Self-contained docker-compose harness that exercises the new bootstrap
branch against a real Continuwuity homeserver. Three tests:
1. fresh bot → bootstrap fires, /keys/query returns master + ssk
with UNPADDED base64 keyids, current device is signed by the
new SSK
2. second startup with same crypto store → bootstrap is skipped
3. MATRIX_RECOVERY_KEY set → existing verify_with_recovery_key path
takes precedence, no new bootstrap
Run via:
docker compose -f tests/e2e/matrix_xsign_bootstrap/docker-compose.yml up -d
python tests/e2e/matrix_xsign_bootstrap/test_bootstrap.py
docker compose -f tests/e2e/matrix_xsign_bootstrap/docker-compose.yml down -v
The test mirrors the bootstrap snippet from matrix.py inline so it can
run without importing the full hermes gateway and its deps. Skipped
automatically when mautrix isn't installed or the homeserver is
unreachable.
All three pass against ghcr.io/continuwuity/continuwuity:latest
(Continuwuity 0.5.7). The unpadded-keyid assertion is the load-bearing
one — it's exactly the property the PR's bootstrap path provides that
the hand-rolled `base64.b64encode().decode()` scripts get wrong.
- Fix duplicate 'timezone' import in e2e conftest
- Fix test_text_before_command_not_detected asserting send() is awaited
when no agent is present in mock setup (text messages don't produce
command output)
New test classes:
- TestSessionLifecycle: /new then /status sequence, idempotent resets
- TestAuthorization: unauthorized users get pairing code, not commands
- TestSendFailureResilience: pipeline survives send() failures
Additional command coverage: /provider, /verbose, /personality, /yolo.
Note: /provider test is xfail - found a real bug where model_cfg is
referenced unbound when config.yaml is absent (run.py:3247).
Tests /help, /status, /new, /stop, /commands through the full adapter
background-task pipeline. Validates command dispatch, session lifecycle,
and response delivery without any LLM involvement.
Fixtures and helpers for driving messages through the full async
pipeline: adapter.handle_message → background task → GatewayRunner
command dispatch → adapter.send (mocked).
Uses the established _make_runner pattern (object.__new__) to skip
filesystem side effects while exercising real command dispatch logic.
