mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-04 20:13:04 +00:00
* feat: SSE notification system
Adds a per-user SSE pipe (GET /api/events) plus a per-message
chat-stream reconnect endpoint (GET /api/messages/<id>/events).
Backend substrate:
- application/events/ — durable journal (Redis Streams) + live
pub/sub for user-scoped events, with publish_user_event() as
the worker-side entrypoint.
- application/streaming/ — broadcast_channel for pub/sub fanout
and event_replay for the per-message snapshot+tail path.
- application/storage/db/repositories/message_events.py +
alembic 0007 — Postgres journal for chat-stream events.
- application/worker.py — ingest/reingest/remote/connector/
attachment/mcp_oauth tasks publish queued/progress/completed/
failed envelopes alongside their existing status updates.
Frontend client:
- frontend/src/events/ — connect/reconnect, Last-Event-ID cursor,
backoff with jitter. Each tab runs its own connection; no
cross-tab dedup (future work).
- frontend/src/notifications/ — recentEvents ring, cursor
tracking, tool-approval toast.
- frontend/src/upload/uploadSlice.ts — extraReducers for
source.ingest.* and attachment.* events.
Coverage: 132 SSE tests across events substrate, replay, journal,
routes, and worker publishes.
* refactor(attachments): remove polling, SSE-only
frontend/src/components/MessageInput.tsx no longer runs a 2s
setInterval against getTaskStatus for every processing
attachment. The attachment.* SSE reducers in uploadSlice.ts are
now the sole driver of attachment state transitions.
* feat(connector): consume source.ingest.* SSE, remove polling
frontend/src/components/ConnectorTree.tsx now mirrors FileTree's
slice-walking pattern: it watches notifications.recentEvents
for source.ingest.{completed,failed} envelopes matching the
sync's source id, and no longer polls /task_status every 2s.
* refactor(source-ingest): remove polling, SSE-only
frontend/src/upload/Upload.tsx and
frontend/src/components/FileTree.tsx no longer run getTaskStatus
polling fallbacks. The source.ingest.* SSE reducers in
uploadSlice.ts and FileTree's slice walk are now the sole
drivers of upload/reingest state transitions.
* refactor(mcp-oauth): carry authorization_url in SSE, remove polling
application/worker.py::mcp_oauth now publishes
authorization_url on the mcp.oauth.awaiting_redirect envelope.
frontend/src/modals/MCPServerModal.tsx consumes it from SSE
instead of polling /oauth_status/<task_id> every 1s.
The URL is generated inside DocsGPTOAuth.redirect_handler when
the FastMCP client triggers OAuth. The worker now plumbs a
publish callback through tool_config -> MCPTool -> DocsGPTOAuth
so the awaiting_redirect publish fires from inside the handler
at the exact point the URL becomes known. The legacy Redis
mcp_oauth_status setex writes and the GET
/api/mcp_server/oauth_status/<task_id> endpoint are kept as
belt-and-suspenders; nothing in the frontend reads them now.
* feat(source-ingest): plumb limited flag through SSE for token-cap UX
application/worker.py::ingest_worker and remote_worker now publish
``limited: bool`` on the source.ingest.completed envelope.
uploadSlice routes ``payload.limited === true`` to a failed status
with a ``tokenLimitReached`` flag, and UploadToast surfaces the
translated tokenLimit i18n string. No worker code path sets
limited=true today; this is a forward-looking contract so when
token-cap detection lands, the UX is already wired.
* refactor(mcp-oauth): read status from SSE journal, drop polling endpoint
MCPOAuthManager.get_oauth_status now walks the per-user SSE Streams
journal (user:{user_id}:stream) for the latest mcp.oauth.* envelope
matching the task id, returning the status string derived from the
event type suffix and the payload fields. The worker is the single
source of truth — its publish_user_event calls write the same
record the SSE client receives live.
Removed:
- /api/mcp_server/oauth_status/<task_id> route in
application/api/user/tools/mcp.py
- mcp_oauth_status worker function and mcp_oauth_status_task Celery
wrapper
- All mcp_oauth_status:{task_id} Redis setex writes (4 in mcp_oauth,
2 in DocsGPTOAuth.redirect_handler / callback_handler)
- The update_status closure in mcp_oauth that wrote the polling
payload
Tests updated:
- get_oauth_status now takes (task_id, user_id); new coverage walks
a fake xrevrange response for the completed envelope, the no-match
case, and a Redis-down case
- Removed TestMCPOAuthStatus route tests and TestMcpOauthStatusTask
celery-wrapper test
- Removed the two oauth_status methods from the integration runner
mcp_oauth:auth_url/state/code/error Redis keys remain — they are
the OAuth flow's own state (not the dropped polling payload).
* chore(mcp-oauth): delete orphaned getMCPOAuthStatus client
The /api/mcp_server/oauth_status/<task_id> endpoint was removed in
the prior commit; the corresponding userService method and the
MCP_OAUTH_STATUS endpoint constant had no remaining callers in the
frontend, so they're deleted along with it.
* fix(events): drop live publish when journal write fails
application/events/publisher.py returned an envelope to live
pubsub subscribers even when the XADD to the durable journal
failed. The envelope had no ``id`` field, which bypassed the SSE
route's dedup floor and broke ``Last-Event-ID`` semantics for any
reconnecting client.
Best-effort delivery means dropping consistently, not delivering
inconsistent state. Now: if the journal write fails the publisher
returns None and skips the live publish entirely.
* fix(notifications): dedupe sseEventReceived against immediate dupes
Snapshot replay + live tail can both deliver the same id when the
live pubsub frame and the replay XRANGE overlap. The route's own
dedup floor catches the common case, but consumers walking
``recentEvents`` (FileTree, ConnectorTree, MCPServerModal,
ToolApprovalToast) would otherwise act on the same envelope
twice when a duplicate slipped through.
Belt-and-suspenders: short-circuit when the most recent id in
the ring matches the incoming one.
* fix(events): skip replay budget INCR when no snapshot work possible
_allow_replay incremented the per-user counter on every
/api/events GET, including no-op connects from a fresh client
with no cursor against an empty backlog. React StrictMode dev
double-mounts plus a few tabs trivially tripped the default
30-per-60s budget on idle reconnects.
XLEN pre-check: when last_event_id is None and the user stream
is empty, the connect can't do snapshot work — return True
without INCR. Cursor-bearing connects still INCR unconditionally
(probing the cursor's relationship to stream contents would
require a redundant XRANGE).
* fix(streaming): tighten journal contract + recover from seq collisions
Two related fixes to application/streaming/message_journal.py.
1. record_event now rejects non-dict payloads at the gate. The
live path (base.py::_emit) wrapped non-dicts as
{"value": payload}; the replay path in event_replay synthesized
{"type": event_type}. A reconnecting client would receive a
different envelope than the one originally streamed. Now both
paths see byte-identical envelopes because non-dicts can't be
journaled at all. The corresponding event_replay fallback is
replaced with a warn-and-skip for any legacy rows.
2. record_event handles IntegrityError on (message_id, sequence_no)
collisions by reading latest_sequence_no and retrying once with
latest+1. The most likely cause is a stale seq seed on a
continuation retry where the route read MAX(seq) from a
separate connection before another writer committed past it.
Previously the error was swallowed and the event silently
dropped from the journal; now it lands at the next available
seq. The live pubsub publish uses the materialised seq so the
journal row and the live frame agree.
* perf(streaming): batch message_events INSERTs per stream
complete_stream previously opened a fresh db_session() per yielded
event, doing one Postgres INSERT + commit per chunk on the WSGI
thread. Streaming answers emit ~100s of answer chunks per response,
so the route was paying ~100 PG roundtrips per stream serialized on
commit latency.
New BatchedJournalWriter in application/streaming/message_journal.py
accumulates rows per stream and flushes on three triggers:
- size: buffer reaches 16 entries
- time: 100ms elapsed since the last flush
- lifecycle: close() at end-of-stream
Live pubsub publishes still fire synchronously per record(), so
subscribers see events in real time — only the durable journal write
is amortized. On bulk INSERT IntegrityError the writer falls back to
per-row record() with the existing seq+1 retry so a single colliding
seq doesn't drop the rest of the batch.
complete_stream wires journal_writer.close() into every exit path
(happy end, tool-approval-paused end, GeneratorExit, error handler)
so the terminal event is committed before the generator returns —
otherwise a reconnecting client could snapshot up to the last flush
boundary and live-tail waiting for an end that's still in memory.
Repository gets bulk_record() — one SQLAlchemy executemany INSERT
for the bulk path. All-or-nothing on collision (Postgres aborts the
whole batch); the writer's per-row fallback handles recovery.
* chore(upload): drop dead UploadTask.lastEventAt field
The lastEventAt field on UploadTask had no remaining consumers — the
matching Attachment.lastEventAt was cleaned up earlier. Remove the
field declaration and the slice write site.
* chore(frontend): drop orphaned getTaskStatus client
After the polling-removal sweep no caller in frontend/src/ references
userService.getTaskStatus or endpoints.USER.TASK_STATUS. The backend
route /api/task_status itself stays — agents, webhooks, e2e specs,
and the public docs still depend on it.
* docs(repo): remove stale planning docs from repo root
notification-channel-design.md, plan.md, and reminder-tool-design.md
were leftover Claude planning artifacts from the SSE substrate work
that landed accidentally. CLAUDE.md prohibits creating planning docs
unless asked — delete them.
* docs(message-events): clarify repo vs wrapper payload contract
MessageEventsRepository.record accepts any JSONB-compatible value; the
streaming wrapper record_event tightens this to dicts only because the
live and replay paths reconstruct non-dict payloads differently. Spell
the split out so the next reader of the repo method doesn't assume the
wrapper's contract applies here.
* refactor(events): raise on malformed stream id instead of lex fallback
stream_id_compare's lex-fallback branch was a footgun: a malformed id
that sorts lex-greater than a real one would pin live-tail dedup
forever, dropping every subsequent legitimate event silently. Both
current callers in application/api/events/routes.py pre-validate
inputs against _STREAM_ID_RE before calling, so changing the function
to raise ValueError is a no-op on the happy path and turns the future-
caller footgun into a loud failure.
* test(tasks): cover cleanup_message_events task body
Adds skipped-when-no-POSTGRES_URI and happy-path coverage for the
Celery janitor. The skipped path returns the documented short-circuit
shape without touching the repo. The happy path seeds a backdated
row, runs the task against the pg_conn fixture, and asserts the
retention window's row is deleted while in-window rows survive.
Mirrors the TestCleanupPendingToolState pattern.
* fix(notifications): treat /c/new as no current conversation
useMatch('/c/:conversationId') treats the literal URL /c/new as a
real conversation id, so the toast suppression check confused
'user is on /c/new' with 'user is on the conversation needing
approval'. Explicit guard: when the matched id is 'new', fall
through to the no-match case so approval toasts still surface.
* docs(events): enumerate publish_user_event None-return paths
The function returns Optional[str] today, with None conflating five
distinct outcomes (missing args / push disabled / unserialisable /
Redis down / XADD failed). Every current call site is fire-and-
forget and ignores the return, so the right move is to document the
five cases rather than promote to an enum return — keeps the API
small while making the diagnostic surface (logs) obvious. If a
future caller needs to react differently per reason, promote then.
* refactor(sources): move source-id derivation out of worker module
application/api/user/sources/upload.py imported _derive_source_id
from application.worker — pulling the entire Celery worker module
into the API process at import time just for a two-line helper.
Move DOCSGPT_INGEST_NAMESPACE and the derivation function to a
new application/storage/db/source_ids.py module that both layers
can import without that dependency edge. worker.py re-exports the
old names (_derive_source_id, DOCSGPT_INGEST_NAMESPACE) for
backward-compatible imports from tests and any other in-tree
callers; new code should import from the new module directly.
* fix(cache): enable Redis health_check_interval to surface half-open TCP
Without health_check_interval, a half-open TCP socket (NAT silently
dropped state, ELB idle-close) can leave pubsub.get_message hanging
past the SSE generator's keepalive cadence — the kernel never
surfaces the dead socket because no payload is in flight. Setting
health_check_interval=10 makes redis-py ping every 10s when
otherwise idle, so the next get_message after the dead window
raises and the SSE loop falls into its reconnect path instead of
silently freezing on the user.
* chore(events): rename attachment.processing.progress to attachment.progress
The event-type taxonomy was inconsistent: source ingest emits
source.ingest.progress (three segments) while attachments emitted
attachment.processing.progress (four segments). Drops the
.processing. infix for parity. Worker publish sites, the slice
reducer's match, and the worker tests all flip together.
No external consumers — the event type is purely internal between
the publisher and the in-tab slice; safe to rename in one commit.
* feat: events cleanup
* fix: better docs
* fix: e2e tests
391 lines
15 KiB
Python
391 lines
15 KiB
Python
"""Unit tests for the SSE substrate (publisher + Topic + route helpers).
|
|
|
|
Round-trip integration tests against a real / fake Redis live in
|
|
``tests/test_events_integration.py``. The tests here lock in the
|
|
closure-mutated, race-sensitive bits the route relies on so future
|
|
refactors can't regress them silently.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
import pytest
|
|
|
|
from application.api.events.routes import (
|
|
_SSE_LINE_SPLIT,
|
|
_format_sse,
|
|
_normalize_last_event_id,
|
|
)
|
|
from application.events.keys import (
|
|
connection_counter_key,
|
|
stream_id_compare,
|
|
stream_key,
|
|
topic_name,
|
|
)
|
|
from application.events.publisher import publish_user_event
|
|
from application.streaming.broadcast_channel import Topic
|
|
|
|
|
|
# ── keys ────────────────────────────────────────────────────────────────
|
|
|
|
|
|
@pytest.mark.unit
|
|
class TestKeys:
|
|
def test_stream_key(self):
|
|
assert stream_key("alice") == "user:alice:stream"
|
|
|
|
def test_topic_name(self):
|
|
assert topic_name("alice") == "user:alice"
|
|
|
|
def test_connection_counter_key(self):
|
|
assert connection_counter_key("alice") == "user:alice:sse_count"
|
|
|
|
|
|
# ── stream_id_compare ───────────────────────────────────────────────────
|
|
|
|
|
|
@pytest.mark.unit
|
|
class TestStreamIdCompare:
|
|
def test_equal(self):
|
|
assert stream_id_compare("1234-0", "1234-0") == 0
|
|
|
|
def test_seq_ordering(self):
|
|
assert stream_id_compare("1234-0", "1234-1") == -1
|
|
assert stream_id_compare("1234-1", "1234-0") == 1
|
|
|
|
def test_ms_ordering(self):
|
|
assert stream_id_compare("1234-0", "5678-0") == -1
|
|
assert stream_id_compare("5678-0", "1234-0") == 1
|
|
|
|
def test_digit_count_does_not_break_int_compare(self):
|
|
# String compare would say "9" > "100"; integer compare must not.
|
|
assert stream_id_compare("9-0", "100-0") == -1
|
|
assert stream_id_compare("100-0", "9-0") == 1
|
|
|
|
def test_missing_seq_treated_as_zero(self):
|
|
assert stream_id_compare("1234", "1234-0") == 0
|
|
|
|
def test_malformed_input_raises(self):
|
|
# Callers must pre-validate; the function refuses to silently
|
|
# lex-compare garbage because a malformed id that sorts
|
|
# lex-greater would pin dedup forever.
|
|
with pytest.raises(ValueError):
|
|
stream_id_compare("foo", "bar")
|
|
with pytest.raises(ValueError):
|
|
stream_id_compare("123-0", "foo")
|
|
with pytest.raises(ValueError):
|
|
stream_id_compare("foo", "123-0")
|
|
|
|
|
|
# ── _format_sse ─────────────────────────────────────────────────────────
|
|
|
|
|
|
@pytest.mark.unit
|
|
class TestFormatSse:
|
|
def test_simple_payload(self):
|
|
assert _format_sse("hello") == "data: hello\n\n"
|
|
|
|
def test_with_event_id(self):
|
|
assert _format_sse("hello", event_id="42-0") == "id: 42-0\ndata: hello\n\n"
|
|
|
|
def test_lf_split(self):
|
|
assert _format_sse("a\nb") == "data: a\ndata: b\n\n"
|
|
|
|
def test_crlf_split(self):
|
|
assert _format_sse("a\r\nb") == "data: a\ndata: b\n\n"
|
|
|
|
def test_cr_only_split(self):
|
|
# WHATWG SSE treats CR alone as a line terminator. Must match.
|
|
assert _format_sse("a\rb") == "data: a\ndata: b\n\n"
|
|
|
|
def test_mixed_terminators(self):
|
|
# Each variant in one payload — all should split.
|
|
out = _format_sse("a\rb\nc\r\nd")
|
|
assert out == "data: a\ndata: b\ndata: c\ndata: d\n\n"
|
|
|
|
def test_empty_payload(self):
|
|
# WHATWG: empty data field is dispatched as a message with data="".
|
|
assert _format_sse("") == "data: \n\n"
|
|
|
|
def test_terminator_regex_compiles(self):
|
|
# Defensive: ensure the regex itself is well-formed.
|
|
assert _SSE_LINE_SPLIT.split("a\r\nb\rc\nd") == ["a", "b", "c", "d"]
|
|
|
|
|
|
# ── _normalize_last_event_id ────────────────────────────────────────────
|
|
|
|
|
|
@pytest.mark.unit
|
|
class TestNormalizeLastEventId:
|
|
def test_none(self):
|
|
assert _normalize_last_event_id(None) is None
|
|
|
|
def test_empty_string(self):
|
|
assert _normalize_last_event_id("") is None
|
|
|
|
def test_whitespace_only(self):
|
|
assert _normalize_last_event_id(" ") is None
|
|
|
|
def test_stripped_valid_id(self):
|
|
assert _normalize_last_event_id(" 1234-0 ") == "1234-0"
|
|
|
|
def test_ms_only(self):
|
|
assert _normalize_last_event_id("1234567890") == "1234567890"
|
|
|
|
def test_ms_seq(self):
|
|
assert _normalize_last_event_id("1234567890-0") == "1234567890-0"
|
|
|
|
def test_high_seq(self):
|
|
assert _normalize_last_event_id("1-99999") == "1-99999"
|
|
|
|
def test_garbage_rejected(self):
|
|
for bad in ("foo", "foo-bar", "1234-foo", "-1", "1234-", "1-2-3", "0x1234"):
|
|
assert _normalize_last_event_id(bad) is None, bad
|
|
|
|
|
|
# ── publisher ───────────────────────────────────────────────────────────
|
|
|
|
|
|
@pytest.mark.unit
|
|
class TestPublishUserEvent:
|
|
def setup_method(self):
|
|
# Reset the cache singleton so the patched mock gets used.
|
|
import application.cache as cache_mod
|
|
|
|
cache_mod._redis_instance = None
|
|
cache_mod._redis_creation_failed = False
|
|
|
|
def teardown_method(self):
|
|
import application.cache as cache_mod
|
|
|
|
cache_mod._redis_instance = None
|
|
cache_mod._redis_creation_failed = False
|
|
|
|
def test_returns_none_on_missing_user_id(self):
|
|
assert publish_user_event("", "x.y", {}) is None
|
|
|
|
def test_returns_none_on_missing_event_type(self):
|
|
assert publish_user_event("alice", "", {}) is None
|
|
|
|
@patch("application.events.publisher.get_redis_instance")
|
|
@patch("application.events.publisher.settings")
|
|
def test_returns_none_when_push_disabled(self, mock_settings, mock_redis):
|
|
mock_settings.ENABLE_SSE_PUSH = False
|
|
mock_settings.EVENTS_STREAM_MAXLEN = 1000
|
|
result = publish_user_event("alice", "src.ingest.progress", {"current": 1})
|
|
assert result is None
|
|
# Must not even reach Redis when the master switch is off.
|
|
mock_redis.assert_not_called()
|
|
|
|
@patch("application.events.publisher.get_redis_instance")
|
|
@patch("application.events.publisher.settings")
|
|
def test_returns_none_when_redis_unavailable(self, mock_settings, mock_redis):
|
|
mock_settings.ENABLE_SSE_PUSH = True
|
|
mock_settings.EVENTS_STREAM_MAXLEN = 1000
|
|
mock_redis.return_value = None
|
|
assert publish_user_event("alice", "x.y", {}) is None
|
|
|
|
@patch("application.events.publisher.get_redis_instance")
|
|
@patch("application.events.publisher.settings")
|
|
def test_returns_none_on_unserializable_payload(
|
|
self, mock_settings, mock_redis
|
|
):
|
|
# Set object can't be JSON-encoded; the publisher must catch
|
|
# this *before* hitting Redis, with a single warning log.
|
|
mock_settings.ENABLE_SSE_PUSH = True
|
|
mock_settings.EVENTS_STREAM_MAXLEN = 1000
|
|
result = publish_user_event(
|
|
"alice", "x.y", {"bad": {1, 2, 3}} # type: ignore[arg-type]
|
|
)
|
|
assert result is None
|
|
mock_redis.assert_not_called()
|
|
|
|
@patch("application.events.publisher.Topic")
|
|
@patch("application.events.publisher.get_redis_instance")
|
|
@patch("application.events.publisher.settings")
|
|
def test_xadd_and_publish_both_invoked_on_happy_path(
|
|
self, mock_settings, mock_redis, mock_topic_cls
|
|
):
|
|
mock_settings.ENABLE_SSE_PUSH = True
|
|
mock_settings.EVENTS_STREAM_MAXLEN = 750
|
|
mock_client = MagicMock()
|
|
mock_client.xadd.return_value = b"1735682400000-0"
|
|
mock_redis.return_value = mock_client
|
|
mock_topic = MagicMock()
|
|
mock_topic_cls.return_value = mock_topic
|
|
|
|
result = publish_user_event(
|
|
"alice",
|
|
"source.ingest.progress",
|
|
{"current": 30, "total": 100},
|
|
scope={"kind": "source", "id": "abc"},
|
|
)
|
|
|
|
assert result == "1735682400000-0"
|
|
|
|
# XADD: stream key, MAXLEN, approximate — and the envelope before
|
|
# the id was known.
|
|
mock_client.xadd.assert_called_once()
|
|
args, kwargs = mock_client.xadd.call_args
|
|
assert args[0] == "user:alice:stream"
|
|
assert kwargs.get("maxlen") == 750
|
|
assert kwargs.get("approximate") is True
|
|
# The envelope inside the XADD does NOT carry an ``id`` yet (it
|
|
# only exists after Redis returns), so the publish-time envelope
|
|
# is the source of truth for ``id``.
|
|
stored_event = json.loads(args[1]["event"])
|
|
assert "id" not in stored_event
|
|
assert stored_event["type"] == "source.ingest.progress"
|
|
assert stored_event["topic"] == "user:alice"
|
|
assert stored_event["payload"] == {"current": 30, "total": 100}
|
|
assert stored_event["scope"] == {"kind": "source", "id": "abc"}
|
|
|
|
# PUBLISH: same envelope plus the ``id`` from XADD.
|
|
mock_topic_cls.assert_called_once_with("user:alice")
|
|
mock_topic.publish.assert_called_once()
|
|
published = json.loads(mock_topic.publish.call_args[0][0])
|
|
assert published["id"] == "1735682400000-0"
|
|
assert published["type"] == "source.ingest.progress"
|
|
|
|
@patch("application.events.publisher.Topic")
|
|
@patch("application.events.publisher.get_redis_instance")
|
|
@patch("application.events.publisher.settings")
|
|
def test_xadd_failure_skips_live_publish(
|
|
self, mock_settings, mock_redis, mock_topic_cls
|
|
):
|
|
"""If the durable journal write fails there is no canonical id
|
|
to ship. Publishing an id-less envelope would put a record on
|
|
the wire that bypasses the SSE route's dedup floor and breaks
|
|
``Last-Event-ID`` semantics for any reconnect — so we drop the
|
|
live publish too. Best-effort delivery means dropping
|
|
consistently, not delivering inconsistent state.
|
|
"""
|
|
mock_settings.ENABLE_SSE_PUSH = True
|
|
mock_settings.EVENTS_STREAM_MAXLEN = 1000
|
|
mock_client = MagicMock()
|
|
mock_client.xadd.side_effect = Exception("redis went down")
|
|
mock_redis.return_value = mock_client
|
|
mock_topic = MagicMock()
|
|
mock_topic_cls.return_value = mock_topic
|
|
|
|
result = publish_user_event("alice", "x.y", {"k": 1})
|
|
|
|
# Backlog write failed → publisher returns None and skips the
|
|
# live publish so subscribers never see an id-less envelope.
|
|
assert result is None
|
|
mock_topic.publish.assert_not_called()
|
|
|
|
|
|
# ── Topic ───────────────────────────────────────────────────────────────
|
|
|
|
|
|
@pytest.mark.unit
|
|
class TestTopic:
|
|
@patch("application.streaming.broadcast_channel.get_redis_instance")
|
|
def test_publish_returns_zero_when_redis_unavailable(self, mock_redis):
|
|
mock_redis.return_value = None
|
|
assert Topic("user:alice").publish("hi") == 0
|
|
|
|
@patch("application.streaming.broadcast_channel.get_redis_instance")
|
|
def test_publish_calls_redis_publish(self, mock_redis):
|
|
client = MagicMock()
|
|
client.publish.return_value = 3
|
|
mock_redis.return_value = client
|
|
result = Topic("user:alice").publish("hi")
|
|
assert result == 3
|
|
client.publish.assert_called_once_with("user:alice", "hi")
|
|
|
|
@patch("application.streaming.broadcast_channel.get_redis_instance")
|
|
def test_publish_swallows_exceptions(self, mock_redis):
|
|
client = MagicMock()
|
|
client.publish.side_effect = Exception("boom")
|
|
mock_redis.return_value = client
|
|
# Must not raise.
|
|
assert Topic("user:alice").publish("hi") == 0
|
|
|
|
@patch("application.streaming.broadcast_channel.get_redis_instance")
|
|
def test_subscribe_returns_immediately_when_redis_unavailable(
|
|
self, mock_redis
|
|
):
|
|
mock_redis.return_value = None
|
|
# Generator should produce nothing, not raise.
|
|
assert list(Topic("user:alice").subscribe(poll_timeout=0.01)) == []
|
|
|
|
@patch("application.streaming.broadcast_channel.get_redis_instance")
|
|
def test_subscribe_yields_none_on_poll_timeout(self, mock_redis):
|
|
client = MagicMock()
|
|
pubsub = MagicMock()
|
|
# Two timeouts (None) then a real message — caller breaks after.
|
|
pubsub.get_message.side_effect = [None, None, {"type": "message", "data": b"x"}]
|
|
client.pubsub.return_value = pubsub
|
|
mock_redis.return_value = client
|
|
|
|
gen = Topic("user:alice").subscribe(poll_timeout=0.01)
|
|
first = next(gen)
|
|
second = next(gen)
|
|
third = next(gen)
|
|
assert first is None
|
|
assert second is None
|
|
assert third == b"x"
|
|
gen.close()
|
|
|
|
@patch("application.streaming.broadcast_channel.get_redis_instance")
|
|
def test_subscribe_fires_on_subscribe_after_ack(self, mock_redis):
|
|
client = MagicMock()
|
|
pubsub = MagicMock()
|
|
pubsub.get_message.side_effect = [
|
|
{"type": "subscribe", "data": 1},
|
|
{"type": "message", "data": b"hi"},
|
|
]
|
|
client.pubsub.return_value = pubsub
|
|
mock_redis.return_value = client
|
|
|
|
callback_calls = []
|
|
|
|
def cb():
|
|
callback_calls.append(1)
|
|
|
|
gen = Topic("user:alice").subscribe(on_subscribe=cb, poll_timeout=0.01)
|
|
# The "subscribe" message is consumed without yielding; the next
|
|
# value yielded is the actual data message.
|
|
msg = next(gen)
|
|
assert msg == b"hi"
|
|
assert callback_calls == [1]
|
|
gen.close()
|
|
|
|
@patch("application.streaming.broadcast_channel.get_redis_instance")
|
|
def test_subscribe_cleans_up_on_generator_close(self, mock_redis):
|
|
client = MagicMock()
|
|
pubsub = MagicMock()
|
|
pubsub.get_message.side_effect = [
|
|
{"type": "subscribe", "data": 1},
|
|
None, # one tick so we stay in the loop
|
|
]
|
|
client.pubsub.return_value = pubsub
|
|
mock_redis.return_value = client
|
|
|
|
gen = Topic("user:alice").subscribe(poll_timeout=0.01)
|
|
next(gen) # advance into the subscribe-confirmation
|
|
gen.close() # client disconnect
|
|
|
|
pubsub.unsubscribe.assert_called_once_with("user:alice")
|
|
pubsub.close.assert_called_once()
|
|
|
|
@patch("application.streaming.broadcast_channel.get_redis_instance")
|
|
def test_subscribe_skips_unsubscribe_if_subscribe_never_acked(
|
|
self, mock_redis
|
|
):
|
|
client = MagicMock()
|
|
pubsub = MagicMock()
|
|
pubsub.subscribe.side_effect = Exception("connection lost")
|
|
client.pubsub.return_value = pubsub
|
|
mock_redis.return_value = client
|
|
|
|
# The generator must not yield, must not raise, and must not call
|
|
# unsubscribe (we never confirmed a subscription).
|
|
list(Topic("user:alice").subscribe(poll_timeout=0.01))
|
|
pubsub.unsubscribe.assert_not_called()
|
|
pubsub.close.assert_called_once()
|