flowchart LR
    Data["CSV / JSON / Live Tool Learning"] -->|"Import & strip secrets"| DB[("SQLite ContextStore\nEntities · Aliases · Parents · Facts")]
    Prompt["User Message\ne.g. 'Any issues for NWH?'"] -->|"Word-boundary + alias\nmatcher (< 2ms)"| Builder["buildTurnContext()\nStrict char/token budget"]
    DB -->|"Matched entity +\nparent + children + facts"| Builder
    Builder -->|"~500–3,500 chars\n(only what matters)"| LLM["Local 4B–9B LLM\n(Ollama / llama.cpp)"]

# Import parent accounts from CSV (with aliases and contact facts)
npx local-llm-context import \
  --db ./my-data.sqlite \
  --file ./accounts.csv \
  --kind account \
  --name account_name \
  --aliases short_code \
  --status status \
  --facts "primary_contact,renewal_date"

# Import child services/domains from JSON and auto-link them to parent accounts
npx local-llm-context import \
  --db ./my-data.sqlite \
  --file ./services.json \
  --kind service \
  --name domain \
  --parent account_name \
  --parent-kind account \
  --status status

# Inspect what exact context block a prompt receives (capped to 3,500 chars)
npx local-llm-context query \
  --db ./my-data.sqlite \
  --prompt "What services belong to NWH and who is the primary contact?"

{
  "mcpServers": {
    "local-context": {
      "command": "npx",
      "args": ["-y", "local-llm-context", "mcp", "--db", "/absolute/path/to/my-data.sqlite"]
    }
  }
}

import {
  ContextStore,
  appendBackgroundNote,
  budgetChatHistory,
  buildTurnContext,
  executeContextTool,
  getContextToolSpecs,
  importJson,
   type ChatTurnMessage,
} from 'local-llm-context';

const store = new ContextStore('./my-data.sqlite');

// 1. Load structured JSON or CSV once (secrets like api_key/password are stripped automatically)
importJson(
  store,
  [
    { name: 'Northwind Health', code: 'NWH', status: 'active', contact: 'dana@example.org' },
  ],
  { kind: 'account', nameField: 'name', aliasFields: ['code'], factFields: ['contact'] },
);

// 2. Per turn: inject ONLY the matched entities (+ parents/children/facts) within a strict budget
const userPrompt = 'Who is our contact at NWH?';
const turnContext = buildTurnContext(userPrompt, store, { budgetChars: 3_500 });

let history: ChatTurnMessage[] = [
  { role: 'system', content: ['You are a concise local assistant.', turnContext].filter(Boolean).join('\n\n') },
  { role: 'user', content: userPrompt },
];

// 3. Safely append background/event notes without overwriting assistant replies or breaking Jinja templates
history = appendBackgroundNote(history, 'Backup job completed at 03:00 UTC.', 'Background Event');

// 4. Normalize orphaned tool calls, strip old <think> traces, and compact stale tool payloads before calling Ollama / llama-server
const safeMessages = budgetChatHistory(history, {
  maxHistoryChars: 48_000,
  staleToolMaxChars: 2_000,
  freshToolMaxChars: 16_000,
});

const response = await fetch('http://127.0.0.1:8080/v1/chat/completions', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    model: 'qwen-local',
    messages: safeMessages,
    tools: getContextToolSpecs().map((t) => ({
      type: 'function',
      function: { name: t.name, description: t.description, parameters: t.parameters },
    })),
  }),
});

npm install
npm test