Skip to content

chore: release main - #91

Open
github-actions[bot] wants to merge 1 commit into
mainfrom
release-please--branches--main
Open

github-actions[bot] wants to merge 1 commit into
mainfrom
release-please--branches--main

Conversation

@github-actions

@github-actions github-actions Bot commented Sep 16, 2026

Copy link
Copy Markdown
Contributor

🤖 I have created a release beep boop

launchdarkly-ai-server: 0.2.3

0.2.3 (2026-09-18)

Features

  • AIC-3106: add multimodal history support to graph().invoke() (#26) (c91132d)
  • client: stamp modelKey and modelVersion from _ldMeta on tracking events (ef103d3)
  • client: stamp modelKey and modelVersion from _ldMeta on tracking events (#97) (4e6998a)
  • evaluations: add LD judge event support (#63) (ce61644)

Bug Fixes

  • client: harden model stamps and keep judge results from inheriting parent model identity (5d1e678)
  • client: only stamp a non-empty string modelKey (8424452)
  • evaluations: dedup criteria case-insensitively, matching the API (4126d7b)
  • evaluations: offline judge message_history must carry FORMATTING_INSTRUCTIONS (0b81f4e)
  • evaluations: prefer an exact-provider judge handler over a wildcard (c61b3a5)
  • evaluations: route judge configs to a compatible handler (1a5e099)
  • extract LangChain content-block text and apply model parameters after eval (#80) (a4e1aad)
  • graph: prefer node tools before synthetic handoff routing (#90) (f830b2c)

Documentation

  • evaluations: document criteria, judge handlers, and scoring policy (5f5a626)
  • evaluations: use a customer-style judge key in examples (ceca049)
  • replace stale launchdarkly-ai package name with launchdarkly-ai-python (#40) (3256db7)
launchdarkly-ai-python: 0.1.7

0.1.7 (2026-09-18)

Features

  • evaluations: add LD judge event support (#63) (ce61644)

Documentation

  • evaluations: document criteria, judge handlers, and scoring policy (5f5a626)
  • evaluations: use a customer-style judge key in examples (ceca049)
  • replace stale launchdarkly-ai package name with launchdarkly-ai-python (#40) (3256db7)
launchdarkly-ai-claude-agents: 0.2.3

0.2.3 (2026-09-18)

Features

  • AIC-3106: add multimodal history support to graph().invoke() (#26) (c91132d)

Documentation

  • replace stale launchdarkly-ai package name with launchdarkly-ai-python (#40) (3256db7)
launchdarkly-ai-claude-messages: 0.2.3

0.2.3 (2026-09-18)

Features

  • AIC-3106: add multimodal history support to graph().invoke() (#26) (c91132d)

Documentation

  • replace stale launchdarkly-ai package name with launchdarkly-ai-python (#40) (3256db7)
launchdarkly-ai-openai-agents: 0.2.3

0.2.3 (2026-09-18)

Features

  • AIC-3106: add multimodal history support to graph().invoke() (#26) (c91132d)

Documentation

  • replace stale launchdarkly-ai package name with launchdarkly-ai-python (#40) (3256db7)
launchdarkly-ai-openai-messages: 0.2.3

0.2.3 (2026-09-18)

Features

  • AIC-3106: add multimodal history support to graph().invoke() (#26) (c91132d)

Documentation

  • replace stale launchdarkly-ai package name with launchdarkly-ai-python (#40) (3256db7)
launchdarkly-ai-langchain-agents: 0.2.3

0.2.3 (2026-09-18)

Features

  • AIC-3106: add multimodal history support to graph().invoke() (#26) (c91132d)

Bug Fixes

  • AIC-3382: support Bedrock configs in LangChain handlers (#101) (04a67c7)
  • apply Claude thinking parameters from the evaluated LangChain config (#99) (8be2318)
  • extract LangChain content-block text and apply model parameters after eval (#80) (a4e1aad)

Documentation

  • replace stale launchdarkly-ai package name with launchdarkly-ai-python (#40) (3256db7)
launchdarkly-ai-langchain-messages: 0.2.3

0.2.3 (2026-09-18)

Features

  • AIC-3106: add multimodal history support to graph().invoke() (#26) (c91132d)

Bug Fixes

  • AIC-3382: support Bedrock configs in LangChain handlers (#101) (04a67c7)
  • apply Claude thinking parameters from the evaluated LangChain config (#99) (8be2318)
  • extract LangChain content-block text and apply model parameters after eval (#80) (a4e1aad)

Documentation

  • replace stale launchdarkly-ai package name with launchdarkly-ai-python (#40) (3256db7)

This PR was generated with Release Please. See documentation.


Note

Overview
This is a Release Please cut that bumps published package versions and changelog entries; it does not introduce new runtime code in the diff itself.

launchdarkly-ai-server 0.2.3 (and the launchdarkly-ai-python 0.1.7 barrel) ship the accumulated SDK work called out in the client changelog: multimodal conversation history for graph().invoke(), LaunchDarkly judge evaluation events, modelKey / modelVersion stamping on tracking events from _ldMeta (with hardening so judges do not inherit the parent model identity), judge handler routing and criteria deduplication aligned with the API, graph tool routing that prefers node tools over synthetic handoffs, and LangChain fixes for content-block text and post-eval model parameters.

Integration packages (Claude, OpenAI, LangChain agents/messages) move to 0.2.3 with the same multimodal graph().invoke() note; LangChain packages additionally document Bedrock config support and Claude thinking parameters from evaluated configs. Doc-only churn replaces stale launchdarkly-ai naming with launchdarkly-ai-python in several changelogs.

Reviewed by Cursor Bugbot for commit 6a8d10c. Bugbot is set up for automated code reviews on this repo. Configure here.

@github-actions
github-actions Bot force-pushed the release-please--branches--main branch 2 times, most recently from ef49b82 to 952f7a6 Compare September 16, 2026 23:04
@github-actions
github-actions Bot force-pushed the release-please--branches--main branch 4 times, most recently from 77f2b8a to d13a44a Compare September 18, 2026 21:25
@github-actions
github-actions Bot force-pushed the release-please--branches--main branch from d13a44a to 6a8d10c Compare September 18, 2026 23:22
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant