mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-27 01:22:18 +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 Delete eight tests the audit found superseded by stronger ones kept in this move.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>
111 lines
4.5 KiB
Python
111 lines
4.5 KiB
Python
"""
|
||
Regression tests for #20885 – ``supports_response_schema`` (and related
|
||
capability flags) must be consistent between the bare model-name entry
|
||
(e.g. ``deepseek-chat``) and the provider-prefixed entry
|
||
(e.g. ``deepseek/deepseek-chat``) in the model-cost map.
|
||
|
||
The bug caused ``supports_response_schema("deepseek/deepseek-chat")`` to
|
||
return ``False`` even though the canonical ``deepseek-chat`` entry has the
|
||
field set to ``True``.
|
||
"""
|
||
|
||
import json
|
||
import os
|
||
|
||
import litellm
|
||
from litellm.utils import (
|
||
_supports_factory,
|
||
)
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Data-level tests – verify the JSON files are in sync
|
||
# ---------------------------------------------------------------------------
|
||
|
||
|
||
def _load_backup_json() -> dict:
|
||
"""Load the backup JSON directly from disk."""
|
||
backup_path = os.path.join(
|
||
os.path.dirname(litellm.__file__),
|
||
"model_prices_and_context_window_backup.json",
|
||
)
|
||
with open(backup_path, encoding="utf-8") as f:
|
||
return json.load(f)
|
||
|
||
|
||
class TestDeepSeekModelCostEntries:
|
||
"""Verify that provider-prefixed DeepSeek entries contain the same
|
||
capability flags as their bare-name counterparts in the JSON files."""
|
||
|
||
def test_deepseek_chat_max_input_tokens_matches_bare_in_backup(self):
|
||
data = _load_backup_json()
|
||
bare = data.get("deepseek-chat", {})
|
||
prefixed = data.get("deepseek/deepseek-chat", {})
|
||
assert prefixed.get("max_input_tokens") == bare.get("max_input_tokens")
|
||
|
||
def test_deepseek_reasoner_max_output_tokens_matches_bare_in_backup(self):
|
||
data = _load_backup_json()
|
||
bare = data.get("deepseek-reasoner", {})
|
||
prefixed = data.get("deepseek/deepseek-reasoner", {})
|
||
assert prefixed.get("max_output_tokens") == bare.get("max_output_tokens")
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# API-level tests – verify supports_response_schema returns True
|
||
# ---------------------------------------------------------------------------
|
||
|
||
|
||
class TestSupportsResponseSchemaDeepSeek:
|
||
"""All calling conventions for DeepSeek should return True for
|
||
``supports_response_schema``."""
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Fallback-logic test – bare model entry used when prefixed is incomplete
|
||
# ---------------------------------------------------------------------------
|
||
|
||
|
||
class TestBareModelFallback:
|
||
"""When a provider-prefixed entry is missing a capability flag, the
|
||
``_supports_factory`` fallback should consult the bare model-name
|
||
entry in ``litellm.model_cost``."""
|
||
|
||
def test_fallback_uses_bare_entry(self):
|
||
"""Temporarily remove ``supports_response_schema`` from the prefixed
|
||
entry and verify the fallback still returns True."""
|
||
key = "deepseek/deepseek-chat"
|
||
original = litellm.model_cost.get(key, {}).get("supports_response_schema")
|
||
try:
|
||
# Simulate the pre-fix state: field missing from prefixed entry
|
||
if key in litellm.model_cost:
|
||
litellm.model_cost[key].pop("supports_response_schema", None)
|
||
result = _supports_factory(
|
||
model="deepseek-chat",
|
||
custom_llm_provider="deepseek",
|
||
key="supports_response_schema",
|
||
)
|
||
assert result is True
|
||
finally:
|
||
# Restore
|
||
if key in litellm.model_cost and original is not None:
|
||
litellm.model_cost[key]["supports_response_schema"] = original
|
||
|
||
def test_no_fallback_when_explicitly_false(self):
|
||
"""If the prefixed entry explicitly sets a capability to ``False``,
|
||
the fallback must NOT override it."""
|
||
key = "deepseek/deepseek-reasoner"
|
||
# After the data fix, deepseek/deepseek-reasoner has
|
||
# supports_function_calling=false (matching the bare entry).
|
||
# Explicitly set it to False to test the guard.
|
||
original = litellm.model_cost.get(key, {}).get("supports_function_calling")
|
||
try:
|
||
if key in litellm.model_cost:
|
||
litellm.model_cost[key]["supports_function_calling"] = False
|
||
result = _supports_factory(
|
||
model="deepseek-reasoner",
|
||
custom_llm_provider="deepseek",
|
||
key="supports_function_calling",
|
||
)
|
||
assert result is False
|
||
finally:
|
||
if key in litellm.model_cost and original is not None:
|
||
litellm.model_cost[key]["supports_function_calling"] = original
|