Skip to main content
Glama

LogNexus State: Set active subtask and file contract

lognexus_state_set_task

Marks a subtask as in progress and persists its delegation contract—allowed/forbidden files, decision budget, verification command—plus active issue tier so commit and audit enforce scope.

Instructions

Mark a subtask as in progress and persist its closed delegation contract (allowed files, forbidden files, decision budget, verification command) plus the active issue tier. Equivalent to 'lognexus state set-task [title]'. Use when you begin a new subtask and need the file scope enforced by the commit engine and the audit. Not for marking a subtask complete (use lognexus_state_finish_task) and not for reading the contract (use lognexus_state_get).

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "tier": "tier-3",
      "title": "Remove dead telemetry dispatch",
      "taskId": "T1",
      "allowedFiles": [
        "src/telemetry/collector.ts"
      ],
      "decisionBudget": "none",
      "forbiddenFiles": [
        "package.json"
      ],
      "verificationCmd": "npm test"
    },
    "name": "lognexus_state_set_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
tierNoOperational routing tier ('tier-1', 'tier-2', 'tier-3').
titleNoOptional human-readable subtask title.
taskIdYesSubtask identifier, e.g. 'T1'.
allowedFilesNoOptional list of files the subtask may modify.
decisionBudgetNoOptional decision budget for the subtask contract.
forbiddenFilesNoOptional list of files the subtask must not modify.
verificationCmdNoOptional verification command for the subtask contract.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.2.6
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "allowedFiles": [
      +      "src/telemetry/collector.ts"
      +    ],
      +    "decisionBudget": "none",
      +    "forbiddenFiles": [
      +      "package.json"
      +    ],
      +    "taskId": "T1",
      +    "tier": "tier-3",
      +    "title": "Remove dead telemetry dispatch",
      +    "verificationCmd": "npm test"
      +  }
      +]
    • changedInput schema / properties / tier / description
      Previous value: -"Optional routing tier to assign to the active issue."New value: +"Operational routing tier ('tier-1', 'tier-2', 'tier-3')."
  2. Changed5 schema fields changedv1.2.5
    • addedInput schema / properties / allowedFiles
      Added value: +{
      +  "description": "Optional list of files the subtask may modify.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / decisionBudget
      Added value: +{
      +  "description": "Optional decision budget for the subtask contract.",
      +  "enum": [
      +    "none",
      +    "narrow",
      +    "full"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / forbiddenFiles
      Added value: +{
      +  "description": "Optional list of files the subtask must not modify.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / tier
      Added value: +{
      +  "description": "Optional routing tier to assign to the active issue.",
      +  "enum": [
      +    "tier-1",
      +    "tier-2",
      +    "tier-3"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / verificationCmd
      Added value: +{
      +  "description": "Optional verification command for the subtask contract.",
      +  "type": "string"
      +}
  3. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description does the heavy lifting: it discloses that the contract is 'closed' and persisted, and that the file scope is enforced downstream by the commit engine and the audit — non-obvious behavior an agent needs. It does not say whether re-calling overwrites an existing contract or is idempotent, which is a remaining gap for a state-mutating tool.

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

Conciseness5/5

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

Three tightly packed sentences: what it does, the CLI equivalent, then when/when-not. Front-loaded and free of filler.

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

Completeness4/5

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

For a 7-parameter mutation tool with no annotations and no output schema, the description covers purpose, persistence, enforcement, and routing to siblings. The only omission is what the call returns or how conflicts with an already-set contract are handled.

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, but the description adds conceptual value by grouping allowedFiles/forbiddenFiles/decisionBudget/verificationCmd under a single 'closed delegation contract' and explaining that the tier is the 'active issue tier' — semantics the per-param schema text alone doesn't convey.

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?

States a specific verb+resource: marking a subtask in progress and persisting its delegation contract (files, budget, verification command) plus issue tier. It maps cleanly to the sibling set and explicitly distinguishes itself from lognexus_state_finish_task and lognexus_state_get.

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?

Gives the trigger condition ('when you begin a new subtask and need the file scope enforced') and names both exclusions with their correct alternatives — lognexus_state_finish_task for completion and lognexus_state_get for reading the contract. Nothing is left to inference.

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