vstack 0.53.0

vstack 0.53.0

Organizational behavior, practiced on AI agents. vstack is a curated library
of 34 diagnostic patterns drawn from organizational behavior, social psychology,
and group dynamics — each rewritten for the domain of AI agents rather than
human teams.

Install

pip install valanistack==0.53.0

Optional extras: [anthropic], [openai], [ollama], [mcp], [api],
[browser], [langchain], [langgraph], [crewai], [llamaindex],
[pydantic-ai], [adapters], [all].

Docker:

docker pull ghcr.io/valani9/vstack:0.53.0

What changed in this release

vstack-import now reads the two dominant LLM-observability exports.

Added

• vstack.ingest.from_langsmith_runs + vstack-import --format langsmith — convert a LangSmith run (with nested child_runs — a run
  tree) or a flat list of runs into an AgentTrace. Maps run_type
  (llm→message, tool→tool_call, chain→thought, retriever→observation, …);
  uses inputs/outputs/error as step content; infers goal/outcome from
  the root run. The CLI accepts a single run, a list, or {"runs": [...]}.
• vstack-import --format phoenix + extended from_otel_spans — reads
  OpenInference attributes (openinference.span.kind, input.value/
  output.value, llm.input_messages/llm.output_messages), so Arize
  Phoenix span exports import cleanly (the generic otel format now covers
  them too).

Compatibility

• All tests pass. Additive only; no breaking changes.

Verify the install

vstack-doctor          # 25+ install checks
vstack-hello           # 30-second end-to-end demo

Resources

• Docs — hosted mkdocs site
• CHANGELOG — full history
• Patterns index — all 34 patterns + literature anchors
• Security policy