wip record doc versions

* `m.login.jwt`, which was never specced and has been deprecated
  since Synapse 1.16.0. (`org.matrix.login.jwt` can be used instead.)
* `uk.half-shot.msc2778.login.application_service`, which was
  stabilized as part of the Matrix spec v1.2 release.

.ci/latest_deps_build_failed_issue_template.md

@@ -0,0 +1,4 @@
+---
+title: CI run against latest deps is failing
+---
+See https://github.com/{{env.GITHUB_REPOSITORY}}/actions/runs/{{env.GITHUB_RUN_ID}}

.ci/patch_for_twisted_trunk.sh

@@ -1,8 +0,0 @@
-#!/bin/sh
-
-# replaces the dependency on Twisted in `python_dependencies` with trunk.
-
-set -e
-cd "$(dirname "$0")"/..
-
-sed -i -e 's#"Twisted.*"#"Twisted @ git+https://github.com/twisted/twisted"#' synapse/python_dependencies.py

.ci/scripts/record_available_doc_versions.py

@@ -0,0 +1,28 @@
+#!/usr/bin/env python3
+# This script will write a json file to $OUTPUT_FILE that contains the name of
+# each available Synapse version with documentation.
+#
+# This script assumes that any top-level directory in the "gh-pages" branch is
+# named after a documentation version and contains documentation website files.
+
+import os.path
+import json
+
+OUTPUT_FILE = "versions.json"
+
+# Determine the list of Synapse versions that have documentation.
+doc_versions = []
+for filepath in os.listdir():
+    if os.path.isdir(filepath):
+        doc_versions.append(filepath)
+
+# Record the documentation versions in a json file, such that the
+# frontend javascript is aware of what versions exist.
+to_write = {
+    "versions": doc_versions,
+    "default_version": "latest",
+}
+
+# Write the file.
+with open(OUTPUT_FILE, "w") as f:
+    f.write(json.dumps(to_write))

.ci/scripts/test_export_data_command.sh

@@ -2,29 +2,24 @@
 
 # Test for the export-data admin command against sqlite and postgres
 
+# Expects Synapse to have been already installed with `poetry install --extras postgres`.
+# Expects `poetry` to be available on the `PATH`.
+
 set -xe
 cd "$(dirname "$0")/../.."
 
-echo "--- Install dependencies"
-
-# Install dependencies for this test.
-pip install psycopg2
-
-# Install Synapse itself. This won't update any libraries.
-pip install -e .
-
 echo "--- Generate the signing key"
 
 # Generate the server's signing key.
-python -m synapse.app.homeserver --generate-keys -c .ci/sqlite-config.yaml
+poetry run synapse_homeserver --generate-keys -c .ci/sqlite-config.yaml
 
 echo "--- Prepare test database"
 
 # Make sure the SQLite3 database is using the latest schema and has no pending background update.
-scripts/update_synapse_database --database-config .ci/sqlite-config.yaml --run-background-updates
+poetry run update_synapse_database --database-config .ci/sqlite-config.yaml --run-background-updates
 
 # Run the export-data command on the sqlite test database
-python -m synapse.app.admin_cmd -c .ci/sqlite-config.yaml  export-data @anon-20191002_181700-832:localhost:8800 \
+poetry run python -m synapse.app.admin_cmd -c .ci/sqlite-config.yaml  export-data @anon-20191002_181700-832:localhost:8800 \
 --output-directory /tmp/export_data
 
 # Test that the output directory exists and contains the rooms directory
@@ -37,14 +32,14 @@ else
 fi
 
 # Create the PostgreSQL database.
-.ci/scripts/postgres_exec.py "CREATE DATABASE synapse"
+poetry run .ci/scripts/postgres_exec.py "CREATE DATABASE synapse"
 
 # Port the SQLite databse to postgres so we can check command works against postgres
 echo "+++ Port SQLite3 databse to postgres"
-scripts/synapse_port_db --sqlite-database .ci/test_db.db --postgres-config .ci/postgres-config.yaml
+poetry run synapse_port_db --sqlite-database .ci/test_db.db --postgres-config .ci/postgres-config.yaml
 
 # Run the export-data command on postgres database
-python -m synapse.app.admin_cmd -c .ci/postgres-config.yaml  export-data @anon-20191002_181700-832:localhost:8800 \
+poetry run python -m synapse.app.admin_cmd -c .ci/postgres-config.yaml  export-data @anon-20191002_181700-832:localhost:8800 \
 --output-directory /tmp/export_data2
 
 # Test that the output directory exists and contains the rooms directory

.ci/scripts/test_old_deps.sh

@@ -1,6 +1,9 @@
 #!/usr/bin/env bash
-# this script is run by GitHub Actions in a plain `focal` container; it installs the
+# this script is run by GitHub Actions in a plain `focal` container; it
-# minimal requirements for tox and hands over to the py3-old tox environment.
+# - installs the minimal system requirements, and poetry;
+# - patches the project definition file to refer to old versions only;
+# - creates a venv with these old versions using poetry; and finally
+# - invokes `trial` to run the tests with old deps.
 
 # Prevent tzdata from asking for user input
 export DEBIAN_FRONTEND=noninteractive
@@ -8,11 +11,71 @@ export DEBIAN_FRONTEND=noninteractive
 set -ex
 
 apt-get update
-apt-get install -y python3 python3-dev python3-pip libxml2-dev libxslt-dev xmlsec1 zlib1g-dev tox libjpeg-dev libwebp-dev
+apt-get install -y \
+        python3 python3-dev python3-pip python3-venv pipx \
+        libxml2-dev libxslt-dev xmlsec1 zlib1g-dev libjpeg-dev libwebp-dev
 
 export LANG="C.UTF-8"
 
 # Prevent virtualenv from auto-updating pip to an incompatible version
 export VIRTUALENV_NO_DOWNLOAD=1
 
-exec tox -e py3-old,combine
+# TODO: in the future, we could use an implementation of
+#   https://github.com/python-poetry/poetry/issues/3527
+#   https://github.com/pypa/pip/issues/8085
+# to select the lowest possible versions, rather than resorting to this sed script.
+
+# Patch the project definitions in-place:
+# - Replace all lower and tilde bounds with exact bounds
+# - Make the pyopenssl 17.0, which is the oldest version that works with
+#   a `cryptography` compiled against OpenSSL 1.1.
+# - Delete all lines referring to psycopg2 --- so no testing of postgres support.
+# - Omit systemd: we're not logging to journal here.
+
+# TODO: also replace caret bounds, see https://python-poetry.org/docs/dependency-specification/#version-constraints
+# We don't use these yet, but IIRC they are the default bound used when you `poetry add`.
+# The sed expression 's/\^/==/g' ought to do the trick. But it would also change
+# `python = "^3.7"` to `python = "==3.7", which would mean we fail because olddeps
+# runs on 3.8 (#12343).
+
+sed -i \
+   -e "s/[~>]=/==/g" \
+   -e "/psycopg2/d" \
+   -e 's/pyOpenSSL = "==16.0.0"/pyOpenSSL = "==17.0.0"/' \
+   -e '/systemd/d' \
+   pyproject.toml
+
+# Use poetry to do the installation. This ensures that the versions are all mutually
+# compatible (as far the package metadata declares, anyway); pip's package resolver
+# is more lax.
+#
+# Rather than `poetry install --no-dev`, we drop all dev dependencies from the
+# toml file. This means we don't have to ensure compatibility between old deps and
+# dev tools.
+
+pip install --user toml
+
+REMOVE_DEV_DEPENDENCIES="
+import toml
+with open('pyproject.toml', 'r') as f:
+    data = toml.loads(f.read())
+
+del data['tool']['poetry']['dev-dependencies']
+
+with open('pyproject.toml', 'w') as f:
+    toml.dump(data, f)
+"
+python3 -c "$REMOVE_DEV_DEPENDENCIES"
+
+pipx install poetry==1.1.12
+~/.local/bin/poetry lock
+
+echo "::group::Patched pyproject.toml"
+cat pyproject.toml
+echo "::endgroup::"
+echo "::group::Lockfile after patch"
+cat poetry.lock
+echo "::endgroup::"
+
+~/.local/bin/poetry install -E "all test"
+~/.local/bin/poetry run trial --jobs=2 tests

.ci/scripts/test_synapse_port_db.sh

@@ -1,41 +1,37 @@
 #!/usr/bin/env bash
 #
 # Test script for 'synapse_port_db'.
-#   - sets up synapse and deps
+#   - configures synapse and a postgres server.
 #   - runs the port script on a prepopulated test sqlite db
 #   - also runs it against an new sqlite db
-
+#
+# Expects Synapse to have been already installed with `poetry install --extras postgres`.
+# Expects `poetry` to be available on the `PATH`.
 
 set -xe
 cd "$(dirname "$0")/../.."
 
-echo "--- Install dependencies"
-
-# Install dependencies for this test.
-pip install psycopg2 coverage coverage-enable-subprocess
-
-# Install Synapse itself. This won't update any libraries.
-pip install -e .
-
 echo "--- Generate the signing key"
 
 # Generate the server's signing key.
-python -m synapse.app.homeserver --generate-keys -c .ci/sqlite-config.yaml
+poetry run synapse_homeserver --generate-keys -c .ci/sqlite-config.yaml
 
 echo "--- Prepare test database"
 
 # Make sure the SQLite3 database is using the latest schema and has no pending background update.
-scripts/update_synapse_database --database-config .ci/sqlite-config.yaml --run-background-updates
+poetry run update_synapse_database --database-config .ci/sqlite-config.yaml --run-background-updates
 
 # Create the PostgreSQL database.
-.ci/scripts/postgres_exec.py "CREATE DATABASE synapse"
+poetry run .ci/scripts/postgres_exec.py "CREATE DATABASE synapse"
 
 echo "+++ Run synapse_port_db against test database"
-coverage run scripts/synapse_port_db --sqlite-database .ci/test_db.db --postgres-config .ci/postgres-config.yaml
+# TODO: this invocation of synapse_port_db (and others below) used to be prepended with `coverage run`,
+# but coverage seems unable to find the entrypoints installed by `pip install -e .`.
+poetry run synapse_port_db --sqlite-database .ci/test_db.db --postgres-config .ci/postgres-config.yaml
 
 # We should be able to run twice against the same database.
 echo "+++ Run synapse_port_db a second time"
-coverage run scripts/synapse_port_db --sqlite-database .ci/test_db.db --postgres-config .ci/postgres-config.yaml
+poetry run synapse_port_db --sqlite-database .ci/test_db.db --postgres-config .ci/postgres-config.yaml
 
 #####
 
@@ -46,12 +42,12 @@ echo "--- Prepare empty SQLite database"
 # we do this by deleting the sqlite db, and then doing the same again.
 rm .ci/test_db.db
 
-scripts/update_synapse_database --database-config .ci/sqlite-config.yaml --run-background-updates
+poetry run update_synapse_database --database-config .ci/sqlite-config.yaml --run-background-updates
 
 # re-create the PostgreSQL database.
-.ci/scripts/postgres_exec.py \
+poetry run .ci/scripts/postgres_exec.py \
   "DROP DATABASE synapse" \
   "CREATE DATABASE synapse"
 
 echo "+++ Run synapse_port_db against empty database"
-coverage run scripts/synapse_port_db --sqlite-database .ci/test_db.db --postgres-config .ci/postgres-config.yaml
+poetry run synapse_port_db --sqlite-database .ci/test_db.db --postgres-config .ci/postgres-config.yaml

.dockerignore

@@ -3,11 +3,9 @@
 
 # things to include
 !docker
-!scripts
 !synapse
-!MANIFEST.in
 !README.rst
-!setup.py
+!pyproject.toml
-!synctl
+!poetry.lock
 
 **/__pycache__

.flake8

@@ -0,0 +1,11 @@
+# TODO: incorporate this into pyproject.toml if flake8 supports it in the future.
+# See https://github.com/PyCQA/flake8/issues/234
+[flake8]
+# see https://pycodestyle.readthedocs.io/en/latest/intro.html#error-codes
+# for error codes. The ones we ignore are:
+#  W503: line break before binary operator
+#  W504: line break after binary operator
+#  E203: whitespace before ':' (which is contrary to pep8?)
+#  E731: do not assign a lambda expression, use a def
+#  E501: Line too long (black enforces this for us)
+ignore=W503,W504,E203,E731,E501

.github/workflows/docs.yaml

@@ -14,7 +14,7 @@ on:
 
 jobs:
   pages:
-    name: GitHub Pages
+    name: Build and deploy docs
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v2
@@ -22,7 +22,7 @@ jobs:
       - name: Setup mdbook
         uses: peaceiris/actions-mdbook@4b5ef36b314c2599664ca107bb8c02412548d79d # v1.1.14
         with:
-          mdbook-version: '0.4.9'
+          mdbook-version: '0.4.17'
 
       - name: Build the documentation
         # mdbook will only create an index.html if we're including docs/README.md in SUMMARY.md.
@@ -63,3 +63,29 @@ jobs:
           github_token: ${{ secrets.GITHUB_TOKEN }}
           publish_dir: ./book
           destination_dir: ./${{ steps.vars.outputs.branch-version }}
+
+  list_available_versions:
+    needs: pages
+    runs-on: ubuntu-latest
+    steps:
+      # Check out the current branch
+      - uses: actions/checkout@v3
+        with:
+          persist-credentials: false
+
+      - name: Save the script
+        run: cp .ci/scripts/record_available_doc_versions.py /
+
+      - uses: actions/setup-python@v3
+
+      # Check out the gh-pages branch, which we'll be pushing the doc versions to
+      - uses: actions/checkout@v3
+        with:
+          persist-credentials: false
+          # Check out the gh-pages branch
+          ref: 'gh-pages'
+
+      - name: Record the available documentation versions
+        run: |
+          # Download the script
+          /record_available_doc_versions

.github/workflows/latest_deps.yml

@@ -0,0 +1,159 @@
+# People who are freshly `pip install`ing from PyPI will pull in the latest versions of
+# dependencies which match the broad requirements. Since most CI runs are against
+# the locked poetry environment, run specifically against the latest dependencies to
+# know if there's an upcoming breaking change.
+#
+# As an overview this workflow:
+# - checks out develop,
+# - installs from source, pulling in the dependencies like a fresh `pip install` would, and 
+# - runs mypy and test suites in that checkout.
+#
+# Based on the twisted trunk CI job.
+
+name: Latest dependencies
+
+on:
+  schedule:
+    - cron: 0 7 * * *
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  mypy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      # 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
+        with:
+          python-version: "3.x"
+          poetry-version: "1.2.0b1"
+          extras: "all"
+      # Dump installed versions for debugging.
+      - run: poetry run pip list > before.txt
+      # Upgrade all runtime dependencies only. This is intended to mimic a fresh
+      # `pip install matrix-synapse[all]` as closely as possible.
+      - run: poetry update --no-dev
+      - run: poetry run pip list > after.txt && (diff -u before.txt after.txt || true)
+      - name: Remove warn_unused_ignores from mypy config
+        run: sed '/warn_unused_ignores = True/d' -i mypy.ini
+      - run: poetry run mypy
+  trial:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        include:
+          - database: "sqlite"
+          - database: "postgres"
+            postgres-version: "14"
+
+    steps:
+      - uses: actions/checkout@v2
+      - run: sudo apt-get -qq install xmlsec1
+      - name: Set up PostgreSQL ${{ matrix.postgres-version }}
+        if: ${{ matrix.postgres-version }}
+        run: |
+          docker run -d -p 5432:5432 \
+            -e POSTGRES_PASSWORD=postgres \
+            -e POSTGRES_INITDB_ARGS="--lc-collate C --lc-ctype C --encoding UTF8" \
+            postgres:${{ matrix.postgres-version }}
+      - uses: actions/setup-python@v2
+        with:
+          python-version: "3.x"
+      - run: pip install .[all,test]
+      - name: Await PostgreSQL
+        if: ${{ matrix.postgres-version }}
+        timeout-minutes: 2
+        run: until pg_isready -h localhost; do sleep 1; done
+      - run: python -m twisted.trial --jobs=2 tests
+        env:
+          SYNAPSE_POSTGRES: ${{ matrix.database == 'postgres' || '' }}
+          SYNAPSE_POSTGRES_HOST: localhost
+          SYNAPSE_POSTGRES_USER: postgres
+          SYNAPSE_POSTGRES_PASSWORD: postgres
+      - name: Dump logs
+        # Logs are most useful when the command fails, always include them.
+        if: ${{ always() }}
+        # Note: Dumps to workflow logs instead of using actions/upload-artifact
+        #       This keeps logs colocated with failing jobs
+        #       It also ignores find's exit code; this is a best effort affair
+        run: >-
+          find _trial_temp -name '*.log'
+          -exec echo "::group::{}" \;
+          -exec cat {} \;
+          -exec echo "::endgroup::" \;
+          || true
+
+
+  sytest:
+    runs-on: ubuntu-latest
+    container:
+      image: matrixdotorg/sytest-synapse:testing
+      volumes:
+        - ${{ github.workspace }}:/src
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - sytest-tag: focal
+
+          - sytest-tag: focal
+            postgres: postgres
+            workers: workers
+            redis: redis
+    env:
+      POSTGRES: ${{ matrix.postgres && 1}}
+      WORKERS: ${{ matrix.workers && 1 }}
+      REDIS: ${{ matrix.redis && 1 }}
+      BLACKLIST: ${{ matrix.workers && 'synapse-blacklist-with-workers' }}
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Ensure sytest runs `pip install`
+        # Delete the lockfile so sytest will `pip install` rather than `poetry install`
+        run: rm /src/poetry.lock
+        working-directory: /src
+      - name: Prepare test blacklist
+        run: cat sytest-blacklist .ci/worker-blacklist > synapse-blacklist-with-workers
+      - name: Run SyTest
+        run: /bootstrap.sh synapse
+        working-directory: /src
+      - name: Summarise results.tap
+        if: ${{ always() }}
+        run: /sytest/scripts/tap_to_gha.pl /logs/results.tap
+      - name: Upload SyTest logs
+        uses: actions/upload-artifact@v2
+        if: ${{ always() }}
+        with:
+          name: Sytest Logs - ${{ job.status }} - (${{ join(matrix.*, ', ') }})
+          path: |
+            /logs/results.tap
+            /logs/**/*.log*
+
+
+  # TODO: run complement (as with twisted trunk, see #12473).
+
+  # open an issue if the build fails, so we know about it.
+  open-issue:
+    if: failure()
+    needs:
+      # TODO: should mypy be included here? It feels more brittle than the other two.
+      - mypy
+      - trial
+      - sytest
+
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v2
+      - uses: JasonEtco/create-an-issue@5d9504915f79f9cc6d791934b8ef34f2353dd74d # v2.5.0, 2020-12-06
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          update_existing: true
+          filename: .ci/latest_deps_build_failed_issue_template.md
+

.github/workflows/release-artifacts.yml

@@ -7,7 +7,7 @@ on:
   # of things breaking (but only build one set of debs)
   pull_request:
   push:
-    branches: ["develop"]
+    branches: ["develop", "release-*"]
 
     # we do the full build on tags.
     tags: ["v*"]
@@ -31,7 +31,7 @@ jobs:
           # if we're running from a tag, get the full list of distros; otherwise just use debian:sid
           dists='["debian:sid"]'
           if [[ $GITHUB_REF == refs/tags/* ]]; then
-              dists=$(scripts-dev/build_debian_packages --show-dists-json)
+              dists=$(scripts-dev/build_debian_packages.py --show-dists-json)
           fi
           echo "::set-output name=distros::$dists"
     # map the step outputs to job outputs
@@ -74,7 +74,7 @@ jobs:
         # see https://github.com/docker/build-push-action/issues/252
         # for the cache magic here
         run: |
-          ./src/scripts-dev/build_debian_packages \
+          ./src/scripts-dev/build_debian_packages.py \
             --docker-build-arg=--cache-from=type=local,src=/tmp/.buildx-cache \
             --docker-build-arg=--cache-to=type=local,mode=max,dest=/tmp/.buildx-cache-new \
             --docker-build-arg=--progress=plain \
@@ -91,17 +91,7 @@ jobs:
 
   build-sdist:
     name: "Build pypi distribution files"
-    runs-on: ubuntu-latest
+    uses: "matrix-org/backend-meta/.github/workflows/packaging.yml@v1"
-    steps:
-      - uses: actions/checkout@v2
-      - uses: actions/setup-python@v2
-      - run: pip install wheel
-      - run: |
-          python setup.py sdist bdist_wheel
-      - uses: actions/upload-artifact@v2
-        with:
-          name: python-dist
-          path: dist/*
 
   # if it's a tag, create a release and attach the artifacts to it
   attach-assets:
@@ -122,7 +112,8 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:
           files: |
-            python-dist/*
+            Sdist/*
+            Wheel/*
             debs.tar.xz
           # if it's not already published, keep the release as a draft.
           draft: true

.github/workflows/tests.yml

@@ -10,22 +10,19 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  lint:
+  check-sampleconfig:
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        toxenv:
-          - "check-sampleconfig"
-          - "check_codestyle"
-          - "check_isort"
-          - "mypy"
-          - "packaging"
-
     steps:
       - uses: actions/checkout@v2
       - uses: actions/setup-python@v2
-      - run: pip install tox
+      - run: pip install .
-      - run: tox -e ${{ matrix.toxenv }}
+      - run: scripts-dev/generate_sample_config.sh --check
+      - run: scripts-dev/config-lint.sh
+
+  lint:
+    uses: "matrix-org/backend-meta/.github/workflows/python-poetry-ci.yml@v1"
+    with:
+      typechecking-extras: "all"
 
   lint-crlf:
     runs-on: ubuntu-latest
@@ -43,29 +40,15 @@ jobs:
           ref: ${{ github.event.pull_request.head.sha }}
           fetch-depth: 0
       - uses: actions/setup-python@v2
-      - run: pip install tox
+      - run: "pip install 'towncrier>=18.6.0rc1'"
-      - run: scripts-dev/check-newsfragment
+      - run: scripts-dev/check-newsfragment.sh
         env:
           PULL_REQUEST_NUMBER: ${{ github.event.number }}
 
-  lint-sdist:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v2
-      - uses: actions/setup-python@v2
-        with:
-          python-version: "3.x"
-      - run: pip install wheel
-      - run: python setup.py sdist bdist_wheel
-      - uses: actions/upload-artifact@v2
-        with:
-          name: Python Distributions
-          path: dist/*
-
   # Dummy step to gate other tests on without repeating the whole list
   linting-done:
     if: ${{ !cancelled() }} # Run this even if prior jobs were skipped
-    needs: [lint, lint-crlf, lint-newsfile, lint-sdist]
+    needs: [lint, lint-crlf, lint-newsfile, check-sampleconfig]
     runs-on: ubuntu-latest
     steps:
       - run: "true"
@@ -78,23 +61,23 @@ jobs:
       matrix:
         python-version: ["3.7", "3.8", "3.9", "3.10"]
         database: ["sqlite"]
-        toxenv: ["py"]
+        extras: ["all"]
         include:
           # Newest Python without optional deps
           - python-version: "3.10"
-            toxenv: "py-noextras"
+            extras: ""
 
           # Oldest Python with PostgreSQL
           - python-version: "3.7"
             database: "postgres"
             postgres-version: "10"
-            toxenv: "py"
+            extras: "all"
 
           # Newest Python with newest PostgreSQL
           - python-version: "3.10"
             database: "postgres"
             postgres-version: "14"
-            toxenv: "py"
+            extras: "all"
 
     steps:
       - uses: actions/checkout@v2
@@ -106,17 +89,16 @@ 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@v2
+      - uses: matrix-org/setup-python-poetry@v1
         with:
           python-version: ${{ matrix.python-version }}
-      - run: pip install tox
+          extras: ${{ matrix.extras }}
       - name: Await PostgreSQL
         if: ${{ matrix.postgres-version }}
         timeout-minutes: 2
         run: until pg_isready -h localhost; do sleep 1; done
-      - run: tox -e ${{ matrix.toxenv }}
+      - run: poetry run trial --jobs=2 tests
         env:
-          TRIAL_FLAGS: "--jobs=2"
           SYNAPSE_POSTGRES: ${{ matrix.database == 'postgres' || '' }}
           SYNAPSE_POSTGRES_HOST: localhost
           SYNAPSE_POSTGRES_USER: postgres
@@ -135,6 +117,7 @@ jobs:
           || true
 
   trial-olddeps:
+    # Note: sqlite only; no postgres
     if: ${{ !cancelled() && !failure() }} # Allow previous steps to be skipped, but not fail
     needs: linting-done
     runs-on: ubuntu-latest
@@ -142,11 +125,11 @@ jobs:
       - uses: actions/checkout@v2
       - name: Test with old deps
         uses: docker://ubuntu:focal # For old python and sqlite
+        # Note: focal seems to be using 3.8, but the oldest is 3.7?
+        # See https://github.com/matrix-org/synapse/issues/12343
         with:
           workdir: /github/workspace
           entrypoint: .ci/scripts/test_old_deps.sh
-        env:
-          TRIAL_FLAGS: "--jobs=2"
       - name: Dump logs
         # Logs are most useful when the command fails, always include them.
         if: ${{ always() }}
@@ -162,23 +145,24 @@ jobs:
 
   trial-pypy:
     # Very slow; only run if the branch name includes 'pypy'
+    # Note: sqlite only; no postgres. Completely untested since poetry move.
     if: ${{ contains(github.ref, 'pypy') && !failure() && !cancelled() }}
     needs: linting-done
     runs-on: ubuntu-latest
     strategy:
       matrix:
         python-version: ["pypy-3.7"]
+        extras: ["all"]
 
     steps:
       - uses: actions/checkout@v2
+      # Install libs necessary for PyPy to build binary wheels for dependencies
       - run: sudo apt-get -qq install xmlsec1 libxml2-dev libxslt-dev
-      - uses: actions/setup-python@v2
+      - uses: matrix-org/setup-python-poetry@v1
         with:
           python-version: ${{ matrix.python-version }}
-      - run: pip install tox
+          extras: ${{ matrix.extras }}
-      - run: tox -e py
+      - run: poetry run trial --jobs=2 tests
-        env:
-          TRIAL_FLAGS: "--jobs=2"
       - name: Dump logs
         # Logs are most useful when the command fails, always include them.
         if: ${{ always() }}
@@ -277,9 +261,10 @@ jobs:
     steps:
       - uses: actions/checkout@v2
       - run: sudo apt-get -qq install xmlsec1
-      - uses: actions/setup-python@v2
+      - uses: matrix-org/setup-python-poetry@v1
         with:
-          python-version: "3.9"
+          python-version: ${{ matrix.python-version }}
+          extras: "postgres"
       - run: .ci/scripts/test_export_data_command.sh
 
   portdb:
@@ -314,9 +299,10 @@ jobs:
     steps:
       - uses: actions/checkout@v2
       - run: sudo apt-get -qq install xmlsec1
-      - uses: actions/setup-python@v2
+      - uses: matrix-org/setup-python-poetry@v1
         with:
           python-version: ${{ matrix.python-version }}
+          extras: "postgres"
       - run: .ci/scripts/test_synapse_port_db.sh
 
   complement:
@@ -345,7 +331,7 @@ jobs:
           path: synapse
 
       # Attempt to check out the same branch of Complement as the PR. If it
-      # doesn't exist, fallback to master.
+      # doesn't exist, fallback to HEAD.
       - name: Checkout complement
         shell: bash
         run: |
@@ -358,8 +344,8 @@ jobs:
           #    for pull requests, otherwise GITHUB_REF).
           # 2. Attempt to use the base branch, e.g. when merging into release-vX.Y
           #    (GITHUB_BASE_REF for pull requests).
-          # 3. Use the default complement branch ("master").
+          # 3. Use the default complement branch ("HEAD").
-          for BRANCH_NAME in "$GITHUB_HEAD_REF" "$GITHUB_BASE_REF" "${GITHUB_REF#refs/heads/}" "master"; do
+          for BRANCH_NAME in "$GITHUB_HEAD_REF" "$GITHUB_BASE_REF" "${GITHUB_REF#refs/heads/}" "HEAD"; do
             # Skip empty branch names and merge commits.
             if [[ -z "$BRANCH_NAME" || $BRANCH_NAME =~ ^refs/pull/.* ]]; then
               continue
@@ -368,61 +354,32 @@ jobs:
             (wget -O - "https://github.com/matrix-org/complement/archive/$BRANCH_NAME.tar.gz" | tar -xz --strip-components=1 -C complement) && break
           done
 
-      # Build initial Synapse image
-      - run: docker build -t matrixdotorg/synapse:latest -f docker/Dockerfile .
-        working-directory: synapse
-        env:
-          DOCKER_BUILDKIT: 1
-
-      # Build a ready-to-run Synapse image based on the initial image above.
-      # This new image includes a config file, keys for signing and TLS, and
-      # other settings to make it suitable for testing under Complement.
-      - run: docker build -t complement-synapse -f Synapse.Dockerfile .
-        working-directory: complement/dockerfiles
-
-      # Run Complement
       - run: |
           set -o pipefail
-          go test -v -json -tags synapse_blacklist,msc2403 ./tests/... 2>&1 | gotestfmt
+          COMPLEMENT_DIR=`pwd`/complement synapse/scripts-dev/complement.sh -json 2>&1 | gotestfmt
         shell: bash
         name: Run Complement Tests
-        env:
-          COMPLEMENT_BASE_IMAGE: complement-synapse:latest
-        working-directory: complement
 
   # a job which marks all the other jobs as complete, thus allowing PRs to be merged.
   tests-done:
     if: ${{ always() }}
     needs:
+      - check-sampleconfig
       - lint
       - lint-crlf
       - lint-newsfile
-      - lint-sdist
       - trial
       - trial-olddeps
       - sytest
+      - export-data
       - portdb
       - complement
     runs-on: ubuntu-latest
     steps:
-      - name: Set build result
+      - uses: matrix-org/done-action@v2
-        env:
+        with:
-          NEEDS_CONTEXT: ${{ toJSON(needs) }}
+          needs: ${{ toJSON(needs) }}
-        # the `jq` incantation dumps out a series of "<job> <result>" lines.
-        # we set it to an intermediate variable to avoid a pipe, which makes it
-        # hard to set $rc.
-        run: |
-          rc=0
-          results=$(jq -r 'to_entries[] | [.key,.value.result] | join(" ")' <<< $NEEDS_CONTEXT)
-          while read job result ; do
-              # The newsfile lint may be skipped on non PR builds
-              if [ $result == "skipped" ] && [ $job == "lint-newsfile" ]; then
-                continue
-              fi
 
-              if [ "$result" != "success" ]; then
+          # The newsfile lint may be skipped on non PR builds
-                  echo "::set-failed ::Job $job returned $result"
+          skippable:
-                  rc=1
+            lint-newsfile
-              fi
-          done <<< $results
-          exit $rc

.github/workflows/twisted_trunk.yml

@@ -6,16 +6,27 @@ on:
 
   workflow_dispatch:
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
   mypy:
     runs-on: ubuntu-latest
 
     steps:
       - uses: actions/checkout@v2
-      - uses: actions/setup-python@v2
+      - uses: matrix-org/setup-python-poetry@v1
-      - run: .ci/patch_for_twisted_trunk.sh
+        with:
-      - run: pip install tox
+          python-version: "3.x"
-      - run: tox -e mypy
+          extras: "all"
+      - run: |
+          poetry remove twisted
+          poetry add --extras tls git+https://github.com/twisted/twisted.git#trunk
+          poetry install --no-interaction --extras "all test"
+      - name: Remove warn_unused_ignores from mypy config
+        run: sed '/warn_unused_ignores = True/d' -i mypy.ini
+      - run: poetry run mypy
 
   trial:
     runs-on: ubuntu-latest
@@ -23,14 +34,15 @@ jobs:
     steps:
       - uses: actions/checkout@v2
       - run: sudo apt-get -qq install xmlsec1
-      - uses: actions/setup-python@v2
+      - uses: matrix-org/setup-python-poetry@v1
         with:
-          python-version: 3.7
+          python-version: "3.x"
-      - run: .ci/patch_for_twisted_trunk.sh
+          extras: "all test"
-      - run: pip install tox
+      - run: |
-      - run: tox -e py
+          poetry remove twisted
-        env:
+          poetry add --extras tls git+https://github.com/twisted/twisted.git#trunk
-          TRIAL_FLAGS: "--jobs=2"
+          poetry install --no-interaction --extras "all test"
+      - run: poetry run trial --jobs 2 tests
 
       - name: Dump logs
         # Logs are most useful when the command fails, always include them.
@@ -55,11 +67,23 @@ jobs:
     steps:
       - uses: actions/checkout@v2
       - name: Patch dependencies
-        run: .ci/patch_for_twisted_trunk.sh
+        # Note: The poetry commands want to create a virtualenv in /src/.venv/,
+        #       but the sytest-synapse container expects it to be in /venv/.
+        #       We symlink it before running poetry so that poetry actually
+        #       ends up installing to `/venv`.
+        run: |
+          ln -s -T /venv /src/.venv
+          poetry remove twisted
+          poetry add --extras tls git+https://github.com/twisted/twisted.git#trunk
+          poetry install --no-interaction --extras "all test"
         working-directory: /src
       - name: Run SyTest
         run: /bootstrap.sh synapse
         working-directory: /src
+        env:
+          # Use offline mode to avoid reinstalling the pinned version of
+          # twisted.
+          OFFLINE: 1
       - name: Summarise results.tap
         if: ${{ always() }}
         run: /sytest/scripts/tap_to_gha.pl /logs/results.tap

.gitignore

@@ -15,6 +15,9 @@ _trial_temp*/
 .DS_Store
 __pycache__/
 
+# We do want the poetry lockfile.
+!poetry.lock
+
 # stuff that is likely to exist when you run a server locally
 /*.db
 /*.log
@@ -30,6 +33,9 @@ __pycache__/
 /media_store/
 /uploads
 
+# For direnv users
+/.envrc
+
 # IDEs
 /.idea/
 /.ropeproject/

MANIFEST.in

@@ -1,56 +0,0 @@
-include synctl
-include LICENSE
-include VERSION
-include *.rst
-include *.md
-include demo/README
-include demo/demo.tls.dh
-include demo/*.py
-include demo/*.sh
-
-include synapse/py.typed
-recursive-include synapse/storage *.sql
-recursive-include synapse/storage *.sql.postgres
-recursive-include synapse/storage *.sql.sqlite
-recursive-include synapse/storage *.py
-recursive-include synapse/storage *.txt
-recursive-include synapse/storage *.md
-
-recursive-include docs *
-recursive-include scripts *
-recursive-include scripts-dev *
-recursive-include synapse *.pyi
-recursive-include tests *.py
-recursive-include tests *.pem
-recursive-include tests *.p8
-recursive-include tests *.crt
-recursive-include tests *.key
-
-recursive-include synapse/res *
-recursive-include synapse/static *.css
-recursive-include synapse/static *.gif
-recursive-include synapse/static *.html
-recursive-include synapse/static *.js
-
-exclude .codecov.yml
-exclude .coveragerc
-exclude .dockerignore
-exclude .editorconfig
-exclude Dockerfile
-exclude mypy.ini
-exclude sytest-blacklist
-exclude test_postgresql.sh
-
-include book.toml
-include pyproject.toml
-recursive-include changelog.d *
-
-prune .circleci
-prune .github
-prune .ci
-prune contrib
-prune debian
-prune demo/etc
-prune docker
-prune snap
-prune stubs

README.rst

@@ -55,7 +55,7 @@ solutions. The hope is for Matrix to act as the building blocks for a new
 generation of fully open and interoperable messaging and VoIP apps for the
 internet.
 
-Synapse is a Matrix "homeserver" implementation developed by the matrix.org core 
+Synapse is a Matrix "homeserver" implementation developed by the matrix.org core
 team, written in Python 3/Twisted.
 
 In Matrix, every user runs one or more Matrix clients, which connect through to
@@ -246,7 +246,7 @@ Password reset
 ==============
 
 Users can reset their password through their client. Alternatively, a server admin
-can reset a users password using the `admin API <docs/admin_api/user_admin_api.rst#reset-password>`_
+can reset a users password using the `admin API <docs/admin_api/user_admin_api.md#reset-password>`_
 or by directly editing the database as shown below.
 
 First calculate the hash of the new password::
@@ -293,36 +293,42 @@ directory of your choice::
     git clone https://github.com/matrix-org/synapse.git
     cd synapse
 
-Synapse has a number of external dependencies, that are easiest
+Synapse has a number of external dependencies. We maintain a fixed development
-to install using pip and a virtualenv::
+environment using `Poetry <https://python-poetry.org/>`_. First, install poetry. We recommend::
 
-    python3 -m venv ./env
+    pip install --user pipx
-    source ./env/bin/activate
+    pipx install poetry
-    pip install -e ".[all,dev]"
+
+as described `here <https://python-poetry.org/docs/#installing-with-pipx>`_.
+(See `poetry's installation docs <https://python-poetry.org/docs/#installation>`_
+for other installation methods.) Then ask poetry to create a virtual environment
+from the project and install Synapse's dependencies::
+
+    poetry install --extras "all test"
 
 This will run a process of downloading and installing all the needed
-dependencies into a virtual env. If any dependencies fail to install,
+dependencies into a virtual env.
-try installing the failing modules individually::
 
-    pip install -e "module-name"
+We recommend using the demo which starts 3 federated instances running on ports `8080` - `8082`::
 
-We recommend using the demo which starts 3 federated instances running on ports `8080` - `8082`
+    poetry run ./demo/start.sh
 
-    ./demo/start.sh
+(to stop, you can use ``poetry run ./demo/stop.sh``)
 
-(to stop, you can use `./demo/stop.sh`)
+See the `demo documentation <https://matrix-org.github.io/synapse/develop/development/demo.html>`_
+for more information.
 
 If you just want to start a single instance of the app and run it directly::
 
     # Create the homeserver.yaml config once
-    python -m synapse.app.homeserver \
+    poetry run synapse_homeserver \
       --server-name my.domain.name \
       --config-path homeserver.yaml \
       --generate-config \
       --report-stats=[yes|no]
 
     # Start the app
-    python -m synapse.app.homeserver --config-path homeserver.yaml
+    poetry run synapse_homeserver --config-path homeserver.yaml
 
 
 Running the unit tests
@@ -331,7 +337,7 @@ Running the unit tests
 After getting up and running, you may wish to run Synapse's unit tests to
 check that everything is installed correctly::
 
-    trial tests
+    poetry run trial tests
 
 This should end with a 'PASSED' result (note that exact numbers will
 differ)::

changelog.d/12273.bugfix

@@ -0,0 +1 @@
+Fix a bug introduced in Synapse v1.48.0 where latest thread reply provided failed to include the proper bundled aggregations.

changelog.d/12356.misc

@@ -0,0 +1 @@
+Fix scripts-dev to pass typechecking.

changelog.d/12406.feature

@@ -0,0 +1 @@
+Add a module API to allow modules to change actions for existing push rules of local users.

changelog.d/12480.misc

@@ -0,0 +1 @@
+Use supervisord to supervise Postgres and Caddy in the Complement image to reduce restart time.

changelog.d/12485.misc

@@ -0,0 +1 @@
+Add some type hints to datastore.

changelog.d/12505.misc

@@ -0,0 +1 @@
+Use `make_awaitable` instead of `defer.succeed` for return values of mocks in tests.

changelog.d/12526.feature

@@ -0,0 +1 @@
+Add new `enable_registration_token_3pid_bypass` configuration option to allow registrations via token as an alternative to verifying a 3pid.

changelog.d/12531.misc

@@ -0,0 +1 @@
+Remove unused `# type: ignore`s.

changelog.d/12541.docker

@@ -0,0 +1 @@
+Explicitly opt-in to using [BuildKit-specific features](https://github.com/moby/buildkit/blob/master/frontend/dockerfile/docs/syntax.md) in the Dockerfile. This fixes issues with building images in some GitLab CI environments.

changelog.d/12544.bugfix

@@ -0,0 +1 @@
+Fix a bug where attempting to send a large amount of read receipts to an application service all at once would result in duplicate content and abnormally high memory usage. Contributed by Brad & Nick @ Beeper.

changelog.d/12556.misc

@@ -0,0 +1 @@
+Release script: confirm the commit to be tagged before tagging.

changelog.d/12564.misc

@@ -0,0 +1 @@
+Consistently check if an object is a `frozendict`.

changelog.d/12570.bugfix

@@ -0,0 +1 @@
+Fix a bug introduced in Synapse 1.57 which could cause `Failed to calculate hosts in room` errors to be logged for outbound federation.

changelog.d/12576.misc

@@ -0,0 +1 @@
+Allow unused `#type: ignore` comments in bleeding edge CI jobs.

changelog.d/12579.doc

@@ -0,0 +1 @@
+Add missing linebreak to pipx install instructions.

changelog.d/12580.bugfix

@@ -0,0 +1 @@
+Fix a long standing bug where status codes would almost always get logged as 200!, irrespective of the actual status code, when clients disconnect before a request has finished processing.

changelog.d/12581.misc

@@ -0,0 +1 @@
+Improve docstrings for the receipts store.

changelog.d/12582.misc

@@ -0,0 +1 @@
+Use constants for read-receipts in tests.

changelog.d/12587.misc

@@ -0,0 +1 @@
+Add `@cancellable` decorator, for use on endpoint methods that can be cancelled when clients disconnect.

changelog.d/12589.misc

@@ -0,0 +1 @@
+Remove special-case for `twisted` logger from default log config.

changelog.d/12594.bugfix

@@ -0,0 +1 @@
+Fix race when persisting an event and deleting a room that could lead to outbound federation breaking.

changelog.d/12596.removal

@@ -0,0 +1 @@
+Remove unstable identifiers from [MSC3069](https://github.com/matrix-org/matrix-doc/pull/3069).

changelog.d/12597.removal

@@ -0,0 +1,2 @@
+Remove the unspecified `m.login.jwt` login type and the unstable `uk.half-shot.msc2778.login.application_service` from 
+[MSC2778](https://github.com/matrix-org/matrix-doc/pull/2778).

changelog.d/12608.misc

@@ -0,0 +1 @@
+Remove redundant lines of config from `mypy.ini`.

changelog.d/12612.bugfix

@@ -0,0 +1 @@
+Fix a typo in the announcement text generated by the Synapse release development script.

changelog.d/12613.removal

@@ -0,0 +1 @@
+Synapse now requires at least Python 3.7.1 (up from 3.7.0), for compatibility with the latest Twisted trunk.

changelog.d/12614.misc

@@ -0,0 +1 @@
+Add extra debug logging to federation sender.

changelog.d/12620.misc

@@ -0,0 +1 @@
+Add a consistency check on events which we read from the database.

changelog.d/12624.misc

@@ -0,0 +1 @@
+Remove use of constantly library and switch to enums for EventRedactBehaviour. Contributed by @andrewdoh.

changelog.d/12627.doc

@@ -0,0 +1 @@
+Fixes to the formatting of README.rst.

contrib/jitsimeetbridge/jitsimeetbridge.py

@@ -193,12 +193,15 @@ class TrivialXmppClient:
         time.sleep(7)
         print("SSRC spammer started")
         while self.running:
-            ssrcMsg = "<presence to='%(tojid)s' xmlns='jabber:client'><x xmlns='http://jabber.org/protocol/muc'/><c xmlns='http://jabber.org/protocol/caps' hash='sha-1' node='http://jitsi.org/jitsimeet' ver='0WkSdhFnAUxrz4ImQQLdB80GFlE='/><nick xmlns='http://jabber.org/protocol/nick'>%(nick)s</nick><stats xmlns='http://jitsi.org/jitmeet/stats'><stat name='bitrate_download' value='175'/><stat name='bitrate_upload' value='176'/><stat name='packetLoss_total' value='0'/><stat name='packetLoss_download' value='0'/><stat name='packetLoss_upload' value='0'/></stats><media xmlns='http://estos.de/ns/mjs'><source type='audio' ssrc='%(assrc)s' direction='sendre'/><source type='video' ssrc='%(vssrc)s' direction='sendre'/></media></presence>" % {
+            ssrcMsg = (
-                "tojid": "%s@%s/%s" % (ROOMNAME, ROOMDOMAIN, self.shortJid),
+                "<presence to='%(tojid)s' xmlns='jabber:client'><x xmlns='http://jabber.org/protocol/muc'/><c xmlns='http://jabber.org/protocol/caps' hash='sha-1' node='http://jitsi.org/jitsimeet' ver='0WkSdhFnAUxrz4ImQQLdB80GFlE='/><nick xmlns='http://jabber.org/protocol/nick'>%(nick)s</nick><stats xmlns='http://jitsi.org/jitmeet/stats'><stat name='bitrate_download' value='175'/><stat name='bitrate_upload' value='176'/><stat name='packetLoss_total' value='0'/><stat name='packetLoss_download' value='0'/><stat name='packetLoss_upload' value='0'/></stats><media xmlns='http://estos.de/ns/mjs'><source type='audio' ssrc='%(assrc)s' direction='sendre'/><source type='video' ssrc='%(vssrc)s' direction='sendre'/></media></presence>"
-                "nick": self.userId,
+                % {
-                "assrc": self.ssrcs["audio"],
+                    "tojid": "%s@%s/%s" % (ROOMNAME, ROOMDOMAIN, self.shortJid),
-                "vssrc": self.ssrcs["video"],
+                    "nick": self.userId,
-            }
+                    "assrc": self.ssrcs["audio"],
+                    "vssrc": self.ssrcs["video"],
+                }
+            )
             res = self.sendIq(ssrcMsg)
             print("reply from ssrc announce: ", res)
             time.sleep(10)

contrib/snap/snapcraft.yaml

@@ -20,7 +20,7 @@ apps:
   generate-config:
     command: generate_config
   generate-signing-key:
-    command: generate_signing_key.py
+    command: generate_signing_key
   register-new-matrix-user:
     command: register_new_matrix_user
     plugs: [network]

debian/build_virtualenv

@@ -30,9 +30,19 @@ case $(dpkg-architecture -q DEB_HOST_ARCH) in
         ;;
 esac
 
-# Use --builtin-venv to use the better `venv` module from CPython 3.4+ rather
+# Manually install Poetry and export a pip-compatible `requirements.txt`
-# than the 2/3 compatible `virtualenv`.
+# We need a Poetry pre-release as the export command is buggy in < 1.2
+TEMP_VENV="$(mktemp -d)"
+python3 -m venv "$TEMP_VENV"
+source "$TEMP_VENV/bin/activate"
+pip install -U pip
+pip install poetry==1.2.0b1
+poetry export --extras all --extras test -o exported_requirements.txt
+deactivate
+rm -rf "$TEMP_VENV"
 
+# Use --no-deps to only install pinned versions in exported_requirements.txt,
+# and to avoid https://github.com/pypa/pip/issues/9644
 dh_virtualenv \
     --install-suffix "matrix-synapse" \
     --builtin-venv \
@@ -41,9 +51,11 @@ dh_virtualenv \
     --preinstall="lxml" \
     --preinstall="mock" \
     --preinstall="wheel" \
+    --extra-pip-arg="--no-deps" \
     --extra-pip-arg="--no-cache-dir" \
     --extra-pip-arg="--compile" \
-    --extras="all,systemd,test"
+    --extras="all,systemd,test" \
+    --requirements="exported_requirements.txt"
 
 PACKAGE_BUILD_DIR="debian/matrix-synapse-py3"
 VIRTUALENV_DIR="${PACKAGE_BUILD_DIR}${DH_VIRTUALENV_INSTALL_ROOT}/matrix-synapse"

debian/changelog

@@ -1,3 +1,106 @@
+matrix-synapse-py3 (1.58.0) stable; urgency=medium
+
+  * New Synapse release 1.58.0.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 03 May 2022 10:52:58 +0100
+
+matrix-synapse-py3 (1.58.0~rc2) stable; urgency=medium
+
+  * New Synapse release 1.58.0rc2.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 26 Apr 2022 17:14:56 +0100
+
+matrix-synapse-py3 (1.58.0~rc1) stable; urgency=medium
+
+  * Use poetry to manage the bundled virtualenv included with this package.
+  * New Synapse release 1.58.0rc1.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 26 Apr 2022 11:15:20 +0100
+
+matrix-synapse-py3 (1.57.1) stable; urgency=medium
+
+  * New synapse release 1.57.1.
+
+ -- Synapse Packaging team <packages@matrix.org>  Wed, 20 Apr 2022 15:27:21 +0100
+
+matrix-synapse-py3 (1.57.0) stable; urgency=medium
+
+  * New synapse release 1.57.0.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 19 Apr 2022 10:58:42 +0100
+
+matrix-synapse-py3 (1.57.0~rc1) stable; urgency=medium
+
+  * New synapse release 1.57.0~rc1.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 12 Apr 2022 13:36:25 +0100
+
+matrix-synapse-py3 (1.56.0) stable; urgency=medium
+
+  * New synapse release 1.56.0.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 05 Apr 2022 12:38:39 +0100
+
+matrix-synapse-py3 (1.56.0~rc1) stable; urgency=medium
+
+  * New synapse release 1.56.0~rc1.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 29 Mar 2022 10:40:50 +0100
+
+matrix-synapse-py3 (1.55.2) stable; urgency=medium
+
+  * New synapse release 1.55.2.
+
+ -- Synapse Packaging team <packages@matrix.org>  Thu, 24 Mar 2022 19:07:11 +0000
+
+matrix-synapse-py3 (1.55.1) stable; urgency=medium
+
+  * New synapse release 1.55.1.
+
+ -- Synapse Packaging team <packages@matrix.org>  Thu, 24 Mar 2022 17:44:23 +0000
+
+matrix-synapse-py3 (1.55.0) stable; urgency=medium
+
+  * New synapse release 1.55.0.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 22 Mar 2022 13:59:26 +0000
+
+matrix-synapse-py3 (1.55.0~rc1) stable; urgency=medium
+
+  * New synapse release 1.55.0~rc1.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 15 Mar 2022 10:59:31 +0000
+
+matrix-synapse-py3 (1.54.0) stable; urgency=medium
+
+  * New synapse release 1.54.0.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 08 Mar 2022 10:54:52 +0000
+
+matrix-synapse-py3 (1.54.0~rc1) stable; urgency=medium
+
+  * New synapse release 1.54.0~rc1.
+
+ -- Synapse Packaging team <packages@matrix.org>  Wed, 02 Mar 2022 10:43:22 +0000
+
+matrix-synapse-py3 (1.53.0) stable; urgency=medium
+
+  * New synapse release 1.53.0.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 22 Feb 2022 11:32:06 +0000
+
+matrix-synapse-py3 (1.53.0~rc1) stable; urgency=medium
+
+  * New synapse release 1.53.0~rc1.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 15 Feb 2022 10:40:50 +0000
+
+matrix-synapse-py3 (1.52.0) stable; urgency=medium
+
+  * New synapse release 1.52.0.
+
+ -- Synapse Packaging team <packages@matrix.org>  Tue, 08 Feb 2022 11:34:54 +0000
+
 matrix-synapse-py3 (1.52.0~rc1) stable; urgency=medium
 
   * New synapse release 1.52.0~rc1.

debian/clean

@@ -0,0 +1 @@
+exported_requirements.txt

demo/.gitignore

@@ -1,7 +1,4 @@
-*.db
+# Ignore all the temporary files from the demo servers.
-*.log
+8080/
-*.log.*
+8081/
-*.pid
+8082/
-
-/media_store.*
-/etc

demo/README

@@ -1,26 +0,0 @@
-DO NOT USE THESE DEMO SERVERS IN PRODUCTION
-
-Requires you to have done:
-    python setup.py develop
-
-
-The demo start.sh will start three synapse servers on ports 8080, 8081 and 8082, with host names localhost:$port. This can be easily changed to `hostname`:$port in start.sh if required.
-
-To enable the servers to communicate untrusted ssl certs are used. In order to do this the servers do not check the certs
-and are configured in a highly insecure way. Do not use these configuration files in production.
-
-stop.sh will stop the synapse servers and the webclient.
-
-clean.sh will delete the databases and log files.
-
-To start a completely new set of servers, run:
-
-    ./demo/stop.sh; ./demo/clean.sh && ./demo/start.sh
-
-
-Logs and sqlitedb will be stored in demo/808{0,1,2}.{log,db}
-
-
-
-Also note that when joining a public room on a different HS via "#foo:bar.net", then you are (in the current impl) joining a room with room_id "foo". This means that it won't work if your HS already has a room with that name.
-

demo/clean.sh

@@ -4,6 +4,9 @@ set -e
 
 DIR="$( cd "$( dirname "$0" )" && pwd )"
 
+# Ensure that the servers are stopped.
+$DIR/stop.sh
+
 PID_FILE="$DIR/servers.pid"
 
 if [ -f "$PID_FILE" ]; then

demo/start.sh

@@ -6,8 +6,6 @@ CWD=$(pwd)
 
 cd "$DIR/.." || exit
 
-mkdir -p demo/etc
-
 PYTHONPATH=$(readlink -f "$(pwd)")
 export PYTHONPATH
 
@@ -21,22 +19,27 @@ for port in 8080 8081 8082; do
     mkdir -p demo/$port
     pushd demo/$port || exit
 
-    #rm $DIR/etc/$port.config
+    # Generate the configuration for the homeserver at localhost:848x.
     python3 -m synapse.app.homeserver \
         --generate-config \
-        -H "localhost:$https_port" \
+        --server-name "localhost:$port" \
-        --config-path "$DIR/etc/$port.config" \
+        --config-path "$port.config" \
         --report-stats no
 
-    if ! grep -F "Customisation made by demo/start.sh" -q "$DIR/etc/$port.config"; then
+    if ! grep -F "Customisation made by demo/start.sh" -q "$port.config"; then
-        # Generate tls keys
+        # Generate TLS keys.
-        openssl req -x509 -newkey rsa:4096 -keyout "$DIR/etc/localhost:$https_port.tls.key" -out "$DIR/etc/localhost:$https_port.tls.crt" -days 365 -nodes -subj "/O=matrix"
+        openssl req -x509 -newkey rsa:4096 \
+          -keyout "localhost:$port.tls.key" \
+          -out "localhost:$port.tls.crt" \
+          -days 365 -nodes -subj "/O=matrix"
 
-        # Regenerate configuration
+        # Add customisations to the configuration.
         {
-            printf '\n\n# Customisation made by demo/start.sh\n'
+            printf '\n\n# Customisation made by demo/start.sh\n\n'
             echo "public_baseurl: http://localhost:$port/"
             echo 'enable_registration: true'
+            echo 'enable_registration_without_verification: true'
+            echo ''
 
 			# Warning, this heredoc depends on the interaction of tabs and spaces.
 			# Please don't accidentaly bork me with your fancy settings.
@@ -63,38 +66,34 @@ for port in 8080 8081 8082; do
 
             echo "${listeners}"
 
-            # Disable tls for the servers
+            # Disable TLS for the servers
-            printf '\n\n# Disable tls on the servers.'
+            printf '\n\n# Disable TLS for the servers.'
             echo '# DO NOT USE IN PRODUCTION'
             echo 'use_insecure_ssl_client_just_for_testing_do_not_use: true'
             echo 'federation_verify_certificates: false'
 
-            # Set tls paths
+            # Set paths for the TLS certificates.
-            echo "tls_certificate_path: \"$DIR/etc/localhost:$https_port.tls.crt\""
+            echo "tls_certificate_path: \"$DIR/$port/localhost:$port.tls.crt\""
-            echo "tls_private_key_path: \"$DIR/etc/localhost:$https_port.tls.key\""
+            echo "tls_private_key_path: \"$DIR/$port/localhost:$port.tls.key\""
 
             # Ignore keys from the trusted keys server
             echo '# Ignore keys from the trusted keys server'
             echo 'trusted_key_servers:'
             echo '  - server_name: "matrix.org"'
             echo '    accept_keys_insecurely: true'
+            echo ''
 
-			# Reduce the blacklist
+			# Allow the servers to communicate over localhost.
-			blacklist=$(cat <<-BLACK
+			allow_list=$(cat <<-ALLOW_LIST
-			# Set the blacklist so that it doesn't include 127.0.0.1, ::1
+			# Allow the servers to communicate over localhost.
-			federation_ip_range_blacklist:
+			ip_range_whitelist:
-			  - '10.0.0.0/8'
+			  - '127.0.0.1/8'
-			  - '172.16.0.0/12'
+			  - '::1/128'
-			  - '192.168.0.0/16'
+			ALLOW_LIST
-			  - '100.64.0.0/10'
-			  - '169.254.0.0/16'
-			  - 'fe80::/64'
-			  - 'fc00::/7'
-			BLACK
 			)
 
-            echo "${blacklist}"
+            echo "${allow_list}"
-        } >> "$DIR/etc/$port.config"
+        } >> "$port.config"
     fi
 
     # Check script parameters
@@ -141,19 +140,18 @@ for port in 8080 8081 8082; do
 			    burst_count: 1000
 			RC
 			)
-            echo "${ratelimiting}" >> "$DIR/etc/$port.config"
+            echo "${ratelimiting}" >> "$port.config"
         fi
     fi
 
-    if ! grep -F "full_twisted_stacktraces" -q  "$DIR/etc/$port.config"; then
+    # Always disable reporting of stats if the option is not there.
-        echo "full_twisted_stacktraces: true" >> "$DIR/etc/$port.config"
+    if ! grep -F "report_stats" -q  "$port.config" ; then
-    fi
+        echo "report_stats: false" >> "$port.config"
-    if ! grep -F "report_stats" -q  "$DIR/etc/$port.config" ; then
-        echo "report_stats: false" >> "$DIR/etc/$port.config"
     fi
 
+    # Run the homeserver in the background.
     python3 -m synapse.app.homeserver \
-        --config-path "$DIR/etc/$port.config" \
+        --config-path "$port.config" \
         -D \
 
     popd || exit

docker/Dockerfile

@@ -1,3 +1,4 @@
+# syntax=docker/dockerfile:1
 # Dockerfile to build the matrixdotorg/synapse docker images.
 #
 # Note that it uses features which are only available in BuildKit - see
@@ -11,23 +12,64 @@
 # There is an optional PYTHON_VERSION build argument which sets the
 # version of python to build against: for example:
 #
-#    DOCKER_BUILDKIT=1 docker build -f docker/Dockerfile --build-arg PYTHON_VERSION=3.9 .
+#    DOCKER_BUILDKIT=1 docker build -f docker/Dockerfile --build-arg PYTHON_VERSION=3.10 .
 #
 
-ARG PYTHON_VERSION=3.8
+# Irritatingly, there is no blessed guide on how to distribute an application with its
+# poetry-managed environment in a docker image. We have opted for
+# `poetry export | pip install -r /dev/stdin`, but there are known bugs in
+# in `poetry export` whose fixes (scheduled for poetry 1.2) have yet to be released.
+# In case we get bitten by those bugs in the future, the recommendations here might
+# be useful:
+#     https://github.com/python-poetry/poetry/discussions/1879#discussioncomment-216865
+#     https://stackoverflow.com/questions/53835198/integrating-python-poetry-with-docker?answertab=scoredesc
+
+
+
+ARG PYTHON_VERSION=3.9
 
 ###
-### Stage 0: builder
+### Stage 0: generate requirements.txt
+###
+FROM docker.io/python:${PYTHON_VERSION}-slim as requirements
+
+# RUN --mount is specific to buildkit and is documented at
+# https://github.com/moby/buildkit/blob/master/frontend/dockerfile/docs/syntax.md#build-mounts-run---mount.
+# Here we use it to set up a cache for apt (and below for pip), to improve
+# rebuild speeds on slow connections.
+RUN \
+   --mount=type=cache,target=/var/cache/apt,sharing=locked \
+   --mount=type=cache,target=/var/lib/apt,sharing=locked \
+ apt-get update && apt-get install -y git \
+    && rm -rf /var/lib/apt/lists/*
+
+# We install poetry in its own build stage to avoid its dependencies conflicting with
+# synapse's dependencies.
+# We use a specific commit from poetry's master branch instead of our usual 1.1.12,
+# to incorporate fixes to some bugs in `poetry export`. This commit corresponds to
+#    https://github.com/python-poetry/poetry/pull/5156 and
+#    https://github.com/python-poetry/poetry/issues/5141 ;
+# without it, we generate a requirements.txt with incorrect environment markers,
+# which causes necessary packages to be omitted when we `pip install`.
+#
+# NB: In poetry 1.2 `poetry export` will be moved into a plugin; we'll need to also
+# pip install poetry-plugin-export (https://github.com/python-poetry/poetry-plugin-export).
+RUN --mount=type=cache,target=/root/.cache/pip \
+  pip install --user git+https://github.com/python-poetry/poetry.git@fb13b3a676f476177f7937ffa480ee5cff9a90a5
+
+WORKDIR /synapse
+
+# Copy just what we need to run `poetry export`...
+COPY pyproject.toml poetry.lock /synapse/
+
+RUN /root/.local/bin/poetry export --extras all -o /synapse/requirements.txt
+
+###
+### Stage 1: builder
 ###
 FROM docker.io/python:${PYTHON_VERSION}-slim as builder
 
 # install the OS build deps
-#
-# RUN --mount is specific to buildkit and is documented at
-# https://github.com/moby/buildkit/blob/master/frontend/dockerfile/docs/syntax.md#build-mounts-run---mount.
-# Here we use it to set up a cache for apt, to improve rebuild speeds on
-# slow connections.
-#
 RUN \
    --mount=type=cache,target=/var/cache/apt,sharing=locked \
    --mount=type=cache,target=/var/lib/apt,sharing=locked \
@@ -45,31 +87,25 @@ RUN \
     zlib1g-dev \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy just what we need to pip install
-COPY scripts /synapse/scripts/
-COPY MANIFEST.in README.rst setup.py synctl /synapse/
-COPY synapse/__init__.py /synapse/synapse/__init__.py
-COPY synapse/python_dependencies.py /synapse/synapse/python_dependencies.py
-
 # To speed up rebuilds, install all of the dependencies before we copy over
-# the whole synapse project so that we this layer in the Docker cache can be
+# the whole synapse project, so that this layer in the Docker cache can be
 # used while you develop on the source
 #
-# This is aiming at installing the `install_requires` and `extras_require` from `setup.py`
+# This is aiming at installing the `[tool.poetry.depdendencies]` from pyproject.toml.
+COPY --from=requirements /synapse/requirements.txt /synapse/
 RUN --mount=type=cache,target=/root/.cache/pip \
-  pip install --prefix="/install" --no-warn-script-location \
+  pip install --prefix="/install" --no-deps --no-warn-script-location -r /synapse/requirements.txt
-    /synapse[all]
 
-# Copy over the rest of the project
+# Copy over the rest of the synapse source code.
 COPY synapse /synapse/synapse/
+# ... and what we need to `pip install`.
+COPY pyproject.toml README.rst /synapse/
 
-# Install the synapse package itself and all of its children packages.
+# Install the synapse package itself.
-#
-# This is aiming at installing only the `packages=find_packages(...)` from `setup.py
 RUN pip install --prefix="/install" --no-deps --no-warn-script-location /synapse
 
 ###
-### Stage 1: runtime
+### Stage 2: runtime
 ###
 
 FROM docker.io/python:${PYTHON_VERSION}-slim
@@ -98,8 +134,6 @@ COPY --from=builder /install /usr/local
 COPY ./docker/start.py /start.py
 COPY ./docker/conf /conf
 
-VOLUME ["/data"]
-
 EXPOSE 8008/tcp 8009/tcp 8448/tcp
 
 ENTRYPOINT ["/start.py"]

docker/Dockerfile-pgtests

@@ -1,30 +0,0 @@
-# Use the Sytest image that comes with a lot of the build dependencies
-# pre-installed
-FROM matrixdotorg/sytest:focal
-
-# The Sytest image doesn't come with python, so install that
-RUN apt-get update && apt-get -qq install -y python3 python3-dev python3-pip
-
-# We need tox to run the tests in run_pg_tests.sh
-RUN python3 -m pip install tox
-
-# Initialise the db
-RUN su -c '/usr/lib/postgresql/10/bin/initdb -D /var/lib/postgresql/data -E "UTF-8" --lc-collate="C.UTF-8" --lc-ctype="C.UTF-8" --username=postgres' postgres
-
-# Add a user with our UID and GID so that files get created on the host owned
-# by us, not root.
-ARG UID
-ARG GID
-RUN groupadd --gid $GID user
-RUN useradd --uid $UID --gid $GID --groups sudo --no-create-home user
-
-# Ensure we can start postgres by sudo-ing as the postgres user.
-RUN apt-get update && apt-get -qq install -y sudo
-RUN echo "user ALL=(ALL) NOPASSWD: ALL" >> /etc/sudoers
-
-ADD run_pg_tests.sh /run_pg_tests.sh
-# Use the "exec form" of ENTRYPOINT (https://docs.docker.com/engine/reference/builder/#entrypoint)
-# so that we can `docker run` this container and pass arguments to pg_tests.sh
-ENTRYPOINT ["/run_pg_tests.sh"]
-
-USER user

docker/Dockerfile-workers

@@ -2,25 +2,36 @@
 FROM matrixdotorg/synapse
 
 # Install deps
-RUN apt-get update
+RUN \
-RUN apt-get install -y supervisor redis nginx
+   --mount=type=cache,target=/var/cache/apt,sharing=locked \
+   --mount=type=cache,target=/var/lib/apt,sharing=locked \
+  apt-get update && \
+  DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
+     redis-server nginx-light
 
-# Remove the default nginx sites
+# Install supervisord with 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
+
+# Disable the default nginx sites
 RUN rm /etc/nginx/sites-enabled/default
 
 # Copy Synapse worker, nginx and supervisord configuration template files
 COPY ./docker/conf-workers/* /conf/
 
+# Copy a script to prefix log lines with the supervisor program name
+COPY ./docker/prefix-log /usr/local/bin/
+
 # Expose nginx listener port
 EXPOSE 8080/tcp
 
-# Volume for user-editable config files, logs etc.
-VOLUME ["/data"]
-
 # A script to read environment variables and create the necessary
 # files to run the desired worker configuration. Will start supervisord.
 COPY ./docker/configure_workers_and_start.py /configure_workers_and_start.py
 ENTRYPOINT ["/configure_workers_and_start.py"]
 
+# Replace the healthcheck with one which checks *all* the workers. The script
+# is generated by configure_workers_and_start.py.
 HEALTHCHECK --start-period=5s --interval=15s --timeout=5s \
     CMD /bin/sh /healthcheck.sh

docker/README-testing.md

@@ -10,10 +10,10 @@ Note that running Synapse's unit tests from within the docker image is not suppo
 
 ## Testing with SQLite and single-process Synapse
 
-> Note that `scripts-dev/complement.sh` is a script that will automatically build 
+> Note that `scripts-dev/complement.sh` is a script that will automatically build
 > and run an SQLite-based, single-process of Synapse against Complement.
 
-The instructions below will set up Complement testing for a single-process, 
+The instructions below will set up Complement testing for a single-process,
 SQLite-based Synapse deployment.
 
 Start by building the base Synapse docker image. If you wish to run tests with the latest
@@ -26,23 +26,22 @@ docker build -t matrixdotorg/synapse -f docker/Dockerfile .
 
 This will build an image with the tag `matrixdotorg/synapse`.
 
-Next, build the Synapse image for Complement. You will need a local checkout 
+Next, build the Synapse image for Complement.
-of Complement. Change to the root of your Complement checkout and run:
 
 ```sh
-docker build -t complement-synapse -f "dockerfiles/Synapse.Dockerfile" dockerfiles
+docker build -t complement-synapse -f "docker/complement/Dockerfile" docker/complement
 ```
 
-This will build an image with the tag `complement-synapse`, which can be handed to 
+This will build an image with the tag `complement-synapse`, which can be handed to
-Complement for testing via the `COMPLEMENT_BASE_IMAGE` environment variable. Refer to 
+Complement for testing via the `COMPLEMENT_BASE_IMAGE` environment variable. Refer to
-[Complement's documentation](https://github.com/matrix-org/complement/#running) for 
+[Complement's documentation](https://github.com/matrix-org/complement/#running) for
 how to run the tests, as well as the various available command line flags.
 
 ## Testing with PostgreSQL and single or multi-process Synapse
 
-The above docker image only supports running Synapse with SQLite and in a 
+The above docker image only supports running Synapse with SQLite and in a
-single-process topology. The following instructions are used to build a Synapse image for 
+single-process topology. The following instructions are used to build a Synapse image for
-Complement that supports either single or multi-process topology with a PostgreSQL 
+Complement that supports either single or multi-process topology with a PostgreSQL
 database backend.
 
 As with the single-process image, build the base Synapse docker image. If you wish to run
@@ -55,7 +54,7 @@ docker build -t matrixdotorg/synapse -f docker/Dockerfile .
 
 This will build an image with the tag `matrixdotorg/synapse`.
 
-Next, we build a new image with worker support based on `matrixdotorg/synapse:latest`. 
+Next, we build a new image with worker support based on `matrixdotorg/synapse:latest`.
 Again, from the root of the repository:
 
 ```sh
@@ -64,21 +63,20 @@ docker build -t matrixdotorg/synapse-workers -f docker/Dockerfile-workers .
 
 This will build an image with the tag` matrixdotorg/synapse-workers`.
 
-It's worth noting at this point that this image is fully functional, and 
+It's worth noting at this point that this image is fully functional, and
-can be used for testing against locally. See instructions for using the container 
+can be used for testing against locally. See instructions for using the container
 under
 [Running the Dockerfile-worker image standalone](#running-the-dockerfile-worker-image-standalone)
 below.
 
 Finally, build the Synapse image for Complement, which is based on
-`matrixdotorg/synapse-workers`. You will need a local checkout of Complement. Change to
+`matrixdotorg/synapse-workers`.
-the root of your Complement checkout and run:
 
 ```sh
-docker build -t matrixdotorg/complement-synapse-workers -f dockerfiles/SynapseWorkers.Dockerfile dockerfiles
+docker build -t matrixdotorg/complement-synapse-workers -f docker/complement/SynapseWorkers.Dockerfile docker/complement
 ```
 
-This will build an image with the tag `complement-synapse`, which can be handed to
+This will build an image with the tag `complement-synapse-workers`, which can be handed to
 Complement for testing via the `COMPLEMENT_BASE_IMAGE` environment variable. Refer to
 [Complement's documentation](https://github.com/matrix-org/complement/#running) for
 how to run the tests, as well as the various available command line flags.
@@ -91,10 +89,10 @@ bundling all necessary components together for a workerised homeserver instance.
 
 This includes any desired Synapse worker processes, a nginx to route traffic accordingly,
 a redis for worker communication and a supervisord instance to start up and monitor all
-processes. You will need to provide your own postgres container to connect to, and TLS 
+processes. You will need to provide your own postgres container to connect to, and TLS
 is not handled by the container.
 
-Once you've built the image using the above instructions, you can run it. Be sure 
+Once you've built the image using the above instructions, you can run it. Be sure
 you've set up a volume according to the [usual Synapse docker instructions](README.md).
 Then run something along the lines of:
 
@@ -112,7 +110,7 @@ docker run -d --name synapse \
     matrixdotorg/synapse-workers
 ```
 
-...substituting `POSTGRES*` variables for those that match a postgres host you have 
+...substituting `POSTGRES*` variables for those that match a postgres host you have
 available (usually a running postgres docker container).
 
 The `SYNAPSE_WORKER_TYPES` environment variable is a comma-separated list of workers to
@@ -130,11 +128,11 @@ Otherwise, `SYNAPSE_WORKER_TYPES` can either be left empty or unset to spawn no
 (leaving only the main process). The container is configured to use redis-based worker
 mode.
 
-Logs for workers and the main process are logged to stdout and can be viewed with 
+Logs for workers and the main process are logged to stdout and can be viewed with
-standard `docker logs` tooling. Worker logs contain their worker name 
+standard `docker logs` tooling. Worker logs contain their worker name
 after the timestamp.
 
 Setting `SYNAPSE_WORKERS_WRITE_LOGS_TO_DISK=1` will cause worker logs to be written to
 `<data_dir>/logs/<worker_name>.log`. Logs are kept for 1 week and rotate every day at 00:
-00, according to the container's clock. Logging for the main process must still be 
+00, according to the container's clock. Logging for the main process must still be
 configured by modifying the homeserver's log config in your Synapse data volume.

docker/complement/Dockerfile

@@ -0,0 +1,22 @@
+# A dockerfile which builds an image suitable for testing Synapse under
+# complement.
+
+ARG SYNAPSE_VERSION=latest
+
+FROM matrixdotorg/synapse:${SYNAPSE_VERSION}
+
+ENV SERVER_NAME=localhost
+
+COPY conf/* /conf/
+
+# generate a signing key
+RUN generate_signing_key -o /conf/server.signing.key
+
+WORKDIR /data
+
+EXPOSE 8008 8448
+
+ENTRYPOINT ["/conf/start.sh"]
+
+HEALTHCHECK --start-period=5s --interval=1s --timeout=1s \
+    CMD curl -fSs http://localhost:8008/health || exit 1

docker/complement/README.md

@@ -0,0 +1 @@
+Stuff for building the docker image used for testing under complement.

docker/complement/SynapseWorkers.Dockerfile

@@ -0,0 +1,50 @@
+# This dockerfile builds on top of 'docker/Dockerfile-worker' in matrix-org/synapse
+# by including a built-in postgres instance, as well as setting up the homeserver so
+# that it is ready for testing via Complement.
+#
+# Instructions for building this image from those it depends on is detailed in this guide:
+# https://github.com/matrix-org/synapse/blob/develop/docker/README-testing.md#testing-with-postgresql-and-single-or-multi-process-synapse
+FROM matrixdotorg/synapse-workers
+
+# Download a caddy server to stand in front of nginx and terminate TLS using Complement's
+# custom CA.
+# We include this near the top of the file in order to cache the result.
+RUN curl -OL "https://github.com/caddyserver/caddy/releases/download/v2.3.0/caddy_2.3.0_linux_amd64.tar.gz" && \
+  tar xzf caddy_2.3.0_linux_amd64.tar.gz && rm caddy_2.3.0_linux_amd64.tar.gz && mv caddy /root
+
+# Install postgresql
+RUN apt-get update && \
+  DEBIAN_FRONTEND=noninteractive apt-get install --no-install-recommends -y postgresql-13
+
+# Configure a user and create a database for Synapse
+RUN pg_ctlcluster 13 main start &&  su postgres -c "echo \
+ \"ALTER USER postgres PASSWORD 'somesecret'; \
+ CREATE DATABASE synapse \
+  ENCODING 'UTF8' \
+  LC_COLLATE='C' \
+  LC_CTYPE='C' \
+  template=template0;\" | psql" && pg_ctlcluster 13 main stop
+
+# Modify the shared homeserver config with postgres support, certificate setup
+# and the disabling of rate-limiting
+COPY conf-workers/workers-shared.yaml /conf/workers/shared.yaml
+
+WORKDIR /data
+
+# Copy the caddy config
+COPY conf-workers/caddy.complement.json /root/caddy.json
+
+COPY conf-workers/postgres.supervisord.conf /etc/supervisor/conf.d/postgres.conf
+COPY conf-workers/caddy.supervisord.conf /etc/supervisor/conf.d/caddy.conf
+
+# Copy the entrypoint
+COPY conf-workers/start-complement-synapse-workers.sh /
+
+# Expose caddy's listener ports
+EXPOSE 8008 8448
+
+ENTRYPOINT ["/start-complement-synapse-workers.sh"]
+
+# Update the healthcheck to have a shorter check interval
+HEALTHCHECK --start-period=5s --interval=1s --timeout=1s \
+    CMD /bin/sh /healthcheck.sh

docker/complement/conf-workers/caddy.complement.json

@@ -0,0 +1,72 @@
+{
+    "apps": {
+      "http": {
+        "servers": {
+          "srv0": {
+            "listen": [
+              ":8448"
+            ],
+            "routes": [
+              {
+                "match": [
+                  {
+                    "host": [
+                      "{{ server_name }}"
+                    ]
+                  }
+                ],
+                "handle": [
+                  {
+                    "handler": "subroute",
+                    "routes": [
+                      {
+                        "handle": [
+                          {
+                            "handler": "reverse_proxy",
+                            "upstreams": [
+                              {
+                                "dial": "localhost:8008"
+                              }
+                            ]
+                          }
+                        ]
+                      }
+                    ]
+                  }
+                ],
+                "terminal": true
+              }
+            ]
+          }
+        }
+      },
+      "tls": {
+        "automation": {
+          "policies": [
+            {
+              "subjects": [
+                "{{ server_name }}"
+              ],
+              "issuers": [
+                {
+                  "module": "internal"
+                }
+              ],
+              "on_demand": true
+            }
+          ]
+        }
+      },
+      "pki": {
+        "certificate_authorities": {
+          "local": {
+            "name": "Complement CA",
+            "root": {
+              "certificate": "/complement/ca/ca.crt",
+              "private_key": "/complement/ca/ca.key"
+            }
+          }
+        }
+      }
+    }
+  }

docker/complement/conf-workers/caddy.supervisord.conf

@@ -0,0 +1,7 @@
+[program:caddy]
+command=/usr/local/bin/prefix-log /root/caddy run --config /root/caddy.json
+autorestart=unexpected
+stdout_logfile=/dev/stdout
+stdout_logfile_maxbytes=0
+stderr_logfile=/dev/stderr
+stderr_logfile_maxbytes=0

docker/complement/conf-workers/postgres.supervisord.conf

@@ -0,0 +1,16 @@
+[program:postgres]
+command=/usr/local/bin/prefix-log /usr/bin/pg_ctlcluster 13 main start --foreground
+
+# Lower priority number = starts first
+priority=1
+
+autorestart=unexpected
+stdout_logfile=/dev/stdout
+stdout_logfile_maxbytes=0
+stderr_logfile=/dev/stderr
+stderr_logfile_maxbytes=0
+
+# Use 'Fast Shutdown' mode which aborts current transactions and closes connections quickly.
+# (Default (TERM) is 'Smart Shutdown' which stops accepting new connections but
+#  lets existing connections close gracefully.)
+stopsignal=INT

docker/complement/conf-workers/start-complement-synapse-workers.sh

@@ -0,0 +1,44 @@
+#!/bin/bash
+#
+# Default ENTRYPOINT for the docker image used for testing synapse with workers under complement
+
+set -e
+
+function log {
+    d=$(date +"%Y-%m-%d %H:%M:%S,%3N")
+    echo "$d $@"
+}
+
+# Replace the server name in the caddy config
+sed -i "s/{{ server_name }}/${SERVER_NAME}/g" /root/caddy.json
+
+# Set the server name of the homeserver
+export SYNAPSE_SERVER_NAME=${SERVER_NAME}
+
+# No need to report stats here
+export SYNAPSE_REPORT_STATS=no
+
+# Set postgres authentication details which will be placed in the homeserver config file
+export POSTGRES_PASSWORD=somesecret
+export POSTGRES_USER=postgres
+export POSTGRES_HOST=localhost
+
+# Specify the workers to test with
+export SYNAPSE_WORKER_TYPES="\
+    event_persister, \
+    event_persister, \
+    background_worker, \
+    frontend_proxy, \
+    event_creator, \
+    user_dir, \
+    media_repository, \
+    federation_inbound, \
+    federation_reader, \
+    federation_sender, \
+    synchrotron, \
+    appservice, \
+    pusher"
+
+# Run the script that writes the necessary config files and starts supervisord, which in turn
+# starts everything else
+exec /configure_workers_and_start.py

docker/complement/conf-workers/workers-shared.yaml

@@ -0,0 +1,72 @@
+## Server ##
+report_stats: False
+trusted_key_servers: []
+enable_registration: true
+enable_registration_without_verification: true
+bcrypt_rounds: 4
+
+## Federation ##
+
+# trust certs signed by Complement's CA
+federation_custom_ca_list:
+- /complement/ca/ca.crt
+
+# unblacklist RFC1918 addresses
+federation_ip_range_blacklist: []
+
+# Disable server rate-limiting
+rc_federation:
+  window_size: 1000
+  sleep_limit: 10
+  sleep_delay: 500
+  reject_limit: 99999
+  concurrent: 3
+
+rc_message:
+  per_second: 9999
+  burst_count: 9999
+
+rc_registration:
+  per_second: 9999
+  burst_count: 9999
+
+rc_login:
+  address:
+    per_second: 9999
+    burst_count: 9999
+  account:
+    per_second: 9999
+    burst_count: 9999
+  failed_attempts:
+    per_second: 9999
+    burst_count: 9999
+
+rc_admin_redaction:
+  per_second: 9999
+  burst_count: 9999
+
+rc_joins:
+  local:
+    per_second: 9999
+    burst_count: 9999
+  remote:
+    per_second: 9999
+    burst_count: 9999
+
+federation_rr_transactions_per_room_per_second: 9999
+
+## Experimental Features ##
+
+experimental_features:
+  # Enable history backfilling support
+  msc2716_enabled: true
+  # Enable spaces support
+  spaces_enabled: true
+  # Enable jump to date endpoint
+  msc3030_enabled: true
+
+server_notices:
+  system_mxid_localpart: _server
+  system_mxid_display_name: "Server Alert"
+  system_mxid_avatar_url: ""
+  room_name: "Server Alert"

docker/complement/conf/homeserver.yaml

@@ -0,0 +1,117 @@
+## Server ##
+
+server_name: SERVER_NAME
+log_config: /conf/log_config.yaml
+report_stats: False
+signing_key_path: /conf/server.signing.key
+trusted_key_servers: []
+enable_registration: true
+enable_registration_without_verification: true
+
+## Listeners ##
+
+tls_certificate_path: /conf/server.tls.crt
+tls_private_key_path: /conf/server.tls.key
+bcrypt_rounds: 4
+registration_shared_secret: complement
+
+listeners:
+  - port: 8448
+    bind_addresses: ['::']
+    type: http
+    tls: true
+    resources:
+      - names: [federation]
+
+  - port: 8008
+    bind_addresses: ['::']
+    type: http
+
+    resources:
+      - names: [client]
+
+## Database ##
+
+database:
+  name: "sqlite3"
+  args:
+    # We avoid /data, as it is a volume and is not transferred when the container is committed,
+    # which is a fundamental necessity in complement.
+    database: "/conf/homeserver.db"
+
+## Federation ##
+
+# trust certs signed by the complement CA
+federation_custom_ca_list:
+- /complement/ca/ca.crt
+
+# unblacklist RFC1918 addresses
+ip_range_blacklist: []
+
+# Disable server rate-limiting
+rc_federation:
+  window_size: 1000
+  sleep_limit: 10
+  sleep_delay: 500
+  reject_limit: 99999
+  concurrent: 3
+
+rc_message:
+  per_second: 9999
+  burst_count: 9999
+
+rc_registration:
+  per_second: 9999
+  burst_count: 9999
+
+rc_login:
+  address:
+    per_second: 9999
+    burst_count: 9999
+  account:
+    per_second: 9999
+    burst_count: 9999
+  failed_attempts:
+    per_second: 9999
+    burst_count: 9999
+
+rc_admin_redaction:
+  per_second: 9999
+  burst_count: 9999
+
+rc_joins:
+  local:
+    per_second: 9999
+    burst_count: 9999
+  remote:
+    per_second: 9999
+    burst_count: 9999
+
+federation_rr_transactions_per_room_per_second: 9999
+
+## API Configuration ##
+
+# A list of application service config files to use
+#
+app_service_config_files:
+AS_REGISTRATION_FILES  
+
+## Experimental Features ##
+
+experimental_features:
+  # Enable spaces support
+  spaces_enabled: true
+  # Enable history backfilling support
+  msc2716_enabled: true
+  # server-side support for partial state in /send_join responses
+  msc3706_enabled: true
+  # client-side support for partial state in /send_join responses
+  faster_joins: true
+  # Enable jump to date endpoint
+  msc3030_enabled: true
+
+server_notices:
+  system_mxid_localpart: _server
+  system_mxid_display_name: "Server Alert"
+  system_mxid_avatar_url: ""
+  room_name: "Server Alert"

docker/complement/conf/log_config.yaml

@@ -0,0 +1,24 @@
+version: 1
+
+formatters:
+  precise:
+   format: '%(asctime)s - %(name)s - %(lineno)d - %(levelname)s - %(request)s - %(message)s'
+
+filters:
+  context:
+    (): synapse.logging.context.LoggingContextFilter
+    request: ""
+
+handlers:
+  console:
+    class: logging.StreamHandler
+    formatter: precise
+    filters: [context]
+    # log to stdout, for easier use with 'docker logs'
+    stream: 'ext://sys.stdout'
+
+root:
+    level: INFO
+    handlers: [console]
+
+disable_existing_loggers: false

docker/complement/conf/start.sh

@@ -0,0 +1,30 @@
+#!/bin/sh
+
+set -e
+
+sed -i "s/SERVER_NAME/${SERVER_NAME}/g" /conf/homeserver.yaml
+
+# Add the application service registration files to the homeserver.yaml config
+for filename in /complement/appservice/*.yaml; do
+  [ -f "$filename" ] || break
+
+  as_id=$(basename "$filename" .yaml)
+
+  # Insert the path to the registration file and the AS_REGISTRATION_FILES marker after 
+  # so we can add the next application service in the next iteration of this for loop
+  sed -i "s/AS_REGISTRATION_FILES/  - \/complement\/appservice\/${as_id}.yaml\nAS_REGISTRATION_FILES/g" /conf/homeserver.yaml
+done
+# Remove the AS_REGISTRATION_FILES entry
+sed -i "s/AS_REGISTRATION_FILES//g" /conf/homeserver.yaml
+
+# generate an ssl key and cert for the server, signed by the complement CA
+openssl genrsa -out /conf/server.tls.key 2048
+
+openssl req -new -key /conf/server.tls.key -out /conf/server.tls.csr \
+  -subj "/CN=${SERVER_NAME}"
+openssl x509 -req -in /conf/server.tls.csr \
+  -CA /complement/ca/ca.crt -CAkey /complement/ca/ca.key -set_serial 1 \
+  -out /conf/server.tls.crt
+
+exec python -m synapse.app.homeserver -c /conf/homeserver.yaml "$@"
+

docker/conf-workers/supervisord.conf.j2

@@ -5,6 +5,9 @@
 nodaemon=true
 user=root
 
+[include]
+files = /etc/supervisor/conf.d/*.conf
+
 [program:nginx]
 command=/usr/sbin/nginx -g "daemon off;"
 priority=500

docker/conf/log.config

@@ -2,11 +2,7 @@ version: 1
 
 formatters:
   precise:
-{% if worker_name %}
-    format: '%(asctime)s - worker:{{ worker_name }} - %(name)s - %(lineno)d - %(levelname)s - %(request)s - %(message)s'
-{% else %}
     format: '%(asctime)s - %(name)s - %(lineno)d - %(levelname)s - %(request)s - %(message)s'
-{% endif %}
 
 handlers:
 {% if LOG_FILE_PATH %}

docker/configure_workers_and_start.py

@@ -29,6 +29,7 @@
 import os
 import subprocess
 import sys
+from typing import Any, Dict, List, Mapping, MutableMapping, NoReturn, Set
 
 import jinja2
 import yaml
@@ -36,7 +37,7 @@ import yaml
 MAIN_PROCESS_HTTP_LISTENER_PORT = 8080
 
 
-WORKERS_CONFIG = {
+WORKERS_CONFIG: Dict[str, Dict[str, Any]] = {
     "pusher": {
         "app": "synapse.app.pusher",
         "listener_resources": [],
@@ -170,7 +171,7 @@ WORKERS_CONFIG = {
 # Templates for sections that may be inserted multiple times in config files
 SUPERVISORD_PROCESS_CONFIG_BLOCK = """
 [program:synapse_{name}]
-command=/usr/local/bin/python -m {app} \
+command=/usr/local/bin/prefix-log /usr/local/bin/python -m {app} \
     --config-path="{config_path}" \
     --config-path=/conf/workers/shared.yaml \
     --config-path=/conf/workers/{name}.yaml
@@ -200,7 +201,7 @@ upstream {upstream_worker_type} {{
 
 
 # Utility functions
-def log(txt: str):
+def log(txt: str) -> None:
     """Log something to the stdout.
 
     Args:
@@ -209,7 +210,7 @@ def log(txt: str):
     print(txt)
 
 
-def error(txt: str):
+def error(txt: str) -> NoReturn:
     """Log something and exit with an error code.
 
     Args:
@@ -219,7 +220,7 @@ def error(txt: str):
     sys.exit(2)
 
 
-def convert(src: str, dst: str, **template_vars):
+def convert(src: str, dst: str, **template_vars: object) -> None:
     """Generate a file from a template
 
     Args:
@@ -289,7 +290,7 @@ def add_sharding_to_shared_config(
         shared_config.setdefault("media_instance_running_background_jobs", worker_name)
 
 
-def generate_base_homeserver_config():
+def generate_base_homeserver_config() -> None:
     """Starts Synapse and generates a basic homeserver config, which will later be
     modified for worker support.
 
@@ -301,13 +302,15 @@ def generate_base_homeserver_config():
     subprocess.check_output(["/usr/local/bin/python", "/start.py", "migrate_config"])
 
 
-def generate_worker_files(environ, config_path: str, data_dir: str):
+def generate_worker_files(
+    environ: Mapping[str, str], config_path: str, data_dir: str
+) -> None:
     """Read the desired list of workers from environment variables and generate
     shared homeserver, nginx and supervisord configs.
 
     Args:
-        environ: _Environ[str]
+        environ: os.environ instance.
-        config_path: Where to output the generated Synapse main worker config file.
+        config_path: The location of the generated Synapse main worker config file.
         data_dir: The location of the synapse data directory. Where log and
             user-facing config files live.
     """
@@ -320,7 +323,8 @@ def generate_worker_files(environ, config_path: str, data_dir: str):
     # and adding a replication listener.
 
     # First read the original config file and extract the listeners block. Then we'll add
-    # another listener for replication. Later we'll write out the result.
+    # another listener for replication. Later we'll write out the result to the shared
+    # config file.
     listeners = [
         {
             "port": 9093,
@@ -339,7 +343,7 @@ def generate_worker_files(environ, config_path: str, data_dir: str):
     # base shared worker jinja2 template.
     #
     # This config file will be passed to all workers, included Synapse's main process.
-    shared_config = {"listeners": listeners}
+    shared_config: Dict[str, Any] = {"listeners": listeners}
 
     # The supervisord config. The contents of which will be inserted into the
     # base supervisord jinja2 template.
@@ -355,7 +359,7 @@ def generate_worker_files(environ, config_path: str, data_dir: str):
     #   worker_type: {1234, 1235, ...}}
     # }
     # and will be used to construct 'upstream' nginx directives.
-    nginx_upstreams = {}
+    nginx_upstreams: Dict[str, Set[int]] = {}
 
     # A map of: {"endpoint": "upstream"}, where "upstream" is a str representing what will be
     # placed after the proxy_pass directive. The main benefit to representing this data as a
@@ -367,13 +371,13 @@ def generate_worker_files(environ, config_path: str, data_dir: str):
     nginx_locations = {}
 
     # Read the desired worker configuration from the environment
-    worker_types = environ.get("SYNAPSE_WORKER_TYPES")
+    worker_types_env = environ.get("SYNAPSE_WORKER_TYPES")
-    if worker_types is None:
+    if worker_types_env is None:
         # No workers, just the main process
         worker_types = []
     else:
         # Split type names by comma
-        worker_types = worker_types.split(",")
+        worker_types = worker_types_env.split(",")
 
     # Create the worker configuration directory if it doesn't already exist
     os.makedirs("/conf/workers", exist_ok=True)
@@ -384,7 +388,11 @@ def generate_worker_files(environ, config_path: str, data_dir: str):
     # A counter of worker_type -> int. Used for determining the name for a given
     # worker type when generating its config file, as each worker's name is just
     # worker_type + instance #
-    worker_type_counter = {}
+    worker_type_counter: Dict[str, int] = {}
+
+    # A list of internal endpoints to healthcheck, starting with the main process
+    # which exists even if no workers do.
+    healthcheck_urls = ["http://localhost:8080/health"]
 
     # For each worker type specified by the user, create config values
     for worker_type in worker_types:
@@ -404,12 +412,14 @@ def generate_worker_files(environ, config_path: str, data_dir: str):
         # e.g. federation_reader1
         worker_name = worker_type + str(new_worker_count)
         worker_config.update(
-            {"name": worker_name, "port": worker_port, "config_path": config_path}
+            {"name": worker_name, "port": str(worker_port), "config_path": config_path}
         )
 
         # Update the shared config with any worker-type specific options
         shared_config.update(worker_config["shared_extra_conf"])
 
+        healthcheck_urls.append("http://localhost:%d/health" % (worker_port,))
+
         # Check if more than one instance of this worker type has been specified
         worker_type_total_count = worker_types.count(worker_type)
         if worker_type_total_count > 1:
@@ -438,21 +448,7 @@ def generate_worker_files(environ, config_path: str, data_dir: str):
 
         # Write out the worker's logging config file
 
-        # Check whether we should write worker logs to disk, in addition to the console
+        log_config_filepath = generate_worker_log_config(environ, worker_name, data_dir)
-        extra_log_template_args = {}
-        if environ.get("SYNAPSE_WORKERS_WRITE_LOGS_TO_DISK"):
-            extra_log_template_args["LOG_FILE_PATH"] = "{dir}/logs/{name}.log".format(
-                dir=data_dir, name=worker_name
-            )
-
-        # Render and write the file
-        log_config_filepath = "/conf/workers/{name}.log.config".format(name=worker_name)
-        convert(
-            "/conf/log.config",
-            log_config_filepath,
-            worker_name=worker_name,
-            **extra_log_template_args,
-        )
 
         # Then a worker config file
         convert(
@@ -475,15 +471,10 @@ def generate_worker_files(environ, config_path: str, data_dir: str):
     # Determine the load-balancing upstreams to configure
     nginx_upstream_config = ""
 
-    # At the same time, prepare a list of internal endpoints to healthcheck
-    # starting with the main process which exists even if no workers do.
-    healthcheck_urls = ["http://localhost:8080/health"]
-
     for upstream_worker_type, upstream_worker_ports in nginx_upstreams.items():
         body = ""
         for port in upstream_worker_ports:
             body += "    server localhost:%d;\n" % (port,)
-            healthcheck_urls.append("http://localhost:%d/health" % (port,))
 
         # Add to the list of configured upstreams
         nginx_upstream_config += NGINX_UPSTREAM_CONFIG_BLOCK.format(
@@ -493,6 +484,10 @@ def generate_worker_files(environ, config_path: str, data_dir: str):
 
     # Finally, we'll write out the config files.
 
+    # log config for the master process
+    master_log_config = generate_worker_log_config(environ, "master", data_dir)
+    shared_config["log_config"] = master_log_config
+
     # Shared homeserver config
     convert(
         "/conf/shared.yaml.j2",
@@ -509,9 +504,10 @@ def generate_worker_files(environ, config_path: str, data_dir: str):
     )
 
     # Supervisord config
+    os.makedirs("/etc/supervisor", exist_ok=True)
     convert(
         "/conf/supervisord.conf.j2",
-        "/etc/supervisor/conf.d/supervisord.conf",
+        "/etc/supervisor/supervisord.conf",
         main_config_path=config_path,
         worker_config=supervisord_config,
     )
@@ -529,15 +525,31 @@ def generate_worker_files(environ, config_path: str, data_dir: str):
         os.mkdir(log_dir)
 
 
-def start_supervisord():
+def generate_worker_log_config(
-    """Starts up supervisord which then starts and monitors all other necessary processes
+    environ: Mapping[str, str], worker_name: str, data_dir: str
+) -> str:
+    """Generate a log.config file for the given worker.
 
-    Raises: CalledProcessError if calling start.py return a non-zero exit code.
+    Returns: the path to the generated file
     """
-    subprocess.run(["/usr/bin/supervisord"], stdin=subprocess.PIPE)
+    # Check whether we should write worker logs to disk, in addition to the console
+    extra_log_template_args = {}
+    if environ.get("SYNAPSE_WORKERS_WRITE_LOGS_TO_DISK"):
+        extra_log_template_args["LOG_FILE_PATH"] = "{dir}/logs/{name}.log".format(
+            dir=data_dir, name=worker_name
+        )
+    # Render and write the file
+    log_config_filepath = "/conf/workers/{name}.log.config".format(name=worker_name)
+    convert(
+        "/conf/log.config",
+        log_config_filepath,
+        worker_name=worker_name,
+        **extra_log_template_args,
+    )
+    return log_config_filepath
 
 
-def main(args, environ):
+def main(args: List[str], environ: MutableMapping[str, str]) -> None:
     config_dir = environ.get("SYNAPSE_CONFIG_DIR", "/data")
     config_path = environ.get("SYNAPSE_CONFIG_PATH", config_dir + "/homeserver.yaml")
     data_dir = environ.get("SYNAPSE_DATA_DIR", "/data")
@@ -564,7 +576,13 @@ def main(args, environ):
 
     # Start supervisord, which will start Synapse, all of the configured worker
     # processes, redis, nginx etc. according to the config we created above.
-    start_supervisord()
+    log("Starting supervisord")
+    os.execl(
+        "/usr/local/bin/supervisord",
+        "supervisord",
+        "-c",
+        "/etc/supervisor/supervisord.conf",
+    )
 
 
 if __name__ == "__main__":

docker/prefix-log

@@ -0,0 +1,12 @@
+#!/bin/bash
+#
+# Prefixes all lines on stdout and stderr with the process name (as determined by
+# the SUPERVISOR_PROCESS_NAME env var, which is automatically set by Supervisor).
+#
+# Usage:
+#   prefix-log command [args...]
+#
+
+exec 1> >(awk '{print "'"${SUPERVISOR_PROCESS_NAME}"' | "$0}' >&1)
+exec 2> >(awk '{print "'"${SUPERVISOR_PROCESS_NAME}"' | "$0}' >&2)
+exec "$@"

docker/run_pg_tests.sh

@@ -1,19 +0,0 @@
-#!/usr/bin/env bash
-
-# This script runs the PostgreSQL tests inside a Docker container. It expects
-# the relevant source files to be mounted into /src (done automatically by the
-# caller script). It will set up the database, run it, and then use the tox
-# configuration to run the tests.
-
-set -e
-
-# Set PGUSER so Synapse's tests know what user to connect to the database with
-export PGUSER=postgres
-
-# Start the database
-sudo -u postgres /usr/lib/postgresql/10/bin/pg_ctl -w -D /var/lib/postgresql/data start
-
-# Run the tests
-cd /src
-export TRIAL_FLAGS="-j 4"
-tox --workdir=./.tox-pg-container -e py37-postgres "$@"

docker/start.py

@@ -6,27 +6,28 @@ import os
 import platform
 import subprocess
 import sys
+from typing import Any, Dict, List, Mapping, MutableMapping, NoReturn, Optional
 
 import jinja2
 
 
 # Utility functions
-def log(txt):
+def log(txt: str) -> None:
     print(txt, file=sys.stderr)
 
 
-def error(txt):
+def error(txt: str) -> NoReturn:
     log(txt)
     sys.exit(2)
 
 
-def convert(src, dst, environ):
+def convert(src: str, dst: str, environ: Mapping[str, object]) -> None:
     """Generate a file from a template
 
     Args:
-        src (str): path to input file
+        src: path to input file
-        dst (str): path to file to write
+        dst: path to file to write
-        environ (dict): environment dictionary, for replacement mappings.
+        environ: environment dictionary, for replacement mappings.
     """
     with open(src) as infile:
         template = infile.read()
@@ -35,25 +36,30 @@ def convert(src, dst, environ):
         outfile.write(rendered)
 
 
-def generate_config_from_template(config_dir, config_path, environ, ownership):
+def generate_config_from_template(
+    config_dir: str,
+    config_path: str,
+    os_environ: Mapping[str, str],
+    ownership: Optional[str],
+) -> None:
     """Generate a homeserver.yaml from environment variables
 
     Args:
-        config_dir (str): where to put generated config files
+        config_dir: where to put generated config files
-        config_path (str): where to put the main config file
+        config_path: where to put the main config file
-        environ (dict): environment dictionary
+        os_environ: environment mapping
-        ownership (str|None): "<user>:<group>" string which will be used to set
+        ownership: "<user>:<group>" string which will be used to set
             ownership of the generated configs. If None, ownership will not change.
     """
     for v in ("SYNAPSE_SERVER_NAME", "SYNAPSE_REPORT_STATS"):
-        if v not in environ:
+        if v not in os_environ:
             error(
                 "Environment variable '%s' is mandatory when generating a config file."
                 % (v,)
             )
 
     # populate some params from data files (if they exist, else create new ones)
-    environ = environ.copy()
+    environ: Dict[str, Any] = dict(os_environ)
     secrets = {
         "registration": "SYNAPSE_REGISTRATION_SHARED_SECRET",
         "macaroon": "SYNAPSE_MACAROON_SECRET_KEY",
@@ -108,7 +114,7 @@ def generate_config_from_template(config_dir, config_path, environ, ownership):
 
     # Hopefully we already have a signing key, but generate one if not.
     args = [
-        "python",
+        sys.executable,
         "-m",
         "synapse.app.homeserver",
         "--config-path",
@@ -127,12 +133,12 @@ def generate_config_from_template(config_dir, config_path, environ, ownership):
     subprocess.check_output(args)
 
 
-def run_generate_config(environ, ownership):
+def run_generate_config(environ: Mapping[str, str], ownership: Optional[str]) -> None:
     """Run synapse with a --generate-config param to generate a template config file
 
     Args:
-        environ (dict): env var dict
+        environ: env vars from `os.enrivon`.
-        ownership (str|None): "userid:groupid" arg for chmod. If None, ownership will not change.
+        ownership: "userid:groupid" arg for chmod. If None, ownership will not change.
 
     Never returns.
     """
@@ -158,7 +164,7 @@ def run_generate_config(environ, ownership):
 
     # generate the main config file, and a signing key.
     args = [
-        "python",
+        sys.executable,
         "-m",
         "synapse.app.homeserver",
         "--server-name",
@@ -175,10 +181,10 @@ def run_generate_config(environ, ownership):
         "--open-private-ports",
     ]
     # log("running %s" % (args, ))
-    os.execv("/usr/local/bin/python", args)
+    os.execv(sys.executable, args)
 
 
-def main(args, environ):
+def main(args: List[str], environ: MutableMapping[str, str]) -> None:
     mode = args[1] if len(args) > 1 else "run"
 
     # if we were given an explicit user to switch to, do so
@@ -254,12 +260,12 @@ running with 'migrate_config'. See the README for more details.
 
     log("Starting synapse with args " + " ".join(args))
 
-    args = ["python"] + args
+    args = [sys.executable] + args
     if ownership is not None:
         args = ["gosu", ownership] + args
         os.execve("/usr/sbin/gosu", args, environ)
     else:
-        os.execve("/usr/local/bin/python", args, environ)
+        os.execve(sys.executable, args, environ)
 
 
 if __name__ == "__main__":

docs/MSC1711_certificates_FAQ.md

@@ -1,314 +0,0 @@
-# MSC1711 Certificates FAQ
-
-## Historical Note
-This document was originally written to guide server admins through the upgrade
-path towards Synapse 1.0. Specifically,
-[MSC1711](https://github.com/matrix-org/matrix-doc/blob/main/proposals/1711-x509-for-federation.md)
-required that all servers present valid TLS certificates on their federation
-API. Admins were encouraged to achieve compliance from version 0.99.0 (released
-in February 2019) ahead of version 1.0 (released June 2019) enforcing the
-certificate checks.
-
-Much of what follows is now outdated since most admins will have already
-upgraded, however it may be of use to those with old installs returning to the
-project.
-
-If you are setting up a server from scratch you almost certainly should look at
-the [installation guide](setup/installation.md) instead.
-
-## Introduction
-The goal of Synapse 0.99.0 is to act as a stepping stone to Synapse 1.0.0. It
-supports the r0.1 release of the server to server specification, but is
-compatible with both the legacy Matrix federation behaviour (pre-r0.1) as well
-as post-r0.1 behaviour, in order to allow for a smooth upgrade across the
-federation.
-
-The most important thing to know is that Synapse 1.0.0 will require a valid TLS
-certificate on federation endpoints. Self signed certificates will not be
-sufficient.
-
-Synapse 0.99.0 makes it easy to configure TLS certificates and will
-interoperate with both >= 1.0.0 servers as well as existing servers yet to
-upgrade.
-
-**It is critical that all admins upgrade to 0.99.0 and configure a valid TLS
-certificate.** Admins will have 1 month to do so, after which 1.0.0 will be
-released and those servers without a valid certificate will not longer be able
-to federate with >= 1.0.0 servers.
-
-Full details on how to carry out this configuration change is given
-[below](#configuring-certificates-for-compatibility-with-synapse-100). A
-timeline and some frequently asked questions are also given below.
-
-For more details and context on the release of the r0.1 Server/Server API and
-imminent Matrix 1.0 release, you can also see our
-[main talk from FOSDEM 2019](https://matrix.org/blog/2019/02/04/matrix-at-fosdem-2019/).
-
-## Timeline
-
-**5th Feb 2019  - Synapse 0.99.0 is released.**
-
-All server admins are encouraged to upgrade.
-
-0.99.0:
-
--   provides support for ACME to make setting up Let's Encrypt certs easy, as
-    well as .well-known support.
-
--   does not enforce that a valid CA cert is present on the federation API, but
-    rather makes it easy to set one up.
-
--   provides support for .well-known
-
-Admins should upgrade and configure a valid CA cert. Homeservers that require a
-.well-known entry (see below), should retain their SRV record and use it
-alongside their .well-known record.
-
-**10th June 2019  - Synapse 1.0.0 is released**
-
-1.0.0 is scheduled for release on 10th June. In
-accordance with the the [S2S spec](https://matrix.org/docs/spec/server_server/r0.1.0.html)
-1.0.0 will enforce certificate validity. This means that any homeserver without a
-valid certificate after this point will no longer be able to federate with
-1.0.0 servers.
-
-## Configuring certificates for compatibility with Synapse 1.0.0
-
-### If you do not currently have an SRV record
-
-In this case, your `server_name` points to the host where your Synapse is
-running. There is no need to create a `.well-known` URI or an SRV record, but
-you will need to give Synapse a valid, signed, certificate.
-
-### If you do have an SRV record currently
-
-If you are using an SRV record, your matrix domain (`server_name`) may not
-point to the same host that your Synapse is running on (the 'target
-domain'). (If it does, you can follow the recommendation above; otherwise, read
-on.)
-
-Let's assume that your `server_name` is `example.com`, and your Synapse is
-hosted at a target domain of `customer.example.net`. Currently you should have
-an SRV record which looks like:
-
-```
-_matrix._tcp.example.com. IN SRV 10 5 8000 customer.example.net.
-```
-
-In this situation, you have three choices for how to proceed:
-
-#### Option 1: give Synapse a certificate for your matrix domain
-
-Synapse 1.0 will expect your server to present a TLS certificate for your
-`server_name` (`example.com` in the above example). You can achieve this by acquiring a
-certificate for the `server_name` yourself (for example, using `certbot`), and giving it
-and the key to Synapse via `tls_certificate_path` and `tls_private_key_path`.
-
-#### Option 2: run Synapse behind a reverse proxy
-
-If you have an existing reverse proxy set up with correct TLS certificates for
-your domain, you can simply route all traffic through the reverse proxy by
-updating the SRV record appropriately (or removing it, if the proxy listens on
-8448).
-
-See [the reverse proxy documentation](reverse_proxy.md) for information on setting up a
-reverse proxy.
-
-#### Option 3: add a .well-known file to delegate your matrix traffic
-
-This will allow you to keep Synapse on a separate domain, without having to
-give it a certificate for the matrix domain.
-
-You can do this with a `.well-known` file as follows:
-
- 1. Keep the SRV record in place - it is needed for backwards compatibility
-    with Synapse 0.34 and earlier.
-
-  2. Give Synapse a certificate corresponding to the target domain
-    (`customer.example.net` in the above example). You can do this by acquire a 
-    certificate for the target domain and giving it to Synapse via `tls_certificate_path`
-    and `tls_private_key_path`.
-
- 3. Restart Synapse to ensure the new certificate is loaded.
-
- 4. Arrange for a `.well-known` file at
-    `https://<server_name>/.well-known/matrix/server` with contents:
-
-    ```json
-    {"m.server": "<target server name>"}
-    ```
-
-    where the target server name is resolved as usual (i.e. SRV lookup, falling
-    back to talking to port 8448).
-
-    In the above example, where synapse is listening on port 8000,
-    `https://example.com/.well-known/matrix/server` should have `m.server` set to one of:
-
-    1. `customer.example.net` ─ with a SRV record on
-       `_matrix._tcp.customer.example.com` pointing to port 8000, or:
-
-    2. `customer.example.net` ─ updating synapse to listen on the default port
-       8448, or:
-
-    3. `customer.example.net:8000` ─ ensuring that if there is a reverse proxy
-       on `customer.example.net:8000` it correctly handles HTTP requests with
-       Host header set to `customer.example.net:8000`.
-
-## FAQ
-
-### Synapse 0.99.0 has just been released, what do I need to do right now?
-
-Upgrade as soon as you can in preparation for Synapse 1.0.0, and update your
-TLS certificates as [above](#configuring-certificates-for-compatibility-with-synapse-100).
-
-### What will happen if I do not set up a valid federation certificate immediately?
-
-Nothing initially, but once 1.0.0 is in the wild it will not be possible to
-federate with 1.0.0 servers.
-
-### What will happen if I do nothing at all?
-
-If the admin takes no action at all, and remains on a Synapse < 0.99.0 then the
-homeserver will be unable to federate with those who have implemented
-.well-known. Then, as above, once the month upgrade window has expired the
-homeserver will not be able to federate with any Synapse >= 1.0.0
-
-### When do I need a SRV record or .well-known URI?
-
-If your homeserver listens on the default federation port (8448), and your
-`server_name` points to the host that your homeserver runs on, you do not need an
-SRV record or `.well-known/matrix/server` URI.
-
-For instance, if you registered `example.com` and pointed its DNS A record at a
-fresh Upcloud VPS or similar, you could install Synapse 0.99 on that host,
-giving it a server_name of `example.com`, and it would automatically generate a
-valid TLS certificate for you via Let's Encrypt and no SRV record or
-`.well-known` URI would be needed.
-
-This is the common case, although you can add an SRV record or
-`.well-known/matrix/server` URI for completeness if you wish.
-
-**However**, if your server does not listen on port 8448, or if your `server_name`
-does not point to the host that your homeserver runs on, you will need to let
-other servers know how to find it.
-
-In this case, you should see ["If you do have an SRV record
-currently"](#if-you-do-have-an-srv-record-currently) above.
-
-### Can I still use an SRV record?
-
-Firstly, if you didn't need an SRV record before (because your server is
-listening on port 8448 of your server_name), you certainly don't need one now:
-the defaults are still the same.
-
-If you previously had an SRV record, you can keep using it provided you are
-able to give Synapse a TLS certificate corresponding to your server name. For
-example, suppose you had the following SRV record, which directs matrix traffic
-for example.com to matrix.example.com:443:
-
-```
-_matrix._tcp.example.com. IN SRV 10 5 443 matrix.example.com
-```
-
-In this case, Synapse must be given a certificate for example.com - or be
-configured to acquire one from Let's Encrypt.
-
-If you are unable to give Synapse a certificate for your server_name, you will
-also need to use a .well-known URI instead. However, see also "I have created a
-.well-known URI. Do I still need an SRV record?".
-
-### I have created a .well-known URI. Do I still need an SRV record?
-
-As of Synapse 0.99, Synapse will first check for the existence of a `.well-known`
-URI and follow any delegation it suggests. It will only then check for the
-existence of an SRV record.
-
-That means that the SRV record will often be redundant. However, you should
-remember that there may still be older versions of Synapse in the federation
-which do not understand `.well-known` URIs, so if you removed your SRV record you
-would no longer be able to federate with them.
-
-It is therefore best to leave the SRV record in place for now. Synapse 0.34 and
-earlier will follow the SRV record (and not care about the invalid
-certificate). Synapse 0.99 and later will follow the .well-known URI, with the
-correct certificate chain.
-
-### It used to work just fine, why are you breaking everything?
-
-We have always wanted Matrix servers to be as easy to set up as possible, and
-so back when we started federation in 2014 we didn't want admins to have to go
-through the cumbersome process of buying a valid TLS certificate to run a
-server. This was before Let's Encrypt came along and made getting a free and
-valid TLS certificate straightforward. So instead, we adopted a system based on
-[Perspectives](https://en.wikipedia.org/wiki/Convergence_(SSL)): an approach
-where you check a set of "notary servers" (in practice, homeservers) to vouch
-for the validity of a certificate rather than having it signed by a CA. As long
-as enough different notaries agree on the certificate's validity, then it is
-trusted.
-
-However, in practice this has never worked properly. Most people only use the
-default notary server (matrix.org), leading to inadvertent centralisation which
-we want to eliminate. Meanwhile, we never implemented the full consensus
-algorithm to query the servers participating in a room to determine consensus
-on whether a given certificate is valid. This is fiddly to get right
-(especially in face of sybil attacks), and we found ourselves questioning
-whether it was worth the effort to finish the work and commit to maintaining a
-secure certificate validation system as opposed to focusing on core Matrix
-development.
-
-Meanwhile, Let's Encrypt came along in 2016, and put the final nail in the
-coffin of the Perspectives project (which was already pretty dead). So, the
-Spec Core Team decided that a better approach would be to mandate valid TLS
-certificates for federation alongside the rest of the Web. More details can be
-found in
-[MSC1711](https://github.com/matrix-org/matrix-doc/blob/main/proposals/1711-x509-for-federation.md#background-the-failure-of-the-perspectives-approach).
-
-This results in a breaking change, which is disruptive, but absolutely critical
-for the security model. However, the existence of Let's Encrypt as a trivial
-way to replace the old self-signed certificates with valid CA-signed ones helps
-smooth things over massively, especially as Synapse can now automate Let's
-Encrypt certificate generation if needed.
-
-### Can I manage my own certificates rather than having Synapse renew certificates itself?
-
-Yes, you are welcome to manage your certificates yourself. Synapse will only
-attempt to obtain certificates from Let's Encrypt if you configure it to do
-so.The only requirement is that there is a valid TLS cert present for
-federation end points.
-
-### Do you still recommend against using a reverse proxy on the federation port?
-
-We no longer actively recommend against using a reverse proxy. Many admins will
-find it easier to direct federation traffic to a reverse proxy and manage their
-own TLS certificates, and this is a supported configuration.
-
-See [the reverse proxy documentation](reverse_proxy.md) for information on setting up a
-reverse proxy.
-
-### Do I still need to give my TLS certificates to Synapse if I am using a reverse proxy?
-
-Practically speaking, this is no longer necessary.
-
-If you are using a reverse proxy for all of your TLS traffic, then you can set
-`no_tls: True`. In that case, the only reason Synapse needs the certificate is
-to populate a legacy 'tls_fingerprints' field in the federation API. This is
-ignored by Synapse 0.99.0 and later, and the only time pre-0.99 Synapses will
-check it is when attempting to fetch the server keys - and generally this is
-delegated via `matrix.org`, which is on 0.99.0.
-
-However, there is a bug in Synapse 0.99.0
-[4554](<https://github.com/matrix-org/synapse/issues/4554>) which prevents
-Synapse from starting if you do not give it a TLS certificate. To work around
-this, you can give it any TLS certificate at all. This will be fixed soon.
-
-### Do I need the same certificate for the client and federation port?
-
-No. There is nothing stopping you from using different certificates,
-particularly if you are using a reverse proxy. However, Synapse will use the
-same certificate on any ports where TLS is configured.
-
-### How do I tell Synapse to reload my keys/certificates after I replace them?
-
-Synapse will reload the keys and certificates when it receives a SIGHUP - for
-example `kill -HUP $(cat homeserver.pid)`. Alternatively, simply restart
-Synapse, though this will result in downtime while it restarts.

docs/SUMMARY.md

@@ -13,11 +13,11 @@
 
 # Upgrading
   - [Upgrading between Synapse Versions](upgrade.md)
-  - [Upgrading from pre-Synapse 1.0](MSC1711_certificates_FAQ.md)
 
 # Usage
   - [Federation](federate.md)
   - [Configuration](usage/configuration/README.md)
+    - [Configuration Manual](usage/configuration/config_documentation.md) 
     - [Homeserver Sample Config File](usage/configuration/homeserver_sample_config.md)
     - [Logging Sample Config File](usage/configuration/logging_sample_config.md)
     - [Structured Logging](structured_logging.md)
@@ -46,6 +46,7 @@
         - [Account validity callbacks](modules/account_validity_callbacks.md)
         - [Password auth provider callbacks](modules/password_auth_provider_callbacks.md)
         - [Background update controller callbacks](modules/background_update_controller_callbacks.md)
+        - [Account data callbacks](modules/account_data_callbacks.md)
         - [Porting a legacy module to the new interface](modules/porting_legacy_module.md)
     - [Workers](workers.md)
       - [Using `synctl` with Workers](synctl_workers.md)
@@ -72,7 +73,7 @@
     - [Understanding Synapse Through Grafana Graphs](usage/administration/understanding_synapse_through_grafana_graphs.md)
     - [Useful SQL for Admins](usage/administration/useful_sql_for_admins.md)
     - [Database Maintenance Tools](usage/administration/database_maintenance_tools.md)
-    - [State Groups](usage/administration/state_groups.md) 
+    - [State Groups](usage/administration/state_groups.md)
     - [Request log format](usage/administration/request_log.md)
     - [Admin FAQ](usage/administration/admin_faq.md)
     - [Scripts]()
@@ -80,8 +81,10 @@
 # Development
   - [Contributing Guide](development/contributing_guide.md)
   - [Code Style](code_style.md)
+  - [Release Cycle](development/releases.md)
   - [Git Usage](development/git.md)
   - [Testing]()
+    - [Demo scripts](development/demo.md)
   - [OpenTracing](opentracing.md)
   - [Database Schemas](development/database_schema.md)
   - [Experimental features](development/experimental_features.md)

docs/admin_api/media_admin_api.md

@@ -2,6 +2,9 @@
 
 These APIs allow extracting media information from the homeserver.
 
+Details about the format of the `media_id` and storage of the media in the file system
+are documented under [media repository](../media_repository.md).
+
 To use it, you will need to authenticate by providing an `access_token`
 for a server admin: see [Admin API](../usage/administration/admin_api).
 

docs/admin_api/user_admin_api.md

@@ -126,7 +126,8 @@ Body parameters:
   [Sample Configuration File](../usage/configuration/homeserver_sample_config.html)
   section `sso` and `oidc_providers`.
   - `auth_provider` - string. ID of the external identity provider. Value of `idp_id`
-    in homeserver configuration.
+    in the homeserver configuration. Note that no error is raised if the provided
+    value is not in the homeserver configuration.
   - `external_id` - string, user ID in the external identity provider.
 - `avatar_url` - string, optional, must be a
   [MXC URI](https://matrix.org/docs/spec/client_server/r0.6.0#matrix-content-mxc-uris).
@@ -331,7 +332,7 @@ An empty body may be passed for backwards compatibility.
 
 The following actions are performed when deactivating an user:
 
-- Try to unpind 3PIDs from the identity server
+- Try to unbind 3PIDs from the identity server
 - Remove all 3PIDs from the homeserver
 - Delete all devices and E2EE keys
 - Delete all access tokens
@@ -539,6 +540,11 @@ The following fields are returned in the JSON response body:
 
 ### List media uploaded by a user
 Gets a list of all local media that a specific `user_id` has created.
+These are media that the user has uploaded themselves
+([local media](../media_repository.md#local-media)), as well as
+[URL preview images](../media_repository.md#url-previews) requested by the user if the
+[feature is enabled](../development/url_previews.md).
+
 By default, the response is ordered by descending creation date and ascending media ID.
 The newest media is on top. You can change the order with parameters
 `order_by` and `dir`.
@@ -635,7 +641,9 @@ The following fields are returned in the JSON response body:
   Media objects contain the following fields:
   - `created_ts` - integer - Timestamp when the content was uploaded in ms.
   - `last_access_ts` - integer - Timestamp when the content was last accessed in ms.
-  - `media_id` - string - The id used to refer to the media.
+  - `media_id` - string - The id used to refer to the media. Details about the format
+    are documented under
+    [media repository](../media_repository.md).
   - `media_length` - integer - Length of the media in bytes.
   - `media_type` - string - The MIME-type of the media.
   - `quarantined_by` - string - The user ID that initiated the quarantine request
@@ -796,7 +804,7 @@ POST /_synapse/admin/v2/users/<user_id>/delete_devices
   "devices": [
     "QBUAZIFURK",
     "AUIECTSRND"
-  ],
+  ]
 }
 ```
 

docs/changelogs/README.md

@@ -0,0 +1 @@
+This directory contains changelogs for previous years.

docs/code_style.md

@@ -6,62 +6,36 @@ The Synapse codebase uses a number of code formatting tools in order to
 quickly and automatically check for formatting (and sometimes logical)
 errors in code.
 
-The necessary tools are detailed below.
+The necessary tools are:
 
-First install them with:
+- [black](https://black.readthedocs.io/en/stable/), a source code formatter;
+- [isort](https://pycqa.github.io/isort/), which organises each file's imports;
+- [flake8](https://flake8.pycqa.org/en/latest/), which can spot common errors; and
+- [mypy](https://mypy.readthedocs.io/en/stable/), a type checker.
+
+Install them with:
 
 ```sh
 pip install -e ".[lint,mypy]"
 ```
 
--   **black**
+The easiest way to run the lints is to invoke the linter script as follows.
 
-    The Synapse codebase uses [black](https://pypi.org/project/black/)
+```sh
-    as an opinionated code formatter, ensuring all comitted code is
+scripts-dev/lint.sh
-    properly formatted.
+```
-
-    Have `black` auto-format your code (it shouldn't change any
-    functionality) with:
-
-    ```sh
-    black . --exclude="\.tox|build|env"
-    ```
-
--   **flake8**
-
-    `flake8` is a code checking tool. We require code to pass `flake8`
-    before being merged into the codebase.
-
-    Check all application and test code with:
-
-    ```sh
-    flake8 synapse tests
-    ```
-
--   **isort**
-
-    `isort` ensures imports are nicely formatted, and can suggest and
-    auto-fix issues such as double-importing.
-
-    Auto-fix imports with:
-
-    ```sh
-    isort -rc synapse tests
-    ```
-
-    `-rc` means to recursively search the given directories.
 
 It's worth noting that modern IDEs and text editors can run these tools
 automatically on save. It may be worth looking into whether this
 functionality is supported in your editor for a more convenient
-development workflow. It is not, however, recommended to run `flake8` on
+development workflow. It is not, however, recommended to run `flake8` or `mypy`
-save as it takes a while and is very resource intensive.
+on save as they take a while and can be very resource intensive.
 
 ## General rules
 
 -   **Naming**:
-    -   Use camel case for class and type names
+    -   Use `CamelCase` for class and type names
-    -   Use underscores for functions and variables.
+    -   Use underscores for `function_names` and `variable_names`.
 -   **Docstrings**: should follow the [google code
     style](https://google.github.io/styleguide/pyguide.html#38-comments-and-docstrings).
     See the
@@ -172,6 +146,6 @@ frobber:
 ```
 
 Note that the sample configuration is generated from the synapse code
-and is maintained by a script, `scripts-dev/generate_sample_config`.
+and is maintained by a script, `scripts-dev/generate_sample_config.sh`.
 Making sure that the output from this script matches the desired format
 is left as an exercise for the reader!

docs/development/contributing_guide.md

@@ -48,19 +48,28 @@ can find many good git tutorials on the web.
 
 # 4. Install the dependencies
 
-Once you have installed Python 3 and added the source, please open a terminal and
+Synapse uses the [poetry](https://python-poetry.org/) project to manage its dependencies
-setup a *virtualenv*, as follows:
+and development environment. Once you have installed Python 3 and added the
+source, you should install `poetry`.
+Of their installation methods, we recommend
+[installing `poetry` using `pipx`](https://python-poetry.org/docs/#installing-with-pipx),
+
+```shell
+pip install --user pipx
+pipx install poetry
+```
+
+but see poetry's [installation instructions](https://python-poetry.org/docs/#installation)
+for other installation methods.
+
+Next, open a terminal and install dependencies as follows:
 
 ```sh
 cd path/where/you/have/cloned/the/repository
-python3 -m venv ./env
+poetry install --extras all
-source ./env/bin/activate
-pip install wheel
-pip install -e ".[all,dev]"
-pip install tox
 ```
 
-This will install the developer dependencies for the project.
+This will install the runtime and developer dependencies for the project.
 
 
 # 5. Get in touch.
@@ -117,11 +126,10 @@ The linters look at your code and do two things:
 - ensure that your code follows the coding style adopted by the project;
 - catch a number of errors in your code.
 
-The linter takes no time at all to run as soon as you've [downloaded the dependencies into your python virtual environment](#4-install-the-dependencies).
+The linter takes no time at all to run as soon as you've [downloaded the dependencies](#4-install-the-dependencies).
 
 ```sh
-source ./env/bin/activate
+poetry run ./scripts-dev/lint.sh
-./scripts-dev/lint.sh
 ```
 
 Note that this script *will modify your files* to fix styling errors.
@@ -131,15 +139,13 @@ If you wish to restrict the linters to only the files changed since the last com
 (much faster!), you can instead run:
 
 ```sh
-source ./env/bin/activate
+poetry run ./scripts-dev/lint.sh -d
-./scripts-dev/lint.sh -d
 ```
 
 Or if you know exactly which files you wish to lint, you can instead run:
 
 ```sh
-source ./env/bin/activate
+poetry run ./scripts-dev/lint.sh path/to/file1.py path/to/file2.py path/to/folder
-./scripts-dev/lint.sh path/to/file1.py path/to/file2.py path/to/folder
 ```
 
 ## Run the unit tests (Twisted trial).
@@ -148,16 +154,14 @@ The unit tests run parts of Synapse, including your changes, to see if anything
 was broken. They are slower than the linters but will typically catch more errors.
 
 ```sh
-source ./env/bin/activate
+poetry run trial tests
-trial tests
 ```
 
 If you wish to only run *some* unit tests, you may specify
 another module instead of `tests` - or a test class or a method:
 
 ```sh
-source ./env/bin/activate
+poetry run trial tests.rest.admin.test_room tests.handlers.test_admin.ExfiltrateData.test_invite
-trial tests.rest.admin.test_room tests.handlers.test_admin.ExfiltrateData.test_invite
 ```
 
 If your tests fail, you may wish to look at the logs (the default log level is `ERROR`):
@@ -169,7 +173,7 @@ less _trial_temp/test.log
 To increase the log level for the tests, set `SYNAPSE_TEST_LOG_LEVEL`:
 
 ```sh
-SYNAPSE_TEST_LOG_LEVEL=DEBUG trial tests
+SYNAPSE_TEST_LOG_LEVEL=DEBUG poetry run trial tests
 ```
 
 By default, tests will use an in-memory SQLite database for test data. For additional
@@ -180,7 +184,7 @@ database state to be stored in a file named `test.db` under the trial process'
 working directory. Typically, this ends up being `_trial_temp/test.db`. For example:
 
 ```sh
-SYNAPSE_TEST_PERSIST_SQLITE_DB=1 trial tests
+SYNAPSE_TEST_PERSIST_SQLITE_DB=1 poetry run trial tests
 ```
 
 The database file can then be inspected with:
@@ -206,9 +210,10 @@ To do so, [configure Postgres](../postgres.md) and run `trial` with the
 following environment variables matching your configuration:
 
 - `SYNAPSE_POSTGRES` to anything nonempty
-- `SYNAPSE_POSTGRES_HOST`
+- `SYNAPSE_POSTGRES_HOST` (optional if it's the default: UNIX socket)
-- `SYNAPSE_POSTGRES_USER`
+- `SYNAPSE_POSTGRES_PORT` (optional if it's the default: 5432)
-- `SYNAPSE_POSTGRES_PASSWORD`
+- `SYNAPSE_POSTGRES_USER` (optional if using a UNIX socket)
+- `SYNAPSE_POSTGRES_PASSWORD` (optional if using a UNIX socket)
 
 For example:
 
@@ -220,26 +225,12 @@ export SYNAPSE_POSTGRES_PASSWORD=mydevenvpassword
 trial
 ```
 
-#### Prebuilt container
+You don't need to specify the host, user, port or password if your Postgres
+server is set to authenticate you over the UNIX socket (i.e. if the `psql` command
+works without further arguments).
 
-Since configuring PostgreSQL can be fiddly, we can make use of a pre-made
+Your Postgres account needs to be able to create databases.
-Docker container to set up PostgreSQL and run our tests for us. To do so, run
 
-```shell
-scripts-dev/test_postgresql.sh
-```
-
-Any extra arguments to the script will be passed to `tox` and then to `trial`,
-so we can run a specific test in this container with e.g.
-
-```shell
-scripts-dev/test_postgresql.sh tests.replication.test_sharded_event_persister.EventPersisterShardTestCase
-```
-
-The container creates a folder in your Synapse checkout called
-`.tox-pg-container` and uses this as a tox environment. The output of any
-`trial` runs goes into `_trial_temp` in your synapse source directory — the same
-as running `trial` directly on your host machine.
 
 ## Run the integration tests ([Sytest](https://github.com/matrix-org/sytest)).
 
@@ -254,8 +245,14 @@ configuration:
 ```sh
 $ docker run --rm -it -v /path/where/you/have/cloned/the/repository\:/src:ro -v /path/to/where/you/want/logs\:/logs matrixdotorg/sytest-synapse:buster
 ```
+(Note that the paths must be full paths! You could also write `$(realpath relative/path)` if needed.)
 
-This configuration should generally cover  your needs. For more details about other configurations, see [documentation in the SyTest repo](https://github.com/matrix-org/sytest/blob/develop/docker/README.md).
+This configuration should generally cover your needs.
+
+- To run with Postgres, supply the `-e POSTGRES=1 -e MULTI_POSTGRES=1` environment flags.
+- To run with Synapse in worker mode, supply the `-e WORKERS=1 -e REDIS=1` environment flags (in addition to the Postgres flags).
+
+For more details about other configurations, see the [Docker-specific documentation in the SyTest repo](https://github.com/matrix-org/sytest/blob/develop/docker/README.md).
 
 
 ## Run the integration tests ([Complement](https://github.com/matrix-org/complement)).
@@ -458,6 +455,17 @@ Git allows you to add this signoff automatically when using the `-s`
 flag to `git commit`, which uses the name and email set in your
 `user.name` and `user.email` git configs.
 
+### Private Sign off
+
+If you would like to provide your legal name privately to the Matrix.org
+Foundation (instead of in a public commit or comment), you can do so
+by emailing your legal name and a link to the pull request to
+[dco@matrix.org](mailto:dco@matrix.org?subject=Private%20sign%20off).
+It helps to include "sign off" or similar in the subject line. You will then
+be instructed further.
+
+Once private sign off is complete, doing so for future contributions will not
+be required.
 
 # 10. Turn feedback into better code.
 

docs/development/database_schema.md

@@ -158,9 +158,9 @@ same as integers.
 There are three separate aspects to this:
 
  * Any new boolean column must be added to the `BOOLEAN_COLUMNS` list in
-   `scripts/synapse_port_db`. This tells the port script to cast the integer
+   `synapse/_scripts/synapse_port_db.py`. This tells the port script to cast
-   value from SQLite to a boolean before writing the value to the postgres
+   the integer value from SQLite to a boolean before writing the value to the
-   database.
+   postgres database.
 
  * Before SQLite 3.23, `TRUE` and `FALSE` were not recognised as constants by
    SQLite, and the `IS [NOT] TRUE`/`IS [NOT] FALSE` operators were not

docs/development/demo.md

@@ -0,0 +1,41 @@
+# Synapse demo setup
+
+**DO NOT USE THESE DEMO SERVERS IN PRODUCTION**
+
+Requires you to have a [Synapse development environment setup](https://matrix-org.github.io/synapse/develop/development/contributing_guide.html#4-install-the-dependencies).
+
+The demo setup allows running three federation Synapse servers, with server
+names `localhost:8080`, `localhost:8081`, and `localhost:8082`.
+
+You can access them via any Matrix client over HTTP at `localhost:8080`,
+`localhost:8081`, and `localhost:8082` or over HTTPS at `localhost:8480`,
+`localhost:8481`, and `localhost:8482`.
+
+To enable the servers to communicate, self-signed SSL certificates are generated
+and the servers are configured in a highly insecure way, including:
+
+* Not checking certificates over federation.
+* Not verifying keys.
+
+The servers are configured to store their data under `demo/8080`, `demo/8081`, and
+`demo/8082`. This includes configuration, logs, SQLite databases, and media.
+
+Note that when joining a public room on a different HS via "#foo:bar.net", then
+you are (in the current impl) joining a room with room_id "foo". This means that
+it won't work if your HS already has a room with that name.
+
+## Using the demo scripts
+
+There's three main scripts with straightforward purposes:
+
+* `start.sh` will start the Synapse servers, generating any missing configuration.
+  * This accepts a single parameter `--no-rate-limit` to "disable" rate limits
+    (they actually still exist, but are very high).
+* `stop.sh` will stop the Synapse servers.
+* `clean.sh` will delete the configuration, databases, log files, etc.
+
+To start a completely new set of servers, run:
+
+```sh
+./demo/stop.sh; ./demo/clean.sh && ./demo/start.sh
+```

docs/development/dependencies.md

@@ -0,0 +1,239 @@
+# Managing dependencies with Poetry
+
+This is a quick cheat sheet for developers on how to use [`poetry`](https://python-poetry.org/).
+
+# Background
+
+Synapse uses a variety of third-party Python packages to function as a homeserver.
+Some of these are direct dependencies, listed in `pyproject.toml` under the
+`[tool.poetry.dependencies]` section. The rest are transitive dependencies (the
+things that our direct dependencies themselves depend on, and so on recursively.)
+
+We maintain a locked list of all our dependencies (transitive included) so that
+we can track exactly which version of each dependency appears in a given release.
+See [here](https://github.com/matrix-org/synapse/issues/11537#issue-1074469665)
+for discussion of why we wanted this for Synapse. We chose to use
+[`poetry`](https://python-poetry.org/) to manage this locked list; see
+[this comment](https://github.com/matrix-org/synapse/issues/11537#issuecomment-1015975819)
+for the reasoning.
+
+The locked dependencies get included in our "self-contained" releases: namely,
+our docker images and our debian packages. We also use the locked dependencies
+in development and our continuous integration.
+
+Separately, our "broad" dependencies—the version ranges specified in
+`pyproject.toml`—are included as metadata in our "sdists" and "wheels" [uploaded
+to PyPI](https://pypi.org/project/matrix-synapse). Installing from PyPI or from
+the Synapse source tree directly will _not_ use the locked dependencies; instead,
+they'll pull in the latest version of each package available at install time.
+
+## Example dependency
+
+An example may help. We have a broad dependency on
+[`phonenumbers`](https://pypi.org/project/phonenumbers/), as declared in
+this snippet from pyproject.toml [as of Synapse 1.57](
+https://github.com/matrix-org/synapse/blob/release-v1.57/pyproject.toml#L133
+):
+
+```toml
+[tool.poetry.dependencies]
+# ...
+phonenumbers = ">=8.2.0"
+```
+
+In our lockfile this is
+[pinned]( https://github.com/matrix-org/synapse/blob/dfc7646504cef3e4ff396c36089e1c6f1b1634de/poetry.lock#L679-L685)
+to version 8.12.44, even though
+[newer versions are available](https://pypi.org/project/phonenumbers/#history).
+
+```toml
+[[package]]
+name = "phonenumbers"
+version = "8.12.44"
+description = "Python version of Google's common library for parsing, formatting, storing and validating international phone numbers."
+category = "main"
+optional = false
+python-versions = "*"
+```
+
+The lockfile also includes a
+[cryptographic checksum](https://github.com/matrix-org/synapse/blob/release-v1.57/poetry.lock#L2178-L2181)
+of the sdists and wheels provided for this version of `phonenumbers`.
+
+```toml
+[metadata.files]
+# ...
+phonenumbers = [
+    {file = "phonenumbers-8.12.44-py2.py3-none-any.whl", hash = "sha256:cc1299cf37b309ecab6214297663ab86cb3d64ae37fd5b88e904fe7983a874a6"},
+    {file = "phonenumbers-8.12.44.tar.gz", hash = "sha256:26cfd0257d1704fe2f88caff2caabb70d16a877b1e65b6aae51f9fbbe10aa8ce"},
+]
+```
+
+We can see this pinned version inside the docker image for that release:
+
+```
+$ docker pull matrixdotorg/synapse:v1.57.0
+...
+$ docker run --entrypoint pip matrixdotorg/synapse:v1.57.0 show phonenumbers
+Name: phonenumbers
+Version: 8.12.44
+Summary: Python version of Google's common library for parsing, formatting, storing and validating international phone numbers.
+Home-page: https://github.com/daviddrysdale/python-phonenumbers
+Author: David Drysdale
+Author-email: dmd@lurklurk.org
+License: Apache License 2.0
+Location: /usr/local/lib/python3.9/site-packages
+Requires:
+Required-by: matrix-synapse
+```
+
+Whereas the wheel metadata just contains the broad dependencies:
+
+```
+$ cd /tmp
+$ wget https://files.pythonhosted.org/packages/ca/5e/d722d572cc5b3092402b783d6b7185901b444427633bd8a6b00ea0dd41b7/matrix_synapse-1.57.0rc1-py3-none-any.whl
+...
+$ unzip -c matrix_synapse-1.57.0rc1-py3-none-any.whl matrix_synapse-1.57.0rc1.dist-info/METADATA | grep phonenumbers
+Requires-Dist: phonenumbers (>=8.2.0)
+```
+
+# Tooling recommendation: direnv
+
+[`direnv`](https://direnv.net/) is a tool for activating environments in your
+shell inside a given directory. Its support for poetry is unofficial (a
+community wiki recipe only), but works solidly in our experience. We thoroughly
+recommend it for daily use. To use it:
+
+1. [Install `direnv`](https://direnv.net/docs/installation.html) - it's likely
+   packaged for your system already.
+2. Teach direnv about poetry. The [shell config here](https://github.com/direnv/direnv/wiki/Python#poetry)
+   needs to be added to `~/.config/direnv/direnvrc` (or more generally `$XDG_CONFIG_HOME/direnv/direnvrc`).
+3. Mark the synapse checkout as a poetry project: `echo layout poetry > .envrc`.
+4. Convince yourself that you trust this `.envrc` configuration and project.
+   Then formally confirm this to `direnv` by running `direnv allow`.
+
+Then whenever you navigate to the synapse checkout, you should be able to run
+e.g. `mypy` instead of `poetry run mypy`; `python` instead of
+`poetry run python`; and your shell commands will automatically run in the
+context of poetry's venv, without having to run `poetry shell` beforehand.
+
+
+# How do I...
+
+## ...reset my venv to the locked environment?
+
+```shell
+poetry install --extras all --remove-untracked
+```
+
+## ...run a command in the `poetry` virtualenv?
+
+Use `poetry run cmd args` when you need the python virtualenv context.
+To avoid typing `poetry run` all the time, you can run  `poetry shell`
+to start a new shell in the poetry virtualenv context. Within `poetry shell`,
+`python`, `pip`, `mypy`, `trial`, etc. are all run inside the project virtualenv
+and isolated from the rest o the system.
+
+Roughly speaking, the translation from a traditional virtualenv is:
+- `env/bin/activate` -> `poetry shell`, and
+- `deactivate` -> close the terminal (Ctrl-D, `exit`, etc.)
+
+See also the direnv recommendation above, which makes `poetry run` and
+`poetry shell` unnecessary.
+
+
+## ...inspect the `poetry` virtualenv?
+
+Some suggestions:
+
+```shell
+# Current env only
+poetry env info
+# All envs: this allows you to have e.g. a poetry managed venv for Python 3.7,
+# and another for Python 3.10.
+poetry env list --full-path
+poetry run pip list
+```
+
+Note that `poetry show` describes the abstract *lock file* rather than your
+on-disk environment. With that said, `poetry show --tree` can sometimes be
+useful.
+
+
+## ...add a new dependency?
+
+Either:
+- manually update `pyproject.toml`; then `poetry lock --no-update`; or else
+- `poetry add packagename`. See `poetry add --help`; note the `--dev`,
+  `--extras` and `--optional` flags in particular.
+  - **NB**: this specifies the new package with a version given by a "caret bound". This won't get forced to its lowest version in the old deps CI job: see [this TODO](https://github.com/matrix-org/synapse/blob/4e1374373857f2f7a911a31c50476342d9070681/.ci/scripts/test_old_deps.sh#L35-L39).
+
+Include the updated `pyproject.toml` and `poetry.lock` files in your commit.
+
+## ...remove a dependency?
+
+This is not done often and is untested, but
+
+```shell
+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`
+files in your commit.
+
+## ...update the version range for an existing dependency?
+
+Best done by manually editing `pyproject.toml`, then `poetry lock --no-update`.
+Include the updated `pyproject.toml` and `poetry.lock` in your commit.
+
+## ...update a dependency in the locked environment?
+
+Use
+
+```shell
+poetry update packagename
+```
+
+to use the latest version of `packagename` in the locked environment, without
+affecting the broad dependencies listed in the wheel.
+
+There doesn't seem to be a way to do this whilst locking a _specific_ version of
+`packagename`. We can workaround this (crudely) as follows:
+
+```shell
+poetry add packagename==1.2.3
+# This should update pyproject.lock.
+
+# Now undo the changes to pyproject.toml. For example
+# git restore pyproject.toml
+
+# Get poetry to recompute the content-hash of pyproject.toml without changing
+# the locked package versions.
+poetry lock --no-update
+```
+
+Either way, include the updated `poetry.lock` file in your commit.
+
+## ...export a `requirements.txt` file?
+
+```shell
+poetry export --extras all
+```
+
+Be wary of bugs in `poetry export` and `pip install -r requirements.txt`.
+
+Note: `poetry export` will be made a plugin in Poetry 1.2. Additional config may
+be required.
+
+## ...build a test wheel?
+
+I usually use
+
+```shell
+poetry run pip install build && poetry run python -m build
+```
+
+because [`build`](https://github.com/pypa/build) is a standardish tool which
+doesn't require poetry. (It's what we use in CI too). However, you could try
+`poetry build` too.

docs/development/releases.md

@@ -0,0 +1,37 @@
+# Synapse Release Cycle
+
+Releases of Synapse follow a two week release cycle with new releases usually
+occurring on Tuesdays:
+
+* Day 0: Synapse `N - 1` is released.
+* Day 7: Synapse `N` release candidate 1 is released.
+* Days 7 - 13: Synapse `N` release candidates 2+ are released, if bugs are found.
+* Day 14: Synapse `N` is released.
+
+Note that this schedule might be modified depending on the availability of the
+Synapse team, e.g. releases may be skipped to avoid holidays.
+
+Release announcements can be found in the
+[release category of the Matrix blog](https://matrix.org/blog/category/releases).
+
+## Bugfix releases
+
+If a bug is found after release that is deemed severe enough (by a combination
+of the impacted users and the impact on those users) then a bugfix release may
+be issued. This may be at any point in the release cycle.
+
+## Security releases
+
+Security will sometimes be backported to the previous version and released
+immediately before the next release candidate. An example of this might be:
+
+* Day 0: Synapse N - 1 is released.
+* Day 7: Synapse (N - 1).1 is released as Synapse N - 1 + the security fix.
+* Day 7: Synapse N release candidate 1 is released (including the security fix).
+
+Depending on the impact and complexity of security fixes, multiple fixes might
+be held to be released together.
+
+In some cases, a pre-disclosure of a security release will be issued as a notice
+to Synapse operators that there is an upcoming security release. These can be
+found in the [security category of the Matrix blog](https://matrix.org/blog/category/security).

docs/development/room-dag-concepts.md

@@ -30,13 +30,58 @@ rather than skipping any that arrived late; whereas if you're looking at a
 historical section of timeline (i.e. `/messages`), you want to see the best
 representation of the state of the room as others were seeing it at the time.
 
+## Outliers
+
+We mark an event as an `outlier` when we haven't figured out the state for the
+room at that point in the DAG yet. They are "floating" events that we haven't
+yet correlated to the DAG.
+
+Outliers typically arise when we fetch the auth chain or state for a given
+event. When that happens, we just grab the events in the state/auth chain,
+without calculating the state at those events, or backfilling their
+`prev_events`. Since we don't have the state at any events fetched in that
+way, we mark them as outliers.
+
+So, typically, we won't have the `prev_events` of an `outlier` in the database,
+(though it's entirely possible that we *might* have them for some other
+reason). Other things that make outliers different from regular events:
+
+ * We don't have state for them, so there should be no entry in
+   `event_to_state_groups` for an outlier. (In practice this isn't always
+   the case, though I'm not sure why: see https://github.com/matrix-org/synapse/issues/12201).
+
+ * We don't record entries for them in the `event_edges`,
+   `event_forward_extremeties` or `event_backward_extremities` tables.
+
+Since outliers are not tied into the DAG, they do not normally form part of the
+timeline sent down to clients via `/sync` or `/messages`; however there is an
+exception:
+
+### Out-of-band membership events
+
+A special case of outlier events are some membership events for federated rooms
+that we aren't full members of. For example:
+
+ * invites received over federation, before we join the room
+ * *rejections* for said invites
+ * knock events for rooms that we would like to join but have not yet joined.
+
+In all the above cases, we don't have the state for the room, which is why they
+are treated as outliers. They are a bit special though, in that they are
+proactively sent to clients via `/sync`.
 
 ## Forward extremity
 
-Most-recent-in-time events in the DAG which are not referenced by any other events' `prev_events` yet.
+Most-recent-in-time events in the DAG which are not referenced by any other
+events' `prev_events` yet. (In this definition, outliers, rejected events, and
+soft-failed events don't count.)
 
-The forward extremities of a room are used as the `prev_events` when the next event is sent.
+The forward extremities of a room (or at least, a subset of them, if there are
+more than ten) are used as the `prev_events` when the next event is sent.
 
+The "current state" of a room (ie: the state which would be used if we
+generated a new event) is, therefore, the resolution of the room states
+at each of the forward extremities.
 
 ## Backward extremity
 
@@ -44,23 +89,14 @@ The current marker of where we have backfilled up to and will generally be the
 `prev_events` of the oldest-in-time events we have in the DAG. This gives a starting point when
 backfilling history.
 
-When we persist a non-outlier event, we clear it as a backward extremity and set
+Note that, unlike forward extremities, we typically don't have any backward
-all of its `prev_events` as the new backward extremities if they aren't already
+extremity events themselves in the database - or, if we do, they will be "outliers" (see
-persisted in the `events` table.
+above). Either way, we don't expect to have the room state at a backward extremity.
-
-
-## Outliers
-
-We mark an event as an `outlier` when we haven't figured out the state for the
-room at that point in the DAG yet.
-
-We won't *necessarily* have the `prev_events` of an `outlier` in the database,
-but it's entirely possible that we *might*.
-
-For example, when we fetch the event auth chain or state for a given event, we
-mark all of those claimed auth events as outliers because we haven't done the
-state calculation ourself.
 
+When we persist a non-outlier event, if it was previously a backward extremity,
+we clear it as a backward extremity and set all of its `prev_events` as the new
+backward extremities if they aren't already persisted as non-outliers. This
+therefore keeps the backward extremities up-to-date.
 
 ## State groups
 

docs/federate.md

@@ -63,4 +63,5 @@ release of Synapse.
 
 If you want to get up and running quickly with a trio of homeservers in a
 private federation, there is a script in the `demo` directory. This is mainly
-useful just for development purposes. See [demo/README](https://github.com/matrix-org/synapse/tree/develop/demo/).
+useful just for development purposes. See
+[demo scripts](https://matrix-org.github.io/synapse/develop/development/demo.html).

docs/jwt.md

@@ -17,9 +17,6 @@ follows:
 }
 ```
 
-Note that the login type of `m.login.jwt` is supported, but is deprecated. This
-will be removed in a future version of Synapse.
-
 The `token` field should include the JSON web token with the following claims:
 
 * A claim that encodes the local part of the user ID is required. By default,

docs/manhole.md

@@ -94,6 +94,6 @@ As a simple example, retrieving an event from the database:
 
 ```pycon
 >>> from twisted.internet import defer
->>> defer.ensureDeferred(hs.get_datastore().get_event('$1416420717069yeQaw:matrix.org'))
+>>> defer.ensureDeferred(hs.get_datastores().main.get_event('$1416420717069yeQaw:matrix.org'))
 <Deferred at 0x7ff253fc6998 current result: <FrozenEvent event_id='$1416420717069yeQaw:matrix.org', type='m.room.create', state_key=''>>
 ```

docs/modules/account_data_callbacks.md

@@ -0,0 +1,106 @@
+# Account data callbacks
+
+Account data callbacks allow module developers to react to changes of the account data
+of local users. Account data callbacks can be registered using the module API's
+`register_account_data_callbacks` method.
+
+## Callbacks
+
+The available account data callbacks are:
+
+### `on_account_data_updated`
+
+_First introduced in Synapse v1.57.0_
+
+```python
+async def on_account_data_updated(
+    user_id: str,
+    room_id: Optional[str],
+    account_data_type: str,
+    content: "synapse.module_api.JsonDict",
+) -> None:
+```
+
+Called after user's account data has been updated. The module is given the
+Matrix ID of the user whose account data is changing, the room ID the data is associated
+with, the type associated with the change, as well as the new content. If the account
+data is not associated with a specific room, then the room ID is `None`.
+
+This callback is triggered when new account data is added or when the data associated with
+a given type (and optionally room) changes. This includes deletion, since in Matrix,
+deleting account data consists of replacing the data associated with a given type
+(and optionally room) with an empty dictionary (`{}`).
+
+Note that this doesn't trigger when changing the tags associated with a room, as these are
+processed separately by Synapse.
+
+If multiple modules implement this callback, Synapse runs them all in order.
+
+## Example
+
+The example below is a module that implements the `on_account_data_updated` callback, and
+sends an event to an audit room when a user changes their account data.
+
+```python
+import json
+import attr
+from typing import Any, Dict, Optional
+
+from synapse.module_api import JsonDict, ModuleApi
+from synapse.module_api.errors import ConfigError
+
+
+@attr.s(auto_attribs=True)
+class CustomAccountDataConfig:
+    audit_room: str
+    sender: str
+
+
+class CustomAccountDataModule:
+    def __init__(self, config: CustomAccountDataConfig, api: ModuleApi):
+        self.api = api
+        self.config = config
+
+        self.api.register_account_data_callbacks(
+            on_account_data_updated=self.log_new_account_data,
+        )
+
+    @staticmethod
+    def parse_config(config: Dict[str, Any]) -> CustomAccountDataConfig:
+        def check_in_config(param: str):
+            if param not in config:
+                raise ConfigError(f"'{param}' is required")
+
+        check_in_config("audit_room")
+        check_in_config("sender")
+
+        return CustomAccountDataConfig(
+            audit_room=config["audit_room"],
+            sender=config["sender"],
+        )
+
+    async def log_new_account_data(
+        self,
+        user_id: str,
+        room_id: Optional[str],
+        account_data_type: str,
+        content: JsonDict,
+    ) -> None:
+        content_raw = json.dumps(content)
+        msg_content = f"{user_id} has changed their account data for type {account_data_type} to: {content_raw}"
+
+        if room_id is not None:
+            msg_content += f" (in room {room_id})"
+
+        await self.api.create_and_send_event_into_room(
+            {
+                "room_id": self.config.audit_room,
+                "sender": self.config.sender,
+                "type": "m.room.message",
+                "content": {
+                    "msgtype": "m.text",
+                    "body": msg_content
+                }
+            }
+        )
+```

docs/modules/password_auth_provider_callbacks.md

@@ -85,7 +85,7 @@ If the authentication is unsuccessful, the module must return `None`.
 If multiple modules implement this callback, they will be considered in order. If a
 callback returns `None`, Synapse falls through to the next one. The value of the first
 callback that does not return `None` will be used. If this happens, Synapse will not call
-any of the subsequent implementations of this callback. If every callback return `None`,
+any of the subsequent implementations of this callback. If every callback returns `None`,
 the authentication is denied.
 
 ### `on_logged_out`
@@ -148,7 +148,7 @@ Here's an example featuring all currently supported keys:
         "address": "33123456789",
         "validated_at": 1642701357084,
     },
-    "org.matrix.msc3231.login.registration_token": "sometoken",  # User has registered through the flow described in MSC3231
+    "m.login.registration_token": "sometoken",  # User has registered through a registration token
 }
 ```
 
@@ -162,10 +162,57 @@ return `None`.
 If multiple modules implement this callback, they will be considered in order. If a
 callback returns `None`, Synapse falls through to the next one. The value of the first
 callback that does not return `None` will be used. If this happens, Synapse will not call
-any of the subsequent implementations of this callback. If every callback return `None`,
+any of the subsequent implementations of this callback. If every callback returns `None`,
 the username provided by the user is used, if any (otherwise one is automatically
 generated).
 
+### `get_displayname_for_registration`
+
+_First introduced in Synapse v1.54.0_
+
+```python
+async def get_displayname_for_registration(
+    uia_results: Dict[str, Any],
+    params: Dict[str, Any],
+) -> Optional[str]
+```
+
+Called when registering a new user. The module can return a display name to set for the
+user being registered by returning it as a string, or `None` if it doesn't wish to force a
+display name for this user.
+
+This callback is called once [User-Interactive Authentication](https://spec.matrix.org/latest/client-server-api/#user-interactive-authentication-api)
+has been completed by the user. It is not called when registering a user via SSO. It is
+passed two dictionaries, which include the information that the user has provided during
+the registration process. These dictionaries are identical to the ones passed to
+[`get_username_for_registration`](#get_username_for_registration), so refer to the
+documentation of this callback for more information about them.
+
+If multiple modules implement this callback, they will be considered in order. If a
+callback returns `None`, Synapse falls through to the next one. The value of the first
+callback that does not return `None` will be used. If this happens, Synapse will not call
+any of the subsequent implementations of this callback. If every callback returns `None`,
+the username will be used (e.g. `alice` if the user being registered is `@alice:example.com`).
+
+## `is_3pid_allowed`
+
+_First introduced in Synapse v1.53.0_
+
+```python
+async def is_3pid_allowed(self, medium: str, address: str, registration: bool) -> bool
+```
+
+Called when attempting to bind a third-party identifier (i.e. an email address or a phone
+number). The module is given the medium of the third-party identifier (which is `email` if
+the identifier is an email address, or `msisdn` if the identifier is a phone number) and
+its address, as well as a boolean indicating whether the attempt to bind is happening as
+part of registering a new user. The module must return a boolean indicating whether the
+identifier can be allowed to be bound to an account on the local homeserver.
+
+If multiple modules implement this callback, they will be considered in order. If a
+callback returns `True`, Synapse falls through to the next one. The value of the first
+callback that does not return `True` will be used. If this happens, Synapse will not call
+any of the subsequent implementations of this callback.
 
 ## Example
 
@@ -175,8 +222,7 @@ The example module below implements authentication checkers for two different lo
     - Is checked by the method: `self.check_my_login`
 - `m.login.password` (defined in [the spec](https://matrix.org/docs/spec/client_server/latest#password-based))
     - Expects a `password` field to be sent to `/login`
-    - Is checked by the method: `self.check_pass` 
+    - Is checked by the method: `self.check_pass`
-
 
 ```python
 from typing import Awaitable, Callable, Optional, Tuple

docs/modules/spam_checker_callbacks.md

@@ -16,10 +16,12 @@ _First introduced in Synapse v1.37.0_
 async def check_event_for_spam(event: "synapse.events.EventBase") -> Union[bool, str]
 ```
 
-Called when receiving an event from a client or via federation. The module can return
+Called when receiving an event from a client or via federation. The callback must return
-either a `bool` to indicate whether the event must be rejected because of spam, or a `str`
+either:
-to indicate the event must be rejected because of spam and to give a rejection reason to
+- an error message string, to indicate the event must be rejected because of spam and 
-forward to clients.
+  give a rejection reason to forward to clients;
+- the boolean `True`, to indicate that the event is spammy, but not provide further details; or
+- the booelan `False`, to indicate that the event is not considered spammy.
 
 If multiple modules implement this callback, they will be considered in order. If a
 callback returns `False`, Synapse falls through to the next one. The value of the first
@@ -35,7 +37,10 @@ async def user_may_join_room(user: str, room: str, is_invited: bool) -> bool
 ```
 
 Called when a user is trying to join a room. The module must return a `bool` to indicate
-whether the user can join the room. The user is represented by their Matrix user ID (e.g.
+whether the user can join the room. Return `False` to prevent the user from joining the
+room; otherwise return `True` to permit the joining.
+
+The user is represented by their Matrix user ID (e.g.
 `@alice:example.com`) and the room is represented by its Matrix ID (e.g.
 `!room:example.com`). The module is also given a boolean to indicate whether the user
 currently has a pending invite in the room.
@@ -58,7 +63,8 @@ async def user_may_invite(inviter: str, invitee: str, room_id: str) -> bool
 
 Called when processing an invitation. The module must return a `bool` indicating whether
 the inviter can invite the invitee to the given room. Both inviter and invitee are
-represented by their Matrix user ID (e.g. `@alice:example.com`).
+represented by their Matrix user ID (e.g. `@alice:example.com`). Return `False` to prevent
+the invitation; otherwise return `True` to permit it.
 
 If multiple modules implement this callback, they will be considered in order. If a
 callback returns `True`, Synapse falls through to the next one. The value of the first
@@ -80,7 +86,8 @@ async def user_may_send_3pid_invite(
 
 Called when processing an invitation using a third-party identifier (also called a 3PID,
 e.g. an email address or a phone number). The module must return a `bool` indicating
-whether the inviter can invite the invitee to the given room.
+whether the inviter can invite the invitee to the given room. Return `False` to prevent
+the invitation; otherwise return `True` to permit it.
 
 The inviter is represented by their Matrix user ID (e.g. `@alice:example.com`), and the
 invitee is represented by its medium (e.g. "email") and its address
@@ -117,6 +124,7 @@ async def user_may_create_room(user: str) -> bool
 
 Called when processing a room creation request. The module must return a `bool` indicating
 whether the given user (represented by their Matrix user ID) is allowed to create a room.
+Return `False` to prevent room creation; otherwise return `True` to permit it.
 
 If multiple modules implement this callback, they will be considered in order. If a
 callback returns `True`, Synapse falls through to the next one. The value of the first
@@ -133,7 +141,8 @@ async def user_may_create_room_alias(user: str, room_alias: "synapse.types.RoomA
 
 Called when trying to associate an alias with an existing room. The module must return a
 `bool` indicating whether the given user (represented by their Matrix user ID) is allowed
-to set the given alias.
+to set the given alias. Return `False` to prevent the alias creation; otherwise return 
+`True` to permit it.
 
 If multiple modules implement this callback, they will be considered in order. If a
 callback returns `True`, Synapse falls through to the next one. The value of the first
@@ -150,7 +159,8 @@ async def user_may_publish_room(user: str, room_id: str) -> bool
 
 Called when trying to publish a room to the homeserver's public rooms directory. The
 module must return a `bool` indicating whether the given user (represented by their
-Matrix user ID) is allowed to publish the given room.
+Matrix user ID) is allowed to publish the given room. Return `False` to prevent the
+room from being published; otherwise return `True` to permit its publication.
 
 If multiple modules implement this callback, they will be considered in order. If a
 callback returns `True`, Synapse falls through to the next one. The value of the first
@@ -162,16 +172,21 @@ any of the subsequent implementations of this callback.
 _First introduced in Synapse v1.37.0_
 
 ```python
-async def check_username_for_spam(user_profile: Dict[str, str]) -> bool
+async def check_username_for_spam(user_profile: synapse.module_api.UserProfile) -> bool
 ```
 
 Called when computing search results in the user directory. The module must return a
-`bool` indicating whether the given user profile can appear in search results. The profile
+`bool` indicating whether the given user should be excluded from user directory 
-is represented as a dictionary with the following keys:
+searches. Return `True` to indicate that the user is spammy and exclude them from 
+search results; otherwise return `False`.
 
-* `user_id`: The Matrix ID for this user.
+The profile is represented as a dictionary with the following keys:
-* `display_name`: The user's display name.
+
-* `avatar_url`: The `mxc://` URL to the user's avatar.
+* `user_id: str`. The Matrix ID for this user.
+* `display_name: Optional[str]`. The user's display name, or `None` if this user
+  has not set a display name.
+* `avatar_url: Optional[str]`. The `mxc://` URL to the user's avatar, or `None`
+  if this user has not set an avatar.
 
 The module is given a copy of the original dictionary, so modifying it from within the
 module cannot modify a user's profile when included in user directory search results.
@@ -225,8 +240,9 @@ async def check_media_file_for_spam(
 ) -> bool
 ```
 
-Called when storing a local or remote file. The module must return a boolean indicating
+Called when storing a local or remote file. The module must return a `bool` indicating
-whether the given file can be stored in the homeserver's media store.
+whether the given file should be excluded from the homeserver's media store. Return
+`True` to prevent this file from being stored; otherwise return `False`.
 
 If multiple modules implement this callback, they will be considered in order. If a
 callback returns `False`, Synapse falls through to the next one. The value of the first

docs/modules/third_party_rules_callbacks.md

@@ -148,6 +148,123 @@ deny an incoming event, see [`check_event_for_spam`](spam_checker_callbacks.md#c
 
 If multiple modules implement this callback, Synapse runs them all in order.
 
+### `check_can_shutdown_room`
+
+_First introduced in Synapse v1.55.0_
+
+```python
+async def check_can_shutdown_room(
+    user_id: str, room_id: str,
+) -> bool:
+```
+
+Called when an admin user requests the shutdown of a room. The module must return a
+boolean indicating whether the shutdown can go through. If the callback returns `False`,
+the shutdown will not proceed and the caller will see a `M_FORBIDDEN` error.
+
+If multiple modules implement this callback, they will be considered in order. If a
+callback returns `True`, Synapse falls through to the next one. The value of the first
+callback that does not return `True` will be used. If this happens, Synapse will not call
+any of the subsequent implementations of this callback.
+
+### `check_can_deactivate_user`
+
+_First introduced in Synapse v1.55.0_
+
+```python
+async def check_can_deactivate_user(
+    user_id: str, by_admin: bool,
+) -> bool:
+```
+
+Called when the deactivation of a user is requested. User deactivation can be
+performed by an admin or the user themselves, so developers are encouraged to check the
+requester when implementing this callback. The module must return a
+boolean indicating whether the deactivation can go through. If the callback returns `False`,
+the deactivation will not proceed and the caller will see a `M_FORBIDDEN` error.
+
+The module is passed two parameters, `user_id` which is the ID of the user being deactivated, and `by_admin` which is `True` if the request is made by a serve admin, and `False` otherwise.
+
+If multiple modules implement this callback, they will be considered in order. If a
+callback returns `True`, Synapse falls through to the next one. The value of the first
+callback that does not return `True` will be used. If this happens, Synapse will not call
+any of the subsequent implementations of this callback.
+
+
+### `on_profile_update`
+
+_First introduced in Synapse v1.54.0_
+
+```python
+async def on_profile_update(
+    user_id: str,
+    new_profile: "synapse.module_api.ProfileInfo",
+    by_admin: bool,
+    deactivation: bool,
+) -> None:
+```
+
+Called after updating a local user's profile. The update can be triggered either by the
+user themselves or a server admin. The update can also be triggered by a user being
+deactivated (in which case their display name is set to an empty string (`""`) and the
+avatar URL is set to `None`). The module is passed the Matrix ID of the user whose profile
+has been updated, their new profile, as well as a `by_admin` boolean that is `True` if the
+update was triggered by a server admin (and `False` otherwise), and a `deactivated`
+boolean that is `True` if the update is a result of the user being deactivated.
+
+Note that the `by_admin` boolean is also `True` if the profile change happens as a result
+of the user logging in through Single Sign-On, or if a server admin updates their own
+profile.
+
+Per-room profile changes do not trigger this callback to be called. Synapse administrators
+wishing this callback to be called on every profile change are encouraged to disable
+per-room profiles globally using the `allow_per_room_profiles` configuration setting in
+Synapse's configuration file.
+This callback is not called when registering a user, even when setting it through the
+[`get_displayname_for_registration`](https://matrix-org.github.io/synapse/latest/modules/password_auth_provider_callbacks.html#get_displayname_for_registration)
+module callback.
+
+If multiple modules implement this callback, Synapse runs them all in order.
+
+### `on_user_deactivation_status_changed`
+
+_First introduced in Synapse v1.54.0_
+
+```python
+async def on_user_deactivation_status_changed(
+    user_id: str, deactivated: bool, by_admin: bool
+) -> None:
+```
+
+Called after deactivating a local user, or reactivating them through the admin API. The
+deactivation can be triggered either by the user themselves or a server admin. The module
+is passed the Matrix ID of the user whose status is changed, as well as a `deactivated`
+boolean that is `True` if the user is being deactivated and `False` if they're being
+reactivated, and a `by_admin` boolean that is `True` if the deactivation was triggered by
+a server admin (and `False` otherwise). This latter `by_admin` boolean is always `True`
+if the user is being reactivated, as this operation can only be performed through the
+admin API.
+
+If multiple modules implement this callback, Synapse runs them all in order.
+
+### `on_threepid_bind`
+
+_First introduced in Synapse v1.56.0_
+
+```python
+async def on_threepid_bind(user_id: str, medium: str, address: str) -> None:
+```
+
+Called after creating an association between a local user and a third-party identifier
+(email address, phone number). The module is given the Matrix ID of the user the
+association is for, as well as the medium (`email` or `msisdn`) and address of the
+third-party identifier.
+
+Note that this callback is _not_ called after a successful association on an _identity
+server_.
+
+If multiple modules implement this callback, Synapse runs them all in order.
+
 ## Example
 
 The example below is a module that implements the third-party rules callback