scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-02 02:11:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 102

fix(anthropic): forward the dangerous-tool-use beta to Azure AI Foundry (#43934)

Browse source 
Map dangerous-tool-use-2026-09-03 for azure_ai in the beta header config so the
Claude Code auto mode beta reaches Foundry instead of being stripped, matching
the anthropic, bedrock, and vertex_ai entries

Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
This commit is contained in:
devin-ai-integration[bot] 2026-09-30 16:40:11 -07:00 • committed by GitHub
parent f8f05767da
commit ed4caebb65
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
litellm/anthropic_beta_headers_config.json
View file

@ -49,7 +49,7 @@
"computer-use-2025-11-24": "computer-use-2025-11-24",
"context-1m-2025-08-07": "context-1m-2025-08-07",
"context-management-2025-06-27": "context-management-2025-06-27",
"dangerous-tool-use-2026-09-03": null,
"dangerous-tool-use-2026-09-03": "dangerous-tool-use-2026-09-03",
"effort-2025-11-24": "effort-2025-11-24",
"fast-mode-2026-02-01": null,
"files-api-2025-04-14": "files-api-2025-04-14",

2
tests/unit/test_anthropic_beta_headers_filtering.py
View file

@ -444,7 +444,7 @@ class TestAnthropicBetaHeadersFiltering:
assert filtered == ["thinking-binding-controls-2026-08-01"]
@pytest.mark.parametrize("provider", ["anthropic", "bedrock", "bedrock_mantle", "vertex_ai"])
@pytest.mark.parametrize("provider", ["anthropic", "azure_ai", "bedrock", "bedrock_mantle", "vertex_ai"])
def test_dangerous_tool_use_forwarded(self, provider):
"""Claude Code's server-side auto-mode classifier sends `safeguards` together with
dangerous-tool-use-2026-09-03. Bedrock Invoke, Bedrock Mantle, and Vertex rawPredict