by)
+
+        # quarantining
+        channel = self.make_request(
+            "POST",
+            self.url % ("quarantine", self.server_name, self.media_id),
+            access_token=self.admin_user_tok,
+        )
+
+        self.assertEqual(200, channel.code, msg=channel.json_body)
+        self.assertFalse(channel.json_body)
+
+        # Test that ALL similar media was quarantined.
+        for media in [self.media_id, self.media_id_2, self.media_id_3]:
+            media_info = self.get_success(self.store.get_local_media(media))
+            assert media_info is not None
+            self.assertTrue(media_info.quarantined_by)
+
+        # Test that other media was not.
+        media_info = self.get_success(self.store.get_local_media(self.media_id_other))
+        assert media_info is not None
+        self.assertFalse(media_info.quarantined_by)
+
+        # remove from quarantine
+        channel = self.make_request(
+            "POST",
+            self.url % ("unquarantine", self.server_name, self.media_id),
+            access_token=self.admin_user_tok,
+        )
+
+        self.assertEqual(200, channel.code, msg=channel.json_body)
+        self.assertFalse(channel.json_body)
+
+        # Test that ALL similar media is now reset.
+        for media in [self.media_id, self.media_id_2, self.media_id_3]:
+            media_info = self.get_success(self.store.get_local_media(media))
+            assert media_info is not None
+            self.assertFalse(media_info.quarantined_by)
+
     def test_quarantine_protected_media(self) -> None:
         """
         Tests that quarantining from protected media fails

tests/rest/client/test_delayed_events.py

@@ -22,7 +22,8 @@ from parameterized import parameterized
 from twisted.test.proto_helpers import MemoryReactor
 
 from synapse.api.errors import Codes
-from synapse.rest.client import delayed_events, room, versions
+from synapse.rest import admin
+from synapse.rest.client import delayed_events, login, room, versions
 from synapse.server import HomeServer
 from synapse.types import JsonDict
 from synapse.util import Clock
@@ -32,7 +33,6 @@ from tests.unittest import HomeserverTestCase
 
 PATH_PREFIX = "/_matrix/client/unstable/org.matrix.msc4140/delayed_events"
 
-_HS_NAME = "red"
 _EVENT_TYPE = "com.example.test"
 
 
@@ -54,23 +54,41 @@ class DelayedEventsUnstableSupportTestCase(HomeserverTestCase):
 class DelayedEventsTestCase(HomeserverTestCase):
     """Tests getting and managing delayed events."""
 
-    servlets = [delayed_events.register_servlets, room.register_servlets]
-    user_id = f"@sid1:{_HS_NAME}"
+    servlets = [
+        admin.register_servlets,
+        delayed_events.register_servlets,
+        login.register_servlets,
+        room.register_servlets,
+    ]
 
     def default_config(self) -> JsonDict:
         config = super().default_config()
-        config["server_name"] = _HS_NAME
         config["max_event_delay_duration"] = "24h"
         return config
 
     def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None:
+        self.user1_user_id = self.register_user("user1", "pass")
+        self.user1_access_token = self.login("user1", "pass")
+        self.user2_user_id = self.register_user("user2", "pass")
+        self.user2_access_token = self.login("user2", "pass")
+
         self.room_id = self.helper.create_room_as(
-            self.user_id,
+            self.user1_user_id,
+            tok=self.user1_access_token,
             extra_content={
-                "preset": "trusted_private_chat",
+                "preset": "public_chat",
+                "power_level_content_override": {
+                    "events": {
+                        _EVENT_TYPE: 0,
+                    }
+                },
             },
         )
 
+        self.helper.join(
+            room=self.room_id, user=self.user2_user_id, tok=self.user2_access_token
+        )
+
     def test_delayed_events_empty_on_startup(self) -> None:
         self.assertListEqual([], self._get_delayed_events())
 
@@ -85,6 +103,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
             {
                 setter_key: setter_expected,
             },
+            self.user1_access_token,
         )
         self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
         events = self._get_delayed_events()
@@ -94,7 +113,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
         self.helper.get_state(
             self.room_id,
             _EVENT_TYPE,
-            "",
+            self.user1_access_token,
             state_key=state_key,
             expect_code=HTTPStatus.NOT_FOUND,
         )
@@ -104,7 +123,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
         content = self.helper.get_state(
             self.room_id,
             _EVENT_TYPE,
-            "",
+            self.user1_access_token,
             state_key=state_key,
         )
         self.assertEqual(setter_expected, content.get(setter_key), content)
@@ -113,7 +132,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
         {"rc_delayed_event_mgmt": {"per_second": 0.5, "burst_count": 1}}
     )
     def test_get_delayed_events_ratelimit(self) -> None:
-        args = ("GET", PATH_PREFIX)
+        args = ("GET", PATH_PREFIX, b"", self.user1_access_token)
 
         channel = self.make_request(*args)
         self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
@@ -123,7 +142,9 @@ class DelayedEventsTestCase(HomeserverTestCase):
 
         # Add the current user to the ratelimit overrides, allowing them no ratelimiting.
         self.get_success(
-            self.hs.get_datastores().main.set_ratelimit_for_user(self.user_id, 0, 0)
+            self.hs.get_datastores().main.set_ratelimit_for_user(
+                self.user1_user_id, 0, 0
+            )
         )
 
         # Test that the request isn't ratelimited anymore.
@@ -134,6 +155,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
         channel = self.make_request(
             "POST",
             f"{PATH_PREFIX}/",
+            access_token=self.user1_access_token,
         )
         self.assertEqual(HTTPStatus.NOT_FOUND, channel.code, channel.result)
 
@@ -141,6 +163,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
         channel = self.make_request(
             "POST",
             f"{PATH_PREFIX}/abc",
+            access_token=self.user1_access_token,
         )
         self.assertEqual(HTTPStatus.BAD_REQUEST, channel.code, channel.result)
         self.assertEqual(
@@ -153,6 +176,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
             "POST",
             f"{PATH_PREFIX}/abc",
             {},
+            self.user1_access_token,
         )
         self.assertEqual(HTTPStatus.BAD_REQUEST, channel.code, channel.result)
         self.assertEqual(
@@ -165,6 +189,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
             "POST",
             f"{PATH_PREFIX}/abc",
             {"action": "oops"},
+            self.user1_access_token,
         )
         self.assertEqual(HTTPStatus.BAD_REQUEST, channel.code, channel.result)
         self.assertEqual(
@@ -178,6 +203,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
             "POST",
             f"{PATH_PREFIX}/abc",
             {"action": action},
+            self.user1_access_token,
         )
         self.assertEqual(HTTPStatus.NOT_FOUND, channel.code, channel.result)
 
@@ -192,6 +218,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
             {
                 setter_key: setter_expected,
             },
+            self.user1_access_token,
         )
         self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
         delay_id = channel.json_body.get("delay_id")
@@ -205,7 +232,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
         self.helper.get_state(
             self.room_id,
             _EVENT_TYPE,
-            "",
+            self.user1_access_token,
             state_key=state_key,
             expect_code=HTTPStatus.NOT_FOUND,
         )
@@ -214,6 +241,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
             "POST",
             f"{PATH_PREFIX}/{delay_id}",
             {"action": "cancel"},
+            self.user1_access_token,
         )
         self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
         self.assertListEqual([], self._get_delayed_events())
@@ -222,7 +250,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
         content = self.helper.get_state(
             self.room_id,
             _EVENT_TYPE,
-            "",
+            self.user1_access_token,
             state_key=state_key,
             expect_code=HTTPStatus.NOT_FOUND,
         )
@@ -237,6 +265,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
                 "POST",
                 _get_path_for_delayed_send(self.room_id, _EVENT_TYPE, 100000),
                 {},
+                self.user1_access_token,
             )
             self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
             delay_id = channel.json_body.get("delay_id")
@@ -247,6 +276,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
             "POST",
             f"{PATH_PREFIX}/{delay_ids.pop(0)}",
             {"action": "cancel"},
+            self.user1_access_token,
         )
         self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
 
@@ -254,13 +284,16 @@ class DelayedEventsTestCase(HomeserverTestCase):
             "POST",
             f"{PATH_PREFIX}/{delay_ids.pop(0)}",
             {"action": "cancel"},
+            self.user1_access_token,
         )
         channel = self.make_request(*args)
         self.assertEqual(HTTPStatus.TOO_MANY_REQUESTS, channel.code, channel.result)
 
         # Add the current user to the ratelimit overrides, allowing them no ratelimiting.
         self.get_success(
-            self.hs.get_datastores().main.set_ratelimit_for_user(self.user_id, 0, 0)
+            self.hs.get_datastores().main.set_ratelimit_for_user(
+                self.user1_user_id, 0, 0
+            )
         )
 
         # Test that the request isn't ratelimited anymore.
@@ -278,6 +311,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
             {
                 setter_key: setter_expected,
             },
+            self.user1_access_token,
         )
         self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
         delay_id = channel.json_body.get("delay_id")
@@ -291,7 +325,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
         self.helper.get_state(
             self.room_id,
             _EVENT_TYPE,
-            "",
+            self.user1_access_token,
             state_key=state_key,
             expect_code=HTTPStatus.NOT_FOUND,
         )
@@ -300,13 +334,14 @@ class DelayedEventsTestCase(HomeserverTestCase):
             "POST",
             f"{PATH_PREFIX}/{delay_id}",
             {"action": "send"},
+            self.user1_access_token,
         )
         self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
         self.assertListEqual([], self._get_delayed_events())
         content = self.helper.get_state(
             self.room_id,
             _EVENT_TYPE,
-            "",
+            self.user1_access_token,
             state_key=state_key,
         )
         self.assertEqual(setter_expected, content.get(setter_key), content)
@@ -319,6 +354,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
                 "POST",
                 _get_path_for_delayed_send(self.room_id, _EVENT_TYPE, 100000),
                 {},
+                self.user1_access_token,
             )
             self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
             delay_id = channel.json_body.get("delay_id")
@@ -329,6 +365,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
             "POST",
             f"{PATH_PREFIX}/{delay_ids.pop(0)}",
             {"action": "send"},
+            self.user1_access_token,
         )
         self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
 
@@ -336,13 +373,16 @@ class DelayedEventsTestCase(HomeserverTestCase):
             "POST",
             f"{PATH_PREFIX}/{delay_ids.pop(0)}",
             {"action": "send"},
+            self.user1_access_token,
         )
         channel = self.make_request(*args)
         self.assertEqual(HTTPStatus.TOO_MANY_REQUESTS, channel.code, channel.result)
 
         # Add the current user to the ratelimit overrides, allowing them no ratelimiting.
         self.get_success(
-            self.hs.get_datastores().main.set_ratelimit_for_user(self.user_id, 0, 0)
+            self.hs.get_datastores().main.set_ratelimit_for_user(
+                self.user1_user_id, 0, 0
+            )
         )
 
         # Test that the request isn't ratelimited anymore.
@@ -360,6 +400,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
             {
                 setter_key: setter_expected,
             },
+            self.user1_access_token,
         )
         self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
         delay_id = channel.json_body.get("delay_id")
@@ -373,7 +414,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
         self.helper.get_state(
             self.room_id,
             _EVENT_TYPE,
-            "",
+            self.user1_access_token,
             state_key=state_key,
             expect_code=HTTPStatus.NOT_FOUND,
         )
@@ -382,6 +423,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
             "POST",
             f"{PATH_PREFIX}/{delay_id}",
             {"action": "restart"},
+            self.user1_access_token,
         )
         self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
 
@@ -393,7 +435,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
         self.helper.get_state(
             self.room_id,
             _EVENT_TYPE,
-            "",
+            self.user1_access_token,
             state_key=state_key,
             expect_code=HTTPStatus.NOT_FOUND,
         )
@@ -403,7 +445,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
         content = self.helper.get_state(
             self.room_id,
             _EVENT_TYPE,
-            "",
+            self.user1_access_token,
             state_key=state_key,
         )
         self.assertEqual(setter_expected, content.get(setter_key), content)
@@ -418,6 +460,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
                 "POST",
                 _get_path_for_delayed_send(self.room_id, _EVENT_TYPE, 100000),
                 {},
+                self.user1_access_token,
             )
             self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
             delay_id = channel.json_body.get("delay_id")
@@ -428,6 +471,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
             "POST",
             f"{PATH_PREFIX}/{delay_ids.pop(0)}",
             {"action": "restart"},
+            self.user1_access_token,
         )
         self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
 
@@ -435,21 +479,66 @@ class DelayedEventsTestCase(HomeserverTestCase):
             "POST",
             f"{PATH_PREFIX}/{delay_ids.pop(0)}",
             {"action": "restart"},
+            self.user1_access_token,
         )
         channel = self.make_request(*args)
         self.assertEqual(HTTPStatus.TOO_MANY_REQUESTS, channel.code, channel.result)
 
         # Add the current user to the ratelimit overrides, allowing them no ratelimiting.
         self.get_success(
-            self.hs.get_datastores().main.set_ratelimit_for_user(self.user_id, 0, 0)
+            self.hs.get_datastores().main.set_ratelimit_for_user(
+                self.user1_user_id, 0, 0
+            )
         )
 
         # Test that the request isn't ratelimited anymore.
         channel = self.make_request(*args)
         self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
 
-    def test_delayed_state_events_are_cancelled_by_more_recent_state(self) -> None:
-        state_key = "to_be_cancelled"
+    def test_delayed_state_is_not_cancelled_by_new_state_from_same_user(
+        self,
+    ) -> None:
+        state_key = "to_not_be_cancelled_by_same_user"
+
+        setter_key = "setter"
+        setter_expected = "on_timeout"
+        channel = self.make_request(
+            "PUT",
+            _get_path_for_delayed_state(self.room_id, _EVENT_TYPE, state_key, 900),
+            {
+                setter_key: setter_expected,
+            },
+            self.user1_access_token,
+        )
+        self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
+        events = self._get_delayed_events()
+        self.assertEqual(1, len(events), events)
+
+        self.helper.send_state(
+            self.room_id,
+            _EVENT_TYPE,
+            {
+                setter_key: "manual",
+            },
+            self.user1_access_token,
+            state_key=state_key,
+        )
+        events = self._get_delayed_events()
+        self.assertEqual(1, len(events), events)
+
+        self.reactor.advance(1)
+        content = self.helper.get_state(
+            self.room_id,
+            _EVENT_TYPE,
+            self.user1_access_token,
+            state_key=state_key,
+        )
+        self.assertEqual(setter_expected, content.get(setter_key), content)
+
+    def test_delayed_state_is_cancelled_by_new_state_from_other_user(
+        self,
+    ) -> None:
+        state_key = "to_be_cancelled_by_other_user"
 
         setter_key = "setter"
         channel = self.make_request(
@@ -458,19 +547,20 @@ class DelayedEventsTestCase(HomeserverTestCase):
             {
                 setter_key: "on_timeout",
             },
+            self.user1_access_token,
         )
         self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
         events = self._get_delayed_events()
         self.assertEqual(1, len(events), events)
 
-        setter_expected = "manual"
+        setter_expected = "other_user"
         self.helper.send_state(
             self.room_id,
             _EVENT_TYPE,
             {
                 setter_key: setter_expected,
             },
-            None,
+            self.user2_access_token,
             state_key=state_key,
         )
         self.assertListEqual([], self._get_delayed_events())
@@ -479,7 +569,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
         content = self.helper.get_state(
             self.room_id,
             _EVENT_TYPE,
-            "",
+            self.user1_access_token,
             state_key=state_key,
         )
         self.assertEqual(setter_expected, content.get(setter_key), content)
@@ -488,6 +578,7 @@ class DelayedEventsTestCase(HomeserverTestCase):
         channel = self.make_request(
             "GET",
             PATH_PREFIX,
+            access_token=self.user1_access_token,
         )
         self.assertEqual(HTTPStatus.OK, channel.code, channel.result)
 

tests/rest/client/test_media.py

@@ -137,6 +137,7 @@ class MediaDomainBlockingTests(unittest.HomeserverTestCase):
                 time_now_ms=clock.time_msec(),
                 upload_name="test.png",
                 filesystem_id=file_id,
+                sha256=file_id,
             )
         )
         self.register_user("user", "password")
@@ -2593,6 +2594,7 @@ class AuthenticatedMediaTestCase(unittest.HomeserverTestCase):
                 time_now_ms=self.clock.time_msec(),
                 upload_name="remote_test.png",
                 filesystem_id=file_id,
+                sha256=file_id,
             )
         )
 
@@ -2676,3 +2678,114 @@ class AuthenticatedMediaTestCase(unittest.HomeserverTestCase):
             access_token=self.tok,
         )
         self.assertEqual(channel10.code, 200)
+
+    def test_authenticated_media_etag(self) -> None:
+        """Test that ETag works correctly with authenticated media over client
+        APIs"""
+
+        # upload some local media with authentication on
+        channel = self.make_request(
+            "POST",
+            "_matrix/media/v3/upload?filename=test_png_upload",
+            SMALL_PNG,
+            self.tok,
+            shorthand=False,
+            content_type=b"image/png",
+            custom_headers=[("Content-Length", str(67))],
+        )
+        self.assertEqual(channel.code, 200)
+        res = channel.json_body.get("content_uri")
+        assert res is not None
+        uri = res.split("mxc://")[1]
+
+        # Check standard media endpoint
+        self._check_caching(f"/download/{uri}")
+
+        # check thumbnails as well
+        params = "?width=32&height=32&method=crop"
+        self._check_caching(f"/thumbnail/{uri}{params}")
+
+        # Inject a piece of remote media.
+        file_id = "abcdefg12345"
+        file_info = FileInfo(server_name="lonelyIsland", file_id=file_id)
+
+        media_storage = self.hs.get_media_repository().media_storage
+
+        ctx = media_storage.store_into_file(file_info)
+        (f, fname) = self.get_success(ctx.__aenter__())
+        f.write(SMALL_PNG)
+        self.get_success(ctx.__aexit__(None, None, None))
+
+        # we write the authenticated status when storing media, so this should pick up
+        # config and authenticate the media
+        self.get_success(
+            self.store.store_cached_remote_media(
+                origin="lonelyIsland",
+                media_id="52",
+                media_type="image/png",
+                media_length=1,
+                time_now_ms=self.clock.time_msec(),
+                upload_name="remote_test.png",
+                filesystem_id=file_id,
+                sha256=file_id,
+            )
+        )
+
+        # ensure we have thumbnails for the non-dynamic code path
+        if self.extra_config == {"dynamic_thumbnails": False}:
+            self.get_success(
+                self.repo._generate_thumbnails(
+                    "lonelyIsland", "52", file_id, "image/png"
+                )
+            )
+
+        self._check_caching("/download/lonelyIsland/52")
+
+        params = "?width=32&height=32&method=crop"
+        self._check_caching(f"/thumbnail/lonelyIsland/52{params}")
+
+    def _check_caching(self, path: str) -> None:
+        """
+        Checks that:
+          1. fetching the path returns an ETag header
+          2. refetching with the ETag returns a 304 without a body
+          3. refetching with the ETag but through unauthenticated endpoint
+             returns 404
+        """
+
+        # Request media over authenticated endpoint, should be found
+        channel1 = self.make_request(
+            "GET",
+            f"/_matrix/client/v1/media{path}",
+            access_token=self.tok,
+            shorthand=False,
+        )
+        self.assertEqual(channel1.code, 200)
+
+        # Should have a single ETag field
+        etags = channel1.headers.getRawHeaders("ETag")
+        self.assertIsNotNone(etags)
+        assert etags is not None  # For mypy
+        self.assertEqual(len(etags), 1)
+        etag = etags[0]
+
+        # Refetching with the etag should result in 304 and empty body.
+        channel2 = self.make_request(
+            "GET",
+            f"/_matrix/client/v1/media{path}",
+            access_token=self.tok,
+            shorthand=False,
+            custom_headers=[("If-None-Match", etag)],
+        )
+        self.assertEqual(channel2.code, 304)
+        self.assertEqual(channel2.is_finished(), True)
+        self.assertNotIn("body", channel2.result)
+
+        # Refetching with the etag but no access token should result in 404.
+        channel3 = self.make_request(
+            "GET",
+            f"/_matrix/media/r0{path}",
+            shorthand=False,
+            custom_headers=[("If-None-Match", etag)],
+        )
+        self.assertEqual(channel3.code, 404)

tests/rest/client/test_rooms.py

@@ -4208,3 +4208,196 @@ class UserSuspensionTests(unittest.HomeserverTestCase):
             shorthand=False,
         )
         self.assertEqual(channel.code, 200)
+
+
+class RoomParticipantTestCase(unittest.HomeserverTestCase):
+    servlets = [
+        login.register_servlets,
+        room.register_servlets,
+        profile.register_servlets,
+        admin.register_servlets,
+    ]
+
+    def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None:
+        self.user1 = self.register_user("thomas", "hackme")
+        self.tok1 = self.login("thomas", "hackme")
+
+        self.user2 = self.register_user("teresa", "hackme")
+        self.tok2 = self.login("teresa", "hackme")
+
+        self.room1 = self.helper.create_room_as(
+            room_creator=self.user1,
+            tok=self.tok1,
+            # Allow user2 to send state events into the room.
+            extra_content={
+                "power_level_content_override": {
+                    "state_default": 0,
+                },
+            },
+        )
+        self.store = hs.get_datastores().main
+
+    @parameterized.expand(
+        [
+            # Should record participation.
+            param(
+                is_state=False,
+                event_type="m.room.message",
+                event_content={
+                    "msgtype": "m.text",
+                    "body": "I am engaging in this room",
+                },
+                record_participation=True,
+            ),
+            param(
+                is_state=False,
+                event_type="m.room.encrypted",
+                event_content={
+                    "algorithm": "m.megolm.v1.aes-sha2",
+                    "ciphertext": "AwgAEnACgAkLmt6qF84IK++J7UDH2Za1YVchHyprqTqsg...",
+                    "device_id": "RJYKSTBOIE",
+                    "sender_key": "IlRMeOPX2e0MurIyfWEucYBRVOEEUMrOHqn/8mLqMjA",
+                    "session_id": "X3lUlvLELLYxeTx4yOVu6UDpasGEVO0Jbu+QFnm0cKQ",
+                },
+                record_participation=True,
+            ),
+            # Should not record participation.
+            param(
+                is_state=False,
+                event_type="m.sticker",
+                event_content={
+                    "body": "My great sticker",
+                    "info": {},
+                    "url": "mxc://unused/mxcurl",
+                },
+                record_participation=False,
+            ),
+            # An invalid **state event** with type `m.room.message`
+            param(
+                is_state=True,
+                event_type="m.room.message",
+                event_content={
+                    "msgtype": "m.text",
+                    "body": "I am engaging in this room",
+                },
+                record_participation=False,
+            ),
+            # An invalid **state event** with type `m.room.encrypted`
+            # Note: this may become valid in the future with encrypted state, though we
+            # still may not want to consider it grounds for marking a user as participating.
+            param(
+                is_state=True,
+                event_type="m.room.encrypted",
+                event_content={
+                    "algorithm": "m.megolm.v1.aes-sha2",
+                    "ciphertext": "AwgAEnACgAkLmt6qF84IK++J7UDH2Za1YVchHyprqTqsg...",
+                    "device_id": "RJYKSTBOIE",
+                    "sender_key": "IlRMeOPX2e0MurIyfWEucYBRVOEEUMrOHqn/8mLqMjA",
+                    "session_id": "X3lUlvLELLYxeTx4yOVu6UDpasGEVO0Jbu+QFnm0cKQ",
+                },
+                record_participation=False,
+            ),
+        ]
+    )
+    def test_sending_message_records_participation(
+        self,
+        is_state: bool,
+        event_type: str,
+        event_content: JsonDict,
+        record_participation: bool,
+    ) -> None:
+        """
+        Test that sending an various events into a room causes the user to
+        appropriately marked or not marked as a participant in that room.
+        """
+        self.helper.join(self.room1, self.user2, tok=self.tok2)
+
+        # user has not sent any messages, so should not be a participant
+        participant = self.get_success(
+            self.store.get_room_participation(self.user2, self.room1)
+        )
+        self.assertFalse(participant)
+
+        # send an event into the room
+        if is_state:
+            # send a state event
+            self.helper.send_state(
+                self.room1,
+                event_type,
+                body=event_content,
+                tok=self.tok2,
+            )
+        else:
+            # send a non-state event
+            self.helper.send_event(
+                self.room1,
+                event_type,
+                content=event_content,
+                tok=self.tok2,
+            )
+
+        # check whether the user has been marked as a participant
+        participant = self.get_success(
+            self.store.get_room_participation(self.user2, self.room1)
+        )
+        self.assertEqual(participant, record_participation)
+
+    @parameterized.expand(
+        [
+            param(
+                event_type="m.room.message",
+                event_content={
+                    "msgtype": "m.text",
+                    "body": "I am engaging in this room",
+                },
+            ),
+            param(
+                event_type="m.room.encrypted",
+                event_content={
+                    "algorithm": "m.megolm.v1.aes-sha2",
+                    "ciphertext": "AwgAEnACgAkLmt6qF84IK++J7UDH2Za1YVchHyprqTqsg...",
+                    "device_id": "RJYKSTBOIE",
+                    "sender_key": "IlRMeOPX2e0MurIyfWEucYBRVOEEUMrOHqn/8mLqMjA",
+                    "session_id": "X3lUlvLELLYxeTx4yOVu6UDpasGEVO0Jbu+QFnm0cKQ",
+                },
+            ),
+        ]
+    )
+    def test_sending_event_and_leaving_does_not_record_participation(
+        self,
+        event_type: str,
+        event_content: JsonDict,
+    ) -> None:
+        """
+        Test that sending an event into a room that should mark a user as a
+        participant, but then leaving the room, results in the user no longer
+        be marked as a participant in that room.
+        """
+        self.helper.join(self.room1, self.user2, tok=self.tok2)
+
+        # user has not sent any messages, so should not be a participant
+        participant = self.get_success(
+            self.store.get_room_participation(self.user2, self.room1)
+        )
+        self.assertFalse(participant)
+
+        # sending a message should now mark user as participant
+        self.helper.send_event(
+            self.room1,
+            event_type,
+            content=event_content,
+            tok=self.tok2,
+        )
+        participant = self.get_success(
+            self.store.get_room_participation(self.user2, self.room1)
+        )
+        self.assertTrue(participant)
+
+        # leave the room
+        self.helper.leave(self.room1, self.user2, tok=self.tok2)
+
+        # user should no longer be considered a participant
+        participant = self.get_success(
+            self.store.get_room_participation(self.user2, self.room1)
+        )
+        self.assertFalse(participant)

tests/rest/media/test_domain_blocking.py

@@ -61,6 +61,7 @@ class MediaDomainBlockingTests(unittest.HomeserverTestCase):
                 time_now_ms=clock.time_msec(),
                 upload_name="test.png",
                 filesystem_id=file_id,
+                sha256=file_id,
             )
         )
 

tests/storage/test_purge.py

@@ -313,46 +313,93 @@ class PurgeTests(HomeserverTestCase):
             self.room_id, "org.matrix.test", body={"number": 2}
         )
         # Create enough state events to require multiple batches of
-        # delete_unreferenced_state_groups_bg_update to be run.
+        # mark_unreferenced_state_groups_for_deletion_bg_update to be run.
         for i in range(200):
             self.helper.send_state(self.room_id, "org.matrix.test", body={"number": i})
-        state2 = self.helper.send_state(
-            self.room_id, "org.matrix.test", body={"number": 3}
-        )
         self.helper.send(self.room_id, body="test4")
         last = self.helper.send(self.room_id, body="test5")
 
-        # Create an unreferenced state group that has a prev group of one of the
-        # to-be-purged events.
+        # Create an unreferenced state group that has no prev group.
+        unreferenced_free_state_group = self.get_success(
+            self.state_store.store_state_group(
+                event_id=last["event_id"],
+                room_id=self.room_id,
+                prev_group=None,
+                delta_ids={("org.matrix.test", ""): state1["event_id"]},
+                current_state_ids={("org.matrix.test", ""): ""},
+            )
+        )
+
+        # Create some unreferenced state groups that have a prev group of one of the
+        # existing state groups.
         prev_group = self.get_success(
             self.store._get_state_group_for_event(state1["event_id"])
         )
-        unreferenced_state_group = self.get_success(
+        unreferenced_end_state_group = self.get_success(
             self.state_store.store_state_group(
                 event_id=last["event_id"],
                 room_id=self.room_id,
                 prev_group=prev_group,
-                delta_ids={("org.matrix.test", ""): state2["event_id"]},
+                delta_ids={("org.matrix.test", ""): state1["event_id"]},
+                current_state_ids=None,
+            )
+        )
+        another_unreferenced_end_state_group = self.get_success(
+            self.state_store.store_state_group(
+                event_id=last["event_id"],
+                room_id=self.room_id,
+                prev_group=unreferenced_end_state_group,
+                delta_ids={("org.matrix.test", ""): state1["event_id"]},
                 current_state_ids=None,
             )
         )
 
-        another_unreferenced_state_group = self.get_success(
+        # Add some other unreferenced state groups which lead to a referenced state
+        # group.
+        # These state groups should not get deleted.
+        chain_state_group = self.get_success(
             self.state_store.store_state_group(
                 event_id=last["event_id"],
                 room_id=self.room_id,
-                prev_group=unreferenced_state_group,
-                delta_ids={("org.matrix.test", ""): state2["event_id"]},
+                prev_group=None,
+                delta_ids={("org.matrix.test", ""): ""},
+                current_state_ids={("org.matrix.test", ""): ""},
+            )
+        )
+        chain_state_group_2 = self.get_success(
+            self.state_store.store_state_group(
+                event_id=last["event_id"],
+                room_id=self.room_id,
+                prev_group=chain_state_group,
+                delta_ids={("org.matrix.test", ""): ""},
                 current_state_ids=None,
             )
         )
+        referenced_chain_state_group = self.get_success(
+            self.state_store.store_state_group(
+                event_id=last["event_id"],
+                room_id=self.room_id,
+                prev_group=chain_state_group_2,
+                delta_ids={("org.matrix.test", ""): ""},
+                current_state_ids=None,
+            )
+        )
+        self.get_success(
+            self.store.db_pool.simple_insert(
+                "event_to_state_groups",
+                {
+                    "event_id": "$new_event",
+                    "state_group": referenced_chain_state_group,
+                },
+            )
+        )
 
         # Insert and run the background update.
         self.get_success(
             self.store.db_pool.simple_insert(
                 "background_updates",
                 {
-                    "update_name": _BackgroundUpdates.DELETE_UNREFERENCED_STATE_GROUPS_BG_UPDATE,
+                    "update_name": _BackgroundUpdates.MARK_UNREFERENCED_STATE_GROUPS_FOR_DELETION_BG_UPDATE,
                     "progress_json": "{}",
                 },
             )
@@ -365,11 +412,11 @@ class PurgeTests(HomeserverTestCase):
             1 + self.state_deletion_store.DELAY_BEFORE_DELETION_MS / 1000
         )
 
-        # We expect that the unreferenced state group has been deleted.
+        # We expect that the unreferenced free state group has been deleted.
         row = self.get_success(
             self.state_store.db_pool.simple_select_one_onecol(
                 table="state_groups",
-                keyvalues={"id": unreferenced_state_group},
+                keyvalues={"id": unreferenced_free_state_group},
                 retcol="id",
                 allow_none=True,
                 desc="test_purge_unreferenced_state_group",
@@ -377,11 +424,21 @@ class PurgeTests(HomeserverTestCase):
         )
         self.assertIsNone(row)
 
-        # We expect that the other unreferenced state group has also been deleted.
+        # We expect that both unreferenced end state groups have been deleted.
         row = self.get_success(
             self.state_store.db_pool.simple_select_one_onecol(
                 table="state_groups",
-                keyvalues={"id": another_unreferenced_state_group},
+                keyvalues={"id": unreferenced_end_state_group},
+                retcol="id",
+                allow_none=True,
+                desc="test_purge_unreferenced_state_group",
+            )
+        )
+        self.assertIsNone(row)
+        row = self.get_success(
+            self.state_store.db_pool.simple_select_one_onecol(
+                table="state_groups",
+                keyvalues={"id": another_unreferenced_end_state_group},
                 retcol="id",
                 allow_none=True,
                 desc="test_purge_unreferenced_state_group",
@@ -399,4 +456,4 @@ class PurgeTests(HomeserverTestCase):
                 desc="test_purge_unreferenced_state_group",
             )
         )
-        self.assertEqual(len(state_groups), 207)
+        self.assertEqual(len(state_groups), 210)

tests/test_utils/__init__.py

@@ -139,6 +139,8 @@ SMALL_PNG = unhexlify(
     b"0000001f15c4890000000a49444154789c63000100000500010d"
     b"0a2db40000000049454e44ae426082"
 )
+# The SHA256 hexdigest for the above bytes.
+SMALL_PNG_SHA256 = "ebf4f635a17d10d6eb46ba680b70142419aa3220f228001a036d311a22ee9d2a"
 
 # A small CMYK-encoded JPEG image used in some tests.
 #