# Agent State Conflict Resolver (`bono718/agent-state-conflict-resolver`) Actor

Resolve conflicting structured state reports using per-field source authority, freshness and explicit invariants. Auditable JSON; abstains on unresolved conflicts.

- **URL**: https://apify.com/bono718/agent-state-conflict-resolver.md
- **Developed by:** [Alessandro Bonometti](https://apify.com/bono718) (community)
- **Categories:** AI, Agents, Developer tools
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $2.00 / 1,000 state reconciliations

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Agent State Conflict Resolver

Resolve conflicting structured reports about the same entity using explicit per-field source authority, freshness and invariants.

For example, Stripe reports payment refunded, a CRM reports payment paid, and a warehouse reports fulfillment shipped. Payment and fulfillment are separate fields: shipped does not contradict refunded automatically. Your contract declares which source has authority for each field and which combinations are forbidden.

### Input

On Apify, paste the contract into the **request** JSON field. HTTP endpoints accept the contract directly.

Required: entity_id, evaluation_time (explicit ISO timestamp), sources, fields and observations. See the prefilled example.

Each field declares source_priority (highest first), max_age_seconds, min_confidence, require_provenance, tie_break (ABSTAIN, LATEST or VERSION), and optionally allowed_values.

Observations contain unique id, entity_id, source_id, field, value, observed_at, optional nonnegative integer version, confidence and provenance reference. Missing confidence is excluded; provenance is required when the field policy says so. Versions are compared only within the winning source, never across unrelated systems.

Optional invariants are explicit implications: {"id":"refund-hold","if":{"field":"payment","equals":"refunded"},"then":{"field":"fulfillment","equals":"held"}}.

### Resolution

1. Validate contract and exclude wrong entity, unauthorized source, stale/future, low confidence, missing provenance or out-of-domain observations.
2. Select the highest-authority eligible source per field.
3. Conflicting values within that source cause abstention by default. LATEST or VERSION may be explicitly enabled; tied winners remain unresolved.
4. Check invariants on the candidate state.
5. Return RESOLVED only when every required field and invariant is resolved. Otherwise canonical_state is null and next_safe_action is ESCALATE.

canonical_state is the state selected under your declared policy, not independently verified real-world truth. candidate_state exposes partial selections for diagnosis. Conflicts, resolved_conflicts, unresolved_conflicts, excluded_observations, provenance and invariant results explain each decision.

Patches are review-only proposals for eligible conflicting observations. They are withheld when anything remains unresolved. Nothing is executed or written to external systems. next_safe_action is limited to USE_CANONICAL_STATE, REVIEW_PATCHES or ESCALATE.

Confidence is the minimum caller-supplied confidence among winning observations. It is not a calibrated truth probability.

### Boundaries

Version 0.1 uses normalized JSON field values and explicit IF-equals / THEN-equals invariants. Object keys are order-independent; arrays are order-sensitive. No LLM inference, free-text interpretation, connector, source authentication, provenance verification, database merge or persistence. Supply source normalization and authority through your integration. This service does not claim to discover semantic equivalence between arbitrary source labels.

At most 100 sources, 100 fields, 1,000 observations and 100 invariants per reconciliation. HTTP gateway body limit: 64 KiB.

### Pricing

One dataset result per reconciliation, including UNRESOLVED results. Invalid contracts fail before producing a result. Consult the live Pricing tab for the current per-result and startup charges.

### Contact

bonometti.work.ai@gmail.com

# Actor input Schema

## `request` (type: `object`):

Structured entity observations, per-field authority policies and optional invariants. See README.

## Actor input object example

```json
{
  "request": {
    "entity_id": "order-42",
    "evaluation_time": "2026-10-18T08:00:00Z",
    "sources": [
      {
        "id": "stripe"
      },
      {
        "id": "crm"
      },
      {
        "id": "warehouse"
      }
    ],
    "fields": {
      "payment": {
        "source_priority": [
          "stripe",
          "crm"
        ],
        "max_age_seconds": 3600,
        "min_confidence": 0.8,
        "require_provenance": true,
        "allowed_values": [
          "paid",
          "refunded"
        ],
        "tie_break": "ABSTAIN"
      },
      "fulfillment": {
        "source_priority": [
          "warehouse"
        ],
        "max_age_seconds": 3600,
        "min_confidence": 0.8,
        "require_provenance": true,
        "allowed_values": [
          "shipped",
          "held"
        ],
        "tie_break": "ABSTAIN"
      }
    },
    "observations": [
      {
        "id": "a",
        "entity_id": "order-42",
        "source_id": "stripe",
        "field": "payment",
        "value": "refunded",
        "observed_at": "2026-10-18T07:55:00Z",
        "confidence": 0.98,
        "provenance": "stripe:event-a"
      },
      {
        "id": "b",
        "entity_id": "order-42",
        "source_id": "crm",
        "field": "payment",
        "value": "paid",
        "observed_at": "2026-10-18T07:59:00Z",
        "confidence": 0.99,
        "provenance": "crm:event-b"
      },
      {
        "id": "c",
        "entity_id": "order-42",
        "source_id": "warehouse",
        "field": "fulfillment",
        "value": "shipped",
        "observed_at": "2026-10-18T07:58:00Z",
        "confidence": 0.95,
        "provenance": "warehouse:event-c"
      }
    ],
    "invariants": []
  }
}
```

# Actor output Schema

## `results` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "request": {
        "entity_id": "order-42",
        "evaluation_time": "2026-10-18T08:00:00Z",
        "sources": [
            {
                "id": "stripe"
            },
            {
                "id": "crm"
            },
            {
                "id": "warehouse"
            }
        ],
        "fields": {
            "payment": {
                "source_priority": [
                    "stripe",
                    "crm"
                ],
                "max_age_seconds": 3600,
                "min_confidence": 0.8,
                "require_provenance": true,
                "allowed_values": [
                    "paid",
                    "refunded"
                ],
                "tie_break": "ABSTAIN"
            },
            "fulfillment": {
                "source_priority": [
                    "warehouse"
                ],
                "max_age_seconds": 3600,
                "min_confidence": 0.8,
                "require_provenance": true,
                "allowed_values": [
                    "shipped",
                    "held"
                ],
                "tie_break": "ABSTAIN"
            }
        },
        "observations": [
            {
                "id": "a",
                "entity_id": "order-42",
                "source_id": "stripe",
                "field": "payment",
                "value": "refunded",
                "observed_at": "2026-10-18T07:55:00Z",
                "confidence": 0.98,
                "provenance": "stripe:event-a"
            },
            {
                "id": "b",
                "entity_id": "order-42",
                "source_id": "crm",
                "field": "payment",
                "value": "paid",
                "observed_at": "2026-10-18T07:59:00Z",
                "confidence": 0.99,
                "provenance": "crm:event-b"
            },
            {
                "id": "c",
                "entity_id": "order-42",
                "source_id": "warehouse",
                "field": "fulfillment",
                "value": "shipped",
                "observed_at": "2026-10-18T07:58:00Z",
                "confidence": 0.95,
                "provenance": "warehouse:event-c"
            }
        ],
        "invariants": []
    }
};

// Run the Actor and wait for it to finish
const run = await client.actor("bono718/agent-state-conflict-resolver").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "request": {
        "entity_id": "order-42",
        "evaluation_time": "2026-10-18T08:00:00Z",
        "sources": [
            { "id": "stripe" },
            { "id": "crm" },
            { "id": "warehouse" },
        ],
        "fields": {
            "payment": {
                "source_priority": [
                    "stripe",
                    "crm",
                ],
                "max_age_seconds": 3600,
                "min_confidence": 0.8,
                "require_provenance": True,
                "allowed_values": [
                    "paid",
                    "refunded",
                ],
                "tie_break": "ABSTAIN",
            },
            "fulfillment": {
                "source_priority": ["warehouse"],
                "max_age_seconds": 3600,
                "min_confidence": 0.8,
                "require_provenance": True,
                "allowed_values": [
                    "shipped",
                    "held",
                ],
                "tie_break": "ABSTAIN",
            },
        },
        "observations": [
            {
                "id": "a",
                "entity_id": "order-42",
                "source_id": "stripe",
                "field": "payment",
                "value": "refunded",
                "observed_at": "2026-10-18T07:55:00Z",
                "confidence": 0.98,
                "provenance": "stripe:event-a",
            },
            {
                "id": "b",
                "entity_id": "order-42",
                "source_id": "crm",
                "field": "payment",
                "value": "paid",
                "observed_at": "2026-10-18T07:59:00Z",
                "confidence": 0.99,
                "provenance": "crm:event-b",
            },
            {
                "id": "c",
                "entity_id": "order-42",
                "source_id": "warehouse",
                "field": "fulfillment",
                "value": "shipped",
                "observed_at": "2026-10-18T07:58:00Z",
                "confidence": 0.95,
                "provenance": "warehouse:event-c",
            },
        ],
        "invariants": [],
    } }

# Run the Actor and wait for it to finish
run = client.actor("bono718/agent-state-conflict-resolver").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "request": {
    "entity_id": "order-42",
    "evaluation_time": "2026-10-18T08:00:00Z",
    "sources": [
      {
        "id": "stripe"
      },
      {
        "id": "crm"
      },
      {
        "id": "warehouse"
      }
    ],
    "fields": {
      "payment": {
        "source_priority": [
          "stripe",
          "crm"
        ],
        "max_age_seconds": 3600,
        "min_confidence": 0.8,
        "require_provenance": true,
        "allowed_values": [
          "paid",
          "refunded"
        ],
        "tie_break": "ABSTAIN"
      },
      "fulfillment": {
        "source_priority": [
          "warehouse"
        ],
        "max_age_seconds": 3600,
        "min_confidence": 0.8,
        "require_provenance": true,
        "allowed_values": [
          "shipped",
          "held"
        ],
        "tie_break": "ABSTAIN"
      }
    },
    "observations": [
      {
        "id": "a",
        "entity_id": "order-42",
        "source_id": "stripe",
        "field": "payment",
        "value": "refunded",
        "observed_at": "2026-10-18T07:55:00Z",
        "confidence": 0.98,
        "provenance": "stripe:event-a"
      },
      {
        "id": "b",
        "entity_id": "order-42",
        "source_id": "crm",
        "field": "payment",
        "value": "paid",
        "observed_at": "2026-10-18T07:59:00Z",
        "confidence": 0.99,
        "provenance": "crm:event-b"
      },
      {
        "id": "c",
        "entity_id": "order-42",
        "source_id": "warehouse",
        "field": "fulfillment",
        "value": "shipped",
        "observed_at": "2026-10-18T07:58:00Z",
        "confidence": 0.95,
        "provenance": "warehouse:event-c"
      }
    ],
    "invariants": []
  }
}' |
apify call bono718/agent-state-conflict-resolver --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,bono718/agent-state-conflict-resolver"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/TIdhzFtgOmhl1x80V/builds/VpfgGBuZGbJry5JCj/openapi.json