mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-22 00:31:44 +00:00
d05e45893e
- Switch all per-cell tests from @pytest.mark.parametrize("model", ...)
(3 sequential invocations) to a single test that fans out to all 3
Claude tiers via run_claude_models_parallel. Per-cell wall time is now
bounded by the slowest model rather than the sum.
- Add 5 new v0 feature dirs (5 providers each, 25 new test files):
web_search, pdf_input, prompt_caching_1h,
tool_use_streaming, thinking_with_tool_use
Manifest expanded to match.
- Add cross-process token-bucket rate limiter (rate_limiter.py + tests)
so xdist workers stay under per-provider req/s limits during full-grid
runs. New env knobs: LITELLM_COMPAT_RATE_{ANTHROPIC,AZURE,VERTEX_AI,
BEDROCK_CONVERSE,BEDROCK_INVOKE}.
- conftest.py: write per-worker shards under <artifact>.shards/, merge
in the controller; preserve the "don't write empty artifact" guard so
unit-test runs don't clobber a real compat-results.json.
- Vertex test_config.yaml: route project/location through env so the
cron VM can target a different GCP project than the upstream default.
- Add run_compat.sh wrapper for binary-searching ideal req/s per
provider against compat-rate-limit-summary.json output.
103 lines
3.9 KiB
YAML
103 lines
3.9 KiB
YAML
# Proxy routing config for the Claude Code Compatibility Matrix PR gate.
|
|
#
|
|
# The tests under `tests/claude_code/` only know **alias** names (e.g.
|
|
# `claude-haiku-4-5-bedrock-invoke`). The proxy is the layer that maps
|
|
# each alias to a real upstream model id, region, and credentials.
|
|
#
|
|
# Adding a new (feature, provider) cell is a three-step change in the
|
|
# test repo (manifest + test file + alias here); changing which upstream
|
|
# model a cell exercises is a one-step change here, with no test edits.
|
|
#
|
|
# Aliases:
|
|
# - claude-{tier} → Anthropic API
|
|
# - claude-{tier}-bedrock-invoke → Bedrock InvokeModel API
|
|
# - claude-{tier}-bedrock-converse → Bedrock Converse API
|
|
# - claude-{tier}-vertex → GCP Vertex AI
|
|
# - claude-{tier}-azure → Microsoft Foundry (Anthropic deployments)
|
|
|
|
model_list:
|
|
# ---- Anthropic ----
|
|
- model_name: claude-haiku-4-5
|
|
litellm_params:
|
|
model: anthropic/claude-haiku-4-5
|
|
api_key: os.environ/ANTHROPIC_API_KEY
|
|
- model_name: claude-sonnet-4-6
|
|
litellm_params:
|
|
model: anthropic/claude-sonnet-4-6
|
|
api_key: os.environ/ANTHROPIC_API_KEY
|
|
- model_name: claude-opus-4-7
|
|
litellm_params:
|
|
model: anthropic/claude-opus-4-7
|
|
api_key: os.environ/ANTHROPIC_API_KEY
|
|
|
|
# ---- Bedrock (InvokeModel) ----
|
|
- model_name: claude-haiku-4-5-bedrock-invoke
|
|
litellm_params:
|
|
model: bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0
|
|
aws_region_name: us-east-1
|
|
- model_name: claude-sonnet-4-6-bedrock-invoke
|
|
litellm_params:
|
|
model: bedrock/us.anthropic.claude-sonnet-4-6
|
|
aws_region_name: us-east-1
|
|
- model_name: claude-opus-4-7-bedrock-invoke
|
|
litellm_params:
|
|
model: bedrock/us.anthropic.claude-opus-4-7
|
|
aws_region_name: us-east-1
|
|
|
|
# ---- Bedrock (Converse) ----
|
|
- model_name: claude-haiku-4-5-bedrock-converse
|
|
litellm_params:
|
|
model: bedrock/converse/us.anthropic.claude-haiku-4-5-20251001-v1:0
|
|
aws_region_name: us-east-1
|
|
- model_name: claude-sonnet-4-6-bedrock-converse
|
|
litellm_params:
|
|
model: bedrock/converse/us.anthropic.claude-sonnet-4-6
|
|
aws_region_name: us-east-1
|
|
- model_name: claude-opus-4-7-bedrock-converse
|
|
litellm_params:
|
|
model: bedrock/converse/us.anthropic.claude-opus-4-7
|
|
aws_region_name: us-east-1
|
|
|
|
# ---- Vertex AI ----
|
|
- model_name: claude-haiku-4-5-vertex
|
|
litellm_params:
|
|
model: vertex_ai/claude-haiku-4-5
|
|
vertex_ai_project: os.environ/VERTEXAI_PROJECT
|
|
vertex_ai_location: os.environ/VERTEXAI_LOCATION
|
|
- model_name: claude-sonnet-4-6-vertex
|
|
litellm_params:
|
|
model: vertex_ai/claude-sonnet-4-6
|
|
vertex_ai_project: os.environ/VERTEXAI_PROJECT
|
|
vertex_ai_location: os.environ/VERTEXAI_LOCATION
|
|
- model_name: claude-opus-4-7-vertex
|
|
litellm_params:
|
|
model: vertex_ai/claude-opus-4-7
|
|
vertex_ai_project: os.environ/VERTEXAI_PROJECT
|
|
vertex_ai_location: os.environ/VERTEXAI_LOCATION
|
|
|
|
# ---- Microsoft Foundry (Anthropic deployments on Azure) ----
|
|
- model_name: claude-haiku-4-5-azure
|
|
litellm_params:
|
|
model: azure_ai/claude-haiku-4-5
|
|
api_base: os.environ/AZURE_FOUNDRY_API_BASE
|
|
api_key: os.environ/AZURE_FOUNDRY_API_KEY
|
|
- model_name: claude-sonnet-4-6-azure
|
|
litellm_params:
|
|
model: azure_ai/claude-sonnet-4-6
|
|
api_base: os.environ/AZURE_FOUNDRY_API_BASE
|
|
api_key: os.environ/AZURE_FOUNDRY_API_KEY
|
|
- model_name: claude-opus-4-7-azure
|
|
litellm_params:
|
|
model: azure_ai/claude-opus-4-7
|
|
api_base: os.environ/AZURE_FOUNDRY_API_BASE
|
|
api_key: os.environ/AZURE_FOUNDRY_API_KEY
|
|
|
|
general_settings:
|
|
# Claude Code sends provider-specific headers (e.g. anthropic-beta) we
|
|
# want to forward verbatim to the upstream so the wire-shape under
|
|
# test matches what real customers send.
|
|
forward_client_headers_to_llm_api: true
|
|
|
|
litellm_settings:
|
|
drop_params: true
|
|
modify_params: true
|