onyx-dot-app/litellm
1
0
Fork 0
mirror of https://github.com/onyx-dot-app/litellm.git synced 2026-07-01 20:44:04 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update docs to reflect session management for all models (#14914)

Browse Source 
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
This commit is contained in:
Teddy Amkie
2025-09-25 15:45:13 -07:00
committed by GitHub
parent 6916bf15de
commit be44735de4
3 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/my-website/docs/response_api.md
+2 -2
View File
@@ -795,9 +795,9 @@ curl http://localhost:4000/v1/responses \
## Session Management - Non-OpenAI Models
## Session Management
LiteLLM Proxy supports session management for non-OpenAI models. This allows you to store and fetch conversation history (state) in LiteLLM Proxy.
LiteLLM Proxy supports session management for all supported models. This allows you to store and fetch conversation history (state) in LiteLLM Proxy.
#### Usage
docs/my-website/release_notes/v1.67.4-stable/index.md
+1 -1
View File
@@ -106,7 +106,7 @@ This release allow you to group requests to LiteLLM proxy into a session. If you
1. Added support for max_completion_tokens parameter [Get Started](https://docs.litellm.ai/docs/providers/sagemaker), [PR](https://github.com/BerriAI/litellm/pull/10300)
- **Responses API**
1. Added support for GET and DELETE operations - `/v1/responses/{response_id}` [Get Started](../../docs/response_api)
2. Added session management support for non-OpenAI models [PR](https://github.com/BerriAI/litellm/pull/10321)
2. Added session management support for all supported models [PR](https://github.com/BerriAI/litellm/pull/10321)
3. Added routing affinity to maintain model consistency within sessions [Get Started](https://docs.litellm.ai/docs/response_api#load-balancing-with-routing-affinity), [PR](https://github.com/BerriAI/litellm/pull/10193)
docs/my-website/static/llms-full.txt
+4 -4
View File
@@ -1699,7 +1699,7 @@ This release allow you to group requests to LiteLLM proxy into a session. If you
1. Added support for max\_completion\_tokens parameter [Get Started](https://docs.litellm.ai/docs/providers/sagemaker), [PR](https://github.com/BerriAI/litellm/pull/10300)
- **Responses API**
1. Added support for GET and DELETE operations - `/v1/responses/{response_id}` [Get Started](https://docs.litellm.ai/docs/response_api)
2. Added session management support for non-OpenAI models [PR](https://github.com/BerriAI/litellm/pull/10321)
2. Added session management support for all supported models [PR](https://github.com/BerriAI/litellm/pull/10321)
3. Added routing affinity to maintain model consistency within sessions [Get Started](https://docs.litellm.ai/docs/response_api#load-balancing-with-routing-affinity), [PR](https://github.com/BerriAI/litellm/pull/10193)
## Spend Tracking Improvements [​](https://docs.litellm.ai/release_notes\#spend-tracking-improvements "Direct link to Spend Tracking Improvements")
@@ -7736,7 +7736,7 @@ This release allow you to group requests to LiteLLM proxy into a session. If you
1. Added support for max\_completion\_tokens parameter [Get Started](https://docs.litellm.ai/docs/providers/sagemaker), [PR](https://github.com/BerriAI/litellm/pull/10300)
- **Responses API**
1. Added support for GET and DELETE operations - `/v1/responses/{response_id}` [Get Started](https://docs.litellm.ai/docs/response_api)
2. Added session management support for non-OpenAI models [PR](https://github.com/BerriAI/litellm/pull/10321)
2. Added session management support for all supported models [PR](https://github.com/BerriAI/litellm/pull/10321)
3. Added routing affinity to maintain model consistency within sessions [Get Started](https://docs.litellm.ai/docs/response_api#load-balancing-with-routing-affinity), [PR](https://github.com/BerriAI/litellm/pull/10193)
## Spend Tracking Improvements [​](https://docs.litellm.ai/release_notes/tags/responses-api\#spend-tracking-improvements "Direct link to Spend Tracking Improvements")
@@ -8295,7 +8295,7 @@ This release allow you to group requests to LiteLLM proxy into a session. If you
1. Added support for max\_completion\_tokens parameter [Get Started](https://docs.litellm.ai/docs/providers/sagemaker), [PR](https://github.com/BerriAI/litellm/pull/10300)
- **Responses API**
1. Added support for GET and DELETE operations - `/v1/responses/{response_id}` [Get Started](https://docs.litellm.ai/docs/response_api)
2. Added session management support for non-OpenAI models [PR](https://github.com/BerriAI/litellm/pull/10321)
2. Added session management support for all supported models [PR](https://github.com/BerriAI/litellm/pull/10321)
3. Added routing affinity to maintain model consistency within sessions [Get Started](https://docs.litellm.ai/docs/response_api#load-balancing-with-routing-affinity), [PR](https://github.com/BerriAI/litellm/pull/10193)
## Spend Tracking Improvements [​](https://docs.litellm.ai/release_notes/tags/security\#spend-tracking-improvements "Direct link to Spend Tracking Improvements")
@@ -8821,7 +8821,7 @@ This release allow you to group requests to LiteLLM proxy into a session. If you
1. Added support for max\_completion\_tokens parameter [Get Started](https://docs.litellm.ai/docs/providers/sagemaker), [PR](https://github.com/BerriAI/litellm/pull/10300)
- **Responses API**
1. Added support for GET and DELETE operations - `/v1/responses/{response_id}` [Get Started](https://docs.litellm.ai/docs/response_api)
2. Added session management support for non-OpenAI models [PR](https://github.com/BerriAI/litellm/pull/10321)
2. Added session management support for all supported models [PR](https://github.com/BerriAI/litellm/pull/10321)
3. Added routing affinity to maintain model consistency within sessions [Get Started](https://docs.litellm.ai/docs/response_api#load-balancing-with-routing-affinity), [PR](https://github.com/BerriAI/litellm/pull/10193)
## Spend Tracking Improvements [​](https://docs.litellm.ai/release_notes/tags/session-management\#spend-tracking-improvements "Direct link to Spend Tracking Improvements")