feat(sse_client): implement issue #1 contract via TDD

Implements docs/contracts/issues/1.contract.md. Four entry points
(stream_turn, reconnect_turn, cancel_turn, _parse_sse_id) + nine
typed Event variants + ten domain exceptions. 37 tests covering
every TESTS: entry verbatim, plus the boundary smoke test still
passes.

Tracer-bullet ordering per the contract's per-FN tracer tags:
_parse_sse_id (foundation; happy_simple) → stream_turn
(happy_one_text_done) → reconnect_turn (happy_resume_from_seq_3) →
cancel_turn (happy_cancel). Each FN's tracer went RED then GREEN
before its other tests landed.

Shared SSE-iteration logic (INV-002 sse_id presence + INV-003
turn_id stability + terminal-break) lives in private _iter_events
helper. expected_turn_id=None gives stream_turn's "establish from
first event" semantics; expected_turn_id=N gives reconnect_turn's
"first event is already a flip-candidate" semantics — the
two-entry-point distinction Volva surfaced during the paraphrase
round.

A few implementation choices worth recording:

- _parse_sse_id uses a `^-?\\d+$` regex pre-check to reject any
  whitespace before int() is called. Python's `int(" 3 ")` silently
  strips, which would have made the trailing_whitespace adversarial
  test pass for the wrong reason.

- The connection_drop test uses a custom httpx.AsyncByteStream
  subclass (_DropAfter) that yields chunks then raises
  RemoteProtocolError mid-stream. respx alone can't simulate
  mid-stream HTTP errors.

- ToolResult.result and ToolStart.arguments are typed as Any
  because the server's tool wire shape varies per tool; the spec
  doesn't pin a generic schema.

- Boundary smoke test (no core.* / worldtree.* imports under
  src/ratatoskr/) still GREEN — INV-005 holds.

Also: one E501 line-length fix in test_no_worldtree_imports.py
that ruff flagged once the new tests pulled it into scope.
This commit is contained in:
vh
2026-05-20 21:25:20 -07:00
parent 1526f0bc8e
commit 02f2a04b37
4 changed files with 1049 additions and 7 deletions
+3 -1
View File
@@ -36,7 +36,9 @@ def test_no_worldtree_imports() -> None:
line = text[: match.start()].count("\n") + 1
violations.append((path, f"line {line}: {match.group(0).strip()}"))
if violations:
report = "\n".join(f" {p.relative_to(_SRC_ROOT.parent.parent)}: {v}" for p, v in violations)
report = "\n".join(
f" {p.relative_to(_SRC_ROOT.parent.parent)}: {v}" for p, v in violations
)
raise AssertionError(
"Ratatoskr must not import from Worldtree source. Violations:\n"
f"{report}\n\n"
+625
View File
@@ -0,0 +1,625 @@
"""Tests for ratatoskr.sse_client per docs/contracts/issues/1.contract.md."""
import httpx
import pytest
import respx
from ratatoskr.sse_client import (
CancelAlreadyCompleted,
Cancelled,
CancelResult,
CancelTurnNotFound,
Done,
Error,
InvalidLastEventId,
MalformedSseId,
ResumeBufferExpired,
ResumeTurnFinished,
SseConnectFailed,
SseId,
Text,
TurnIdFlip,
_parse_sse_id,
cancel_turn,
reconnect_turn,
stream_turn,
)
_DONE_42_6 = {
"type": "done",
"phase": "succeeded",
"response": "hello",
"model": "m",
"duration_ms": 1,
"usage": {
"prompt_tokens": 0,
"completion_tokens": 0,
"total_tokens": 0,
"cached_input_tokens": 0,
},
}
def _sse_chunk(sse_id: str, body: dict[str, object]) -> bytes:
"""Compose one SSE event in wire format. Trailing blank line per spec."""
import json
return f"id: {sse_id}\ndata: {json.dumps(body)}\n\n".encode()
class TestParseSseId:
def test_happy_simple(self) -> None:
"""happy_simple [happy,tracer]: '42:3' -> SseId(turn_id=42, seq=3)."""
assert _parse_sse_id("42:3") == SseId(turn_id=42, seq=3)
def test_happy_seq_one(self) -> None:
"""happy_seq_one: smallest valid id per spec — first event of first turn."""
assert _parse_sse_id("1:1") == SseId(turn_id=1, seq=1)
def test_empty(self) -> None:
"""empty [adversarial]: '' -> ValueError."""
with pytest.raises(ValueError):
_parse_sse_id("")
def test_no_colon(self) -> None:
"""no_colon [adversarial]: '42' -> ValueError with '42' in the message."""
with pytest.raises(ValueError, match="42"):
_parse_sse_id("42")
def test_too_many_colons(self) -> None:
"""too_many_colons [adversarial]: '42:3:7' -> ValueError."""
with pytest.raises(ValueError):
_parse_sse_id("42:3:7")
def test_alpha_turn_id(self) -> None:
"""alpha_turn_id [adversarial]: 'foo:3' -> ValueError."""
with pytest.raises(ValueError):
_parse_sse_id("foo:3")
def test_alpha_seq(self) -> None:
"""alpha_seq [adversarial]: '42:bar' -> ValueError."""
with pytest.raises(ValueError):
_parse_sse_id("42:bar")
def test_zero_turn_id(self) -> None:
"""zero_turn_id [adversarial]: '0:3' -> ValueError (turn_id ≥ 1)."""
with pytest.raises(ValueError):
_parse_sse_id("0:3")
def test_zero_seq(self) -> None:
"""zero_seq [adversarial]: '1:0' -> ValueError (seq ≥ 1, spec line 705)."""
with pytest.raises(ValueError):
_parse_sse_id("1:0")
def test_negative_turn_id(self) -> None:
"""negative_turn_id [adversarial]: '-1:3' -> ValueError."""
with pytest.raises(ValueError):
_parse_sse_id("-1:3")
def test_negative_seq(self) -> None:
"""negative_seq [adversarial]: '42:-1' -> ValueError."""
with pytest.raises(ValueError):
_parse_sse_id("42:-1")
def test_trailing_whitespace(self) -> None:
"""trailing_whitespace [adversarial]: '42:3 ' -> ValueError (strict; no strip)."""
with pytest.raises(ValueError):
_parse_sse_id("42:3 ")
def test_truncation(self) -> None:
"""truncation [security]: 5000-char no-colon -> ValueError msg contains only raw[:64]."""
raw = "a" * 5000
with pytest.raises(ValueError) as exc_info:
_parse_sse_id(raw)
assert raw not in str(exc_info.value), "full 5000-char input must not appear in message"
assert raw[:64] in str(exc_info.value), "first 64 chars must appear in message"
class TestStreamTurn:
@respx.mock
async def test_happy_one_text_done(self) -> None:
"""happy_one_text_done: text then done; same turn_id; iter ends after done."""
stream = _sse_chunk("42:1", {"type": "text", "content": "hello"}) + _sse_chunk(
"42:2",
{
"type": "done",
"phase": "succeeded",
"response": "hello",
"model": "glm5-turbo",
"duration_ms": 100,
"usage": {
"prompt_tokens": 0,
"completion_tokens": 0,
"total_tokens": 0,
"cached_input_tokens": 0,
},
},
)
respx.post("https://w.example/sessions/s1/messages").mock(
return_value=httpx.Response(
200, headers={"content-type": "text/event-stream"}, content=stream
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
events = [e async for e in stream_turn(client, "s1", "hi")]
assert len(events) == 2
assert isinstance(events[0], Text)
assert events[0].content == "hello"
assert events[0].sse_id == SseId(42, 1)
assert isinstance(events[1], Done)
assert events[1].sse_id == SseId(42, 2)
assert events[0].sse_id.turn_id == events[1].sse_id.turn_id
@respx.mock
async def test_full_event_vocab(self) -> None:
"""full_event_vocab: one of each variant; all carry parsed sse_id."""
stream = b"".join(
[
_sse_chunk(
"42:1",
{"type": "worker_phase", "phase": "BuildingPrompt", "turn_id": 42},
),
_sse_chunk("42:2", {"type": "thinking", "content": "thinking out loud"}),
_sse_chunk("42:3", {"type": "text", "content": "hello"}),
_sse_chunk(
"42:4",
{
"type": "text_boundary",
"kind": "sentence",
"char_offset": 5,
"ts": "2026-05-21T00:00:00Z",
},
),
_sse_chunk(
"42:5",
{"type": "tool_start", "name": "search", "arguments": {"q": "x"}},
),
_sse_chunk(
"42:6",
{
"type": "tool_result",
"name": "search",
"result": {"n": 1},
"duration_ms": 12,
},
),
_sse_chunk("42:7", {"type": "text", "content": " world"}),
_sse_chunk(
"42:8",
{
"type": "done",
"phase": "succeeded",
"response": "hello world",
"model": "m",
"duration_ms": 50,
"usage": {
"prompt_tokens": 0,
"completion_tokens": 0,
"total_tokens": 0,
"cached_input_tokens": 0,
},
},
),
]
)
respx.post("https://w.example/sessions/s1/messages").mock(
return_value=httpx.Response(
200, headers={"content-type": "text/event-stream"}, content=stream
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
events = [e async for e in stream_turn(client, "s1", "hi")]
types_seen = [type(e).__name__ for e in events]
assert types_seen == [
"WorkerPhase",
"Thinking",
"Text",
"TextBoundary",
"ToolStart",
"ToolResult",
"Text",
"Done",
]
# INV-002: every event carries parsed sse_id with turn_id, seq >= 1
for e in events:
assert e.sse_id.turn_id == 42
assert e.sse_id.seq >= 1
@respx.mock
async def test_error_terminal(self) -> None:
"""error_terminal: text then error; iteration ends; error_code populated."""
stream = _sse_chunk("42:1", {"type": "text", "content": "x"}) + _sse_chunk(
"42:2",
{
"type": "error",
"phase": "failed",
"error_code": "llm_output_invalid",
"message": "boom",
},
)
respx.post("https://w.example/sessions/s1/messages").mock(
return_value=httpx.Response(
200, headers={"content-type": "text/event-stream"}, content=stream
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
events = [e async for e in stream_turn(client, "s1", "hi")]
assert len(events) == 2
assert isinstance(events[1], Error)
assert events[1].error_code == "llm_output_invalid"
assert events[1].message == "boom"
@respx.mock
async def test_cancelled_terminal(self) -> None:
"""cancelled_terminal: cancelled with phase=cancelled, turn_id; iteration ends."""
stream = _sse_chunk(
"42:1",
{
"type": "cancelled",
"phase": "cancelled",
"turn_id": 42,
"reason": "user_cancel",
"partial_message_id": None,
},
)
respx.post("https://w.example/sessions/s1/messages").mock(
return_value=httpx.Response(
200, headers={"content-type": "text/event-stream"}, content=stream
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
events = [e async for e in stream_turn(client, "s1", "hi")]
assert len(events) == 1
assert isinstance(events[0], Cancelled)
assert events[0].turn_id == 42
assert events[0].reason == "user_cancel"
@respx.mock
async def test_session_not_found(self) -> None:
"""session_not_found: 404 -> SseConnectFailed(status=404)."""
respx.post("https://w.example/sessions/missing/messages").mock(
return_value=httpx.Response(404, json={"error": "session_not_found"})
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
with pytest.raises(SseConnectFailed) as exc_info:
_ = [e async for e in stream_turn(client, "missing", "hi")]
assert exc_info.value.status == 404
@respx.mock
async def test_malformed_id_no_seq(self) -> None:
"""malformed_id_no_seq: id `42` (missing :seq) -> MalformedSseId; no event yielded."""
stream = b"id: 42\ndata: {\"type\":\"text\",\"content\":\"x\"}\n\n"
respx.post("https://w.example/sessions/s1/messages").mock(
return_value=httpx.Response(
200, headers={"content-type": "text/event-stream"}, content=stream
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
events: list[object] = []
with pytest.raises(MalformedSseId):
async for e in stream_turn(client, "s1", "hi"):
events.append(e)
assert events == []
@respx.mock
async def test_malformed_id_alpha(self) -> None:
"""malformed_id_alpha: id `foo:bar` -> MalformedSseId."""
stream = b"id: foo:bar\ndata: {\"type\":\"text\",\"content\":\"x\"}\n\n"
respx.post("https://w.example/sessions/s1/messages").mock(
return_value=httpx.Response(
200, headers={"content-type": "text/event-stream"}, content=stream
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
with pytest.raises(MalformedSseId):
_ = [e async for e in stream_turn(client, "s1", "hi")]
@respx.mock
async def test_turn_id_flip(self) -> None:
"""turn_id_flip: 42:1 then 99:2 -> TurnIdFlip; only first yielded."""
stream = _sse_chunk("42:1", {"type": "text", "content": "a"}) + _sse_chunk(
"99:2", {"type": "text", "content": "b"}
)
respx.post("https://w.example/sessions/s1/messages").mock(
return_value=httpx.Response(
200, headers={"content-type": "text/event-stream"}, content=stream
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
yielded: list[Text] = []
with pytest.raises(TurnIdFlip) as exc_info:
async for e in stream_turn(client, "s1", "hi"):
yielded.append(e) # type: ignore[arg-type]
assert len(yielded) == 1
assert exc_info.value.established == 42
assert exc_info.value.got == 99
@respx.mock
async def test_connection_drop(self) -> None:
"""connection_drop: RemoteProtocolError after one text -> SseConnectionDropped((42,1))."""
from ratatoskr.sse_client import SseConnectionDropped
class _DropAfter(httpx.AsyncByteStream):
def __init__(self, chunks: list[bytes]) -> None:
self._chunks = chunks
async def __aiter__(self): # type: ignore[no-untyped-def]
for c in self._chunks:
yield c
raise httpx.RemoteProtocolError("simulated mid-stream drop")
async def aclose(self) -> None:
return None
first = _sse_chunk("42:1", {"type": "text", "content": "x"})
respx.post("https://w.example/sessions/s1/messages").mock(
return_value=httpx.Response(
200,
headers={"content-type": "text/event-stream"},
stream=_DropAfter([first]),
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
yielded: list[Text] = []
with pytest.raises(SseConnectionDropped) as exc_info:
async for e in stream_turn(client, "s1", "hi"):
yielded.append(e) # type: ignore[arg-type]
assert len(yielded) == 1
assert exc_info.value.last_seen_sse_id == SseId(42, 1)
@respx.mock
async def test_no_text_aggregation(self) -> None:
"""no_text_aggregation: consumer yields each text event separately; no concat."""
stream = (
_sse_chunk("42:1", {"type": "text", "content": "hello "})
+ _sse_chunk("42:2", {"type": "text", "content": "world"})
+ _sse_chunk(
"42:3",
{
"type": "done",
"phase": "succeeded",
"response": "hello world",
"model": "m",
"duration_ms": 1,
"usage": {
"prompt_tokens": 0,
"completion_tokens": 0,
"total_tokens": 0,
"cached_input_tokens": 0,
},
},
)
)
respx.post("https://w.example/sessions/s1/messages").mock(
return_value=httpx.Response(
200, headers={"content-type": "text/event-stream"}, content=stream
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
events = [e async for e in stream_turn(client, "s1", "hi")]
texts = [e for e in events if isinstance(e, Text)]
assert [t.content for t in texts] == ["hello ", "world"]
class TestReconnectTurn:
@respx.mock
async def test_happy_resume_from_seq_3(self) -> None:
"""happy_resume_from_seq_3 [scenario,tracer]: replay 42:4,42:5 then live 42:6 done."""
stream = (
_sse_chunk("42:4", {"type": "text", "content": "d"})
+ _sse_chunk("42:5", {"type": "text", "content": "e"})
+ _sse_chunk("42:6", _DONE_42_6)
)
respx.post("https://w.example/sessions/s1/messages").mock(
return_value=httpx.Response(
200, headers={"content-type": "text/event-stream"}, content=stream
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
events = [e async for e in reconnect_turn(client, "s1", "original", "42:3")]
assert len(events) == 3
assert [e.sse_id.seq for e in events] == [4, 5, 6]
assert all(e.sse_id.turn_id == 42 for e in events)
assert isinstance(events[-1], Done)
@respx.mock
async def test_header_verbatim(self) -> None:
"""header_verbatim: outbound carries Last-Event-ID: 42:3 exactly."""
stream = _sse_chunk("42:4", _DONE_42_6)
route = respx.post("https://w.example/sessions/s1/messages").mock(
return_value=httpx.Response(
200, headers={"content-type": "text/event-stream"}, content=stream
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
_ = [e async for e in reconnect_turn(client, "s1", "x", "42:3")]
req = route.calls[0].request
assert req.headers["Last-Event-ID"] == "42:3"
@respx.mock
async def test_body_threads_content(self) -> None:
"""body_threads_content: outbound JSON body is {'content': <content>} byte-for-byte."""
import json as _json
stream = _sse_chunk("42:4", _DONE_42_6)
route = respx.post("https://w.example/sessions/s1/messages").mock(
return_value=httpx.Response(
200, headers={"content-type": "text/event-stream"}, content=stream
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
_ = [
e async for e in reconnect_turn(client, "s1", "hello mimir", "42:3")
]
body = _json.loads(route.calls[0].request.content)
assert body == {"content": "hello mimir"}
@respx.mock
async def test_buffer_expired(self) -> None:
"""buffer_expired: 412 -> ResumeBufferExpired(turn_id=42, buffered_from_seq=10)."""
respx.post("https://w.example/sessions/s1/messages").mock(
return_value=httpx.Response(
412,
json={"error": "buffer_expired", "buffered_from_seq": 10, "turn_id": 42},
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
with pytest.raises(ResumeBufferExpired) as exc_info:
_ = [e async for e in reconnect_turn(client, "s1", "x", "42:3")]
assert exc_info.value.turn_id == 42
assert exc_info.value.buffered_from_seq == 10
@respx.mock
async def test_turn_finished(self) -> None:
"""turn_finished: 410 -> ResumeTurnFinished(turn_id=42)."""
respx.post("https://w.example/sessions/s1/messages").mock(
return_value=httpx.Response(
410, json={"error": "turn_finished", "turn_id": 42}
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
with pytest.raises(ResumeTurnFinished) as exc_info:
_ = [e async for e in reconnect_turn(client, "s1", "x", "42:3")]
assert exc_info.value.turn_id == 42
@respx.mock
async def test_invalid_last_event_id_server(self) -> None:
"""invalid_last_event_id_server: 400 -> InvalidLastEventId."""
respx.post("https://w.example/sessions/s1/messages").mock(
return_value=httpx.Response(400, json={"error": "invalid_last_event_id"})
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
with pytest.raises(InvalidLastEventId):
_ = [e async for e in reconnect_turn(client, "s1", "x", "42:3")]
@respx.mock
async def test_malformed_input(self) -> None:
"""malformed_input: caller passes '42' (no seq) -> ValueError; no HTTP issued."""
route = respx.post("https://w.example/sessions/s1/messages").mock(
return_value=httpx.Response(200, content=b"")
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
with pytest.raises(ValueError):
_ = [e async for e in reconnect_turn(client, "s1", "x", "42")]
assert route.call_count == 0
@respx.mock
async def test_turn_id_flip_on_first_event(self) -> None:
"""turn_id_flip_on_first_event: server's first event 99:4 -> TurnIdFlip pre-yield."""
stream = _sse_chunk("99:4", {"type": "text", "content": "wrong turn"})
respx.post("https://w.example/sessions/s1/messages").mock(
return_value=httpx.Response(
200, headers={"content-type": "text/event-stream"}, content=stream
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
yielded: list[Text] = []
with pytest.raises(TurnIdFlip) as exc_info:
async for e in reconnect_turn(client, "s1", "x", "42:3"):
yielded.append(e) # type: ignore[arg-type]
assert yielded == []
assert exc_info.value.established == 42
assert exc_info.value.got == 99
class TestCancelTurn:
@respx.mock
async def test_happy_cancel(self) -> None:
"""happy_cancel [happy,tracer]: 200 -> CancelResult(42, True, None, None)."""
respx.post("https://w.example/sessions/s1/turns/42/cancel").mock(
return_value=httpx.Response(
200,
json={
"turn_id": 42,
"cancelled": True,
"reason": None,
"partial_message_id": None,
},
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
result = await cancel_turn(client, "s1", 42)
assert result == CancelResult(
turn_id=42, cancelled=True, reason=None, partial_message_id=None
)
@respx.mock
async def test_persist_partial_query(self) -> None:
"""persist_partial_query [trace]: persist_partial=True -> URL has ?persist_partial=true."""
route = respx.post("https://w.example/sessions/s1/turns/42/cancel").mock(
return_value=httpx.Response(
200,
json={
"turn_id": 42,
"cancelled": True,
"reason": None,
"partial_message_id": None,
},
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
await cancel_turn(client, "s1", 42, persist_partial=True)
assert "persist_partial=true" in str(route.calls[0].request.url)
@respx.mock
async def test_default_no_persist(self) -> None:
"""default_no_persist [trace]: default call -> URL has no persist_partial param."""
route = respx.post("https://w.example/sessions/s1/turns/42/cancel").mock(
return_value=httpx.Response(
200,
json={
"turn_id": 42,
"cancelled": True,
"reason": None,
"partial_message_id": None,
},
)
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
await cancel_turn(client, "s1", 42)
assert "persist_partial" not in str(route.calls[0].request.url)
@respx.mock
async def test_cancel_already_completed(self) -> None:
"""cancel_already_completed [error]: 409 -> CancelAlreadyCompleted(turn_id=42)."""
respx.post("https://w.example/sessions/s1/turns/42/cancel").mock(
return_value=httpx.Response(409, json={"error": "turn_already_completed"})
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
with pytest.raises(CancelAlreadyCompleted) as exc_info:
await cancel_turn(client, "s1", 42)
assert exc_info.value.turn_id == 42
@respx.mock
async def test_cancel_turn_not_found(self) -> None:
"""cancel_turn_not_found [error]: 404 -> CancelTurnNotFound(turn_id=42)."""
respx.post("https://w.example/sessions/s1/turns/42/cancel").mock(
return_value=httpx.Response(404, json={"error": "turn_not_found"})
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
with pytest.raises(CancelTurnNotFound) as exc_info:
await cancel_turn(client, "s1", 42)
assert exc_info.value.turn_id == 42
@respx.mock
async def test_cancel_idempotent(self) -> None:
"""cancel_idempotent: first 200 -> happy; second 409 -> CancelAlreadyCompleted."""
respx.post("https://w.example/sessions/s1/turns/42/cancel").mock(
side_effect=[
httpx.Response(
200,
json={
"turn_id": 42,
"cancelled": True,
"reason": None,
"partial_message_id": None,
},
),
httpx.Response(409, json={"error": "turn_already_completed"}),
]
)
async with httpx.AsyncClient(base_url="https://w.example") as client:
first = await cancel_turn(client, "s1", 42)
assert first.cancelled is True
with pytest.raises(CancelAlreadyCompleted):
await cancel_turn(client, "s1", 42)