Skip to content

docs: state that Agent Skills and Evaluations from Code need 1.0.0 - #149

Merged
ld-paul merged 1 commit into
mainfrom
devin/1792519283-skills-min-version
Oct 29, 2026
Merged

ld-paul merged 1 commit into
mainfrom
devin/1792519283-skills-min-version

Conversation

@ld-paul

@ld-paul ld-paul commented Oct 20, 2026 •

Copy link
Copy Markdown
Contributor

Human

Agent Skills and Evaluations from Code are both in core now, and both need the 1.0.0 release. This PR says so where people read about each feature.

Bot

  • packages/client/README.md: a "Requires @launchdarkly/ai-server 1.0.0 or later (or @launchdarkly/ai-node 1.0.0 or later)" callout at the top of the Agent Skills and Evaluations from Code sections.
  • packages/ai-node/README.md: the Agent Skills and Evaluations from Code paragraphs each state the @launchdarkly/ai-node 1.0.0 floor.

Replaces the earlier version of this PR, which gave 0.4.0 and 0.3.0 floors and described Skills as experimental. Docs only. It lands in 1.0.0 if it merges before #171. The Python half is launchdarkly/python-ai-sdk#191.

🤖 Generated with Claude Code

@devin-ai-integration

Copy link
Copy Markdown
Contributor

I'll fix CI failures and address comments from users with write access. I'll skip comments containing "(aside)".

  • Disable automatic comment, CI, and merge conflict monitoring

@devin-ai-integration
devin-ai-integration Bot marked this pull request as ready for review October 20, 2026 18:44
@ld-paul
ld-paul requested review from atornsii and knfreemLD October 20, 2026 18:46
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
@ld-paul
ld-paul force-pushed the devin/1792519283-skills-min-version branch from 2c9af45 to 7cbff13 Compare October 29, 2026 19:15
@ld-paul ld-paul changed the title docs(skills): state the minimum SDK version for Agent Skills docs: state that Agent Skills and Evaluations from Code need 1.0.0 Oct 29, 2026
@ld-paul
ld-paul merged commit 97113cf into main Oct 29, 2026
13 checks passed
@ld-paul
ld-paul deleted the devin/1792519283-skills-min-version branch October 29, 2026 21:05
ld-paul added a commit to launchdarkly/python-ai-sdk that referenced this pull request Oct 29, 2026
)

# Human

Agent Skills and Evaluations from Code are both in core now, and both
need the 1.0.0 release. This PR says so where people read about each
feature.

# Bot

- `packages/client/README.md`: a "Requires `launchdarkly-ai-server`
1.0.0 or later" callout at the top of the Agent Skills and Run an
evaluation from code sections. Each one notes that upgrading
`launchdarkly-ai-python` alone can leave an older
`launchdarkly-ai-server` installed and gives `pip install --upgrade
"launchdarkly-ai-server>=1.0.0"`.
- `packages/ai/README.md`: the Agent Skills section already stated
1.0.0. The Evaluations from Code paragraph now states it too.

Replaces the earlier version of this PR, which gave a 0.3.0 floor and
described Skills as experimental. Docs only. It lands in 1.0.0 if it
merges before #231.
The JS half is launchdarkly/js-ai-sdk#149.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

<!-- CURSOR_SUMMARY -->
---

> [!NOTE]
> **Overview**
> Documentation now consistently states that **Agent Skills** and
**Evaluations from Code** require **`launchdarkly-ai-server` 1.0.0 or
later**, because those capabilities moved into core at that release.
> 
> In **`packages/client/README.md`**, matching blockquote callouts were
added at the start of the **Run an evaluation from code** and **Agent
Skills** sections. Each explains that older server versions lack the
feature in core, that upgrading **`launchdarkly-ai-python` alone** may
leave an outdated **`launchdarkly-ai-server`** installed, and gives
**`pip install --upgrade "launchdarkly-ai-server>=1.0.0"`**.
> 
> In **`packages/ai/README.md`**, the Evaluations from Code blurb was
aligned with the existing Agent Skills wording by adding the same
**1.0.0** dependency note before the evaluations guide link.
> 
> <sup>Reviewed by [Cursor Bugbot](https://cursor.com/bugbot) for commit
e0abb76. Bugbot is set up for automated
code reviews on this repo. Configure
[here](https://www.cursor.com/dashboard/bugbot).</sup>
<!-- /CURSOR_SUMMARY -->

Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants