ollama_repo_pack

Repo pack (writes artifact). PACK. Runs the full repo ONBOARDING job: corpus_search (if corpus given) → repo_brief → targeted ollama_extract (narrow onboarding schema: packages, entrypoints, scripts, config_files, exposed_surfaces, runtime_hints) → deterministic markdown+JSON artifact on disk. Corpus-first posture: when a corpus is given, it’s the main working surface alongside source_paths. Not repo Q&A — this is get me onboarded fast with a stable operator artifact. Response is compact; full brief + extracted facts live in the artifact.

Parameters

Parameter	Type	Required	Default	Description
source_paths	string[]	yes	—	Files the onboarding brief should read (README, key src entries, package/manifest, docs). Required — these are the repo’s concrete source-of-truth.
corpus	string	no	—	Optional named corpus (e.g. ‘handbook’, ‘doctrine’) for cross-cutting architecture context. When given, queried as the pack’s main working surface alongside source_paths.
corpus_query	string	no	—	Corpus query (defaults to ‘repo architecture and surfaces’).
title	string	no	—	Short human title — used in the artifact header and filename slug. Defaults to the repo thesis head.
artifact_dir	string	no	—	Directory to write the repo.md + repo.json artifact pair. Defaults to ~/.ollama-intern/artifacts/repo/.
per_file_max_chars	integer	no	—
max_key_surfaces	integer	no	—
max_risk_areas	integer	no	—
max_read_next	integer	no	—

Full input schema

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

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "source_paths": {
      "minItems": 1,
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1
      },
      "description": "Files the onboarding brief should read (README, key src entries, package/manifest, docs). Required — these are the repo's concrete source-of-truth."
    },
    "corpus": {
      "description": "Optional named corpus (e.g. 'handbook', 'doctrine') for cross-cutting architecture context. When given, queried as the pack's main working surface alongside source_paths.",
      "type": "string",
      "pattern": "^[a-zA-Z0-9_-]+$"
    },
    "corpus_query": {
      "description": "Corpus query (defaults to 'repo architecture and surfaces').",
      "type": "string",
      "minLength": 1
    },
    "title": {
      "description": "Short human title — used in the artifact header and filename slug. Defaults to the repo thesis head.",
      "type": "string",
      "minLength": 1,
      "maxLength": 120
    },
    "artifact_dir": {
      "description": "Directory to write the repo.md + repo.json artifact pair. Defaults to ~/.ollama-intern/artifacts/repo/.",
      "type": "string",
      "minLength": 1
    },
    "per_file_max_chars": {
      "type": "integer",
      "minimum": 1000,
      "maximum": 200000
    },
    "max_key_surfaces": {
      "type": "integer",
      "minimum": 1,
      "maximum": 20
    },
    "max_risk_areas": {
      "type": "integer",
      "minimum": 1,
      "maximum": 10
    },
    "max_read_next": {
      "type": "integer",
      "minimum": 1,
      "maximum": 15
    }
  },
  "required": [
    "source_paths"
  ]
}

Envelope

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

Source

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

---

Back to the Tool Reference.