Aziel Runtime

Advanced: raw runtime_run

runtime_run

[advanced/internal] Advanced exec façade: admit a slug+op (still DecisionGATE-admitted) and run it through a raw session. Not the default door. Use this when you were explicitly asked for the raw runtime_run path. Do not use it for the default agent exec path or an already-open session you were asked to exec on; use fraggate_call (default) or runtime_session_exec (existing session_id) instead. Side effects are operation-dependent. Not a backdoor past FragGate. Opens a session when session_id is omitted. slug and op are required for an explicit run. A question in q, question, or text with slug omitted asks the mesh router to pick one live Softwares slug and op. That pick does not exec unless confirm=true. dry_run=true returns the pick and writes nothing. session_id optional; omit to auto-open. Extra keys other than payload/session_id may be treated as payload. Mutation requires confirm=true (runtime gate) or dry_run=true (preview only, no write). confirm and dry_run stay optional on inputSchema.required. dry_run still returns FG-HALLUC-TOOL, FG-STUB, FG-UNKNOWN-OP, or FG-LOCAL-ONLY when a confirm call would refuse. confirm is consent, not tenant auth, and it does not upgrade shared public-demo isolation. Returns exec display envelope with session_id, result, engine_digest, ran_in, and refusal when gated.

Input Schema

TableJSON Schema

Name	Required	Description
`op`	Yes	Required allowlisted op. Stubs refuse FG-STUB.
`slug`	Yes	Required catalog slug (or name alias). Unknown slugs refuse FG-HALLUC-TOOL.
`confirm`	No	Documented confirmation flag. Optional in inputSchema.required (connector refresh must not break). tools/call still refuses MCP-CONFIRM-REQUIRED when confirm is missing or false unless dry_run=true. confirm is consent to run the call. It is not tenant auth and it does not upgrade shared public-demo isolation.
`dry_run`	No	Optional preview flag. When true, do not write and do not stamp a ledger tip. Allowlist, hallucination, stub, and local-only checks still run and return the same FragGate refuse code a confirm call would get. MCP-DRY-RUN is returned only when that call would have been allowed to proceed. confirm is consent, not tenant auth, and it does not upgrade shared public-demo isolation.
`payload`	No	Optional op payload object. Engine-specific.
`session_id`	No	Optional existing raw session id. If omitted, a session is opened automatically. Prefer leaving session plumbing invisible unless asked.

Output Schema

TableJSON Schema

Name	Required	Description
`code`	No	FragGate or fabric code when present: FG-OK, FG-HALLUC-TOOL, FG-STUB, FG-LOCAL-ONLY, FG-UNKNOWN-OP, FG-GATE-REFUSE, FG-LAMB-REFUSE, or a module refuse such as MESH-* / AKM-*.
`door`	No	Door name. The public door is fraggate.
`ran_in`	No	Execution locale (for example aziel-runtime) when present.
`result`	No	Machine payload. FragGate-style results commonly include ok, code, slug, op, status, engine_slug, engine_op, engine_digest, ran_in, provenance, refusal, limitations, and ledger_tip.
`status`	No	HTTP-like status when present on wrappers (200 ok; 400+ error / refuse).
`display`	No	Human-facing envelope. Show display.action, title, and summary, then take the next input. Never echo raw tool names.
`receipt`	No	Optional receipt, ledger tip, or TemporalLock/ForgeReceipts exit when the door stamped one.
`refusal`	No	Explicit refuse object, code, or message when the door or engine refused.
`engine_op`	No	Resolved engine op when present (often inside result).
`ledger_tip`	No	Ask/refuse ledger tip when the door stamped one.
`provenance`	No	Provenance / input packet when the pipeline attached one.
`session_id`	No	Raw session id when session plumbing was used. Hidden unless the user asked for the chain.
`engine_slug`	No	Resolved engine slug when present (often inside result).
`limitations`	No	Capability limitations or Remain-OFF notes when present.
`engine_digest`	No	64-hex engine_digest when a true in-process engine ran (often inside result).

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedSep 27, 2026

changedOutput schema / description

Previous value: -"Display envelope shown to the user (display.title / display.summary) plus the machine result. Extra engine fields may appear."New value: +"Display envelope shown to the user (display.action / display.title / display.summary) plus the machine result. Extra engine fields may appear. Do not echo raw tool names."

changedOutput schema / properties / display / description

Previous value: -"Human-facing envelope. Show title and summary, then take the next input."New value: +"Human-facing envelope. Show display.action, title, and summary, then take the next input. Never echo raw tool names."

addedOutput schema / properties / display / properties / action

Added value: +{
+  "description": "Human-visible run frame. Always \"Run aziel runtime\". Product verb titles stay on title. Not a tool name.",
+  "type": "string"
+}

addedOutput schema / properties / display / properties / image

Added value: +{
+  "additionalProperties": true,
+  "description": "Present only when a real production included png_b64, jpeg_b64 (or the same byte family), or a cited http(s) image URL. No invented thumbs. Omitted on dry_run. reviewed is true only when executed production bytes are attached; a dry_run never mints reviewed.",
+  "properties": {
+    "data": {
+      "description": "Base64 image bytes copied from the production. Omitted for a URL-only cite. Never present on dry_run.",
+      "type": "string"
+    },
+    "mimeType": {
+      "description": "Sniffed image media type (image/png, image/jpeg, image/webp, or image/gif).",
+      "type": "string"
+    },
+    "reviewed": {
+      "description": "True only when data came from an executed production. False for a URL cite without bytes. Never true on dry_run.",
+      "type": "boolean"
+    },
+    "source": {
+      "description": "Production field the image was taken from (for example png_b64, jpeg_b64, or image_url).",
+      "type": "string"
+    },
+    "url": {
+      "description": "Cited http(s) image URL when the production named one. Not invented.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

changedOutput schema / properties / display / properties / title / description

Previous value: -"Short result title for the AI client."New value: +"Product verb title for the AI client. Not a raw tool name."

Changed2 schema fields changedSep 25, 2026

changedInput schema / properties / confirm / description

Previous value: -"Documented confirmation flag. Optional in inputSchema.required (connector refresh must not break). tools/call still refuses MCP-CONFIRM-REQUIRED when confirm is missing or false unless dry_run=true (preview, no write)."New value: +"Documented confirmation flag. Optional in inputSchema.required (connector refresh must not break). tools/call still refuses MCP-CONFIRM-REQUIRED when confirm is missing or false unless dry_run=true. confirm is consent to run the call. It is not tenant auth and it does not upgrade shared public-demo isolation."

changedInput schema / properties / dry_run / description

Previous value: -"Optional preview flag. When true, return a would-mutate preview and do not write. Alternative to confirm=true. Does not mutate."New value: +"Optional preview flag. When true, do not write and do not stamp a ledger tip. Allowlist, hallucination, stub, and local-only checks still run and return the same FragGate refuse code a confirm call would get. MCP-DRY-RUN is returned only when that call would have been allowed to proceed. confirm is consent, not tenant auth, and it does not upgrade shared public-demo isolation."

First observedSep 24, 2026

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false, but the description goes well beyond them: side effects are operation-dependent, it is 'not a backdoor past FragGate,' session auto-open behavior is disclosed, dry_run semantics are detailed, refusal codes are enumerated, and confirm is explicitly distinguished from tenant auth. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with 'Advanced exec façade' and 'Not the default door,' but it is a dense wall of text with some redundancy: 'confirm is consent, not tenant auth...' appears in the description and again in schema parameter descriptions, and 'slug and op are required' is repeated. The content is valuable, but structure could be tightened with separation of concerns.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex, advanced internal tool with 6 parameters, nested objects, an output schema, and annotations, the description covers when to use it, when not to, session lifecycle, dry_run behavior, confirm semantics, FragGate refusal behavior, and the return envelope fields. Nothing an agent needs to select or invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds meaningful semantics beyond the schema: extra keys other than payload/session_id may be treated as payload, slug+op are required for an explicit run, and a question in q/question/text with slug omitted triggers mesh-router selection. It also clarifies confirm/dry_run interaction with the runtime gate. Minor redundancy with schema text keeps it from a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('admit a slug+op ... run it through a raw session') and immediately distinguishes itself from siblings: 'Not the default door' and explicit references to fraggate_call and runtime_session_exec. An agent can tell exactly what this tool does and how it differs from nearby alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is explicitly scoped: 'Use this when you were explicitly asked for the raw runtime_run path' and 'Do not use it for the default agent exec path or an already-open session... use fraggate_call (default) or runtime_session_exec (existing session_id) instead.' It also covers the alternative question-routing path when slug is omitted. This is model guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Aziel Runtime tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.