Skip to content
DarkPrint
Aautogenrunbook-resolver1.0.0

Runbook Resolver

Get card

Clone

npx -y darkprint clone runbook-resolver@1.0.0

There is no repository and no history behind a card. Download hands you the document as it stands, and Clone fetches the same document by name.

↓ 1 downloads

Match the routed alert to a runbook in the versioned store and return it as Markdown, pinned to the revision that was current when the incident opened.

used in 1 blueprint

Specification

115 words · handed to the agent

Build a lookup key out of the routed alert on query, its label plus the affected service, and pull the three closest runbooks from the versioned store. Drop anything scoring below 0.4 and emit the best of the rest on runbook as Markdown, with its preconditions and its steps intact and in their original order. Resolve it at the store revision that was current when the incident opened, not at the tip, and write that revision into the output: an edit landing mid-incident must not change the runbook that is already being carried forward. If nothing clears 0.4, emit nothing, no runbook is a better answer than a runbook that does not fit the alert.

Interfaces

1 in · 1 out

Inputs

1
Inputs declared by this node card
NameData typeRequiredDescription
queryjson requiredThe routed alert, whose label and affected service form the lookup key.

Outputs

1
Outputs declared by this node card
NameData typeDescription
runbookmarkdownThe matched runbook at a pinned revision, preconditions and steps intact.

Dependencies

1

The upstream nodes this card expects to receive from. Whenever a blueprint pins this card, each name is checked against a real edge in that graph. A name without a link is not a published card; it refers to a node inside some graph.

Card values

16 declared

Who the node is. The id is the key the DOT pins.

id
runbook-resolver
name
Runbook Resolver
type
tool
phases
none declared
Behaviourcard spec →

What it does, and the prose the agent is handed when the graph runs.

action27 words
Match the routed alert to a runbook in the versioned store and return it as Markdown, pinned to the revision that was current when the incident opened.
spec115 words
Build a lookup key out of the routed alert on query, its label plus the affected service, and pull the three closest runbooks from the versioned store. Drop anything scoring below 0.4 and emit the best of the rest on runbook as Markdown, with its preconditions and its steps intact and in their original order. Resolve it at the store revision that was current when the incident opened, not at the tip, and write that revision into the output: an edit landing mid-incident must not change the runbook that is already being carried forward. If nothing clears 0.4, emit nothing, no runbook is a better answer than a runbook that does not fit the alert.in full above
model
whatever the graph supplies
agent
not named
skill
skills/runbook-resolver.md
tools
Vector store, Git
mcp
qdrant, git
params
k: 3, min_score: 0.4
Interfacescard spec →

What arrives, what leaves, which nodes it expects to hear from, and what may not.

inputs
query : json
outputs
runbook : markdown
dependencies
intent-router
cannot
no type is refused
will_not
resolve a runbook at any revision but the one current when the incident opened
Evaluation metadatacard spec →

The keys the static analysis reads. Nothing here instructs the agent.

risk_markers
none
notes44 words
Pinning the revision matters more than the match. A runbook that changes mid-incident is how the mitigation that runs stops being the mitigation that was reviewed. git here reads the factory's own versioned store, which is why no external-access marker is inferred from it.
Service fieldscard spec →

The card's own version, and who wrote it.

version
1.0.0
author
autogen
provenance
not stated

Definitions for every card field

Version history

1 version published
  1. runbook-resolver@1.0.0currentsha256:f87c06df3b820b2b5bafd371bd130edebd54629b22eea78db4288c008ad59fde

    pinned byIncident Commanderautogen/incident-commander

A digest is a fingerprint (SHA-256) of the card's content, computed without the author and provenance fields. The same card from two people gets the same digest; any edit gets a new one.

First published version, so there is nothing to compare yet. Versions are never edited in place: the next change arrives as a new version, and the differences between the two documents are listed here.

Community notes (0)

No notes yet.

Nobody has posted about this node card yet.

Sign in to post a note.