bb00a53786
Put reasoning summary behind feat flag
2026-01-06 11:36:20 +05:30
12f02f6c54
feat: Add GigaChat provider support ( #18564 )
...
* feat: Add GigaChat provider support
Add native support for GigaChat API (Sber AI, Russia's leading LLM).
Supported features:
- Chat completions (sync/async)
- Streaming (sync/async)
- Function calling / Tools
- Structured output via JSON schema (emulated through function calls)
- Image input (base64 and URL)
- Embeddings
Closes #18515
* fix: resolve mypy type errors in GigaChat handler
- Fix _prepare_file_data return type (use 3-tuple for cleaner type flow)
- Add type annotations for lists in _process_content_parts methods
- Add type annotations in _collapse_user_messages
- Use ChatCompletionToolCallChunk for proper tool_use typing
- Add type: ignore[override] for astreaming async generator
* refactor(gigachat): migrate to BaseConfig pattern
* fix: remove unused imports
* fix: resolve mypy type errors
* fix: mypy type errors
* refactor: address review feedback for GigaChat provider
- Remove singleton pattern, reuse litellm HTTPHandler
- Move constants/errors to transformation files, delete common_utils.py
- Add models to model_prices_and_context_window.json
- Fix ssl_verify not passed to HTTP client for embeddings
* docs: update GigaChat documentation with ssl_verify requirement
2026-01-06 10:10:02 +05:30
31470032ad
Merge pull request #18681 from BerriAI/litellm_feat_mcp-server-visibility-configurable
...
[feat] mcp server visibility configurable
2026-01-06 12:53:07 +09:00
29e658012a
docs: add user_mcp_management_mode
2026-01-06 11:43:58 +09:00
375f3ed439
fix: missing mcp_allow_all_ui.png
2026-01-06 11:23:22 +09:00
100f617a8f
Merge pull request #18668 from BerriAI/litellm_feat_noma_mcp_guardrail
...
[feat] add support MCP guardrail to noma
2026-01-06 07:01:57 +09:00
bdd95314a7
docs: mention MCP prompt/resources types in overview
2026-01-06 06:29:37 +09:00
4eecf59f86
feat: add support MCP guardrail to noma
2026-01-06 06:15:56 +09:00
b6a64ff99a
feature/ add qualifire guardrails ( #18594 )
...
* init guardrails
* init guardrails
* some fixes
* some fixes
* ruff
* some fixes
* some fixes
* some fixes
* some fixes
* some fixes
* some fixes
* docs
2026-01-06 01:34:43 +05:30
d8d10f5e25
lasso-guardrail-api docs ( #18652 )
2026-01-05 20:58:26 +05:30
f752ec3eaf
fix
2026-01-05 20:25:39 +05:30
bf1c5bef59
[UI] Add view for estimating costs across requests ( #18645 )
...
* add estimate_cost endpoint
* TestCostEstimateEndpoint
* fix estimate_cost
* add /cost/estimate to spend tracking routes
* fix code QA checks
* fixes endpoint
* v0 cost estimator
* v0 cost estimator
* formatNumberWithCommas
* fix admin view
* docs
* docs fix + export PDF/CSV
* fixes for export
2026-01-05 19:19:58 +05:30
fee9553c51
feat: add allow_all_keys doc
2026-01-05 16:56:19 +09:00
399579f8ea
feat: Add Levo AI integration ( #18529 )
2026-01-05 08:49:21 +05:30
9b1c5f7e36
feat(zai): Add GLM-4.7 model with reasoning support ( #18476 )
...
Add support for Z.AI GLM-4.7, latest flagship model with enhanced reasoning capabilities.
Changes:
- Add zai/glm-4.7 to model pricing with /bin/bash.60/M input, .20/M output
- Add cached input pricing (/bin/bash.11/M) for GLM-4.7
- Add supports_reasoning flag to enable thinking parameter
- Update ZAIChatConfig to support thinking parameter for models with reasoning
- Update documentation with GLM-4.7 as latest flagship model
- Add cached input column to pricing table (GLM-4.7 only)
- Add tests for GLM-4.7 reasoning support and cost calculation
- Update all examples to use GLM-4.7
Model specifications:
- Context: 200K input, 128K output
- Supports: reasoning, function calling, tool choice, prompt caching
- Pricing: Same as GLM-4.6 with cache support
See: https://docs.z.ai/guides/llm/glm-4.7
2026-01-04 00:44:19 +05:30
969790c463
Iam roles anywhere docs ( #18559 )
...
* Add documentation for IAM Roles Anywhere
Co-authored-by: krrishdholakia <krrishdholakia@gmail.com >
* Refactor Bedrock provider docs for IAM Roles Anywhere
Co-authored-by: krrishdholakia <krrishdholakia@gmail.com >
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com >
2026-01-04 00:10:07 +05:30
87fe62229f
feat: Add adopters page and data structure ( #18605 )
...
Co-authored-by: Cursor Agent <cursoragent@cursor.com >
2026-01-03 21:51:19 +05:30
0aae5153b6
docs: Clarify Bedrock AgentCore documentation ( #18603 )
...
Co-authored-by: Cursor Agent <cursoragent@cursor.com >
2026-01-03 16:06:07 +05:30
687adc6024
Add log_format parameter to GenericAPILogger ( #18587 )
...
Adds log_format parameter supporting json_array (default), ndjson, and single formats. NDJSON format enables webhook integrations like Sumo Logic to parse individual log records at ingest time. Defaults to json_array for backward compatibility.
2026-01-02 23:28:30 +05:30
c8bb92afdc
Merge pull request #18579 from BerriAI/litellm_remove_prompt_chaching_header
...
Remove prompt caching headers as the support has been removed
2026-01-02 21:01:50 +05:30
e9365c496d
Merge pull request #18580 from BerriAI/litellm_feat_support_metaurl_on_ui
...
feat: add UI support for configuring meta URLs
2026-01-02 17:54:26 +09:00
edc8413f1e
Add Kubernetes ServiceAccount JWT authentication support ( #18055 )
...
* Allow get_nested_value dot notation to support escaping for Kubernetes JWT Support
* Add support for team and org alias fields, add docs, tests
* Fix lint issue with max statements in handle jwt logic
2026-01-02 14:02:31 +05:30
35f9a75d55
feat: add UI support for configuring meta URLs
2026-01-02 15:07:37 +09:00
ca94990307
remove prompt caching headers as the support has been removed
2026-01-02 11:08:35 +05:30
936aa6821f
[Fix] CI/CD - litellm_security_tests ( #18567 )
2026-01-01 14:20:04 -08:00
a7da4833da
[Fix] CI/CD - check_code_and_doc_quality ( #18560 )
2026-01-01 11:18:59 -08:00
b343d15157
fix: prevent LiteLLM from closing external OTEL spans
2026-01-01 08:28:48 +09:00
b720fba142
Fix formatting in proxy configs documentation
...
Got an error message:
{"error":{"message":"Invalid JSON payload: trailing comma is not allowed: line 8 column 8 (char 141)","type":"invalid_request_error","param":"request_body","code":"400"}}%
2025-12-28 23:48:43 -06:00
9f4a4fd271
Add docs as follow on to #18362 ( #18388 )
2025-12-25 11:08:47 +05:30
1123cfa928
[Feat] AI Gateway - Add support for Platform Fee / Margins ( #18427 )
...
* init cost_margin_config
* feat: add cost margin
* init types
* LITELLM_SETTINGS_SAFE_DB_OVERRIDES
* feat _apply_cost_margin
* ui endpoint
* ui provider margins
* add margin
* refactored ui
* test cost margins
* refactored ui
* provider discounts
* add cost_breakdown to spendLogs
* add CostBreakdownViewer
* fix cost breakdown
* docs fix
* doc margins
* docs margins
2025-12-25 11:07:27 +05:30
42121ad13b
Update minimax docs to be in proper format
2025-12-24 09:25:36 +05:30
55bfb24ef8
Merge pull request #18324 from BerriAI/litellm_feat_dynamic_env_propagation_for_stdio_MCP_server
...
feat: support MCP stdio header env overrides
2025-12-24 06:29:53 +09:00
4f7682f670
[Feat] RAG query endpoint - Add RAG Search / Query endpoint ( #18376 )
...
* add rag query to llm api endpoints
* add rag query as a new endpoint
* docs - new endpoint
* ingest+query
* docs add rag query
2025-12-23 22:30:37 +05:30
0f63cbea59
[Feat] Interactions API - allow using all litellm providers (interactions -> responses api bridge) ( #18373 )
...
* add BaseInteractionsTest
* add interactions_api_handler
* init bridge
* init LiteLLMResponsesInteractionsConfig
* LiteLLMResponsesInteractionsHandler
* mv test
* fixes api spec
* docs
* fix transform+iterators
* docs fix
* fix iterator
2025-12-23 22:30:22 +05:30
c7e0366925
Add support for minmax tts
2025-12-23 21:53:53 +05:30
a2240775c4
correct doc
2025-12-23 21:46:34 +05:30
e18cfc0cf6
corrected provider name
2025-12-23 21:42:51 +05:30
26c0396146
Add documentation for chat compeltion minmax
2025-12-23 17:10:06 +05:30
af8483b37e
Fix: documentation for litellm sdk
2025-12-23 16:27:35 +05:30
0174c56c90
Fix: documentation for litellm sdk
2025-12-23 16:23:53 +05:30
7559869359
Merge branch 'main' into litellm_minmax_anthropic_spec
2025-12-23 16:13:47 +05:30
403875256c
Add minmax documentation
2025-12-23 16:11:26 +05:30
40fac60ea7
docs(openai): fix gpt-5-mini reasoning_effort supported values ( #18346 )
...
Remove 'none' from gpt-5-mini's supported reasoning_effort values in the documentation table. gpt-5-mini does not support reasoning_effort="none", only minimal, low, medium, and high.
2025-12-23 15:50:57 +05:30
c47079ba3a
Merge pull request #18062 from Chesars/fix/groq-deprecated-models
...
fix: remove deprecated Groq models and update model registry
2025-12-23 12:06:27 +05:30
f6350aac9b
Merge pull request #18349 from prasadkona/feat/databricks-partner-integration
...
feat(databricks): Add enhanced authentication, security features, and custom user-agent support
2025-12-23 09:45:28 +05:30
5534038e93
Fix CI: Revert security scan changes and add GitGuardian ignore rules ( #18358 )
2025-12-22 17:03:53 -08:00
87fc81f3e6
Add cloudzero ui docs
2025-12-22 13:19:03 -08:00
d33c54ee0c
Merge branch 'main' into feat/databricks-partner-integration
2025-12-22 12:30:03 -08:00
3a1baae45c
feat(databricks): Add enhanced authentication, security features, and custom user-agent support
...
- Add OAuth M2M (Machine-to-Machine) authentication via DATABRICKS_CLIENT_ID and DATABRICKS_CLIENT_SECRET
- Add Databricks SDK auto-auth with automatic credential discovery
- Add sensitive data redaction for secure logging (tokens, API keys, secrets)
- Add custom user_agent parameter for partner attribution in Databricks telemetry
- Support user_agent in LiteLLM Proxy via config.yaml litellm_params
- Add 49 mocked unit tests for all new functionality
- Add 13 E2E tests for real-world validation (skipped in CI)
- Update documentation with new features and examples
2025-12-22 12:02:51 -08:00
30fa90f70d
[Feat] Enable async_post_call_failure_hook to transform error responses ( #18348 )
2025-12-22 11:24:30 -08:00
Sameer Kankute