feat: add LiteLLM as AI gateway prompt target#2154
Open
RheagalFire wants to merge 4 commits into
Open
Conversation
Contributor
|
I've been wanting to do this also; @RheagalFire this is a great start. I'll likely push to your branch to flush it out and support all the things (multi-modal, identifiers, underlying model, integration tests, capabilities detection, other gaps). So from your perspective I would consider this "merged" and I'll take it and try to get it in before the next release. TY for the help and nudge! |
…s, token usage) Extends the LiteLLM target for parity with OpenAIChatTarget and shares logic instead of reinventing it: - Extract shared Chat Completions helpers (chat_completions_message_builder, chat_completions_response_parser) used by both OpenAIChatTarget and LiteLLMChatTarget for request building and response parsing (text, image, audio, tool calls, content-filter handling). - Add multimodal support (image + audio input, audio output via audio_response_config) with capabilities derived from LiteLLM's model registry and a conservative text-only fallback. - Support the full OpenAI parameter set plus an extra_body_parameters passthrough; auth via sync/async token providers; identifiers that exclude the api_key; underlying_model capability lookup; and LiteLLM-owned retry (num_retries from PyRIT's global convention) to avoid double-retrying. - Add a provider-neutral TokenUsage value object (input/output/total/reasoning/cached + extra) and capture it for both targets; capture LiteLLM per-call cost. - Add litellm as an optional extra and include it in the 'all' extra. - Modernize type syntax (X | None), tidy docstrings per the style guide, and add unit + integration tests (image/audio on a gpt-5 deployment). Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
… object Make TokenUsage a pure value object (fields + to_metadata/from_metadata) and move Chat Completions usage parsing into chat_completions_response_parser as token_usage_from_chat_completion, explicit to the one wire shape both chat targets actually send. - Drop the speculative Responses-API sniffing (no caller sends that shape); a Responses target should parse its own usage in its own module. - Tolerate dict-or-attribute usage payloads so a mapping no longer silently yields all-None counts. - Capture LiteLLM/Anthropic top-level cache fields (cache_read_input_tokens -> cached_tokens, cache_creation_input_tokens -> extra), preserving a zero cached count. - Move/expand parsing tests into test_chat_completions_helpers; test_token_usage now covers only metadata round-tripping. - Convert remaining Sphinx roles to plain double-backtick references. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
…ts to gpt-5.4 Revert the PLATFORM_OPENAI_CHAT_MODEL / PLATFORM_OPENAI_AUDIO_MODEL additions to .env_example and default the chat/vision integration fixtures to the deployed gpt-5.4 model instead of the generic "gpt-5". Also convert two stray Sphinx roles in the integration test docstrings to plain double-backtick references. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
romanlutz
reviewed
Jul 10, 2026
| "azure-cognitiveservices-speech>=1.46.0", | ||
| ] | ||
| litellm = [ | ||
| "litellm>=1.83.0,<2.0.0", |
Contributor
There was a problem hiding this comment.
FWIW it doesn't add a ton on top of what we already have. Could consider making it a dependency without extra. That could change for litellm, of course, and then we'd have to move it into an extra. The current state as extra is probably the safest.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Adds
LiteLLMChatTarget- a new prompt target that uses the LiteLLM SDK to access 100+ LLM providers (Anthropic, AWS Bedrock, Google Vertex, Cohere, etc.) directly, without requiring a separate proxy server.Changes:
pyrit/prompt_target/litellm_chat_target.py- NewLiteLLMChatTargetextendingPromptTargetwith:litellm.acompletion()for async chat completionsdrop_params=Trueby default (silently drops provider-unsupported kwargs for cross-provider compatibility)litellm.exceptions.*mapped to PyRIT'sRateLimitException/PyritExceptionhierarchy (no bareExceptioncatches)import litellmso users without the package are unaffectedpyrit/prompt_target/__init__.py- RegisteredLiteLLMChatTargetpyproject.toml- Addedlitellm>=1.83.0,<2.0.0as optional dependency (pip install pyrit[litellm])Tests and Documentation
22 unit tests in
tests/unit/prompt_target/target/test_litellm_chat_target.py:ValueError,LITELLM_MODELenv var fallback, explicit overridedrop_params=Truedefault + opt-out withdrop_params=FalseEmptyResponseException, empty content raisesEmptyResponseExceptionlitellm.exceptions.RateLimitError->RateLimitException,AuthenticationError->PyritException,APIConnectionError/Timeout-> retryableRateLimitException, unknown errors ->PyritExceptionstop,length,tool_calls,content_filteraccepted; unknown reasons raisePyritExceptionAll 22 tests pass:
Ruff lint clean (line-length=120, preview=true).
JupyText not applicable - no notebook documentation added for this target yet.