Skip to content

armgit / ruflo

Public Imported from GitHub
0

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

3.2 KB
Raw Blame

Changelog: ruflo-ruvector

Newest first. One ## <version> β€” <date> heading per version, then feat:, fix:, breaking: and chore: bullets (ADR-478). Built from git history; older versions: git log -- plugins/ruflo-ruvector.

0.3.8 β€” 2026-10-29

  • chore: operational skills are user-invoked only (disable-model-invocation: true) and long skill/command descriptions are cut to one sentence, so they cost less prompt on every turn (ADR-507, #4588). Every skill is still available as /<skill>.

0.3.7 β€” 2026-10-14

  • fix: vector-hyperbolic no longer claims a normalised text embedding encodes depth (every unit-norm vector lands at the same radius); it now says to set radius from depth and measure on your own tree (#4159, thanks @ronmikailov)

0.3.6 β€” 2026-10-14

  • fix: pin [email protected], which bundles the ONNX wasm that 0.2.25 lacks, so embed text works with no add-on; drop the ruvector-onnx-embeddings-wasm remedy that never fixed it, and refresh the limitation tables against 0.3.3 (optimize, force-learn, midstream now run; 97 MCP tools) (#4158)

0.3.5 β€” 2026-10-12

  • fix: the shared text screen now catches .env and e-mailed credentials, no longer flags a model's token talk (--max-tokens, /oauth/token, "token usage"), and no longer flags values that only name where a secret lives (./service-account.json, --set-secrets=NAME=NAME:latest); every rule stays linear (#4094, thanks @proffesor-for-testing)

0.3.4 β€” 2026-10-05

  • fix: a domain plugin's refusal of another plugin's memory_store no longer claims the write (variant B, review #8)

0.3.3 β€” 2026-10-05

  • fix: shared textsOf reports truncation and every guard fails closed on it

0.3.2 β€” 2026-10-04

  • feat: vendor the flag option parser from one origin with the screen sync and drift check (review #2)
  • fix: one iterative textsOf in the shared screen β€” depth, sibling, size caps, object keys and the invisible-character set fixed at the root (ADR-…
  • fix: secret screen β€” a 20+ char value under a secret-named key is a secret even all-letter or UUID-shaped, unless a clear reference (ADR-445)
  • fix: secret screen judges values, not names β€” fewer false positives, vendor keys, URL credentials, env assignments, 200 KB scan (ADR-445)
  • chore: one source for the secret screen β€” sync-mod-screen.mjs regenerates the shared region of 37 screen.ts copies, --check in all-plugins-smoke (…

0.3.1 β€” 2026-10-04

  • fix: live-check W5 β€” guards read key names and every field; trader gates the package's real order tools

0.3.0 β€” 2026-10-04

  • feat: function-hook mod (ADR-445)

0.2.2 β€” 2026-07-16

  • fix: harden hooks, statusline, security, and plugin MCP integration
  • chore: darwin-plugins iter 3 β€” ruflo-ruvector: fix stale 103 MCP tool count in agent (missed by iter 2)
  • chore: darwin-plugins iter 2 β€” ruflo-ruvector: correct MCP tool count 103β†’91 (verified via mcp tools)
  • chore: darwin-plugins iter 1 β€” ruflo-ruvector: add ADR-112 'Use when' trigger to vector-engineer agent description

0.2.1 β€” 2026-05-04

0.2.0 β€” 2026-04-30

  • feat: upgrade neural-trader, ruvector, rag-memory plugins to wrap npm packages