scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-21 00:21:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 74
49757 commits 2565 branches 1413 tags 3.2 GiB
Commit graph

49757 commits

This branch
This branch
All branches
Author SHA1 Message Date
Yujong Lee
1771e5bb68 refactor callback 2026-09-16 17:50:11 +00:00
Yujong Lee
75548d30f5 move io to core 2026-09-16 17:50:11 +00:00
Yujong Lee
5a7ea7ef71 refactor(python-bridge): make deferred logging callable 2026-09-16 17:50:11 +00:00
Yujong Lee
9bc6426ae1 refactor(python-bridge): bind OCR arguments once in Rust 
The request crossed the boundary four times: Python bind_request into a
dataclass, Rust re-reading each field back with its own precedence rules,
a BridgeOcrRequest copy, then the core request. The dataclass was retained
for the whole call only so map_failure could read model and kwargs at the
end.

Add a route-agnostic Signature binder that reproduces Python's positional
and keyword binding rules and TypeError messages, and project straight
from the bound arguments into the core request. This removes the Python
LiteLLMOcrRequest dataclass, bind_request, PythonOcrInput, BridgeOcrRequest,
and the retained boundary_request, document, api_key and callback_inputs
Python objects. api_key for pre_call now comes from core's resolved
connection, matching the legacy handler, and core no longer carries
retained_fields or retains_document since the bridge stopped re-aliasing.
 2026-09-16 17:50:11 +00:00
Yujong Lee
678e59c6b4 refactor(python-bridge): drop OCR callback fast path and body re-aliasing 
The bridge kept a Rust-side shadow of Logging's callback registries and
elided pre_call/post_call/success_handler when it thought nothing was
listening. That forked the logging contract and hid a bug: with callbacks
present, the during-call hook re-inserted the caller's original document
and unmapped optional params over the provider-transformed body.

Call the real Logging handlers unconditionally, like the Python wrapper
does, and hand callbacks a fresh dict built from core's composed body
instead of re-aliasing caller objects into it.
 2026-09-16 17:50:11 +00:00
Yujong Lee
7167bd0ff0 cleanup dead code 2026-09-16 17:50:11 +00:00
Yujong Lee
b9fca28c6e simplify 2026-09-16 17:50:11 +00:00
Yujong Lee
6d66be8bef refactor(python-bridge): make route bindings explicit 2026-09-16 17:50:11 +00:00
Yujong Lee
22a593d606 remove prepare_request 2026-09-16 17:50:11 +00:00
Yujong Lee
6c893a7dba remove input.py 2026-09-16 17:50:11 +00:00
Yujong Lee
2f25875ce6 refactor(ocr): separate unresolved connection state 2026-09-16 17:50:11 +00:00
Yujong Lee
056487a283 wip 2026-09-16 17:50:11 +00:00
Yujong Lee
5de196af63 wip 2026-09-16 17:50:11 +00:00
Yujong Lee
31b48f6191 more fixing 2026-09-16 17:50:11 +00:00
Yujong Lee
3a64b12911 more porting alignment 2026-09-16 17:50:10 +00:00
Yujong Lee
266ebcf4aa remove router from core 2026-09-16 17:50:10 +00:00
Yujong Lee
ec26f2a5a0 fix cohere 2026-09-16 17:50:10 +00:00
Yujong Lee
03a1c4a938 inlineing more errors 2026-09-16 17:50:10 +00:00
Yujong Lee
8cfb59082a refactor(rust): localize route errors 2026-09-16 17:50:10 +00:00
Yujong Lee
55fe8d40d0 refactor(ocr): flatten Azure transformation 2026-09-16 17:50:10 +00:00
Yujong Lee
0d63ecd931 wip 2026-09-16 17:50:10 +00:00
Yujong Lee
57e7bce5ed refactor(auth): localize AWS errors 2026-09-16 17:50:10 +00:00
Yujong Lee
3ef381a7b0 refactor(ocr): execute prepared request directly 2026-09-16 17:50:10 +00:00
Yujong Lee
9f13bf59b6 build(rust): scope provider auth dependencies 2026-09-16 17:50:10 +00:00
Yujong Lee
ddd101a780 wip 2026-09-16 17:50:10 +00:00
Yujong Lee
f4a6f695c9 refactor(rust): type provider model namespaces 2026-09-16 17:50:10 +00:00
Yujong Lee
c80617c4a6 wip 2026-09-16 17:49:20 +00:00
Yujong Lee
cc88a9479e wip 2026-09-16 17:49:20 +00:00
Yujong Lee
ff3185f385 fix(ocr): avoid duplicate post-call callback after Azure polling 2026-09-16 17:49:02 +00:00
Yujong Lee
451e96661e refactor(core): centralize opaque provider params 2026-09-16 17:49:02 +00:00
Yujong Lee
30ad040b25 refactor(ocr): remove stateless config fields 2026-09-16 17:48:53 +00:00
Yujong Lee
9ee2f0bdca fix(ocr): clean up mistral imports 2026-09-16 17:48:53 +00:00
Yujong Lee
4d903da85c refactor(ocr): mirror Python provider layout 2026-09-16 17:48:53 +00:00
kerry-berri
4e996400e2
Merge pull request #41154 from BerriAI/litellm-providers/price-sync 
chore(prices): sync Azure, Azure AI, Gemini, OpenAI, Bedrock, Together AI, Fireworks and Vertex prices: 278 models, 59 new, 30 deprecated
 2026-09-16 10:37:21 -07:00
Yassin Kortam
8aebd4ff63
Merge pull request #40571 from BerriAI/litellm_presidio_mcp_mode_no_post_call_scan 
fix(guardrails): don't add post_call output scan for MCP-only Presidio modes
 2026-09-16 10:09:12 -07:00
yujonglee
a7cfdd4cd5
Merge pull request #41432 from BerriAI/litellm_remove_rust_gateway_router_realtime 
refactor(rust): remove gateway, config, router, realtime, and Rust trace-parity instrumentation
 2026-09-16 10:06:31 -07:00
Yassin Kortam
8491d01668
Merge pull request #41268 from BerriAI/litellm_outbound_http2_opt_in 
feat(http): opt-in outbound HTTP/2 for httpx clients
 2026-09-16 10:05:37 -07:00
kerry
b9ab36279b fix(prices): add tpm and rpm to gemini 3.8 live rows 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-16 16:49:17 +00:00
kerry
eed760a37d test: drop azure gpt-5.6 rate tests pinned to a dated price page 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-16 16:49:15 +00:00
yassin
8a43fed20c fix(guardrails): use explicit returns in _configured_event_hooks 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-16 16:48:15 +00:00
Yassin Kortam
f0474bb70e
Merge pull request #41310 from BerriAI/litellm_model_access_denied_message 
fix(proxy): hide model allowlist from client-facing model access denied errors
 2026-09-16 09:38:29 -07:00
kerry
cab6732928 test: drop price-pinning tests that break on catalog updates 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-16 16:32:37 +00:00
yassin
7b3582aa66 fix(guardrails): treat tag-based Mode as MCP-only when all hooks are MCP hooks 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-16 16:31:44 +00:00
yassin
e48dde7b9b fix(tests): drop leftover merge markers in test_handle_jwt 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-16 16:28:13 +00:00
yassin
5fee1c8710 Merge remote-tracking branch 'origin/main' into litellm_model_access_denied_message 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

# Conflicts:
#	tests/test_litellm/proxy/auth/test_handle_jwt.py
 2026-09-16 16:27:18 +00:00
berriai-litellm-provider-info-sync[bot]
809685603a
chore(prices): sync Azure prices: 247 models 
azure_ai/Codestral-2501: 
azure_ai/cohere-command-a: 
azure_ai/deepseek-r1: 
azure_ai/deepseek-v3: 
azure_ai/deepseek-v3-0324: 
azure_ai/deepseek-v3.1: 
azure_ai/deepseek-v3.2: 
azure_ai/deepseek-v3.2-speciale: 
azure_ai/deepseek-v4-flash: 
azure_ai/DeepSeek-V4-Flash-0731: 
azure_ai/deepseek-v4-pro: 
azure_ai/embed-v-4-0: 
azure_ai/FW-DeepSeek-V3.2: 
azure_ai/FW-DeepSeek-V4-Pro: 
azure_ai/FW-GLM-5: 
azure_ai/FW-GLM-5.1: 
azure_ai/FW-GLM-5.2: 
azure_ai/FW-GLM-5.2-Fast: 
azure_ai/FW-Inkling: 
azure_ai/FW-Kimi-K2.5: 
azure_ai/FW-Kimi-K2.6: 
azure_ai/FW-Kimi-K2.7-Code: 
azure_ai/FW-Kimi-K3: 
azure_ai/FW-MiniMax-M2.5: 
azure_ai/FW-MiniMax-M3: 
azure_ai/FW-Nemotron-3-Ultra-NVFP4: 
azure_ai/FW-Nemotron-Lightning-3.5-30B-A3B: 
azure_ai/gpt-oss-120b: 
azure_ai/grok-3: 
azure_ai/global/grok-3: 
azure_ai/grok-3-mini: 
azure_ai/global/grok-3-mini: 
azure_ai/grok-4: 
azure_ai/grok-4-1-fast-non-reasoning: 
azure_ai/grok-4-1-fast-reasoning: 
azure_ai/grok-4-20-non-reasoning: 
azure_ai/grok-4-20-reasoning: 
azure_ai/grok-4-fast-non-reasoning: 
azure_ai/grok-4-fast-reasoning: 
azure_ai/grok-4.3: 
azure_ai/grok-4.6: 
azure_ai/grok-code-fast-1: 
azure_ai/kimi-k2.5: 
azure_ai/kimi-k2.6: 
azure_ai/kimi-k2.7-code: 
azure_ai/Llama-3.3-70B-Instruct: 
azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8: 
azure_ai/MAI-DS-R1: 
azure_ai/MAI-Image-2.5: 
azure_ai/MAI-Image-2.5-Flash: 
azure_ai/MAI-Image-2e: 
azure_ai/MAI-Thinking-1: 
azure_ai/mistral-large-3: 
azure_ai/Phi-3-medium-128k-instruct: 
azure_ai/Phi-3-medium-4k-instruct: 
azure_ai/Phi-3-mini-128k-instruct: 
azure_ai/Phi-3-mini-4k-instruct: 
azure_ai/Phi-3-small-128k-instruct: 
azure_ai/Phi-3-small-8k-instruct: 
azure_ai/Phi-3.5-mini-instruct:
 2026-09-16 16:26:23 +00:00
Yassin Kortam
e941edd08a
Merge pull request #41407 from BerriAI/litellm_content_filter_stream_bounded_scan 
perf(content_filter): scan a bounded window per streamed chunk
 2026-09-16 09:25:23 -07:00
kerry
d398c9199c Merge remote-tracking branch 'origin/main' into HEAD 2026-09-16 16:18:47 +00:00
jesus
47117d880c fix(guardrails): don't add post_call output scan for MCP-only Presidio modes 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-16 16:15:49 +00:00
Yujong Lee
6330d80efa refactor(rust): glob workspace members 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-16 16:15:46 +00:00