mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-10 22:41:41 +00:00
a677242d6f
When the headroom_retrieve tool is exposed to a client that runs its own tool-execution loop (the LiteLLM MCP gateway path), the client executes the retrieve call and sends the recovered original content back as a tool result on the next turn. The guardrail then compressed that row again, and because CCR is content-addressed it collapsed back to the exact same hash it was just retrieved from. The model never saw the expansion and the agent looped. Hold tool-result rows that carry headroom_retrieve output back from the compression service, the same way the live turn and trailing tool exchange are already protected, so the expansion survives. Retrieve calls are matched by the direct headroom_retrieve name and the mcp__<server>__headroom_retrieve gateway name. Because a long gateway name is truncated past 64 chars in the OpenAI-translated view the guardrail scans, the pairing also falls back to the tool-call id read from the request's own untranslated messages, which is never truncated. Fixes #38558 |
||
|---|---|---|
| .. | ||
| guardrail_hooks | ||
| test_content_filter_path_traversal.py | ||
| test_content_utils.py | ||
| test_custom_code_security.py | ||
| test_deferred_guardrail_logging.py | ||
| test_guardrail_coverage.py | ||
| test_guardrail_endpoints.py | ||
| test_guardrail_registry.py | ||
| test_init_guardrails.py | ||
| test_llm_as_a_judge.py | ||
| test_mcp_jwt_signer.py | ||
| test_pillar_guardrails.py | ||
| test_prompt_security_guardrails.py | ||
| test_qostodian_nexus_guardrail.py | ||
| test_usage_endpoints.py | ||
| test_usage_tracking.py | ||