Ashlr release
Phantom published releases 3.30.67 and 3.30.66. Lexicon and Locus updated documentation on test selection and adapter guidance.
This briefing covers a release from Ashlr’s own developer-tool projects. Product claims come from the linked sources; this is not an independent review.
Phantom merged the release pull request for version 3.30.67. The pull request lists multiple bridge jobs including RQ-DEVINCLOUD-RQ-DVL-BUS-1795344379-N17 and RQ-PHX-DOCSLAND776.
Phantom also merged the release pull request for version 3.30.66. The pull request lists the change RQ-DEVINCLOUD-RQ-DVL-BUS-1795343255-N17.
A Phantom bridge pull request for RQ-DEVINCLOUD-RQ-DVL-BUS-1795343255-N17 added an item kind filter to the unified communications inbox. The pull request says invalid or incorrectly cased values are rejected.
Lexicon merged a bridge pull request that clarified documentation for test-select. The pull request says it chooses tests for reviewed mapped paths and recommends npm test when paths are not mapped.
Locus merged a bridge pull request that updated documentation on adapter registration. The pull request says it added references to consistency checks and clarified credential compatibility including fail-closed behavior for phm resolution from v0.5.1.
Review the updated test selection and adapter documentation in Lexicon and Locus before making path or credential changes.
The Phantom releases incorporate the listed bridge job changes.
Check the release notes for Phantom 3.30.67. Review the new inbox filter behavior if using communications features.
Ashlr tools connected to this story. Review their source and setup requirements.
Work with eligible coding-agent accounts and local models in one workbench; review fleet proposals under signed authority.
Source material behind this briefing. Our practical implications are Ashlr’s interpretation.
This briefing was prepared with AI assistance from the linked sources. The analysis may include interpretation; consult the original sources for complete context. Cover artwork is illustrative.
EngineeringThe briefing
AI-generated illustration
The AI evaluation nonprofit added tasks that require research taste and judgment to its time-horizon evaluation. Frontier models still lag humans on these tasks even while they continue to double the length of verifiable tasks they can complete every four months.


Ashlr release

Keep coding agents scoped to the right client, account, and tenant. Manage identity bindings across command-line tools and MCP connections.
Keep a personal vocabulary of names and speech-to-text corrections in one YAML file, then use it across coding-agent tools, MCP connections, and browser workflows.
Several Phantom pull requests updated the unified inbox to show legacy bus messages and inbox triage counts. Other changes added fleet yield, landed, and pace tools plus documentation updates across projects.
The briefing
AI-generated illustration
Several projects received documentation updates and minor code changes. Phantom added bus status details and supply card support.