chore(release): v0.0.14#101
Merged
Merged
Conversation
Ships 10 commits worth of features and fixes since v0.0.13: Features - agent: grab_frame tool + Gemini Vision provider + image-in-chat (#96) - dashboard: Chat tab with HTTP+SSE agent gateway (#91) - agent: client-side turn cancellation via Zenoh cancel topic (#94, #95) - chat: multi-provider login status, 404 on unknown agent, Claude OAuth risk warning (#93) - mcp: 'bubbaloop mcp --token' prints bearer token for .mcp.json (#90) Fixes - agent: grab_frame reads binary JPEG payload + JSON metadata attachment from camera nodes (#99) - chat: clear Responding state after multi-camera grab_frame (#98) - mcp: eliminate token race between gateway and agent runtime (#89) Chores - dashboard: remove LibraryView component (#92, replaced by Chat tab) Docs - Comprehensive sync across README, CHANGELOG (backfilled v0.0.8 to v0.0.13), CLAUDE.md, ARCHITECTURE.md, ROADMAP.md, concept/reference/ dashboard docs to match the new feature surface (#100) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Qodo reviews are paused for this user.Troubleshooting steps vary by plan Learn more → On a Teams plan? Using GitHub Enterprise Server, GitLab Self-Managed, or Bitbucket Data Center? |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Cuts v0.0.14 — ships 10 commits worth of features and fixes since v0.0.13.
Highlights
Agent goes vision-capable.
grab_framelets the agent pull a single JPEG from a camera node and feed it to a vision-capable provider (Gemini / Claude). Multi-camera fan-out supported.Dashboard Chat tab. Talk to agents from the browser over HTTP+SSE. Renders tool-call traces inline and surfaces images returned by
grab_frameas inline chat entries.Gemini as the recommended default. Free tier, strong vision. Set
GEMINI_API_KEYor~/.bubbaloop/gemini-key. Claude and Ollama remain fully supported.Turn cancellation. Ctrl-C in the REPL — or the Chat tab's cancel button — publishes to a per-agent Zenoh cancel topic; the daemon aborts the in-flight LLM call.
bubbaloop mcp --token. Prints the stored bearer token so.mcp.jsoncan pick it up without races.Full changelog
See CHANGELOG.md (this PR's branch has the v0.0.14 entry already; v0.0.8 → v0.0.13 backfill landed in #100).
Test plan
cargo check -p bubbaloop --libpassesCargo.toml+Cargo.lockv0.0.14, create GitHub release (triggers binary build workflow)🤖 Generated with Claude Code