← Docs hub

Configuration Reference

Complete reference for all CLI subcommands, flags, environment variables, and configuration options.

CLI subcommands

sessionwiki init

Scaffold the raw/, wiki/, site/ directory structure and seed initial wiki files.

python3 -m sessionwiki init

No options. Creates directories and seeds wiki/index.md, wiki/log.md, wiki/overview.md if they don't already exist.

sessionwiki sync

Convert agent session transcripts (.jsonl) into markdown under raw/sessions/.

python3 -m sessionwiki sync [options]

sessionwiki build

Compile the static HTML site from raw/ and wiki/.

python3 -m sessionwiki build [options]

sessionwiki serve

Start a local HTTP server for the built site.

python3 -m sessionwiki serve [options]

sessionwiki adapters

List every registered adapter and whether its session store is present.

python3 -m sessionwiki adapters

No options.

sessionwiki graph

Build the knowledge graph from wiki/ wikilinks.

python3 -m sessionwiki graph [options]

sessionwiki export

Export AI-consumable formats from the built site.

python3 -m sessionwiki export <format> [options]

sessionwiki all (v1.2)

Run the full pipeline: build → graph → export all → lint.

python3 -m sessionwiki all [options]

sessionwiki version

Print the current version.

python3 -m sessionwiki version

Config file (config.json)

Every CLI command loads a layered config:

examples/sessions_config.json  →  config.json  →  config.local.json

config.json and config.local.json are gitignored. Nested objects merge, so a local file can override only the keys it needs; lists replace the base list. This is where machine-specific backend URLs, API keys, redaction patterns, and adapter toggles belong.

To start from the full example:

cp examples/sessions_config.json config.json

Full schema

{
  "filters": {
    "live_session_minutes": 60,
    "include_projects": [],
    "exclude_projects": [],
    "drop_record_types": ["queue-operation", "file-history-snapshot", "progress"]
  },

  "redaction": {
    "real_username": "",
    "replacement_username": "USER",
    "extra_patterns": [
      "(?i)(api[_-]?key|secret|token|bearer|password)[\"'\\s:=]+[\\w\\-\\.]{8,}",
      "sk-[A-Za-z0-9]{20,}",
      "[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\\.[a-zA-Z0-9-.]+"
    ]
  },

  "truncation": {
    "tool_result_chars": 500,
    "bash_stdout_lines": 5,
    "write_content_preview_lines": 5,
    "user_prompt_chars": 4000,
    "assistant_text_chars": 8000
  },

  "drop_thinking_blocks": true,

  "adapters": {
    "obsidian": {
      "vault_paths": ["~/Documents/Obsidian Vault"],
      "exclude_folders": [".obsidian", "Templates"],
      "min_content_chars": 50
    },
    "codex_cli": {
      "roots": ["~/.codex/sessions", "~/.codex/projects"]
    },
    "gemini_cli": {
      "roots": ["~/.gemini"]
    }
  }
}

Section reference

Environment variables

.llmwikiignore

Gitignore-style file at the repo root. One pattern per line. Sessions matching any pattern are skipped during sync.

# Skip a whole project
confidential-client/*

# Skip anything before a date
*2025-11-*

# Skip a specific session
ai-newsletter/2026-04-04-*secret*

# Comments start with #
# Blank lines are ignored

Per-adapter configuration

Each adapter can be configured in the adapters section of config.json. The key must match the adapter's registry name.

Non-AI-session adapters are opt-in only (#326) — set {name}.enabled: true in this config to have them fire on sync.

Example:

{
  "adapters": {
    "copilot_chat": {
      "roots": ["/custom/path/to/vscode/workspaceStorage"]
    }
  }
}