Commit graph

33301 commits

Author SHA1 Message Date
Sameer Kankute
0296ca0b53 fix(openai): preserve reasoning_effort summary field for Responses API
When reasoning_effort is passed as a dict with additional fields like 'summary' or 'generate_summary', preserve the full dict format instead of normalizing it to a string. This ensures that when requests are routed to the OpenAI Responses API, all reasoning parameters are correctly included.

The normalization to string format now only happens for simple dicts with just the 'effort' key, which is appropriate for the Chat Completions API.

Fixes issue where summary field was being dropped when routing gpt-5.4+ requests with tools + reasoning to Responses API.

Made-with: Cursor
2026-03-09 18:32:56 +05:30
Sameer Kankute
d19bfae968 Add tests for rotuing to responses when tools + reasoning for gpt-5.4 2026-03-09 01:00:35 +05:30
Sameer Kankute
2aed1f5b15 Add rotuing to responses when tools + reasoning for gpt-5.4 2026-03-09 01:00:17 +05:30
Sameer Kankute
814e36353b Fix output config error 2026-03-07 00:36:22 +05:30
Sameer Kankute
273932c923 Fix model map 2026-03-06 22:56:14 +05:30
Sameer Kankute
00ff413f8f Fix model map 2026-03-06 22:56:14 +05:30
Sameer Kankute
4eb243fc19 Fixed o file 2026-03-06 22:56:14 +05:30
Sameer Kankute
7ab911ac6c Fixed o file 2026-03-06 22:56:14 +05:30
Sameer Kankute
3c80351b57 feat(openai): add 272K tier pricing for GPT-5.4/5.4-pro
Prompts >272K input tokens priced at 2x input, 1.5x output for full session
(standard, batch, flex). Applies to models with 1.05M context window (gpt-5.4,
gpt-5.4-pro).

- Add input/output_cost_per_token_above_272k_tokens to model_prices
- Add above_272k fields to ModelInfoBase and get_model_info extraction
- Add test_generic_cost_per_token_gpt54_above_272k_tokens

Made-with: Cursor
2026-03-06 22:56:14 +05:30
Sameer Kankute
4c26c1847b feat(openai): drop reasoning_effort for gpt-5.4 when tools present
Function calls not supported with reasoning_effort != 'none' on gpt-5.4.
Drop reasoning_effort when tools are in the request (small minority of volume).

Made-with: Cursor
2026-03-06 22:55:54 +05:30
Sameer Kankute
b684106385 feat(openai): normalize reasoning_effort dict to string for chat completion API
The OpenAI chat completion API expects reasoning_effort as a string
('none', 'low', 'medium', 'high', 'xhigh'). Config/deployments may pass
the Responses API format: {'effort': 'high', 'summary': 'detailed'}.

Fix BadRequestError when model config uses dict format by extracting
the 'effort' value before passing to the API.

Made-with: Cursor
2026-03-06 22:55:54 +05:30
Sameer Kankute
b126c22cad fix: update blog post with correct docker tag (gpt-5.4 not gpt-4o)
Made-with: Cursor
2026-03-05 23:48:40 +05:30
Sameer Kankute
c55a5d4ba2 Add day 0 support for gpt-5.4 2026-03-05 23:44:25 +05:30
Sameer Kankute
e1f9c940bc Add day 0 support for gpt-5.4 2026-03-05 23:44:25 +05:30
ryan-crabbe
0435375b12 Merge pull request #22247 from BerriAI/litellm_fix_client_closed_on_eviction
fix: remove cache eviction close that kills in-use httpx clients
2026-02-27 09:52:10 -08:00
yuneng-jiang
50263270f7
Merge pull request #22038 from BerriAI/logging_path_rc
[Patch] Spend Logging in RC
2026-02-24 13:02:30 -08:00
yuneng-jiang
6c3d0a3d9f fixing merge artifacts 2026-02-24 12:58:50 -08:00
yuneng-jiang
5cc055ffce Merge pull request #22029 from BerriAI/litellm_spend_tracking_logging
[Infra] Add Spend Tracking Lifecycle Logging
2026-02-24 12:55:52 -08:00
ryan-crabbe
1e906b0d57
Merge pull request #22037 from BerriAI/litellm_fix_rc_duplicate_schema
fix(schema): remove duplicate LiteLLM_DeletedTeamTable definition
2026-02-24 12:37:27 -08:00
Ryan Crabbe
690758a49d fix(schema): remove duplicate LiteLLM_DeletedTeamTable definition 2026-02-24 11:47:25 -08:00
Ishaan Jaffer
e157f5a8f2 docs fix 2026-02-21 17:35:16 -08:00
Ishaan Jaffer
661c6faac6 docs fix 2026-02-21 17:28:04 -08:00
Ishaan Jaffer
efebd37183 docs fix 2026-02-21 17:28:04 -08:00
yuneng-jiang
6228148963
Merge pull request #21857 from BerriAI/litellm_yj_docs_feb21
[Doc] Server Root Path Regression Incident Doc#21853
2026-02-21 17:26:43 -08:00
yuneng-jiang
386a8fbd5b
Merge branch 'main' into litellm_yj_docs_feb21 2026-02-21 17:21:35 -08:00
Ishaan Jaffer
7e567a5352 ui new build 2026-02-21 17:16:10 -08:00
Ishaan Jaffer
67a64266ef fix rendering 2026-02-21 17:15:18 -08:00
yuneng-jiang
823bb023df
Merge branch 'main' into litellm_yj_docs_feb21 2026-02-21 17:12:28 -08:00
Ishaan Jaffer
44f69038de UI new build 2026-02-21 17:00:45 -08:00
Ishaan Jaffer
52294029a0 test_vertex_ai_gemini_2_5_pro_streaming 2026-02-21 16:59:22 -08:00
Ishaan Jaffer
2270a3aaf3 Revert "Merge pull request #21140 from BerriAI/litellm_perf_user_api_key_auth"
This reverts commit 0e1db3f7e4, reversing
changes made to 7e2d6f2355.
2026-02-21 16:57:42 -08:00
milan-berri
5390469c1b
fix: replace Zapier webhook with Google Form for survey submission (#21621)
* Replace Zapier webhook with Google Form for survey submission

* Add back error logging for survey submission debugging

---------

Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
2026-02-21 16:55:59 -08:00
Ishaan Jaffer
ab032c292c docs fix 2026-02-21 16:36:22 -08:00
ryan-crabbe
0e1db3f7e4
Merge pull request #21140 from BerriAI/litellm_perf_user_api_key_auth
perf: optimize user_api_key_auth
2026-02-21 16:23:54 -08:00
ryan-crabbe
ce22524ac5
Merge branch 'main' into litellm_perf_user_api_key_auth 2026-02-21 16:05:33 -08:00
yuneng-jiang
241141d70b Merge branch 'doc_yj_feb21' of github.com:BerriAI/litellm into doc_yj_feb21 2026-02-21 16:05:27 -08:00
yuneng-jiang
aefc7c14f6 Merge remote-tracking branch 'origin' into doc_yj_feb21 2026-02-21 16:05:07 -08:00
Ishaan Jaffer
7e2d6f2355 ui fix 2026-02-21 16:05:03 -08:00
yuneng-jiang
70fd2aa219 fixing syntax 2026-02-21 16:04:42 -08:00
Ryan Crabbe
643c9b6c04 Merge remote-tracking branch 'origin/main' into litellm_perf_user_api_key_auth 2026-02-21 16:03:31 -08:00
yuneng-jiang
2e8d942d17
Merge branch 'main' into doc_yj_feb21 2026-02-21 16:00:46 -08:00
yuneng-jiang
153bf1d856 server root path regression doc 2026-02-21 15:57:06 -08:00
Ishaan Jaffer
d31d5b8486 fix failing tests 2026-02-21 15:48:26 -08:00
Ishaan Jaffer
775fb79260 fix 2026-02-21 15:45:03 -08:00
Ishaan Jaffer
26ea29afd3 test_get_usage_as_dict 2026-02-21 15:39:06 -08:00
Ishaan Jaffer
a58232ac5b fix prisma 2026-02-21 15:35:50 -08:00
Krish Dholakia
1f7eeb274c
Agent Builder - improve rejected response detection based on agent response (#21850)
* fix: feat: add litellm_system_prompt support

* feat: support new 'litellm_agent' model provider

* feat: ui/ - new agent builder ui

* fix(anthropic/chat/transformation.py): normalize max_tokens if decimal

* feat(agentbuilderview.tsx): run compliance datasets against litellm agent

* feat: new response rejection detector

* fix: multiple fixes

* feat: add mcp tools support to agent builder

create an agent with access to llm's + mcp servers
2026-02-21 15:34:42 -08:00
Krish Dholakia
9fc6fd647c
Agent Builder - support new experimental agent builder, to ensure agents pass compliance checks (#21817)
* fix: feat: add litellm_system_prompt support

* feat: support new 'litellm_agent' model provider

* feat: ui/ - new agent builder ui

* fix(anthropic/chat/transformation.py): normalize max_tokens if decimal

* feat(agentbuilderview.tsx): run compliance datasets against litellm agent
2026-02-21 15:32:47 -08:00
Ishaan Jaffer
2acc93e451 BUMP 2026-02-21 15:28:18 -08:00
Ishaan Jaff
bab4127cae
fix(tests): fix flaky test_use_prisma_db_push_flag_behavior (#21849)
Replace Click CliRunner with standalone_mode=False to avoid
"I/O operation on closed file" errors caused by Click's stream
isolation in CI environments.
2026-02-21 15:23:55 -08:00