Local AI Reply Envelope Schema

The uniform JSON envelope that every Local AI call returns — both the ChatRequest Display action and the AI.Execute script API (canonical surface; legacy alias TK.AIExecute forwards to it) — including success, error, disabled, and truncated cases.

AI Integration → Local AI → Reply Envelope Schema

Why a single envelope

Both Local AI consumer paths return the same JSON shape on every call. The shape is the same for success, for errors, for the master kill-switch being off, and for wall-clock truncation. Customers parse one structure and dispatch on the status field — never on a thrown exception, never on a missing field, never on a special-cased error string.

Schema

{
  "text":      "<the LLM answer text, or empty string on non-ok status>",
  "status":    "ok | error | disabled | truncated",
  "toolTrace": [ ... ],
  "latencyMs": 480,
  "warnings":  [ ... ]
}

Field reference

No optional fields. Every field present on every envelope, every code path. Callers can parse with confidence:

var reply  = JObject.Parse(replyJson);
string status = reply.Value<string>("status");        // never null
long   ms     = reply.Value<long>("latencyMs");       // always parseable
string text   = reply.Value<string>("text") ?? "";    // empty on non-ok

Status values

ok

The LLM POST completed and returned a terminal reply. text contains the model's answer. warnings may still be non-empty if a hook handler threw mid-turn (the chat continues; warnings list the failure).

error

Pre-POST validation failed, or the HTTP call failed, or response parsing failed, or an exception was caught. text is empty. warnings carries the message(s) describing the failure. latencyMs reflects elapsed time to the error point.

disabled

A master gate is off:

• SolutionCapabilities[LocalAI].Enabled = false — applies to BOTH paths.
• SolutionSettings.ModelOptions bit 0x02 (EnableRuntimeMCP) is OFF — applies to ChatRequest only. AI.Execute does not consult this bit.

text is empty. warnings carries the gate identifier so the caller can log which gate blocked the call. latencyMs is 0 (early-exit before any work).

truncated

One of the budget caps tripped mid-turn:

• Wall-clock budget exceeded (default 60 seconds for the full turn).
• Tool-dispatch cap reached (ChatRequest only; the LLM kept asking for more tool calls than the platform permits in one turn).
• Tool-dispatch loop hit the iteration limit before the LLM produced a terminal reply (ChatRequest only).

text carries the partial reply if the LLM produced one before truncation; otherwise empty. warnings describes which cap tripped.

Status decision matrix

Tool trace entry

Each entry in toolTrace[] records one tool dispatch (cached ChatRequest path only — atomic AI.Execute calls always return an empty toolTrace):

{
  "name":      "runtime_get_value",
  "args":      { "tag": "Pump1.MotorCurrent" },
  "result":    { "value": 12.4, "quality": "Good" },
  "status":    "ok",
  "timestamp": "2026-04-26T14:32:15.123Z",
  "elapsedMs": 3
}

JSON examples by status

Successful turn (atomic AI.Execute)

{
  "text": "The likely cause is a partially blocked impeller given the high motor current with low flow rate.",
  "status": "ok",
  "toolTrace": [],
  "latencyMs": 832,
  "warnings": []
}

Successful chat turn with one tool dispatch

{
  "text": "Pump1.MotorCurrent is currently 12.4 A.",
  "status": "ok",
  "toolTrace": [
    {
      "name": "runtime_get_value",
      "args": { "tag": "Pump1.MotorCurrent" },
      "result": { "value": 12.4, "quality": "Good" },
      "status": "ok",
      "timestamp": "2026-04-26T14:32:15.123Z",
      "elapsedMs": 3
    }
  ],
  "latencyMs": 1247,
  "warnings": []
}

Master kill-switch is off

{
  "text": "",
  "status": "disabled",
  "toolTrace": [],
  "latencyMs": 0,
  "warnings": [ "Local AI master kill-switch (SolutionCapabilities[LocalAI].Enabled) is off." ]
}

LLM endpoint unreachable

{
  "text": "",
  "status": "error",
  "toolTrace": [],
  "latencyMs": 1043,
  "warnings": [ "LLM endpoint HTTP error: Connection refused (http://localhost:11434/v1/chat/completions)" ]
}

Wall-clock truncation with partial reply

{
  "text": "Based on the readings I have so far, the early indicators suggest...",
  "status": "truncated",
  "toolTrace": [ /* dispatched tools up to truncation */ ],
  "latencyMs": 60012,
  "warnings": [ "LLM POST wall-clock budget (60s) exceeded." ]
}

Consuming the envelope

From a Server.Class script

// Requires T.Toolkit.LocalAI in NamespaceDeclarations,
// or call as T.Toolkit.LocalAI.AI.Execute(query) fully qualified.
string replyJson = AI.Execute(query);
JObject reply    = JObject.Parse(replyJson);

switch (reply.Value<string>("status"))
{
    case "ok":
        @Tag.Last.Answer = reply.Value<string>("text");
        break;
    case "disabled":
        @Tag.Last.Answer = "Local AI is currently disabled.";
        break;
    case "truncated":
        @Tag.Last.Answer = reply.Value<string>("text");
        // log warnings for diagnostics
        break;
    default: // "error"
        @Tag.Last.Answer = "Could not generate a reply.";
        // warnings array carries the cause
        break;
}

From a Display Action with no scripting

If the reply tag is typed JSON, the platform's tag-method surface lets a Display Expression extract fields directly:

• @Tag.Chat.ReplyJson.JsonString("text") — the answer text.
• @Tag.Chat.ReplyJson.JsonString("status") — the envelope status.
• @Tag.Chat.ReplyJson.JsonValue<long>("latencyMs") — the wall-clock latency.

Wire these into Result expressions on the ChatRequest Action; see ChatRequest Action Reference.

Guarantees

• Always parseable. Every envelope is well-formed JSON. JObject.Parse(reply) never throws on a Local AI reply.
• Field-level stability. Adding new top-level fields in future versions is non-breaking; existing five fields stay present and stay typed as documented.
• No exceptions ever surface to the caller. Network failures, parser failures, gate-off conditions, exceptions in the platform's own LLM-handling code — all become envelopes with status="error" and a populated warnings array.

In this section...