Aziel Runtime

Advanced: raw session exec

runtime_session_exec

[advanced/internal] Raw session exec on an already-open session_id (FragGate-admitted). Not fraggate_call and not runtime_run auto-open. Use this when you already have a session_id and were asked for raw session exec. Do not use it for the default agent exec path or opening a session; use fraggate_call or runtime_session_open instead. Side effects are operation-dependent (read, write, or refuse). Does not mint a session_id — missing id fails before admit. Sealed sessions refuse session_closed (409); TTL 6h refuses session_expired (410); receipt cap 64 refuses receipt_cap (409). Rate-limited (exec). Binding-only ops stay per-op proxy_fallback. Prefer fraggate_call. session_id or id, plus slug and op, are required for an explicit exec. 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. payload is optional and engine-specific; leftover keys are not auto-payload the way fraggate_call leftover keys are. Unknown slugs refuse FG-HALLUC-TOOL; stubs refuse FG-STUB. 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 result with engine_slug, engine_op, engine_digest, ran_in, receipt, and refusal when gated.

Input Schema

TableJSON Schema

Name	Required	Description
`id`	No	Alias of session_id. The door accepts either key; do not send two different values.
`op`	Yes	Required allowlisted op. Stubs refuse FG-STUB. UI aliases still forward only after FragGate admit.
`slug`	Yes	Required catalog slug to exec. Alias: product. Unknown slugs refuse FG-HALLUC-TOOL. This tool does not auto-open.
`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.
`outcome`	No	Optional sealed status. completed marks the attempt that finished the action. retry and failed are earlier attempts. Defaults from HTTP status when omitted.
`payload`	No	Optional op payload object. Engine-specific. Unlike fraggate_call, leftover top-level keys are not used as payload.
`product`	No	Alias of slug. Do not send two different values.
`attempt_n`	No	Optional 1-based attempt number. Omitted increments from the prior session receipt with the same request_id, or 1.
`request_id`	No	Optional logical request id shared by retries of one action. Same value across attempts. Omitted mints a new id for this exec.
`session_id`	Yes	Required. Raw session id from runtime_session_open (sess_ + 32 lowercase hex). Alias: id. Missing both fails with session_id required; unknown id returns session_not_found.
`correlation_id`	No	Optional client correlation id. Sealed on the session receipt. Null when omitted.
`parent_receipt_id`	No	Optional prior attempt receipt hash. Null on the first attempt. Omitted links to the prior session receipt with the same request_id. Not FragGate ledger prev.

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	Exec body: session, receipt, engine_slug, engine_op, engine_digest, ran_in, refusal when gated. Errors: session_id required, session_closed, session_expired, receipt_cap, FG-HALLUC-TOOL, FG-STUB.
`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 only provide readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false. The description adds substantial behavioral context: side effects are operation-dependent, missing session_id fails before admit, sealed sessions refuse session_closed (409), TTL 6h refuses session_expired (410), receipt cap 64 refuses receipt_cap (409), rate-limited (exec), binding-only ops stay per-op proxy_fallback, mutation requires confirm=true or dry_run=true, dry_run still returns refusal codes, and confirm is consent not tenant auth. This far exceeds what annotations convey.

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 information-dense and front-loaded with the core purpose, but it is a long wall of text with many clauses packed into a few sentences. Every sentence carries information, but the density makes it harder to parse. It earns a 3 — appropriately sized for the complexity but not well-structured for quick consumption.

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?

Given the tool's complexity (13 params, nested objects, output schema, many refusal codes, routing alternatives), the description covers the critical operational context: when to use, what fails, what refuses, what confirm/dry_run mean, what the return contains, and how it differs from fraggate_call. The output schema exists, so return values need not be re-explained. Nothing essential for correct invocation 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 description coverage is 100%, so the baseline is 3. The description adds meaningful semantics beyond the schema: it explains the q/question/text alternative path where slug is omitted and the mesh router picks a slug/op, clarifies that leftover keys are not auto-payload the way fraggate_call leftover keys are, and explains the confirm/dry_run interaction. It doesn't enumerate every parameter, but the schema already covers them fully. The added semantics about the question-based routing and payload behavior justify a 4.

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 opens with '[advanced/internal] Raw session exec on an already-open session_id (FragGate-admitted)' — a specific verb, resource, and scope. It explicitly distinguishes itself from fraggate_call and runtime_run auto-open, and names sibling tools (fraggate_call, runtime_session_open) for the alternative paths. An agent can immediately tell this is the low-level exec on an existing session, not the default path.

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?

The description gives explicit when-to-use ('when you already have a session_id and were asked for raw session exec') and when-not-to-use ('Do not use it for the default agent exec path or opening a session; use fraggate_call or runtime_session_open instead'). It also states 'Prefer fraggate_call' as a routing preference. This is exemplary usage 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.