mirror of
https://github.com/BerriAI/litellm.git
synced 2026-08-28 05:25:59 +00:00
* fix(bedrock): respect s3_region_name for batch file uploads (#23569) * fix(bedrock): respect s3_region_name for batch file uploads (GovCloud fix) * fix: s3_region_name always wins over aws_region_name for S3 signing (Greptile feedback) * fix: _filter_headers_for_aws_signature - Bedrock KB (#23571) * fix: _filter_headers_for_aws_signature * fix: filter None header values in all post-signing re-merge paths Addresses Greptile feedback: None-valued headers were being filtered during SigV4 signing but re-merged back into the final headers dict afterward, which would cause downstream HTTP client failures. Made-with: Cursor * feat(router): tag_regex routing — route by User-Agent regex without per-developer tag config (#23594) * feat(router): add tag_regex support for header-based routing Adds a new `tag_regex` field to litellm_params that lets operators route requests based on regex patterns matched against request headers — primarily User-Agent — without requiring per-developer tag configuration. Use case: route all Claude Code traffic (User-Agent: claude-code/x.y.z) to a dedicated deployment by setting: tag_regex: - "^User-Agent: claude-code\\/" in the deployment's litellm_params. Works alongside existing `tags` routing; exact tag match takes precedence over regex match. Unmatched requests fall through to deployments tagged `default`. The matched deployment, pattern, and user_agent are recorded in `metadata["tag_routing"]` so they flow through to SpendLogs automatically. * fix(tag_regex): address backwards-compat, metadata overwrite, and warning noise Three issues from code review: 1. Backwards-compat: `has_tag_filter` was widened to activate on any non-empty User-Agent, which would raise ValueError for existing deployments using plain tags without a `default` fallback. Fix: only activate header-based regex filtering when at least one candidate deployment has `tag_regex` configured. 2. Metadata overwrite: `metadata["tag_routing"]` was overwritten for every matching deployment in the loop, leaving inaccurate provenance when multiple deployments match. Fix: write only for the first match. 3. Warning noise: an invalid regex pattern logged one warning per header string rather than once per pattern. Fix: compile first (catching re.error once), then iterate over header strings. Also adds two new tests covering these cases, and adds docs page for tag_regex routing with a Claude Code walk-through. * refactor(tag_regex): remove unnecessary _healthy_list copy * docs: merge tag_regex section into tag_routing.md, remove standalone page - Add ## Regex-based tag routing (tag_regex) section to existing tag_routing.md instead of a separate page - Remove tag_regex_routing.md standalone doc (odd UX to have a separate page for a sub-feature) - Remove proxy/tag_regex_routing from sidebars.js - Add match_any=False debug warning in tag_based_routing.py when regex routing fires under strict mode (regex always uses OR semantics) * fix(tag_regex): address greptile review - security docs, strict-mode enforcement, validation order - Strengthen security note in tag_routing.md: explicitly state User-Agent is client-supplied and can be set to any value; frame tag_regex as a traffic classification hint, not an access-control mechanism - Move tag_regex startup validation before _add_deployment() so an invalid pattern never leaves partial router state - Enforce match_any=False strict-tag policy: when a deployment has both tags and tag_regex and the strict tag check fails, skip the regex fallback rather than silently bypassing the operator's intent - Extract per-deployment match logic into _match_deployment() helper to keep get_deployments_for_tag() readable - Add two new tests: strict-mode blocks regex fallback, regex-only deployment still matches under match_any=False * fix(ci): apply Black formatting to 14 files and stabilize flaky caplog tests - Run Black formatter on 14 files that were failing the lint check - Replace caplog-based assertions in TestAliasConflicts with unittest.mock.patch on verbose_logger.warning for xdist compatibility - The caplog fixture can produce empty text in pytest-xdist workers in certain CI environments, causing flaky test failures Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
245 lines
8.6 KiB
Python
245 lines
8.6 KiB
Python
"""
|
|
Tests for the ``aliases`` feature in the model cost map.
|
|
|
|
The ``_expand_model_aliases`` function processes ``aliases`` lists from model
|
|
entries, creating shared dict references for alias entries at load time.
|
|
"""
|
|
|
|
from unittest.mock import patch
|
|
|
|
from litellm import verbose_logger
|
|
from litellm.litellm_core_utils.get_model_cost_map import _expand_model_aliases
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Core expansion behaviour
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestExpandModelAliases:
|
|
"""Unit tests for _expand_model_aliases."""
|
|
|
|
def test_basic_expansion(self):
|
|
"""Aliases are added as top-level entries in model_cost."""
|
|
model_cost = {
|
|
"my-model-latest": {
|
|
"aliases": ["my-model-20250101"],
|
|
"input_cost_per_token": 1e-06,
|
|
"litellm_provider": "test",
|
|
"mode": "chat",
|
|
},
|
|
}
|
|
result = _expand_model_aliases(model_cost)
|
|
|
|
assert "my-model-20250101" in result
|
|
assert result["my-model-20250101"]["input_cost_per_token"] == 1e-06
|
|
assert result["my-model-20250101"]["litellm_provider"] == "test"
|
|
|
|
def test_multiple_aliases(self):
|
|
"""A single entry can declare multiple aliases."""
|
|
model_cost = {
|
|
"provider/model-latest": {
|
|
"aliases": ["provider/model-v1", "provider/model-v2"],
|
|
"input_cost_per_token": 5e-06,
|
|
"litellm_provider": "provider",
|
|
"mode": "chat",
|
|
},
|
|
}
|
|
result = _expand_model_aliases(model_cost)
|
|
|
|
assert "provider/model-v1" in result
|
|
assert "provider/model-v2" in result
|
|
|
|
def test_shared_dict_reference(self):
|
|
"""Alias entries share the same dict object as the canonical entry (no copy)."""
|
|
model_cost = {
|
|
"canonical-model": {
|
|
"aliases": ["alias-model"],
|
|
"input_cost_per_token": 2e-06,
|
|
"litellm_provider": "test",
|
|
"mode": "chat",
|
|
},
|
|
}
|
|
result = _expand_model_aliases(model_cost)
|
|
|
|
assert result["alias-model"] is result["canonical-model"]
|
|
|
|
def test_aliases_key_removed(self):
|
|
"""The ``aliases`` key is removed from the entry after expansion."""
|
|
model_cost = {
|
|
"my-model": {
|
|
"aliases": ["my-model-alias"],
|
|
"input_cost_per_token": 1e-06,
|
|
"litellm_provider": "test",
|
|
"mode": "chat",
|
|
},
|
|
}
|
|
result = _expand_model_aliases(model_cost)
|
|
|
|
assert "aliases" not in result["my-model"]
|
|
assert "aliases" not in result["my-model-alias"]
|
|
|
|
def test_entries_without_aliases_unchanged(self):
|
|
"""Entries with no ``aliases`` key are left untouched."""
|
|
model_cost = {
|
|
"plain-model": {
|
|
"input_cost_per_token": 3e-06,
|
|
"litellm_provider": "test",
|
|
"mode": "chat",
|
|
},
|
|
}
|
|
result = _expand_model_aliases(model_cost)
|
|
|
|
assert "plain-model" in result
|
|
assert result["plain-model"]["input_cost_per_token"] == 3e-06
|
|
assert len(result) == 1
|
|
|
|
def test_empty_aliases_list(self):
|
|
"""An empty ``aliases`` list is treated the same as no aliases."""
|
|
model_cost = {
|
|
"model-a": {
|
|
"aliases": [],
|
|
"input_cost_per_token": 1e-06,
|
|
"litellm_provider": "test",
|
|
"mode": "chat",
|
|
},
|
|
}
|
|
result = _expand_model_aliases(model_cost)
|
|
|
|
assert len(result) == 1
|
|
assert "model-a" in result
|
|
assert "aliases" not in result["model-a"]
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Conflict handling
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestAliasConflicts:
|
|
"""Tests for alias conflict detection and handling."""
|
|
|
|
def test_alias_conflicts_with_canonical_entry(self):
|
|
"""Alias that matches an existing canonical entry is skipped with a warning."""
|
|
model_cost = {
|
|
"model-latest": {
|
|
"aliases": ["model-dated"],
|
|
"input_cost_per_token": 1e-06,
|
|
"litellm_provider": "test",
|
|
"mode": "chat",
|
|
},
|
|
"model-dated": {
|
|
"input_cost_per_token": 1e-06,
|
|
"litellm_provider": "test",
|
|
"mode": "chat",
|
|
},
|
|
}
|
|
with patch.object(verbose_logger, "warning") as mock_warn:
|
|
result = _expand_model_aliases(model_cost)
|
|
|
|
# The canonical "model-dated" entry is preserved, not overwritten
|
|
assert "model-dated" in result
|
|
# Verify a warning about the alias conflict was logged
|
|
mock_warn.assert_called()
|
|
warning_messages = " ".join(str(c) for c in mock_warn.call_args_list)
|
|
assert "alias conflict" in warning_messages.lower()
|
|
|
|
def test_duplicate_alias_across_entries(self):
|
|
"""Same alias claimed by two different entries: second one is skipped."""
|
|
model_cost = {
|
|
"model-a": {
|
|
"aliases": ["shared-alias"],
|
|
"input_cost_per_token": 1e-06,
|
|
"litellm_provider": "test",
|
|
"mode": "chat",
|
|
},
|
|
"model-b": {
|
|
"aliases": ["shared-alias"],
|
|
"input_cost_per_token": 2e-06,
|
|
"litellm_provider": "test",
|
|
"mode": "chat",
|
|
},
|
|
}
|
|
with patch.object(verbose_logger, "warning") as mock_warn:
|
|
result = _expand_model_aliases(model_cost)
|
|
|
|
# "shared-alias" should point to model-a (first one wins)
|
|
assert "shared-alias" in result
|
|
assert result["shared-alias"]["input_cost_per_token"] == 1e-06
|
|
# Verify a warning about the alias conflict was logged
|
|
mock_warn.assert_called()
|
|
warning_messages = " ".join(str(c) for c in mock_warn.call_args_list)
|
|
assert "alias conflict" in warning_messages.lower()
|
|
|
|
def test_canonical_entry_not_overwritten_by_alias(self):
|
|
"""An alias must never overwrite an existing canonical entry's data."""
|
|
original_cost = 9.99e-06
|
|
model_cost = {
|
|
"existing-model": {
|
|
"input_cost_per_token": original_cost,
|
|
"litellm_provider": "test",
|
|
"mode": "chat",
|
|
},
|
|
"other-model": {
|
|
"aliases": ["existing-model"],
|
|
"input_cost_per_token": 1e-06,
|
|
"litellm_provider": "test",
|
|
"mode": "chat",
|
|
},
|
|
}
|
|
result = _expand_model_aliases(model_cost)
|
|
|
|
# Original entry must be preserved
|
|
assert result["existing-model"]["input_cost_per_token"] == original_cost
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Integration with model_cost dict mutation
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestAliasIntegration:
|
|
"""Higher-level tests verifying aliases work with the model_cost dict."""
|
|
|
|
def test_mutation_through_alias_visible_on_canonical(self):
|
|
"""Since alias is a shared reference, mutations are visible on both."""
|
|
model_cost = {
|
|
"canonical": {
|
|
"aliases": ["alias"],
|
|
"input_cost_per_token": 1e-06,
|
|
"litellm_provider": "test",
|
|
"mode": "chat",
|
|
},
|
|
}
|
|
result = _expand_model_aliases(model_cost)
|
|
|
|
# Mutate via alias
|
|
result["alias"]["input_cost_per_token"] = 999
|
|
assert result["canonical"]["input_cost_per_token"] == 999
|
|
|
|
def test_mixed_entries_with_and_without_aliases(self):
|
|
"""A model_cost dict with a mix of aliased and plain entries."""
|
|
model_cost = {
|
|
"model-with-alias": {
|
|
"aliases": ["alias-1", "alias-2"],
|
|
"input_cost_per_token": 1e-06,
|
|
"litellm_provider": "test",
|
|
"mode": "chat",
|
|
},
|
|
"plain-model": {
|
|
"input_cost_per_token": 2e-06,
|
|
"litellm_provider": "test",
|
|
"mode": "chat",
|
|
},
|
|
}
|
|
result = _expand_model_aliases(model_cost)
|
|
|
|
assert len(result) == 4 # 2 canonical + 2 aliases
|
|
assert "alias-1" in result
|
|
assert "alias-2" in result
|
|
assert "plain-model" in result
|
|
assert "model-with-alias" in result
|
|
|
|
def test_expand_on_empty_dict(self):
|
|
"""Expanding an empty dict returns an empty dict."""
|
|
assert _expand_model_aliases({}) == {}
|