pisama 0.5.6

Multi-agent failure detection for production AI systems

Pisama

Find and fix failures in AI agent systems. No LLM calls required.

Pisama ships 32 core heuristic detectors. They apply across frameworks including n8n, LangGraph, Dify and OpenClaw, with per-platform gating (for example coordination runs only on multi-agent platforms). They run locally with zero LLM cost on the heuristic tier. An archived, in-distribution run on the TRAIL benchmark reports 59.9% joint accuracy (span and category). It is not a held-out result: 144 of the 148 traces appeared in calibration material, and the published archive does not contain the prediction-level data needed to recompute joint accuracy. The public confusion counts do reproduce the reported macro-F1 (0.7535) and micro-F1 (0.7463). See the benchmark evidence and its reproducibility boundary.

Install

pip install pisama

Usage

from pisama import analyze

result = analyze("trace.json")  # also accepts dicts and JSON strings

for issue in result.issues:
    print(f"[{issue.type}] {issue.summary} (severity: {issue.severity})")
    print(f"  Fix: {issue.recommendation}")

CLI

pisama analyze trace.json          # Analyze a trace
pisama watch python my_agent.py    # Watch a live agent (pip install pisama[auto])
pisama replay <trace-id>           # Re-run detection on stored traces
pisama smoke-test --last 50        # Batch test recent traces
pisama detectors                   # List all 32 core detectors
pisama mcp-server                  # Start MCP server (pip install pisama[mcp])

MCP Server

Works in Cursor, Claude Desktop, and Windsurf. No API key is needed:

{
  "mcpServers": {
    "pisama": { "command": "pisama", "args": ["mcp-server"] }
  }
}

Detectors

32 core detectors, gated per platform (n8n, LangGraph, Dify, OpenClaw and others). A representative selection:

Detector	What It Catches
loop	Infinite loops, retry storms, stuck patterns
coordination	Deadlocked handoffs, message storms
hallucination	Factual errors, fabricated tool results
injection	Prompt injection, jailbreak attempts
corruption	State corruption, type drift
persona_drift	Persona drift, role confusion
derailment	Task deviation, goal drift
context	Context neglect, ignored instructions
specification	Output vs. requirement mismatch
communication	Inter-agent message breakdown
decomposition	Poor task breakdown, circular dependencies
workflow	Unreachable nodes, missing error handling
completion	Premature completion, unfinished work
withholding	Suppressed findings, hidden errors
convergence	Metric plateau, regression, thrashing
overflow	Context window exhaustion
propagation	Silent error propagation across steps
citation	Fabricated citations and source misattribution
routing	Inputs misrouted to the wrong specialist agent
mcp_protocol	MCP tool-communication failures

Benchmark Results

TRAIL (trace-level failure detection, 148 traces). Archived April 2026 run, in-distribution and not held out: 144 of 148 traces appeared in calibration material.

Method	Joint Accuracy
Pisama archived run	59.9%

Reproducible from the archive: macro-F1 0.7535, micro-F1 0.7463 (benchmarks/verify_report.py). Joint accuracy is not recomputable from the public archive, which lacks prediction-level data. LLM-judge baselines are omitted here because trail_llm_baselines.json carries confusion counts but "result": null for every model, so no comparable joint-accuracy figure exists in the artifact. See the reproducibility boundary.

Who&When (ICML 2025, multi-agent attribution, 58 hand-crafted cases):

Method	Agent Accuracy	Step Accuracy
GPT-5.4 Mini	60.3%	22.4%
Pisama + Sonnet 4	60.3%	24.1%

Links

• Documentation
• GitHub
• Platform

License

MIT

Source boundary

This repository is the public source for the MIT-licensed pisama Python package. It does not contain the Pisama Cloud backend, dashboard, calibration data, managed detection tiers, or paid automation.