mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-26 01:12:21 +00:00
f6882246d4
* ci: run the unit_selection.sh shard files on every event instead of only fork pull requests Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * ci: rename fork-flag to unit-flag now that it applies on every event * test: move tests/test_litellm root and small trees into tests/unit Pure renames, no content changes. Follow-up commits in this PR fix references, merge the three files that already existed in tests/unit, keep live-provider tests in tests/test_litellm and wire CI. * test: carry tests/test_litellm conftest isolation into tests/unit Callback lists, routing fallbacks, cached HTTP clients, logger state, AWS, proxy-URL and keychain env, and session-end client cleanup now reset for unit tests too. The environment isolation owns its MonkeyPatch so a test's own monkeypatch is undone before the model-cost teardown runs. * test: merge, split and prune the moved root and small-tree tests Merge batches/test_batch_utils.py and the chat_completions and messages dispatch tests into the files that already existed in tests/unit. Keep the live Gemini interactions tests, the async image-fetch format test and the OpenAI embedding scorer test in tests/test_litellm since they need real network or keys. Put test_router.py under tests/unit/test_router so the existing package no longer shadows it. Delete eight tests the audit found superseded by stronger ones kept in this move. * ci: run the moved root and small-tree tests under their legacy flags Add the misc and responses-caching-types flags to unit_selection.sh and CircleCI, extend enterprise-routing and mcp-integration, and point the legacy GHA shards, Makefile, redis-compat workflow, merge smoke manifest and change classifier at the new paths. * test: make the new tests/unit directories packages tests/unit/test_package_layout.py requires every directory to carry an __init__.py, and without one the moved and retained test_litellm_responses_bridge.py modules collide on import. * test: scope the unit socket block to tests/unit in shared sessions The GHA shards collect the legacy test-path and the unit selection in one pytest session. The unit conftest's loopback-only block leaked into legacy modules that reach the network at import. The legacy conftest now lifts the restriction at collect and setup time, and the unit conftest re-applies it when collecting its own modules. * test: give the shard-script tests their own GITHUB_OUTPUT They only passed where the runner set it. The CircleCI unit job's env allowlist drops it, so the script's redirect failed there. * test: point the router and module-deletion checks at tests/unit router_code_coverage and code_qa_check_tests only searched tests/test_litellm, so the moved router tests no longer counted. The two silent-experiment tests the audit deleted were the only direct callers of those methods; they are replaced with tests that assert the forwarded shadow request and the recursion guard. --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
191 lines
5.6 KiB
Python
191 lines
5.6 KiB
Python
"""
|
|
Tests for stream_chunk_builder annotation merging.
|
|
|
|
Previously, stream_chunk_builder only took annotations from the FIRST
|
|
annotation chunk, losing any annotations that arrived in later chunks.
|
|
This fix merges annotations from ALL chunks.
|
|
"""
|
|
|
|
from litellm import stream_chunk_builder
|
|
from litellm.types.utils import Delta, ModelResponseStream, StreamingChoices
|
|
|
|
|
|
def test_stream_chunk_builder_merges_annotations_from_multiple_chunks():
|
|
"""
|
|
stream_chunk_builder must merge annotations from ALL streaming chunks,
|
|
not just take them from the first annotation chunk.
|
|
|
|
Providers may spread annotations across multiple chunks (e.g. Gemini
|
|
sends grounding metadata in the final chunk, while intermediate chunks
|
|
may carry different annotations).
|
|
"""
|
|
annotation_a = {
|
|
"type": "url_citation",
|
|
"url_citation": {
|
|
"url": "https://example.com/a",
|
|
"title": "Source A",
|
|
"start_index": 0,
|
|
"end_index": 10,
|
|
},
|
|
}
|
|
annotation_b = {
|
|
"type": "url_citation",
|
|
"url_citation": {
|
|
"url": "https://example.com/b",
|
|
"title": "Source B",
|
|
"start_index": 20,
|
|
"end_index": 30,
|
|
},
|
|
}
|
|
|
|
chunks = [
|
|
ModelResponseStream(
|
|
id="chatcmpl-test",
|
|
created=1700000000,
|
|
model="test-model",
|
|
object="chat.completion.chunk",
|
|
choices=[
|
|
StreamingChoices(
|
|
finish_reason=None,
|
|
index=0,
|
|
delta=Delta(
|
|
content="Part one. ",
|
|
role="assistant",
|
|
annotations=[annotation_a],
|
|
),
|
|
)
|
|
],
|
|
),
|
|
ModelResponseStream(
|
|
id="chatcmpl-test",
|
|
created=1700000000,
|
|
model="test-model",
|
|
object="chat.completion.chunk",
|
|
choices=[
|
|
StreamingChoices(
|
|
finish_reason=None,
|
|
index=0,
|
|
delta=Delta(content="Part two."),
|
|
)
|
|
],
|
|
),
|
|
ModelResponseStream(
|
|
id="chatcmpl-test",
|
|
created=1700000000,
|
|
model="test-model",
|
|
object="chat.completion.chunk",
|
|
choices=[
|
|
StreamingChoices(
|
|
finish_reason="stop",
|
|
index=0,
|
|
delta=Delta(
|
|
content=None,
|
|
annotations=[annotation_b],
|
|
),
|
|
)
|
|
],
|
|
),
|
|
]
|
|
|
|
response = stream_chunk_builder(chunks=chunks)
|
|
assert response is not None
|
|
|
|
message = response["choices"][0]["message"]
|
|
assert message.annotations is not None
|
|
assert len(message.annotations) == 2
|
|
assert message.annotations[0] == annotation_a
|
|
assert message.annotations[1] == annotation_b
|
|
|
|
|
|
def test_stream_chunk_builder_single_annotation_chunk_still_works():
|
|
"""
|
|
When annotations come from a single chunk (most common case),
|
|
stream_chunk_builder must still work correctly (no regression).
|
|
"""
|
|
annotation = {
|
|
"type": "url_citation",
|
|
"url_citation": {
|
|
"url": "https://example.com/only",
|
|
"title": "Only Source",
|
|
"start_index": 0,
|
|
"end_index": 5,
|
|
},
|
|
}
|
|
|
|
chunks = [
|
|
ModelResponseStream(
|
|
id="chatcmpl-test",
|
|
created=1700000000,
|
|
model="test-model",
|
|
object="chat.completion.chunk",
|
|
choices=[
|
|
StreamingChoices(
|
|
finish_reason=None,
|
|
index=0,
|
|
delta=Delta(content="Hello", role="assistant"),
|
|
)
|
|
],
|
|
),
|
|
ModelResponseStream(
|
|
id="chatcmpl-test",
|
|
created=1700000000,
|
|
model="test-model",
|
|
object="chat.completion.chunk",
|
|
choices=[
|
|
StreamingChoices(
|
|
finish_reason="stop",
|
|
index=0,
|
|
delta=Delta(content=None, annotations=[annotation]),
|
|
)
|
|
],
|
|
),
|
|
]
|
|
|
|
response = stream_chunk_builder(chunks=chunks)
|
|
assert response is not None
|
|
|
|
message = response["choices"][0]["message"]
|
|
assert message.annotations is not None
|
|
assert len(message.annotations) == 1
|
|
assert message.annotations[0] == annotation
|
|
|
|
|
|
def test_stream_chunk_builder_no_annotations():
|
|
"""
|
|
When no chunks contain annotations, the message should not have
|
|
an annotations key (no regression).
|
|
"""
|
|
chunks = [
|
|
ModelResponseStream(
|
|
id="chatcmpl-test",
|
|
created=1700000000,
|
|
model="test-model",
|
|
object="chat.completion.chunk",
|
|
choices=[
|
|
StreamingChoices(
|
|
finish_reason=None,
|
|
index=0,
|
|
delta=Delta(content="Hello", role="assistant"),
|
|
)
|
|
],
|
|
),
|
|
ModelResponseStream(
|
|
id="chatcmpl-test",
|
|
created=1700000000,
|
|
model="test-model",
|
|
object="chat.completion.chunk",
|
|
choices=[
|
|
StreamingChoices(
|
|
finish_reason="stop",
|
|
index=0,
|
|
delta=Delta(content=None),
|
|
)
|
|
],
|
|
),
|
|
]
|
|
|
|
response = stream_chunk_builder(chunks=chunks)
|
|
assert response is not None
|
|
|
|
message = response["choices"][0]["message"]
|
|
assert not hasattr(message, "annotations") or message.annotations is None
|