Skip to content

Commit e3f54e9

Browse files
lnhsinghkatmayb
lnhsingh
and
katmayb
authored
docs: [Self-Hosted Changelog Bot] Changelog updates for new version(s) (#2977)
Automated changelog update created by the LangGraph Server Changelog Bot. Feel free to merge anytime. --------- Co-authored-by: Kathryn May <44557882+katmayb@users.noreply.github.com>
1 parent d448f41 commit e3f54e9

File tree

1 file changed

+125
-0
lines changed

1 file changed

+125
-0
lines changed

‎src/langsmith/self-hosted-changelog.mdx‎

Lines changed: 125 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -10,6 +10,131 @@ rss: true
1010

1111
[Self-hosted LangSmith](/langsmith/self-hosted) is an add-on to the Enterprise plan designed for our largest, most security-conscious customers. For more details, refer to [Pricing](https://www.langchain.com/pricing). [Contact our sales team](https://www.langchain.com/contact-sales) if you want to get a license key to trial LangSmith in your environment.
1212

13+
<Update label="2026-03-07" tags={["self-hosted"]}>
14+
## langsmith-observability-0.2.0
15+
16+
- Implemented async sandbox creation UI with status polling to improve user workflow.
17+
- Enhanced experiment comparison with JSON/YAML syntax highlighting for better readability.
18+
- Improved thread trace open behavior by removing the expand button for a cleaner UI.
19+
- Introduced sandbox endpoint in smith-go to expand sandbox capabilities.
20+
- Updated backend to eliminate n+1 query in `list_personal_access_tokens_for_org` for better performance.
21+
- Supported OpenAI compatible endpoint in smith-polly for broader integration options.
22+
- Timeouts for bulk exports stuck in `CREATED` status to prevent process hanging.
23+
- Made gpt-5.4 the default OpenAI playground model to highlight the new version.
24+
- Added gpt-5.4 and gpt-5.4-pro model support in the playground for enhanced capabilities.
25+
- Enhanced the experiments table with models and prompts columns for better data organization.
26+
- Redesigned custom chart CRUD for an improved user experience.
27+
- Added filtering and grouping by prompt in the experiments table to streamline data handling.
28+
- Addressed agent builder runs rejection issue when limits change for better process control.
29+
- AWS IAM role support added for Agent Builder, Polly, and Insights to enhance security and integration.
30+
- Introduced ABAC-based UI project and run write permissions for refined access control.
31+
- Implemented sticky headers on new messages for better usability.
32+
- Updated Agent Builder with improved inbox counts and thread fetching logic for better message management.
33+
34+
**Download the Helm chart:** [`langsmith-observability-0.2.0.tgz`](https://github.com/langchain-ai/helm/releases/download/langsmith-observability-0.2.0/langsmith-observability-0.2.0.tgz)
35+
</Update>
36+
37+
<Update label="2026-03-07" tags={["self-hosted"]}>
38+
## langsmith-observability-0.2.0
39+
40+
- Fixed an Insights agent bug that was not persisting categories.
41+
- Improved the UI for async sandbox creation with status polling.
42+
- Added JSON/YAML syntax highlighting to the experiment comparison feature.
43+
- Improved thread trace open behavior and removed the expand button in the frontend.
44+
- Added a new sandbox endpoint to smith-go.
45+
- Supported OpenAI-compatible endpoints for smith-polly.
46+
- Fixed the timeout issue with bulk exports stuck in `CREATED` status.
47+
- Allowed service identity access to create repo endpoint.
48+
- Recorded hub prompt commit in experiment session metadata in the playground.
49+
- Improved authorization for the `/sessions` shadow query.
50+
- Added new ABAC backend deployments (v2) for better security management.
51+
- Implemented projects and runs write permissions in the UI.
52+
- Added support for GPT-5.4 and GPT-5.4-pro models, including pricing and playground integration.
53+
- Made GPT-5.4 the default model for the OpenAI playground.
54+
- Increased the maximum number of tags displayed in the RunTags component.
55+
- Fixed an Agent Builder issue where runs were rejected when limits changed.
56+
- Resolved float errors in the `/sessions` go endpoint.
57+
- Ensured Redis cache returns fetched value when cache `SET` fails.
58+
- Supported AWS IAM roles for the Agent Builder, Polly, and Insights integration.
59+
- Improved the custom chart CRUD interface on the frontend.
60+
- Added the ability to filter and group experiments by prompt in the experiments table.
61+
- Updated inbox counts and thread fetching logic in Agent Builder.
62+
63+
**Download the Helm chart:** [`langsmith-observability-0.2.0.tgz`](https://github.com/langchain-ai/helm/releases/download/langsmith-observability-0.2.0/langsmith-observability-0.2.0.tgz)
64+
</Update>
65+
66+
<Update label="2026-03-07" tags={["self-hosted"]}>
67+
## langsmith-observability-0.2.0
68+
69+
- Fixed an Insights agent bug that was not persisting categories.
70+
- Updated the UI for async sandbox creation with status polling.
71+
- Made the logo bigger in the sidebar.
72+
- Added JSON/YAML syntax highlighting to experiment comparisons.
73+
- Improved thread trace open behavior and removed the expand button.
74+
- Eliminated n+1 query in list personal access tokens for the organization.
75+
- Added a sandbox endpoint to smith-go.
76+
- Supported OpenAI compatible endpoint in smith-polly.
77+
- Timed out bulk exports stuck in `CREATED` status.
78+
- Allowed service identity access to create repo endpoint.
79+
- Recorded hub prompt commit in experiment session metadata in the playground.
80+
- Added models and prompts columns to the experiments table.
81+
- Increased maximum tags displayed in the RunTags component.
82+
- Added gpt-5.4 and gpt-5.4-pro model pricing and playground support.
83+
- Made gpt-5.4 the default OpenAI playground model.
84+
- Added support for AWS IAM role in Agent Builder, Polly, and Insights.
85+
- Redesigned custom chart CRUD UI.
86+
- Added functionality to filter and group by prompt in the experiments table.
87+
- Updated inbox counts and thread fetching logic in the Agent Builder.
88+
89+
**Download the Helm chart:** [`langsmith-observability-0.2.0.tgz`](https://github.com/langchain-ai/helm/releases/download/langsmith-observability-0.2.0/langsmith-observability-0.2.0.tgz)
90+
</Update>
91+
92+
<Update label="2026-03-07" tags={["self-hosted"]}>
93+
## langsmith-observability-0.2.0
94+
95+
- Improved UI with async sandbox creation and status polling, enhancing user experience.
96+
- Enhanced experiment comparison with JSON/YAML syntax highlighting.
97+
- Improved thread trace open behavior by removing the expand button.
98+
- Resolved a bug in insights agent that was not persisting categories.
99+
- Fixed bulk exports stuck in CREATED status to improve reliability.
100+
- Increased max tags displayed in the RunTags component in the frontend.
101+
- Improved logo size in the sidebar for better visibility.
102+
- Resolved issues in the backend concerning personal access tokens to enhance performance.
103+
- Enhanced playground with support for GPT-5.4 and GPT-5.4-pro models.
104+
- Made GPT-5.4 the default model in the OpenAI playground.
105+
- Added models and prompts columns to the experiments table for better data visualization.
106+
- Fixed image preview issues with large attachments to improve user experience.
107+
- Introduced sticky headers for new messages to enhance readability.
108+
- Redesigned the custom chart CRUD UI for a more intuitive user interface.
109+
- Added filtering and grouping by prompts in the experiments table for improved data analysis.
110+
- Resolved AWS IAM role support issues for agent builder, Polly, and insights.
111+
- Fixed bugs in the Agent Builder to enhance its reliability and performance.
112+
113+
**Download the Helm chart:** [`langsmith-observability-0.2.0.tgz`](https://github.com/langchain-ai/helm/releases/download/langsmith-observability-0.2.0/langsmith-observability-0.2.0.tgz)
114+
</Update>
115+
116+
<Update label="2026-03-07" tags={["self-hosted"]}>
117+
## langsmith-auth-proxy-0.0.2
118+
119+
- Fixed multiple security alerts in the frontend and backend, enhancing overall system security.
120+
- Fixed a security vulnerability preventing XSS attacks via unescaped URLs in the RichTextEditor.
121+
- Improved self-hosted playground functionality, ensuring better reliability.
122+
123+
**Download the Helm chart:** [`langsmith-auth-proxy-0.0.2.tgz`](https://github.com/langchain-ai/helm/releases/download/langsmith-auth-proxy-0.0.2/langsmith-auth-proxy-0.0.2.tgz)
124+
</Update>
125+
126+
<Update label="2026-03-07" tags={["self-hosted"]}>
127+
## langsmith-0.13.23
128+
129+
- Fixed security vulnerabilities in the smith-frontend and smith-polly components.
130+
- Addressed a code injection vulnerability to enhance application security.
131+
- Restricted the `--allow-run` command to only the deno binary in smith-ace for improved security.
132+
- Prevented XSS in the frontend by ensuring URLs in the RichTextEditor are properly escaped.
133+
- Fixed Playground functionality issues in self-hosted environments.
134+
135+
**Download the Helm chart:** [`langsmith-0.13.23.tgz`](https://github.com/langchain-ai/helm/releases/download/langsmith-0.13.23/langsmith-0.13.23.tgz)
136+
</Update>
137+
13138
<Update label="2026-03-06" tags={["self-hosted"]} rss={{ title: "2026-03-06 - self-hosted" }}>
14139
## langsmith-0.13.21
15140

0 commit comments

Comments
 (0)