Skip to content

chore(release): version packages - #40

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

chore(release): version packages#40
github-actions[bot] wants to merge 1 commit into
mainfrom
changeset-release/main

Conversation

@github-actions

@github-actions github-actions Bot commented Aug 3, 2026

Copy link
Copy Markdown
Contributor

This PR was opened by the Changesets release GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated.

Releases

bazilion@0.12.0

Minor Changes

  • 6991fde Thanks @rullopat! - Add an opt-in reviewed learning loop for long-lived Agents. Successful user turns can enqueue
    durable, restricted background reviews that produce evidence-backed private or shared lesson
    proposals. Operators can configure cadence/model/reasoning, inspect and edit proposals, approve or
    reject them, and later revoke approved lessons through authenticated HTTP, CLI, and the Agent
    Learning web tab. Approved private lessons enter only that Agent's prompt; shared lessons become
    deterministic Team-memory notes.

  • f0395a7 Thanks @rullopat! - Add a durable agent-message loop circuit breaker. Messages now retain causal
    chain and hop metadata, inbox wake turns propagate that ancestry even when an
    Agent omits reply_to, and the daemon rejects over-budget sends before they can
    wake another LLM turn. Configure the ceiling with
    BAZILION_AGENT_LOOP_MAX_HOPS; inspect payload-free stop events through the
    Agent API, bazilion inbox loop-breaks, or the web inbox.

@bazilion/api-types@0.12.0

Minor Changes

  • 6991fde Thanks @rullopat! - Add an opt-in reviewed learning loop for long-lived Agents. Successful user turns can enqueue
    durable, restricted background reviews that produce evidence-backed private or shared lesson
    proposals. Operators can configure cadence/model/reasoning, inspect and edit proposals, approve or
    reject them, and later revoke approved lessons through authenticated HTTP, CLI, and the Agent
    Learning web tab. Approved private lessons enter only that Agent's prompt; shared lessons become
    deterministic Team-memory notes.

  • f0395a7 Thanks @rullopat! - Add a durable agent-message loop circuit breaker. Messages now retain causal
    chain and hop metadata, inbox wake turns propagate that ancestry even when an
    Agent omits reply_to, and the daemon rejects over-budget sends before they can
    wake another LLM turn. Configure the ceiling with
    BAZILION_AGENT_LOOP_MAX_HOPS; inspect payload-free stop events through the
    Agent API, bazilion inbox loop-breaks, or the web inbox.

@bazilion/client@0.12.0

Minor Changes

  • f0395a7 Thanks @rullopat! - Add a durable agent-message loop circuit breaker. Messages now retain causal
    chain and hop metadata, inbox wake turns propagate that ancestry even when an
    Agent omits reply_to, and the daemon rejects over-budget sends before they can
    wake another LLM turn. Configure the ceiling with
    BAZILION_AGENT_LOOP_MAX_HOPS; inspect payload-free stop events through the
    Agent API, bazilion inbox loop-breaks, or the web inbox.

Patch Changes

@github-actions
github-actions Bot force-pushed the changeset-release/main branch from ffc2426 to 90e22f9 Compare August 4, 2026 16:25
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.

0 participants