Configuration

DRAGON is configured two ways: launch flags passed to the daemon at start, and persisted settings updated live over the wire. Flags shadow persisted settings per-field for the duration of a run and never write the store. This page covers both, the data directory, and how the layers combine.

Daemon launch flags

The shell launches dragond for you, but the daemon accepts flags directly when run from a CLI or supervised. Key flags:

Flag	Default	Purpose
`-addr`	`127.0.0.1:7717`	The loopback bind address. There is no routable bind by design.
`-data`	OS user config dir `/dragon`	The single user-data directory.
`-max-sessions`	`64`	Concurrent live-session cap; each session pins a transport.
`-exit-with-parent`	off	Shut the daemon down when the parent's held stdin pipe breaks. The shell sets this.
`-llama-bin`	unset	Path to the `llama-server` binary for embedded inference.
`-llama-model`	unset	Path to the GGUF model file for embedded inference.
`-rag-roots`	home and data-dir parent	Allowed roots for RAG ingestion; ingestion is confined to these.
`-profiles`	embedded	Override the embedded device profiles with a directory.
`-prompts`	embedded	Override the embedded prompt templates with a directory.

Flags shadow persisted settings per-field for the run only. They never mutate the store, so a flag override is non-destructive and reverts on the next normal launch.

-exit-with-parent is off by default so a CLI launch, where stdin may already be closed, is unaffected. The shell always sets it so a shell crash does not orphan the daemon.

Persisted settings

Settings are fetched and updated live over the wire and stored as key-value JSON in dragon.db. A settings update is a partial update applied immediately. Configurable fields:

ai.mode — embedded or endpoint.
ai.endpoint — the base URL for endpoint mode.
ai.model — the chat model name.
ai.embedModel — the embedding model name.
ai.apiKey — the endpoint API key. Write-only on the wire: the settings response reports only whether a key is present, never the key.
quietMode — the global ambient-quiet toggle.

What hot-swaps and what does not

Endpoint-mode changes apply live. Updating the endpoint, model, embedding model, or key reconfigures the inference client, the embedder, and the redaction strictness without a restart.

Switching ai.mode to embedded is persisted but not applied live. The handler returns an explicit instruction to restart the daemon with -llama-bin and -llama-model. Plan a restart when moving from endpoint to embedded inference.

Redaction strictness

Redaction strictness is not a manual setting — it is derived. When the active inference endpoint is non-loopback, the daemon enables strict redaction automatically, adding the high-entropy heuristic on top of the structural rules. Switching from a local embedded model to a remote endpoint tightens redaction without operator action. See redaction and the audit log.

Credentials

Credentials are never configured in files. SSH passwords and AI API keys live exclusively in the OS keychain — Windows DPAPI, macOS Keychain, or Linux Secret Service — under the service name ethrx-dragon. The store keeps only an opaque keychain reference.

On a headless Linux host without a Secret Service backend, the keychain probe fails and DRAGON degrades to session-only secrets rather than writing anything to disk.

RAG roots

RAG ingestion is confined to the allowed roots in -rag-roots, default the user home and the data-directory parent. The daemon resolves symlinks and rejects sibling-prefix escapes, so a source path of /home/userEVIL does not satisfy a root of /home/user. Point the roots at the directories you intend to index and nothing wider.

Data directory layout

Everything lives under one directory, created with 0o700 permissions and trivially backed up:

text

<data dir>/
  dragon.db                       SQLite store: sessions, records, suggestions, settings, saved tree
  audit/audit-YYYY-MM-DD.jsonl    hash-chained audit log, continuous across days
  rag/chromem/                    persistent vector store
  logs/{session}-{ts}.raw.log     per-session rotating raw byte logs
  known_hosts                     TOFU SSH host keys, OpenSSH format

Secrets are not in this directory. They live in the OS keychain, referenced from the store by opaque ref only.

Device profiles and prompts

Profiles and prompt templates are embedded in the daemon binary, so DRAGON runs self-contained. Override either by pointing -profiles or -prompts at a directory.

A device profile is a TOML file: prompt regexes, the mode state machine, pagination markers, and anomaly patterns. Adding one is pure data; register it for the UI picker.
A prompt template is a versioned data file carrying a mandatory version-and-task header, one system template plus one per task type.