unsloth/studio/backend/tests/test_llama_route_timeouts.py
Wasim Yousef Said 37166efcfc
Fix Gemma 4 GGUF OpenAI API streams (#6476)
* Fix Gemma 4 GGUF OpenAI API streams

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Avoid duplicate Responses stream disconnect watcher

* Keep reasoning-only Responses output hidden

* Address Gemma stream review comments

* Avoid Responses stream task-group cleanup

* Harden OpenAI chat completion streams

* Address OpenAI stream review issues

* Clean up Studio OpenAI stream helpers

* Fix Studio passthrough cold stream timeout

* Fix tool parser compatibility exports lint

* Preserve audio stream disconnect cancellation

* Avoid synthetic finish after passthrough errors

* Address stream cleanup and Gemma parser reviews

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Gemma 4: parse bare-string tool args and keep safetensors tools for native <|tool_call>

- Quote bare unquoted string values in Gemma native tool-call args (e.g.
  {location:Tokyo,unit:celsius}) so they parse; JSON scalars stay typed.
- Stop _detect_safetensors_features from suppressing supports_tools for
  templates that emit Gemma native <|tool_call>, which the shared parser
  now reads.
- Add tests for both.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Harden Gemma tool-call parsing and stream-error detection

Address three issues in the Gemma-native tool-call path:

- _quote_gemma_object_keys stopped a bare (unquoted) string value at the
  first comma, so an argument like `location:New York, NY` was split
  mid-value and the synthesized JSON failed to parse, dropping the whole
  tool call. A bare value now ends only at `}` or a comma that begins the
  next `key:` pair.

- parse_tool_calls_from_text scanned the entire response for Gemma markers
  even inside a tool call already parsed from a `<tool_call>{...}` JSON
  block, so a marker-like string inside an argument (data) was promoted to
  a second, unintended tool call. Matches inside an already-consumed call
  span are now skipped.

- _openai_passthrough_stream relied on _monitor_openai_sse_line to flag a
  stream error, which returns early when monitor_id is None
  (skip_api_monitor), so an upstream error chunk left saw_stream_error
  unset and the synthetic-finish guard emitted a successful finish_reason
  after a failed stream. Error chunks are now detected independently of API
  monitoring.

Adds tests/test_gemma_tool_parse_edge_cases.py covering the comma and
marker-injection cases.

* Emit the terminal finish_reason chunk in GGUF streams

The OpenAI chat-completions GGUF tool stream and plain stream both built a
final ChatCompletionChunk carrying finish_reason but never yielded it, so
clients received the optional usage chunk and [DONE] with no chunk carrying
finish_reason. OpenAI-compatible consumers rely on that terminal choice to
distinguish stop/length/tool_calls. Yield it before the usage chunk and
[DONE], matching the other streaming paths.

* Parse tool calls in document order and skip nested markers both ways

Unify the JSON- and Gemma-format tool-call passes into a single
position-ordered scan:

- Calls are now emitted in byte order across both formats, so a mixed
  output like `<|tool_call>call:create{...}<tool_call|> ... <tool_call>
  {"name":"read",...}</tool_call>` executes create before read, matching
  the order they appear in (tools run in returned order).

- A candidate that starts inside an already-accepted call's span is
  skipped, in both directions: a JSON marker inside a Gemma argument and a
  Gemma marker inside a JSON argument are treated as data, not promoted to
  a second executable tool call.

Extends tests/test_gemma_tool_parse_edge_cases.py with the ordering and
JSON-in-Gemma nesting cases.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Quote bare Gemma array elements; order finish before trailing usage

- _quote_gemma_object_keys skipped array values, so a Gemma call with a
  bare-string array argument like labels:[bug,ui] produced invalid JSON and
  the whole tool call was dropped. Array values are now scanned and bare
  string elements quoted, while numbers, quoted strings, and JSON literals
  are preserved.

- In the OpenAI passthrough stream, a trailing usage-only chunk
  (stream_options.include_usage) that arrived before any finish chunk was
  relayed before the synthetic finish, producing usage -> finish -> [DONE].
  Emit the synthetic finish before that usage chunk so the order matches the
  other streams (finish -> usage -> [DONE]).

Extends tests/test_gemma_tool_parse_edge_cases.py with the bare-array cases.

* Harden Gemma array parsing, XML-parameter guard, and stream teardown

Address five review findings on the Gemma tool-call and OpenAI passthrough
streaming paths:

- parse_tool_calls_from_text collected JSON and Gemma markers without the
  _inside_open_parameter guard, so a marker embedded in an existing
  <function=...><parameter=...> value was promoted to a separate tool call.
  Candidates that start inside an open XML parameter are now skipped, matching
  the guard the XML-style parser already applies.

- _quote_gemma_array_elements preserved array elements starting with { or [
  verbatim, so an array of objects (items:[{path:a}]) or a nested array failed
  json.loads and the whole call was dropped. Object and nested-array elements
  are now normalised recursively.

- _openai_passthrough_stream synthesized a finish chunk before a trailing
  usage-only chunk and set saw_finish_reason, which made the EOF guard skip the
  [DONE] sentinel. The EOF path now emits [DONE] whenever the upstream omitted
  it, even after a finish chunk was already synthesized.

- /generate/stream drove generation through asyncio.to_thread with no
  disconnect watcher, so a client disconnect during a long generation went
  unnoticed until the next send. It now runs _await_disconnect_then_cancel
  against the request, matching the other local streaming endpoints.

- _SameTaskStreamingResponse closed the body iterator with aclose() on a
  send-side disconnect, raising GeneratorExit so the generators' cancellation
  handlers (which finish the api_monitor entry) never ran. It now throws
  CancelledError, falling back to aclose() when athrow is unavailable.

Extends tests/test_gemma_tool_parse_edge_cases.py with array-of-objects,
nested-array, and marker-inside-XML-parameter cases.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Watch disconnects on Anthropic streams; keep timestamps in Gemma values

Two follow-ups on the streaming and tool-parse paths:

- _anthropic_tool_stream and _anthropic_plain_stream drove generation through
  asyncio.to_thread(next, gen, ...) and only polled is_disconnected() between
  events, so a client disconnect during prefill or a long generation/tool step
  held the decode slot until the next event or a failed send. Both now run the
  _await_disconnect_then_cancel watcher used by the other local streams, stop it
  in finally, and break promptly when cancel_event is set.

- _GEMMA_NEXT_KEY_RE treated any comma followed by word-chars-then-colon as the
  next key, so a bare value such as "meet at 10:00, 11:00 tomorrow" was split
  into bogus keys. The next-key token must now be identifier-shaped (start with
  a letter or underscore), so a comma before a timestamp, ratio, or other
  numeric-then-colon text stays part of the value.

Adds a timestamp-in-bare-value regression test.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Guard nested markers, reset on disconnect, clean unstarted streams

Three follow-ups on the tool-parse and streaming paths:

- parse_tool_calls_from_text only skipped markers that fell inside a span it
  had already parsed successfully, so when an unquoted Gemma argument contained
  a literal marker (code:<|tool_call>call:terminal{...}<tool_call|>) the outer
  object failed to normalize, its span was never recorded, and the inner marker
  was promoted to a standalone terminal call. Candidates nested inside any other
  candidate's brace span are now skipped regardless of whether the enclosing
  candidate parsed, so a marker in malformed outer data is never executed.

- /generate/stream skipped backend.reset_generation_state() when the disconnect
  watcher set cancel_event between chunks: the loop broke and the finally's reset
  is guarded on cancel_event being unset. A subprocess backend kept decoding
  after the client left. The cancel-break path now resets the backend.

- _SameTaskStreamingResponse threw CancelledError / called aclose() on the body
  iterator on a send-side disconnect, but neither runs the try/finally of a
  generator that never started (early disconnect on http.response.start), so the
  passthrough's eagerly-opened upstream httpx stream and cancel-registry entry
  leaked. It now tracks whether the body started and, when it did not, runs an
  optional unstarted_cleanup hook; the OpenAI passthrough wires it to close the
  upstream resp/client and exit the cancel tracker.

Adds a nested-unquoted-marker regression test.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
2026-06-23 06:13:56 -07:00

205 lines
5.9 KiB
Python

# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.
import asyncio
import os
import sys
import time
import threading
from types import SimpleNamespace
_backend = os.path.join(os.path.dirname(__file__), "..")
sys.path.insert(0, _backend)
import routes.inference as inf_mod # noqa: E402
def test_non_streaming_generation_timeout_has_read_deadline():
timeout = inf_mod._llama_non_streaming_generation_timeout()
assert timeout.read == inf_mod._DEFAULT_FIRST_TOKEN_TIMEOUT_S
def test_stream_first_item_deadline_after_headers():
async def _run():
class _Never:
async def __anext__(self):
await asyncio.Future()
started = time.monotonic()
try:
async for _ in inf_mod._aiter_llama_stream_items(
_Never(),
first_token_deadline = started + 0.02,
):
pass
except inf_mod.httpx.ReadTimeout:
pass
else:
raise AssertionError("first item deadline did not fire")
assert time.monotonic() - started < 0.5
asyncio.run(_run())
def test_stream_first_item_deadline_does_not_hop_tasks():
async def _run():
outer_task = asyncio.current_task()
seen_tasks = []
class _One:
def __init__(self):
self.done = False
async def __anext__(self):
seen_tasks.append(asyncio.current_task())
if self.done:
raise StopAsyncIteration
self.done = True
return "data: {}"
out = []
async for item in inf_mod._aiter_llama_stream_items(
_One(),
first_token_deadline = time.monotonic() + 1,
):
out.append(item)
assert out == ["data: {}"]
assert seen_tasks == [outer_task, outer_task]
asyncio.run(_run())
def test_stream_first_item_deadline_uses_compat_timeout_without_task_hop(monkeypatch):
monkeypatch.setattr(inf_mod.asyncio, "timeout", None, raising = False)
async def _run():
outer_task = asyncio.current_task()
seen_tasks = []
class _One:
def __init__(self):
self.done = False
async def __anext__(self):
seen_tasks.append(asyncio.current_task())
if self.done:
raise StopAsyncIteration
self.done = True
return "data: {}"
out = []
async for item in inf_mod._aiter_llama_stream_items(
_One(),
first_token_deadline = time.monotonic() + 1,
):
out.append(item)
assert out == ["data: {}"]
assert seen_tasks == [outer_task, outer_task]
asyncio.run(_run())
def test_stream_wait_stops_on_known_disconnect_before_read():
async def _run():
state = SimpleNamespace(disconnect_checks = 0)
cancel_event = threading.Event()
class _Request:
async def is_disconnected(self):
state.disconnect_checks += 1
return True
class _Unread:
async def __anext__(self):
raise AssertionError("stream should stop before reading upstream")
async for _ in inf_mod._aiter_llama_stream_items(
_Unread(),
cancel_event = cancel_event,
request = _Request(),
first_token_deadline = time.monotonic() + 1,
):
raise AssertionError("stream should stop after disconnect")
assert cancel_event.is_set()
assert state.disconnect_checks == 1
asyncio.run(_run())
def test_stream_wait_does_not_shorten_upstream_read_for_disconnect_poll():
async def _run():
response = SimpleNamespace(request = SimpleNamespace(extensions = {"timeout": {}}))
seen_read_timeouts = []
class _Request:
async def is_disconnected(self):
return False
class _NoItem:
async def __anext__(self):
seen_read_timeouts.append(response.request.extensions["timeout"]["read"])
raise StopAsyncIteration
async for _ in inf_mod._aiter_llama_stream_items(
_NoItem(),
cancel_event = threading.Event(),
request = _Request(),
response = response,
first_token_deadline = time.monotonic() + 1,
):
raise AssertionError("stream should end")
assert seen_read_timeouts
assert seen_read_timeouts[0] > inf_mod._STREAM_DISCONNECT_POLL_TIMEOUT_S
asyncio.run(_run())
def test_preheader_send_cleanup_on_disconnect_and_cancel():
async def _run(cancel_parent):
state = SimpleNamespace(disconnected = False, closed = False, cancelled = False)
started = asyncio.Event()
class _Client:
async def send(
self,
req,
stream = False,
):
started.set()
try:
await asyncio.Future()
except asyncio.CancelledError:
state.cancelled = True
raise
async def aclose(self):
state.closed = True
class _Request:
async def is_disconnected(self):
return state.disconnected
task = asyncio.create_task(
inf_mod._send_stream_with_preheader_cancel(_Client(), object(), request = _Request())
)
await started.wait()
if cancel_parent:
task.cancel()
try:
await task
except asyncio.CancelledError:
pass
else:
raise AssertionError("helper cancellation did not propagate")
else:
state.disconnected = True
assert await task is None
assert state.closed
assert state.cancelled
asyncio.run(_run(False))
asyncio.run(_run(True))