vstack 0.54.0

vstack 0.54.0

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==0.54.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.54.0

What changed in this release

One-command CI onboarding.

Added

• vstack-config init-ci — scaffolds a ready-to-run GitHub Actions
  workflow (.github/workflows/vstack-agent-quality.yml) that wires up the
  full gate: diagnose a trace on each PR, fail-on: high, upload SARIF to
  code scanning, and post a sticky PR comment. Pins the Action to the
  installed vstack version. --out / --force / --dry-run like
  install-skills. Takes a repo from "installed" to "gating in CI" in one
  command.

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

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

vstack 0.52.0

vstack 0.52.0

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==0.52.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.52.0

What changed in this release

The Action's CI UX is now complete: gate · annotate · comment.

Added

• GitHub Action comment input + output — set comment: vstack-comment.md
  and the Action writes the findings summary (Markdown) to that path; the
  example workflow posts it as a sticky PR comment via
  marocchino/sticky-pull-request-comment, so findings land in the PR
  conversation (not just the job summary). Complements the existing build
  gate (fail-on) and code-scanning annotations (sarif). +1 test.

Compatibility

• All tests pass. Opt-in; 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

vstack 0.51.0

vstack 0.51.0

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==0.51.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.51.0

What changed in this release

Bring-your-own-traces: import the logs you already have into a vstack trace.

Added

• vstack.ingest — trace importers that build the canonical
  AgentTrace from real data:
  • from_chat_messages(messages, …) — OpenAI/Anthropic chat logs
    ({role, content, tool_calls}); maps system/user/assistant/tool to
    trace steps, infers goal (first user message) + outcome (last
    assistant message), flattens multimodal content.
  • from_otel_spans(spans, …) — OpenTelemetry spans (best-effort; reads
    gen_ai.* attributes as a dict or OTLP {key,value} list, orders by
    start time, classifies GenAI vs other spans).
• vstack-import CLI — vstack-import --format {messages,otel} input.json
  emits an AgentTrace JSON, designed to pipe straight into
  vstack-diagnose --trace -. (CLI surface: 59 → 60.)
• _ingest wired into CI (pytest + ruff + mypy --strict).

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

vstack 0.50.0

vstack 0.50.0

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==0.50.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.50.0

What changed in this release

GitHub Marketplace launch of the Action.

Changed

• action.yml description shortened to 96 chars to meet the GitHub
  Marketplace limit (descriptions must be < 125 characters), so the Action
  can be published/listed in the Marketplace. No behavior change.

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

vstack 0.49.0

vstack 0.49.0

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==0.49.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.49.0

What changed in this release

The CI ratchet — gate only on new findings — plus a vdiff correctness fix.

Added

• vstack-diagnose --baseline <report.json> — compare the current run
  against a saved diagnose report and, with --fail-on, gate only on
  findings that are new relative to the baseline. This is the standard
  ratchet: a gate won't fail on pre-existing, already-accepted findings, and
  it tightens as you re-baseline. Prints a vs baseline: N new, M pre-existing summary to stderr.

Fixed

• vstack.vdiff.diff_reports crashed on real reports. It assumed
  per_pattern was a name-keyed dict, but actual DiagnoseReports (and
  their JSON) carry per_pattern as a list. diff_reports (and therefore
  the vstack-vdiff CLI) raised TypeError on genuine vstack-diagnose
  output; it now normalizes both shapes. Regression test added.

Changed

• _gate_exit_code now takes a list of severities (so the gate can score
  either all findings or only the new ones).

Compatibility

• All tests pass. --baseline is opt-in; 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

vstack 0.48.0

vstack 0.48.0

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==0.48.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.48.0

What changed in this release

SARIF output — vstack findings now flow into GitHub code scanning (Security
tab + PR annotations).

Added

• vstack-diagnose --sarif — emit a SARIF 2.1.0 report instead of
  Markdown/JSON. Each pattern becomes a SARIF rule; each finding a result
  whose level maps from severity (critical/high → error, medium/moderate →
  warning, low/trace → note). Results carry the trace path as their
  artifact location.
• vstack.diagnose.to_sarif(report, *, trace_uri=..., version=...) — the
  public renderer behind the flag.
• GitHub Action sarif input + output — set sarif: vstack.sarif to also
  write a SARIF report (single diagnose run) and upload it with
  github/codeql-action/upload-sarif; the example workflow shows the upload.
  Findings then appear in the Security tab and as inline PR annotations.

Compatibility

• All tests pass (7 SARIF + 1 Action-SARIF test added). No breaking changes —
  --sarif is opt-in.

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

vstack 0.47.0

vstack 0.47.0

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==0.47.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.47.0

What changed in this release

Citability + positioning: a JOSS software-paper draft and a "why vstack"
comparison.

Added

• JOSS paper draft — paper/paper.md (+ paper/paper.bib), a Journal
  of Open Source Software submission draft with a Summary and Statement of
  Need, grounded in vstack's real OB citations (Lewin, Edmondson, Lencioni,
  Tversky & Kahneman, Staw, Latané et al., and others). The ORCID is a
  placeholder flagged for the author to fill before submission.
• "vstack vs. eval/observability" comparison table in the README,
  clarifying that vstack answers why a run failed and what the fix is —
  complementary to eval (pass/fail) and observability (telemetry).
• "Citing vstack" README section pointing at CITATIONS.md,
  CITATION.cff, and the paper.

Changed

• CITATION.cff brought current: version 0.7.0 → 0.47.0, "12 invocation
  surfaces" → 13, and the adapter list updated to all ten frameworks.

Compatibility

• Documentation/metadata only — no code or API changes. All tests pass.

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

vstack 0.46.0

vstack 0.46.0

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==0.46.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.46.0

What changed in this release

A new CI-gate primitive on the core CLI + launch-grade README demo.

Added

• vstack-diagnose --fail-on <severity> — the diagnose CLI is now a
  self-contained CI gate: it exits 3 when any finding is at or above the
  given severity (none…critical), so any CI (not just the GitHub
  Action) can gate on agent quality with one command. Omit the flag to
  never fail on findings (current behavior). The GitHub Action and the
  standalone CLI now share the same severity semantics.
• Launch demo assets — docs/assets/demo.svg (an inline, GitHub-
  rendered terminal card built from real vstack-hello --offline output)
  and docs/assets/demo.cast (an asciinema v2 recording of the session).
  The README now opens with the demo.

Changed

• README hero: added the terminal demo + a one-line "30 seconds, no API
  key" call to action up top.

Compatibility

• All tests pass (new --fail-on gate + helper covered). No breaking
  changes — --fail-on defaults to off.

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

vstack 0.45.0

vstack 0.45.0

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==0.45.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.45.0

What changed in this release

A new invocation surface: vstack now ships as a GitHub Action to gate
agent quality in CI. Thirteen invocation surfaces.

Added

• GitHub Action (uses: valani9/vstack@v0.45.0) — a composite action
  that installs vstack, runs vstack-diagnose on a trace, and fails the
  build when any finding is at or above a fail-on severity threshold
  (none…critical). Inputs: trace, fail-on, mode, recipe,
  client, shape, version, python-version. Outputs: max-severity,
  findings-count, report. Writes a findings table to the job summary.
  client: none (default) runs the deterministic analyzers with no API key
  — a free smoke gate; set a provider for full LLM-backed findings.
  • action.yml (repo root) + .github/action/gate.py (gate logic, reuses
    vstack's own severity_rank) + 9 unit tests, wired into CI.
  • Example consumer workflow:
    examples/github-action/agent-quality-gate.yml.

Compatibility

• All tests pass. 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