vstack 0.36.0

vstack 0.36.0

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==0.36.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.36.0

What changed in this release

Five more feature modules: redaction + health + priority_queue +
snippet + aggregate. Thirty-four feature modules total since v0.23.0.

Added

• vstack.redaction — PII / secret scrubbing for traces.
  RedactionPattern (regex + replacement); built-in
  DEFAULT_PATTERNS covering email, US/CA phone, SSN, credit card,
  AWS access/secret keys, sk-prefixed API keys, Bearer tokens, JWT,
  IPv4, URLs with user:pass@ credentials. Redactor tracks per-
  pattern match counts; scrub_trace() returns a redacted copy of
  the trace with goal/outcome/step content scrubbed (original
  unmutated).
• vstack.health — composite health checks. Check protocol +
  CallableCheck adapter. HealthReport aggregates with
  HEALTHY / DEGRADED / UNHEALTHY status (critical UNHEALTHY →
  UNHEALTHY; non-critical UNHEALTHY → DEGRADED). HealthMonitor
  with tick() (interval-aware) + force_tick() for scheduler-
  driven probes.
• vstack.priority_queue — finding priority queue with aging
  boost. FindingPriorityQueue heap-backed; score = severity_weight
  (high=100/med=10/low=1) × confidence_multiplier (0.5-1.0) +
  age_boost (aging_multiplier × hours_elapsed) + manual_boost.
  boost() / remove_pattern() / snapshot() helpers. Aging
  prevents low-severity starvation.
• vstack.snippet — minimal trace excerpts. find_relevant_steps()
  uses token-overlap (lowercase, stopword-filtered, ≥3 chars)
  between finding text and step content. extract_snippet() pulls
  N context steps around relevant steps with omission counts.
  render_snippet() produces markdown with → markers on relevant
  steps + elision for long content.
• vstack.aggregate — cross-report aggregation. aggregate_reports()
  returns AggregateSummary with per-pattern stats (high/med/low
  • severity_score), severity_counts, agent_counts.
    top_n_patterns() / top_n_agents() (optionally severity-
    filtered), severity_distribution(), cooccurrence_matrix()
    (pairs that appear in the same report).

Changed

• Test count: 3,014 → 3,127 (+113 from the five new modules).

Compatibility

• All 3,127 tests pass (1 skipped: crewai not installed).
• Public API surface strictly expanded.

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 0.35.0

vstack 0.35.0

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==0.35.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.35.0

What changed in this release

Three more feature modules: alerting + eval_gates + intervention_tracker.
Twenty-nine feature modules total since v0.23.0.

Added

• vstack.alerting — multi-channel alert dispatcher. Pluggable
  AlertSink protocol with built-in SlackSink (webhook payload
  • severity emoji), PagerDutySink (Events API v2 + vstack→PD
    severity mapping + dedup_key), WebhookSink (generic JSON POST),
    EmailSink (RFC 5322 envelope), ConsoleSink (stdout),
    NullSink (testing). AlertDispatcher fans out per-alert with
    per-sink retries, severity floors that short-circuit retries, and
    contextvar-based dry-run mode for tests. All sinks accept a
    user-supplied sender callable so network I/O stays out of the
    module's dependencies.
• vstack.eval_gates — CI gate primitives. Gate protocol;
  built-in gates: SeverityCountGate (max findings by severity),
  F1Gate / PrecisionGate / RecallGate (eval metric floors),
  BaselineComparisonGate (max new high findings + max overall-score
  drop), CustomGate (user predicate). GateSet.check() evaluates
  in order, captures gate exceptions as failures, returns
  GateResult with passed flag + exit_code() for CI scripts.
• vstack.intervention_tracker — track applied interventions +
  outcomes. InterventionTracker records remediations with the
  finding snapshot that triggered them. InterventionOutcome enum:
  PENDING / RESOLVED / PARTIAL / NO_EFFECT / REGRESSED / ROLLED_BACK.
  Query by pattern / applied_by / pending / closed. effectiveness_score()
  ranks interventions by efficacy (resolved = 1.0, partial = 0.5,
  no_effect/regressed = 0); rank_patterns_by_effectiveness() surfaces
  which patterns benefit most from intervention.

Changed

• Test count: 2,931 → 3,014 (+83 from the three new modules).

Compatibility

• All 3,014 tests pass (1 skipped: crewai not installed).
• Public API surface strictly expanded.

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 0.34.0

vstack 0.34.0

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==0.34.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.34.0

What changed in this release

Three more feature modules: timeline + cost_sim + findings_router.
Twenty-six feature modules total since v0.23.0.

Added

• vstack.timeline — chronological event view + ASCII
  sparklines. build_timeline() buckets findings by minute /
  hour / day / week (UTC). Timeline exposes peak_bucket,
  velocity per period/hour/day, quiet_bucket count. Bucket
  stacks severities. render_sparkline() produces unicode
  block-char sparklines; render_markdown_timeline() produces
  a tabular report.
• vstack.cost_sim — what-if cost scenarios for production
  budget planning. Scenario parameterizes traces/day, sample
  rate, mode (quick/standard/forensic), pattern list, and
  optional failure_upgrade (10% assumed forensic re-run). Built-
  in per-pattern pricing for all 34 shipped patterns; override
  via custom_pricing. simulate() projects daily / monthly /
  annual cost. compare_scenarios() produces side-by-side
  markdown table.
• vstack.findings_router — smart routing of findings to
  owners / teams with channel metadata (jira_project /
  github_label / pagerduty_service / slack_channel). OwnerRoute
  matches on pattern / severity (with floor) / confidence range.
  FindingsRouter evaluates routes in order, first match wins,
  falls back to default_owner. Assignment carries channel
  routing for downstream issue creation.

Changed

• Test count: 2,863 → 2,931 (+68 from the three new modules).

Compatibility

• All 2,931 tests pass (1 skipped: crewai not installed).
• Public API surface strictly expanded.

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 0.33.0

vstack 0.33.0

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==0.33.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.33.0

What changed in this release

Three more feature modules: export + findings_db + trace_diff.
Twenty-three feature modules total since v0.23.0.

Added

• vstack.export — export findings to CSV / JSON / Markdown /
  Jira ADF / GitHub PR comment. export_csv(), export_json(),
  export_markdown() (severity-grouped), export_jira() (Atlassian
  Document Format), export_github_comment() (PR-comment-sized
  with 65k char truncation, severity emoji 🔴🟡🔵).
• vstack.findings_db — SQLite-backed finding store. FindingsDB
  with auto-schema, store_finding/store_report, find() with rich
  filters (pattern / severity / agent_id / run_id / timestamp range,
  multi-value match, limit), count_by() aggregation, indexes on all
  filter columns. Context-manager safe with del cleanup.
  In-memory or persistent (file) backing.
• vstack.trace_diff — structural comparison of two AgentTraces.
  Myers-style alignment via SequenceMatcher. diff_traces() returns
  TraceDelta with added / removed / changed / unchanged step diffs,
  goal_changed / outcome_changed / success_flipped flags,
  is_regression() / is_recovery() helpers, summary() + to_markdown()
  • to_dict().

Changed

• Test count: 2,799 → 2,863 (+64 from the three new modules).

Compatibility

• All 2,863 tests pass (1 skipped: crewai not installed).
• Public API surface strictly expanded.

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 0.32.0

vstack 0.32.0

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==0.32.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.32.0

What changed in this release

Two more feature modules: budgeter + tracer. Twenty feature
modules total since v0.23.0.

Added

• vstack.budgeter — cost projection + multi-tier budget
  alerts. Companion to vstack.budget for monthly-budget
  forecasting. Budgeter tracks spend events, projects monthly
  total at current burn rate, computes days-until-limit, and
  fires once-each multi-tier alerts at 50/75/90/100% thresholds
  (configurable). forecast_burn() helper for one-shot
  projections.
• vstack.tracer — inline trace recorder for live agents.
  Fluent Tracer builder with thought() / tool_call() /
  observation() / message() / decision() methods, chainable
  return-self pattern. Context manager support: exits mark
  failure on exception. finalize() produces an AgentTrace.

Changed

• Test count: 2,761 → 2,799 (+38 from the two new modules).

Compatibility

• All 2,799 tests pass (1 skipped: crewai not installed).
• Public API surface strictly expanded.

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 0.31.0

vstack 0.31.0

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==0.31.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.31.0

What changed in this release

Two more feature modules: heatmap + policy. Eighteen feature
modules total since v0.23.0.

Added

• vstack.heatmap — ASCII + HTML heatmap visualization.
  build_pattern_dimension_grid() produces pattern × dimension
  grids; build_pattern_trace_grid() produces pattern × trace
  grids. render_heatmap() outputs ASCII art with intensity
  ramp; render_heatmap_html() produces a color-graded HTML
  table (HSL green→red gradient).
• vstack.policy — declarative finding-action policies.
  Rule matches findings on pattern / severity / confidence
  (exact / list / range). Action subclasses: ActionLog,
  ActionAlert, ActionPage, ActionEscalate, ActionIgnore,
  ActionCustom. Policy evaluates rules in order; first match
  wins; default_action for unmatched findings. evaluate_policy()
  produces ordered Decision list. Range matches use
  {"min": 0.7, "max": 1.0}.

Changed

• Test count: 2,719 → 2,761 (+42 from the two new modules).

Compatibility

• All 2,761 tests pass (1 skipped: crewai not installed).
• Public API surface strictly expanded.

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 0.30.0

vstack 0.30.0

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==0.30.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.30.0

What changed in this release

Two more feature modules: veval + recipes_dsl. Sixteen feature
modules total since v0.23.0.

Added

• vstack.veval — pattern-vs-ground-truth evaluation harness.
  EvalCase carries trace + expected severity. EvalHarness.run()
  invokes the pattern, compares predicted vs expected severity,
  returns EvalResult. compute_metrics() produces precision,
  recall, F1, accuracy, and confusion matrix (TP/FP/FN/TN).
  JSON-serializable results.
• vstack.recipes_dsl — declarative YAML/JSON DSL for custom
  recipes. validate_recipe() enforces shape/cluster constraints
  • pattern format. load_recipe_from_dict / load_recipe_from_file
    / load_recipes_from_dir. Built-in minimal YAML parser (falls
    back to PyYAML if installed). RecipeDSL dataclass with full
    metadata pass-through.

Changed

• Test count: 2,678 → 2,719 (+41 from the two new modules).

Compatibility

• All 2,719 tests pass (1 skipped: crewai not installed).
• Public API surface strictly expanded.

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 0.29.0

vstack 0.29.0

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==0.29.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.29.0

What changed in this release

Two more feature modules: signing + synth.

Added

• vstack.signing — HMAC-based integrity signing for reports.
  Signer class with sign/verify methods. Canonical JSON
  serialization for stable hashing. SHA-256 + SHA-512 support.
  VerificationError on signature mismatch. Convenience
  functions sign_report() / verify_report(). Key-order
  independence verified.
• vstack.synth — programmatic synthetic trace generator.
  8 built-in generators: generate_stuck_in_loop,
  generate_hallucination, generate_sycophancy,
  generate_over_apology, generate_premature_completion,
  generate_tool_misuse, generate_anxious_overhedge,
  generate_healthy. Each takes parameters (retry_count,
  turns, etc.) for varying difficulty. generate_batch()
  produces N traces with parameterized seeds for reproducibility.
  Template registry with register_template / get_template /
  list_templates for custom generators.

Changed

• Test count: 2,631 → 2,678 (+47 from the two new modules).

Compatibility

• All 2,678 tests pass (1 skipped: crewai not installed).
• Public API surface strictly expanded.

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 0.28.0

vstack 0.28.0

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==0.28.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.28.0

What changed in this release

Two more feature modules: vbench + markers.

Added

• vstack.vbench — in-process pattern benchmark harness.
  BenchHarness runs patterns × traces × reps and tabulates
  per-run metrics: latency, finding count, severity distribution.
  BenchResult aggregates with Statistics (mean/median/p95/p99).
  compare_results() flags regressions and improvements between
  two results. JSON-serializable.
• vstack.markers — structured markers for trace steps.
  Built-in marker constructors: cost_marker, latency_marker,
  quality_marker, safety_marker. CustomMarker for user-
  defined kinds. attach_marker() stores markers on dict or
  object-style steps. analyze_markers() aggregates across all
  steps with cost rollup, slow-step detection (configurable
  threshold), quality average, blocked-step count, and custom
  marker grouping.

Changed

• Test count: 2,588 → 2,631 (+43 from the two new modules).
• pyproject.toml adds _vbench, _markers to force-include +
  testpaths.

Compatibility

• All 2,631 tests pass (1 skipped: crewai not installed).
• Public API surface strictly expanded.

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 0.27.0

vstack 0.27.0

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==0.27.0

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

Docker:

docker pull ghcr.io/valani9/vstack:0.27.0

What changed in this release

Two more feature modules: calibrate + streaming.

Added

• vstack.calibrate — confidence calibration curves.
  Pure-Python implementations of:
  • IsotonicCalibration: classical pool-adjacent-violators
    isotonic regression. Monotonic by construction. Block
    aggregation algorithm.
  • PlattCalibration: σ(ax+b) sigmoid calibration. Gradient
    descent on log loss.
  • CalibrationMetrics: Brier score, log loss, expected
    calibration error (ECE).
  • evaluate_calibration(): compute all metrics in one pass.
    Curves are JSON-serializable. No dependency on sklearn/scipy.
• vstack.streaming — SSE-friendly event stream for live
  diagnoses. EventStream emits run_started / pattern_started
  / finding_emitted / pattern_completed / run_completed /
  error events. Listener registration (decorator + add_listener),
  wildcard listeners, queue-based iteration, exception-swallowing
  for safe broadcast. SSEStreamWriter converts events to
  Server-Sent Events format for HTTP streaming.

Changed

• Test count: 2,548 → 2,588 (+40 from the two new modules).
• pyproject.toml adds _calibrate, _streaming to force-
  include + testpaths.

Compatibility

• All 2,588 tests pass (1 skipped: crewai not installed).
• Public API surface strictly expanded.

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