Skip to content

fix: strip cache_breakpoint in LiteLLM path and expand Anthropic prefixes #5914

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
superShen0916 wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix: strip cache_breakpoint in LiteLLM path and expand Anthropic prefixes #5914

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
303d166
fix: strip cache_breakpoint in LiteLLM path and expand Anthropic pref…
May 23, 2026
bf1d95b
Merge upstream/main into fix/llm-routing-improvements
superShen0916 May 30, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 12 additions & 1 deletion lib/crewai/src/crewai/llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -453,7 +453,8 @@ def _matches_provider_pattern(cls, model: str, provider: str) -> bool:

if provider == "anthropic" or provider == "claude":
return any(
model_lower.startswith(prefix) for prefix in ["claude-", "anthropic."]
model_lower.startswith(prefix)
for prefix in ["claude-", "anthropic.", "anthropic--"]
)

if provider == "gemini" or provider == "google":
Expand Down Expand Up @@ -2084,6 +2085,16 @@ def _format_messages_for_provider(
"Invalid message format. Each message must be a dict with 'role' and 'content' keys"
)

# Strip cache-breakpoint flags before sending to LiteLLM.
# Native providers already handle this via BaseLLM._format_messages,
# but the LiteLLM fallback path uses this method directly.
from crewai.llms.cache import strip_cache_breakpoint

messages = [dict(msg) for msg in messages]
for msg in messages:
strip_cache_breakpoint(msg)

# Handle O1 models specially
if "o1" in self.model.lower():
formatted_messages = []
for msg in messages:
Expand Down