Skip to content

ollama_incident_pack

Incident pack (writes artifact). PACK. Runs the full incident job end-to-end: triage_logs → corpus_search → incident_brief → deterministic markdown+JSON artifact on disk. Single call, single completed job, single pair of files the operator can keep and diff. Response is compact ({artifact:{markdown_path,json_path}, summary, steps}) — the full brief lives in the artifact, not the MCP payload. Fixed pipeline, fixed markdown layout, no prose drift. Use this instead of calling triage_logs + incident_brief manually when you want one deliverable.

Parameter Type Required Default Description
log_text string no Raw log blob. Combine with source_paths and/or corpus for richer coverage.
source_paths any no File paths read server-side (related source, config, incident notes). Optional — log-driven calls work without it; runtime requires at least one of log_text or source_paths.
corpus string no Optional named corpus for background context (e.g. ‘doctrine’, ‘memory’).
corpus_query string no Corpus query (defaults to the log head).
title string no Short human title — used in the artifact header and filename slug.
artifact_dir string no Directory to write the incident.md + incident.json artifact pair. Defaults to ~/.ollama-intern/artifacts/incident/.
per_file_max_chars integer no
max_hypotheses integer no

The JSON Schema below is generated from the same zod schema the server validates against at the wire — it cannot drift from runtime behavior.

{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"log_text": {
"description": "Raw log blob. Combine with source_paths and/or corpus for richer coverage.",
"type": "string",
"minLength": 1
},
"source_paths": {
"description": "File paths read server-side (related source, config, incident notes). Optional — log-driven calls work without it; runtime requires at least one of log_text or source_paths."
},
"corpus": {
"description": "Optional named corpus for background context (e.g. 'doctrine', 'memory').",
"type": "string",
"pattern": "^[a-zA-Z0-9_-]+$"
},
"corpus_query": {
"description": "Corpus query (defaults to the log head).",
"type": "string",
"minLength": 1
},
"title": {
"description": "Short human title — used in the artifact header and filename slug.",
"type": "string",
"minLength": 1,
"maxLength": 120
},
"artifact_dir": {
"description": "Directory to write the incident.md + incident.json artifact pair. Defaults to ~/.ollama-intern/artifacts/incident/.",
"type": "string",
"minLength": 1
},
"per_file_max_chars": {
"type": "integer",
"minimum": 1000,
"maximum": 200000
},
"max_hypotheses": {
"type": "integer",
"minimum": 1,
"maximum": 10
}
}
}

Every tool returns the standard envelope — tier_used, model, tokens_in/tokens_out, elapsed_ms, backend provenance, warnings. See Envelope & tiers.

Schema + handler: src/tools/packs/incidentPack.ts · registration: src/index.ts


Back to the Tool Reference.