A full-page Project Assistant, organization-wide control over remote identity providers, and policy audiences

The Project Assistant grows up: ask it anything from a dedicated full-page chat with starter prompts and your recent conversations, while the docked composer keeps working seamlessly as you move between the two. Organization admins get a new surface to manage remote identity providers, their clients, and active sessions across every project, and policies can now be scoped to specific audiences.

Features

• Full-page Project Assistant chat #3449  - Open the assistant as its own page with a personalized composer, a slash menu of starter prompts, and your recent conversations grouped by time. The dock and the full page share one runtime, so an in-flight reply continues without interruption when you expand the dock into the page. (Author: @adaam2 )
• Organization admin UI for remote identity providers #3404  - Manage remote session issuers, their clients, and sessions across the whole organization from one place: list organizational and project-specific issuers with client counts, drill into each client’s attached MCP servers and sessions, and revoke a single session or all of a client’s sessions. Destructive actions are audited. (Author: @bflad )
• Define audiences when configuring policies #3431  - Scope a policy to specific audiences when you configure it, so the right rules apply to the right callers. (Author: @tgmendes )
• Enterprise onboarding for Cursor and the Anthropic Compliance API #3408  - Configure Cursor and Anthropic Compliance API integrations through optional onboarding steps, with Codex instrumentation and the OpenAI Compliance API shown as coming soon. (Author: @subomi )
• Employee detail drilldowns #3472  - Drill from an employee into their tool logs, agent sessions, and risk events to see exactly what an individual has been doing. (Author: @alx-xo )
• Slack assistants can stay silent when a reply adds no value #3395  - A Slack-connected assistant now decides whether a reply is worthwhile before posting: ambient thread messages can be answered with silence, while @-mentions always get a response. (Author: @simplesagar )
• Parsed objects in MCP tool results #3454  - MCP tool calls that return a JSON object now also include structuredContent, so clients can consume a parsed object instead of re-parsing the text result. (Author: @danielkov )
• Default assistant model upgraded to Claude Opus 4.7 #3446  - Newly created assistants now default to Claude Opus 4.7 for stronger reasoning. Existing assistants are unaffected. (Author: @simplesagar )
• Beta badges for the Project Assistant #3493  - The Project Assistant and the broader Assistants surface are promoted from Preview to Beta, with consistent badges across every entry point. (Author: @simplesagar )
• Unified tool logs #3441  - Tool logs across hosted MCP servers, shadow MCP servers, local tools, and skills now share one view, so all tool activity lives in a single place. (Author: @alx-xo )

Bug fixes

• Project Assistant chat no longer hangs after a tool turn #3497  - Fixed the chat getting stuck loading after a tool-using turn, where the assistant had already replied but the composer stayed disabled. (Author: @danielkov )
• MCP servers screen survives non-critical load failures #3460  - When a non-critical request fails, the screen keeps showing the most recently loaded servers with a subtle “couldn’t refresh” indicator instead of replacing the page with an error. (Author: @danielkov )
• Codex observability install script works without codex on PATH #3400  - The install script now probes well-known locations, including the Codex desktop app bundle, and writes feature flags inside the [features] table to avoid a duplicate-key config error. (Author: @danielkov )
• Codex sessions record the final assistant message #3451  - Codex sessions now capture the final assistant message at the end of a turn, matching Claude Code behavior. (Author: @danielkov )
• Correct RBAC checks in the remote MCP proxy #3405  - Per-tool mcp:connect checks now resolve grants against the same resource as the server-level check, so access decisions stay consistent. (Author: @bflad )