Skip to main content
Glama

Advanced: raw runtime_run

runtime_run

Execute a cataloged operation via raw session. Supports confirm for mutations and dry_run for preview, with gated refusal codes.

Instructions

[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. 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
NameRequiredDescriptionDefault
opYesRequired allowlisted op. Stubs refuse FG-STUB.
slugYesRequired catalog slug (or name alias). Unknown slugs refuse FG-HALLUC-TOOL.
confirmNoDocumented 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_runNoOptional 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.
payloadNoOptional op payload object. Engine-specific.
session_idNoOptional existing raw session id. If omitted, a session is opened automatically. Prefer leaving session plumbing invisible unless asked.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
codeNoFragGate 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-*.
doorNoDoor name. The public door is fraggate.
ran_inNoExecution locale (for example aziel-runtime) when present.
resultNoMachine 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.
statusNoHTTP-like status when present on wrappers (200 ok; 400+ error / refuse).
displayNoHuman-facing envelope. Show title and summary, then take the next input.
receiptNoOptional receipt, ledger tip, or TemporalLock/ForgeReceipts exit when the door stamped one.
refusalNoExplicit refuse object, code, or message when the door or engine refused.
engine_opNoResolved engine op when present (often inside result).
ledger_tipNoAsk/refuse ledger tip when the door stamped one.
provenanceNoProvenance / input packet when the pipeline attached one.
session_idNoRaw session id when session plumbing was used. Hidden unless the user asked for the chain.
engine_slugNoResolved engine slug when present (often inside result).
limitationsNoCapability limitations or Remain-OFF notes when present.
engine_digestNo64-hex engine_digest when a true in-process engine ran (often inside result).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.0.8
    • 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."
  2. Changed3 schema fields changedv2.0.2
    • changedInput schema / description
      Previous value: -"slug and op are required. Extra keys other than payload/session_id may be treated as payload."New value: +"slug and op are required. Extra keys other than payload/session_id may be treated as payload. Mutation requires confirm=true or dry_run=true."
    • addedInput schema / properties / confirm
      Added value: +{
      +  "description": "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).",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / dry_run
      Added value: +{
      +  "description": "Optional preview flag. When true, return a would-mutate preview and do not write. Alternative to confirm=true. Does not mutate.",
      +  "type": "boolean"
      +}
  3. Changed7 schema fields changedv1.6.2
    • addedInput schema / description
      Added value: +"slug and op are required. Extra keys other than payload/session_id may be treated as payload."
    • addedInput schema / properties / op / description
      Added value: +"Required allowlisted op. Stubs refuse FG-STUB."
    • addedInput schema / properties / payload / additionalProperties
      Added value: +true
    • addedInput schema / properties / payload / description
      Added value: +"Optional op payload object. Engine-specific."
    • addedInput schema / properties / session_id / description
      Added value: +"Optional existing raw session id. If omitted, a session is opened automatically. Prefer leaving session plumbing invisible unless asked."
    • addedInput schema / properties / slug / description
      Added value: +"Required catalog slug (or name alias). Unknown slugs refuse FG-HALLUC-TOOL."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "description": "Display envelope shown to the user (display.title / display.summary) plus the machine result. Extra engine fields may appear.",
      +  "properties": {
      +    "code": {
      +      "description": "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-*.",
      +      "type": "string"
      +    },
      +    "display": {
      +      "additionalProperties": true,
      +      "description": "Human-facing envelope. Show title and summary, then take the next input.",
      +      "properties": {
      +        "fields": {
      +          "description": "Optional labeled scalars copied from the result for display.",
      +          "items": {
      +            "additionalProperties": true,
      +            "properties": {
      +              "label": {
      +                "description": "Field label.",
      +                "type": "string"
      +              },
      +              "value": {
      +                "description": "Field value as text.",
      +                "type": "string"
      +              }
      +            },
      +            "type": "object"
      +          },
      +          "type": "array"
      +        },
      +        "next": {
      +          "description": "What the agent should do after showing this output.",
      +          "type": "string"
      +        },
      +        "summary": {
      +          "description": "One-line outcome or refuse reason.",
      +          "type": "string"
      +        },
      +        "title": {
      +          "description": "Short result title for the AI client.",
      +          "type": "string"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "door": {
      +      "description": "Door name. The public door is fraggate.",
      +      "type": "string"
      +    },
      +    "engine_digest": {
      +      "description": "64-hex engine_digest when a true in-process engine ran (often inside result).",
      +      "type": "string"
      +    },
      +    "engine_op": {
      +      "description": "Resolved engine op when present (often inside result).",
      +      "type": "string"
      +    },
      +    "engine_slug": {
      +      "description": "Resolved engine slug when present (often inside result).",
      +      "type": "string"
      +    },
      +    "ledger_tip": {
      +      "description": "Ask/refuse ledger tip when the door stamped one."
      +    },
      +    "limitations": {
      +      "description": "Capability limitations or Remain-OFF notes when present."
      +    },
      +    "provenance": {
      +      "description": "Provenance / input packet when the pipeline attached one."
      +    },
      +    "ran_in": {
      +      "description": "Execution locale (for example aziel-runtime) when present.",
      +      "type": "string"
      +    },
      +    "receipt": {
      +      "description": "Optional receipt, ledger tip, or TemporalLock/ForgeReceipts exit when the door stamped one."
      +    },
      +    "refusal": {
      +      "description": "Explicit refuse object, code, or message when the door or engine refused."
      +    },
      +    "result": {
      +      "description": "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."
      +    },
      +    "session_id": {
      +      "description": "Raw session id when session plumbing was used. Hidden unless the user asked for the chain.",
      +      "type": "string"
      +    },
      +    "status": {
      +      "description": "HTTP-like status when present on wrappers (200 ok; 400+ error / refuse).",
      +      "type": "integer"
      +    }
      +  },
      +  "type": "object"
      +}
  4. Changed4 schema fields changed
    • removedInput schema / properties / op / description
      Removed value: -"Product verb, e.g. fold-preview, submit, score"
    • removedInput schema / properties / payload / description
      Removed value: -"What the software needs as input"
    • removedInput schema / properties / session_id / description
      Removed value: -"Optional. Reuse an open session."
    • removedInput schema / properties / slug / description
      Removed value: -"Product slug, e.g. foldlock, godlock, azclce"
  5. First observedv1.5.0

TDQS

A4.8/5.0
Behavior5/5

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

Adds substantial runtime behavior beyond annotations: mutation requires confirm=true or dry_run=true, dry_run still runs gate checks and returns FragGate refusal codes, a session auto-opens when session_id is omitted, and confirm is consent but not tenant auth. This materially affects call outcomes and is exactly the kind of context an agent needs.

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

Conciseness4/5

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

Dense but front-loaded with the critical 'not the default door' caveat and alternatives before the details. Some sentences repeat schema parameter descriptions, especially the confirm-is-consent caveat, so it is slightly longer than strictly necessary; however, every sentence carries useful operational context.

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 high-complexity advanced façade with sparse annotations, the description covers invocation context, mutation gating, dry-run preview semantics, refusal codes, session handling, and the return envelope shape. Nothing essential is left to inference, and the existing output schema covers structured returns.

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% and the schema already documents each parameter well, so the baseline is 3. The description adds cross-parameter semantics: slug+op are required, extra keys other than payload/session_id may be treated as payload, and confirm/dry_run are optional in the schema but enforced at runtime.

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?

Identifies a specific façade contract: admit slug+op and run it through a raw session while still DecisionGATE-admitted. It explicitly contrasts this path with fraggate_call and runtime_session_exec, so an agent can distinguish the raw internal door from the default/alternate doors.

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?

Explicitly states the only trigger condition: use this when explicitly asked for the raw runtime_run path. It also names the two alternatives with the conditions that select them (default agent exec path -> fraggate_call, already-open session -> runtime_session_exec), and adds a negative guardrail: not a backdoor past FragGate.

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