feat(litellm): Add async callbacks

[alexander-alderman-webb]

Description

Add asynchronous variants of callbacks to litellm.input_callback and litellm.success_callback

Issues

Reminders

• Please add tests to validate your changes, and lint your code using tox -e linters.
• Add GH Issue ID & Linear ID (if applicable)
• PR title should use conventional commit style (feat:, fix:, ref:, meta:)
• For external contributors: CONTRIBUTING.md, Sentry SDK development docs, Discord community

[github-actions]

Codecov Results 📊

✅ 100 passed | ⏭️ 1 skipped | Total: 101 | Pass Rate: 99.01% | Execution Time: 33.64s

📊 Comparison with Base Branch

Metric	Change
Total Tests	📈 +49
Passed Tests	📈 +51
Failed Tests	—
Skipped Tests	📉 -2

All tests are passing successfully.

❌ Patch coverage is 0.00%. Project has 14749 uncovered lines.
✅ Project coverage is 30.69%. Comparing base (base) to head (head).

Files with missing lines (1)

File	Patch %	Lines
litellm.py	0.00%	⚠️ 147 Missing

Coverage diff

@@            Coverage Diff             @@
##          main       #PR       +/-##
==========================================
+ Coverage    26.75%    30.69%    +3.94%
==========================================
  Files          191       191         —
  Lines        21282     21279        -3
  Branches      7006      7010        +4
==========================================
+ Hits          5692      6530      +838
- Misses       15590     14749      -841
- Partials       490       537       +47

---

Generated by Codecov Action

[github-actions]

Semver Impact of This PR

🟡 Minor (new features)

📋 Changelog Preview

This is how your changes will appear in the changelog.
Entries from this PR are highlighted with a left border (blockquote style).

---

New Features ✨

• (ai) Redact base64 data URLs in image_url content blocks by ericapisani in #5953
• (integrations) Instrument pyreqwest tracing by servusdei2018 in #5682

• (litellm) Add async callbacks by alexander-alderman-webb in #5969

Bug Fixes 🐛

Anthropic

• Capture exceptions for stream() calls by alexander-alderman-webb in #5950
• Stop setting transaction status when child span fails by alexander-alderman-webb in #5717
• Only finish relevant spans in .create() patches by alexander-alderman-webb in #5716

Pydantic Ai

• Adapt import for new library versions by alexander-alderman-webb in #5984
• Use first-class hooks when available by alexander-alderman-webb in #5947

Other

• (huggingface_hub) Stop setting transaction status when a child span fails by Zenithatic in #5952
• (litellm) Avoid double span exits when streaming by alexander-alderman-webb in #5933
• (wsgi) Respect HTTP_X_FORWARDED_PROTO in request.url construction by sl0thentr0py in #5963

Internal Changes 🔧

Litellm

• Replace mocks with httpx types in rate-limit test by alexander-alderman-webb in #5975
• Replace mocks with httpx types in embedding tests by alexander-alderman-webb in #5970
• Replace mocks with httpx types in nonstreaming completion() tests by alexander-alderman-webb in #5937
• Remove dead attributes by alexander-alderman-webb in #5985

Other

• (ai) Remove gen_ai.tool.type span attribute by ericapisani in #5964
• (anthropic) Separate sync and async .create() patches by alexander-alderman-webb in #5715
• (openai) Split token counting by API for easier deprecation by ericapisani in #5930
• (openai-agents) Remove error attributes by alexander-alderman-webb in #5986
• (opentelemetry) Ignore mypy error by alexander-alderman-webb in #5927
• 🤖 Update test matrix with new releases (04/13) by github-actions in #5983
• Fix license metadata in setup.py by sl0thentr0py in #5934
• Update validate-pr workflow by stephanie-anderson in #5931

Other

• Handle None span context in the span processor and pin tokenizers version for anthropic tests on Python 3.8 by alexander-alderman-webb in #5967

---

_{🤖 This preview updates automatically when you update the PR.}

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

Bugbot Autofix prepared a fix for the issue found in the latest run.

• ✅ Fixed: Test mocks embeddings path instead of completions
  • Updated test_async_exception_handling to patch client.completions._client._client so the mock target matches the litellm.acompletion code path.

Or push these changes by commenting:

@cursor push 270c50b1f3

Preview (270c50b1f3)

diff --git a/tests/integrations/litellm/test_litellm.py b/tests/integrations/litellm/test_litellm.py
--- a/tests/integrations/litellm/test_litellm.py
+++ b/tests/integrations/litellm/test_litellm.py
@@ -867,7 +867,7 @@
     model_response = get_rate_limit_model_response()
 
     with mock.patch.object(
-        client.embeddings._client._client,
+        client.completions._client._client,
         "send",
         return_value=model_response,
     ):

_{This Bugbot Autofix run was free. To enable autofix for future PRs, go to the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit 6626a1b. Configure here.}