…REFIX

The lab previously shared tests/docker/docker-compose.yaml with the test
env and drove workflow import through docker exec in traffic_generator.py.
That coupled two consumers with different port expectations (the test env
uses find_free_ports for parallel safety; the lab needs a fixed URL for
docs, agent config, and the traffic generator) and put workflow lifecycle
in two places.

Add tests/lab/docker-compose.yaml that hardcodes 5678/5680 and bind-mounts
both the test fixtures and the lab workflows under /workflows/. Gate the
compose + port selection in tests/common.py on N8N_IS_LAB so the same
conftest serves both modes. Move workflow import/activate into conftest
(scanning the bind-mount, reading stable ids from JSON), and add a
lab-only logs block + docker_volumes yield so the Datadog Agent picks up
n8n stdout via autodiscovery and the event-bus log files via the data
volume. Drop the docker-exec workflow import from traffic_generator.py
now that conftest owns it. Update the README log-collection section to
reflect that event-bus logs live under the n8n user folder rather than
N8N_LOG_FILE_LOCATION.

- Tighten _generate_workflow_traffic success check to == 200 so a
  webhook that responds 4xx (e.g. not yet registered after restart) does
  not falsely count as a healthy workflow run; capture last_status /
  last_exc and surface them in the RuntimeError so CI failures point at
  the real cause.
- Replace the bespoke time.monotonic() wait loops with WaitFor + raise
  predicates (the dominant pattern across integrations-core). Restructure
  dd_environment conditions so the docker_run condition chain runs:
  wait for /healthz, activate workflows, then assert /metrics reachable
  on main + worker. Workflow-started wait stays inline since
  _generate_workflow_traffic is not idempotent.
- Drop drop_rare_event_metrics; pass the public exclude= parameter to
  assert_metrics_using_metadata so we don't reach into AggregatorStub
  internals.
- Replace bare try/except RequestException: pass blocks with
  contextlib.suppress.
- Parametrize the two unit-fixture metadata tests; add the missing
  pytestmark = pytest.mark.unit and a comment explaining why the
  unit assertion is version-pinned to major=2.
- Re-word the lab traffic generator reload-failure messages so it's
  clear the lab keeps running with the previous config.
- Add N8N_METRICS_INCLUDE_WORKFLOW_EXECUTION_DURATION to the
  README's version-specific block and to the changelog flag list; indent
  the changelog sub-bullets so towncrier nests them under the wrapping
  bullet.

- Remove stray scratch notes accidentally committed at the end of the
  file (numbered questions and a changelog-process note that didn't
  belong in the public README).
- Sentence-case the 'Data collected' and 'Service checks' headings.
- Replace hyphen-as-em-dash usage (' - ') by splitting into separate
  sentences.
- Replace slash-as-and/or in lists and tag descriptions:
  'enqueued/dequeued/completed/failed/stalled counters' -> spelled-out
  list; 'result:success/failure' -> 'result:success or result:failure';
  'stdout/stderr' -> 'stdout and stderr'.

In the previous refactor _generate_workflow_traffic and the
_workflow_started_non_zero wait were moved into the body of the
dd_environment context manager. That made them vulnerable to fixture
re-invocation paths (e.g. session teardown or flaky-plugin retry) that
fired the body code against torn-down containers, producing a setup
error after the e2e test had already passed.

Put both back into conditions=[...]. That keeps them inside docker_run's
set_up() retry envelope (attempts=2 in CI), and they are no longer
exposed to the post-yield teardown path. The post-restart /healthz wait
moves back inside _activate_imported_workflows so the function stays
self-contained as a condition. Restore the (instances, E2E_METADATA)
tuple yield for non-lab mode so the e2e Agent container still gets the
docker_volumes mount it expects.

- conftest.py: parse n8n_workflow_started_total samples as floats instead
  of string-matching ' 0', so '0.0' / '0e+0' counter values are not
  treated as non-zero and OpenMetrics '# HELP'/'# TYPE' comment lines
  that share the prefix are skipped.
- common.py: collapse the get_all_metadata_metrics passthrough into
  get_metadata_metrics_for_version (update integration + e2e call sites)
  and document the intentional V2_ONLY / RARE_EVENT overlap so future
  contributors do not assume the duplication is accidental.
- check.py: cache the readiness endpoint with functools.cached_property
  (it is derived from immutable config) and parameterise the dict return
  / argument types as dict[str, Any].
- traffic_generator.py: scope the asyncio.Event and current config to
  _run_traffic instead of holding them at module level, threading both
  through _config_reloader. Switches the SIGINT/SIGTERM hook to
  loop.add_signal_handler so a second 'generate' invocation in the same
  process starts from a clean state.

- conftest.py: move the worker CheckEndpoints to after _activate_imported_workflows
  so any cascade from the n8n main restart is caught before downstream conditions
  scrape the worker.
- test_unit.py: import the requests module and reference
  requests.ConnectionError at the call site so the builtin ConnectionError
  name is not shadowed for the rest of the module.
- traffic_generator.py: extract _make_output_table() so the table schema lives
  in one place and _print_row() only owns row data.

On n8n 2.x, /healthz comes back after `docker compose restart n8n` before
n8n has finished re-registering the active workflows' webhook routes. The
existing WaitFor(_n8n_healthy) inside _activate_imported_workflows was
satisfied while /webhook/test still returned 404, so _generate_workflow_traffic
raced the registration and failed with last_status=404.

Add a second WaitFor poll on the integration-test webhook itself so the
registration is observed before downstream conditions run. v1 happens to
register fast enough that the gap is not observable there, but the extra
check costs at most one poll on the happy path.