Starstruk Logo MarkStarstruk

v0.6.5

mountain-loop/yaakv0.6.5May 12, 2026by jaberjaber23

AI Summary

Focuses on agent management improvements, introducing new API endpoints for agent activation and cloning, and enhancing the web dashboard with provider overhauls and Telegram integration.

Key Highlights

  • New `agent_activate` tool and endpoint to wake suspended agents
  • New `cloneAgent` API for deep cloning agent templates
  • Server-assigned UUID v4 message IDs for debugging
  • Providers screen overhaul with search, filtering, and grouping
  • Lenient binding parse to prevent entire table drops on malformed entries

New Features

  • Agent activation tool and endpoint
  • Clone agent API
  • Server-assigned message IDs
  • Inference indicator in dashboard
  • Providers screen overhaul
  • Telegram user ID support
  • Lenient binding parse

Full Release Notes

Resolves **8 community issues** + 3 PRs merged from trusted contributors. 2585 tests passing, zero clippy warnings, zero regressions.

### Agents
- **#890** New `agent_activate` tool and `POST /api/agents/{id}/activate` endpoint. Orchestrator agents can wake suspended or crashed peers. Idempotent on Running, rejects Terminated.
- **#868** cloneAgent API. `POST /api/agents/{template_id}/clone` deep-clones a template, applies overrides, assigns a fresh agent ID and workspace path. Excludes `MEMORY.md` so the new agent starts fresh.
- **#869** Server-assigned message IDs. Every `Message` now carries a UUID v4 `msg_id` stamped at construction, plus an optional `provider_msg_id` for debugging. Legacy on-disk sessions get fresh IDs on first load.

### Web Dashboard
- **#1026** Inferencing indicator. Live pulse next to agents currently calling the LLM. Computed from `running_tasks` DashMap.
- **#931** Providers screen overhauled. Search, filter by status, group by category (frontier / oss / aggregator / regional / local), configured providers first.
- **#915** Telegram `user_id` surfaced. `metadata.telegram_user_id` and prompt prefix `[From: Name (tg_id:NNN)]` give agents a stable per-user identifier.

### Channels
- **#1146** Lenient binding parse. One malformed binding entry no longer drops the entire bindings table. Bad entries are logged at ERROR and dropped, survivors pass through.

### Docs
- **#1097** Workspaces gap documented (multi-component refactor needed, design comment posted).
- **#1037** follow-up. `docs/configuration.md` auth posture wording corrected. Middleware fail-closes on authenticated routes but a small set of public routes (health, static, OAuth callback) remain reachable so the login page can render. `OPENFANG_ALLOW_NO_AUTH` opt-in still required for open access.
- **#1175** Getting-started doc links fixed.

### Dependencies
- open 5.3.3 to 5.3.4

### Stats
- 2585 tests passing (+42 from v0.6.4)
- Zero clippy warnings (`--workspace --all-targets`)
- Zero regressions

**Full Changelog**: https://github.com/RightNow-AI/openfang/compare/v0.6.4...v0.6.5