✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
agents
ai-monitoring
ai-observability
aiengineering
anthropic
datasets
+10 more
evals
langchain
llamaindex
llm-eval
llm-evaluation
llmops
llms
openai
prompt-engineering
smolagents
Affected surfaces
auth
Summary
AI summaryUpdates 17.9.0, Bug Fixes, and 2026-06-19 across a mixed release.
Full changelog
17.9.0 (2026-06-19)
Features
- agents: add PHOENIX_AGENTS_DISABLE_BASH to disable server-side bash (#13841) (0adf1f7)
- agents: add serverside bash tool (#13767) (dceb57c)
- auth: add ROLE_RESYNC for OAuth2 IDPs to preserve manual role overrides (#13838) (585dd40)
- prompts/datasets: filter by label, manage labels from the list, prompt model column (#13830) (669498a)
- pxi: add prompt route contexts (#13834) (4524f82)
- pxi: render every tool call individually with execution summaries (#13824) (279e1f5)
- ui: show usage counts for dataset and prompt labels (#13831) (b9b1589)
Bug Fixes
- agents: explicitly deny network in server bash when web access off (#13842) (dab3a5e)
- app frame corner overlfow (#13832) (4b936e9)
- server: actionable GraphQL errors for opaque node/trace id handling (#13835) (3b40e5c)
- ui: annotation display and summary preview nits (#13829) (8e61d4a)
- ui: show three significant digits in GitHub star count (#13844) (a975add)
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
Related context
Related tools
Earlier breaking changes
- varize-phoenix-v19.0.0 GraphQL createUserApiKey and createSystemApiKey reject API-key callers.
- varize-phoenix-v18.0.0 Changes session time-range filters to use interval-overlap semantics.
- varize-phoenix-v17.0.0 Adds system settings for admin-managed assistant enablement and trace recording policy
- varize-phoenix-v16.0.0 Sandboxing and Code Evaluators introduce breaking changes in Phoenix v16.0.0.
- varize-phoenix-v15.7.0 Removes v1 /chat route and associated code
Beta — feedback welcome: [email protected]