Skip to content

AgenticX v0.5.0

Choose a tag to compare

@DemonDamon DemonDamon released this 08 Aug 03:01
· 328 commits to main since this release

Published Python package: agenticx==0.5.0

Installation

pip install -U agenticx==0.5.0

PyPI

Highlights

  • Core / Runtime

    • ToolSearch projects only the tools needed each round (with MCP catalog adapter and adaptive threshold/hysteresis), cutting tool-schema bloat on large MCP setups.
    • Stronger turn reliability: stuck-prevention self-healing, futile-resume circuit breaker, empty-tool-turn fallback, truncated-reply auto-retry, and SSE drop / auto-resume continuation.
    • Human-in-the-loop primitives: blocking request_clarification, generic action confirmation, and a canonical assistant-output protocol with terminal reply finalization.
    • Context efficiency: prompt-cache hit awareness, vision-history budget trimming, smarter autocompact driven by token-window usage, and persisted compaction notices across reload.
    • widget_flow_guard auto-retries text “flow diagrams” into proper widget rendering; reasoning chains persist across session reload.
  • Memory

    • Graph search merges into memory_search / recall; chunk composite rerank and access reinforcement improve hit quality.
    • Subject-scoped workspace resolution with group-chat bootstrap; memory_append / memory_search route by subject.
    • Turn-archive recall plus episode governance (retention / natural-language forget) and corrupt Kuzu DB auto-recovery for end users.
  • Skills / Learning

    • Skill self-evolution reaches Hermes-parity gates (GEPA + five quality gates) for safer auto skill creation.
    • In-chat blocking confirm for skill_manage proposals; new research skills code-deep-research and code-module-summaries (custom layout + batch subagent workflow).
  • MCP

    • MCPServerConfig gains transport / url / headers; MCPClientV2 supports streamable-HTTP remote MCP servers.
  • Studio / Server

    • Sub-agent run records + activity timeline with review REST API.
    • video_understand tool (adaptive frame extraction + optional audio transcription).
    • Background bash toolchain for interactive/long-running commands; session completion truth aligned with turn_terminal.
  • Hooks

    • New hook_manage agent tool for conversation-driven hook creation, with safety gating for command-type hooks.

Fixes & Improvements

  • Core / Runtime

    • Hardened LLM stream watchdog / stop spinning; fixed repeated budget compress, same-turn double-compact, and post-compact context-chain breakage that could silently end tasks.
    • Reasoning-only empty turns no longer strand users; streamed reasoning is preserved across fallbacks; GLM stream finalization and inline tool parse improved.
    • Sub-agent completion reliability: fewer false failed judgments, output-path priority over generic path detection, and retry reuse of the original agent_id.
    • Current date/time grounded on the local clock for Desktop and Enterprise runtimes.
  • Memory

    • CJK substring search for workspace memory; sanitize long entries before writing MEMORY.md.
    • Memory-graph stability: empty Qwen ingest handling, episode endpoint NameError, delete deadlocks, and Kuzu DELETE SIGSEGV workarounds via rebuild-style delete.
  • Studio / Server

    • Cold-start empty window fixed (SQLite lock contention + supervisor materialization); restored GroupChatRegistry import that could crash agx serve.
    • Session “false idle” while tool chains were still running; background bash job ownership isolation; document/image hydration before model turns.
    • Meta default workspace unified to ~/.agenticx/workspace and scoped per session where needed.
  • LLMs

    • Keyless intranet OpenAI-compatible gateways; context-window faults classified with compact notices; LiteLLM noise suppressed; MOMA slash model ids routed via openai/ for LiteLLM gateways; Kimi K3 temperature forced to 1.
  • MCP / Skills / Extensions

    • load_mcp_config tolerates per-entry parse failures; default ClawHub market when no registry is configured; third-party skill provenance / source labeling.
  • Packaging

    • Desktop packaging path hardened for ChromaDB collect + BailianEmbedding cross-loop session reuse (keeps local knowledge-base installs usable in bundled backends).

Stats

  • Commits: 706 commits over 63 days (2026-06-06 → 2026-08-08)

Full Changelog