* feat(guardrails): Add deduplication and session tracking
- Implement deduplication logic to prevent duplicate scans (via call_id; add _check_and_mark_scanned) caused by LiteLLM callback system
- Add session tracking using litellm_trace_id as AI Session ID for Prisma AIRS SCM logging
- Extract helper methods _extract_prompt_from_request maintainability
- Use httpxSpecialProvider import (LoggingCallback -> GuardrailCallback)
- Add comprehensive tests for deduplication and session tracking (7 new tests)
- Update documentation with multi-turn conversation tracking examples
* docs: update PANW Prisma AIRS multi-turn conversation example to use industry-standard terminology
- Clearer example for conversation tracking
- Updated terminology from 'AI Session ID' to 'Prisma AIRS AI Session ID' for clarity
* fix: remove unused asyncio import
* fix: correct mypy type ignore comment
* Fix embeddings endpoint call_type to use valid CallTypes enum value
Fixed bug where the `/embeddings` endpoint was passing `call_type="embeddings"`
to guardrail hooks, but "embeddings" is not a valid value in the CallTypes enum.
Changed to use `call_type="aembedding"` (async embedding) which is the correct
CallTypes enum value and matches the route_type used in the same function.
Added unit tests to verify:
- "embeddings" is not a valid CallTypes enum value
- "aembedding" is the correct valid value
- The fix prevents ValueError when guardrails are enabled
Fixes#16240
* Inline embeddings call type regression check
* Ensure embedding test preserves proxy metadata
## Problem
The `extra_body` parameter in `litellm.responses()` and `litellm.aresponses()`
was being accepted but never passed to the HTTP request sent to the LLM provider.
This prevented users from sending custom/experimental parameters to provider APIs.
## Changes
- Added `data.update(extra_body)` in `async_response_api_handler` (line 2138)
- Added `data.update(extra_body)` in `response_api_handler` (line 2012)
- Added tests to `test_openai_responses_api.py` for extra_body functionality
## Testing
- Tests verify extra_body params are passed in both sync and async modes
- Existing Responses API tests continue to pass
- Manually verified with OpenAI API that custom params are sent correctly
## Impact
Users can now pass custom/experimental parameters via extra_body:
```python
litellm.aresponses(
model="gpt-4o",
input="hello",
extra_body={"custom_param": "value"} # Now works!
)
```
This aligns with the OpenAI SDK pattern and matches behavior in other
LiteLLM endpoints (completion, embedding, etc.) that already support extra_body.
* Update MCP version from 1.10.1 to 1.20.0
- Update mcp dependency: 1.10.1 -> 1.20.0 in requirements.txt, pyproject.toml, and CI config
- Update uvicorn dependency: 0.29.0 -> 0.31.1 (required by MCP 1.20.0)
- Update PyJWT constraint to support newer versions required by MCP
- Update all CI pipeline references to MCP 1.20.0
- Add test to verify MCP version and import compatibility
MCP 1.20.0 requires uvicorn >=0.31.1 and PyJWT >=2.10.1.
MCP package remains Python >=3.10 only (no change to version constraint).
* Update poetry.lock for MCP 1.20.0
* Fix bug, add new unit test
* Extract payload builder code to a separate namespace
* Update opik.py to use logic from the new namespace
* Code cleanup, type hints improvements
* Run linter
* Log model name as span field
* Reformat arguments in payload builders
* Use dataclasses for payloads, use opik native client if it's available
* Add cost and provider
* Add provider mapping
- Add HCP_VAULT_MOUNT_NAME env var to override default 'secret' mount
- Add HCP_VAULT_PATH_PREFIX env var to add prefix to secret paths
- Update get_url() method to construct URLs with configurable mount and prefix
- Add test coverage for custom mount names and path prefixes
- Maintain backward compatibility with existing configurations
This allows users to configure Vault paths like:
- Custom mount: {VAULT_ADDR}/v1/{MOUNT_NAME}/data/{SECRET}
- With prefix: {VAULT_ADDR}/v1/secret/data/{PREFIX}/{SECRET}
- Both: {VAULT_ADDR}/v1/{MOUNT_NAME}/data/{PREFIX}/{SECRET}
Resolves issue where mount name was hardcoded and path prefixes weren't supported.
* KeyManagementSystem add cyberark
* add CyberArkSecretManager
* add CyberArkSecretManager
* add CyberArkSecretManager
* docs add CyberArkSecretManager
* docs
* refactor to use get_secret_from_manager
* Potential fix for code scanning alert no. 3645: Clear-text logging of sensitive information
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Potential fix for code scanning alert no. 3650: Clear-text logging of sensitive information
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Potential fix for code scanning alert no. 3649: Clear-text logging of sensitive information
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Potential fix for code scanning alert no. 3646: Clear-text logging of sensitive information
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
---------
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* noma support v2 api and images with during call
* supporting streams and images with texts
* Supporting text now
* annonymization works
* removing function
* fixing noma.py
* all old tests pass
* adding new tests
* removing changes
* Fixing application id headers
* fix whitespace
* deleting unused imports
* Add gemini api key in the custom api url
* Update tests
* Use api key n the header
* Use api key n the header
* fix mypy error
* fix mypy error
* fix test gemini auth
* fix(redis): handle float redis_version from AWS ElastiCache Valkey
AWS ElastiCache Valkey returns redis_version as a float (7.0) instead
of a string ('7.0.0'), causing AttributeError: 'float' object has no
attribute 'split' in async_lpop when parsing version for LPOP count.
Changes:
- Extract version parsing into _parse_redis_major_version() helper
- Add DEFAULT_REDIS_MAJOR_VERSION constant (replaces magic number)
- Support multiple version formats: string, float, int, malformed
- Add comprehensive test coverage for all version format edge cases
Fixes: 'LiteLLM Redis Cache LPOP: - Got exception from REDIS' error
during db_spend_update_job cronjobs
* refactor: move DEFAULT_REDIS_MAJOR_VERSION to constants.py
