scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-04 02:31:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 70

docs

Browse source
This commit is contained in:
Ishaan Jaffer 2026-02-14 16:23:13 -08:00
parent 7c8bea3551
commit 112624c146
3 changed files with 18 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/my-website/docs/proxy/guardrails/policy_templates.md
View file

@ -16,8 +16,6 @@ Policy templates provide pre-configured guardrail policies that you can use as a
6. Review and customize the pre-filled policy form
7. Click **"Create Policy"** to save
![Policy Templates UI](/img/policy_templates_ui.png)
### Workflow
```

7
docs/my-website/package-lock.json generated
View file

@ -20455,6 +20455,13 @@
"url": "https://opencollective.com/webpack"
}
},
"node_modules/search-insights": {
"version": "2.17.3",
"resolved": "https://registry.npmjs.org/search-insights/-/search-insights-2.17.3.tgz",
"integrity": "sha512-RQPdCYTa8A68uM2jwxoY842xDhvx3E5LFL1LxvxCNMev4o5mLuokczhzjAgGwUZBAmOKZknArSxLKmXtIi2AxQ==",
"license": "MIT",
"peer": true
},
"node_modules/section-matter": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/section-matter/-/section-matter-1.0.0.tgz",

24
docs/my-website/release_notes/v1.81.12.md
View file

@ -1,5 +1,5 @@
---
title: "[Preview] v1.81.12 - Guardrail Pipelines, MCP OAuth2 M2M, Scaleway Provider"
title: "[Preview] v1.81.12 - Guardrail Policy Templates & Action Builder"
slug: "v1-81-12"
date: 2026-02-14T00:00:00
authors:
@ -18,7 +18,6 @@ hide_table_of_contents: false
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
import Image from '@theme/IdealImage';
<Tabs>
<TabItem value="docker" label="Docker">
@ -42,12 +41,12 @@ pip install litellm==1.81.12.rc1
## Key Highlights
- **Guardrail Pipelines & Policy Templates** - [Add conditional sequential execution for guardrail pipelines and pre-configured policy templates for NSFW, toxic content, and child safety filtering](../../docs/proxy/guardrails)
- **Guardrail Pipelines & Policy Templates** - [Add conditional sequential execution for guardrail pipelines and pre-configured policy templates for NSFW, toxic content, and child safety filtering](../../docs/apply_guardrail)
- **MCP OAuth2 M2M + Discovery UI + Tracing** - [Machine-to-machine OAuth2 for MCP servers, a discovery UI for browsing available MCP servers, and OpenTelemetry tracing for MCP calls](../../docs/mcp)
- **Scaleway Provider** - [New Scaleway provider for chat completions](../../docs/providers/scaleway)
- **Responses API Enhancements** - [Server-side context management (compaction) and Shell tool support for the OpenAI Responses API](../../docs/response_api)
- **Access Groups** - [Create access groups to manage model, MCP server, and agent access across teams and keys](../../docs/proxy/access_groups)
- **60+ New Bedrock Models** - DeepSeek V3.2, MiniMax M2.1, Kimi K2.5, Qwen3 Coder Next, and NVIDIA Nemotron Nano across multiple regions
- **Access Groups** - [Create access groups to manage model, MCP server, and agent access across teams and keys](../../docs/proxy/model_access_groups)
- **50+ New Bedrock Regional Model Entries** - DeepSeek V3.2, MiniMax M2.1, Kimi K2.5, Qwen3 Coder Next, and NVIDIA Nemotron Nano across multiple regions
- **Perplexity Research API** - [Use Perplexity's Research API with preset search and provider-specific model routing](../../docs/providers/perplexity)
---
@ -65,7 +64,7 @@ pip install litellm==1.81.12.rc1
## New Models / Updated Models
#### New Model Support (30+ new models)
#### New Model Support (19 highlighted models)
| Provider | Model | Context Window | Input ($/1M tokens) | Output ($/1M tokens) |
| -------- | ----- | -------------- | ------------------- | -------------------- |
@ -107,7 +106,6 @@ pip install litellm==1.81.12.rc1
- Extend model support with 4 new beta models - [PR #21035](https://github.com/BerriAI/litellm/pull/21035)
- Add Claude Opus 4.6 to `_supports_tool_search_on_bedrock` - [PR #21017](https://github.com/BerriAI/litellm/pull/21017)
- Correct Bedrock Claude Opus 4.6 model IDs (remove `:0` suffix) - [PR #20564](https://github.com/BerriAI/litellm/pull/20564), [PR #20671](https://github.com/BerriAI/litellm/pull/20671)
- Fix Azure batches issues - [PR #21092](https://github.com/BerriAI/litellm/pull/21092)
- Add `output_config` as supported param - [PR #20748](https://github.com/BerriAI/litellm/pull/20748)
- **[Vertex AI](../../docs/providers/vertex)**
@ -140,6 +138,7 @@ pip install litellm==1.81.12.rc1
- **[Azure AI](../../docs/providers/azure_ai)**
- Add `azure_ai/kimi-k2.5` to Azure model DB - [PR #20896](https://github.com/BerriAI/litellm/pull/20896)
- Support Azure AD token auth for non-Claude azure_ai models - [PR #20981](https://github.com/BerriAI/litellm/pull/20981)
- Fix Azure batches issues - [PR #21092](https://github.com/BerriAI/litellm/pull/21092)
- **[DeepSeek](../../docs/providers/deepseek)**
- Sync DeepSeek model metadata and add bare-name fallback - [PR #20938](https://github.com/BerriAI/litellm/pull/20938)
@ -161,7 +160,7 @@ pip install litellm==1.81.12.rc1
- Fix `get_supported_anthropic_messages_params` - [PR #20752](https://github.com/BerriAI/litellm/pull/20752)
- Fix `base_model` name for body and deployment name in URL - [PR #20747](https://github.com/BerriAI/litellm/pull/20747)
- **[Azure](../../docs/providers/azure)**
- **[Azure](../../docs/providers/azure/azure)**
- Preserve `content_policy_violation` error details from Azure OpenAI - [PR #20883](https://github.com/BerriAI/litellm/pull/20883)
- **[Vertex AI](../../docs/providers/vertex)**
@ -268,7 +267,7 @@ pip install litellm==1.81.12.rc1
### Logging
- **[PostHog](../../docs/observability/posthog)**
- **[PostHog](../../docs/observability/posthog_integration)**
- Fix JSON serialization error for non-serializable objects - [PR #20668](https://github.com/BerriAI/litellm/pull/20668)
- **[Prometheus](../../docs/proxy/logging#prometheus)**
@ -302,11 +301,11 @@ pip install litellm==1.81.12.rc1
- Agent Guardrails on streaming output - [PR #21206](https://github.com/BerriAI/litellm/pull/21206)
- Pipeline flow builder UI - [PR #21188](https://github.com/BerriAI/litellm/pull/21188)
- **[Zscaler AI Guard](../../docs/proxy/guardrails)**
- **[Zscaler AI Guard](../../docs/apply_guardrail)**
- Zscaler AI Guard bug fixes and support during post-call - [PR #20801](https://github.com/BerriAI/litellm/pull/20801)
- Zscaler AI Guard UI - [PR #21077](https://github.com/BerriAI/litellm/pull/21077)
- **[ZGuard](../../docs/proxy/guardrails)**
- **[ZGuard](../../docs/apply_guardrail)**
- Add team policy mapping for ZGuard - [PR #20608](https://github.com/BerriAI/litellm/pull/20608)
- **General**
@ -340,7 +339,6 @@ pip install litellm==1.81.12.rc1
- **Fix MCP StreamableHTTP backend** - Use `anyio.fail_after` instead of `asyncio.wait_for` - [PR #20891](https://github.com/BerriAI/litellm/pull/20891)
- **Inject `NPM_CONFIG_CACHE`** into STDIO MCP subprocess env - [PR #21069](https://github.com/BerriAI/litellm/pull/21069)
- **Block spaces and hyphens** in MCP server names and aliases - [PR #21074](https://github.com/BerriAI/litellm/pull/21074)
- **Use Authorization Bearer** for OAuth tokens instead of x-api-key - [PR #21039](https://github.com/BerriAI/litellm/pull/21039)
---
@ -373,7 +371,7 @@ pip install litellm==1.81.12.rc1
---
## Documentation Updates (12 updates)
## Documentation Updates (14 updates)
- LiteLLM Observatory section added to v1.81.9 release notes - [PR #20675](https://github.com/BerriAI/litellm/pull/20675)
- Callback registration optimization added to release notes - [PR #20681](https://github.com/BerriAI/litellm/pull/20681)