Skip to main content
FluffBuzz reads an optional config from ~/.fluffbuzz/fluffbuzz.json. The active config path must be a regular file. Symlinked fluffbuzz.json layouts are unsupported for FluffBuzz-owned writes; an atomic write may replace the path instead of preserving the symlink. If you keep config outside the default state directory, point FLUFFBUZZ_CONFIG_PATH directly at the real file. If the file is missing, FluffBuzz uses safe defaults. Common reasons to add a config:
  • Connect channels and control who can message the bot
  • Set models, tools, sandboxing, or automation (cron, hooks)
  • Tune sessions, media, networking, or UI
See the full reference for every available field.
New to configuration? Start with fluffbuzz onboard for interactive setup, or check out the Configuration Examples guide for complete copy-paste configs.

​
Minimal config

// ~/.fluffbuzz/fluffbuzz.json
{
  agents: { defaults: { workspace: "~/.fluffbuzz/workspace" } },
  channels: { whatsapp: { allowFrom: ["+15555550123"] } },
}

​
Editing config

fluffbuzz onboard       # full onboarding flow
fluffbuzz configure     # config wizard

​
Strict validation

FluffBuzz only accepts configurations that fully match the schema. Unknown keys, malformed types, or invalid values cause the Gateway to refuse to start. The only root-level exception is $schema (string), so editors can attach JSON Schema metadata.
fluffbuzz config schema prints the canonical JSON Schema used by Control UI and validation. config.schema.lookup fetches a single path-scoped node plus child summaries for drill-down tooling. Field title/description docs metadata carries through nested objects, wildcard (*), array-item ([]), and anyOf/ oneOf/allOf branches. Runtime plugin and channel schemas merge in when the manifest registry is loaded. When validation fails:
  • The Gateway does not boot
  • Only diagnostic commands work (fluffbuzz doctor, fluffbuzz logs, fluffbuzz health, fluffbuzz status)
  • Run fluffbuzz doctor to see exact issues
  • Run fluffbuzz doctor --fix (or --yes) to apply repairs
The Gateway keeps a trusted last-known-good copy after each successful startup. If fluffbuzz.json later fails validation (or drops gateway.mode, shrinks sharply, or has a stray log line prepended), FluffBuzz preserves the broken file as .clobbered.*, restores the last-known-good copy, and logs the recovery reason. The next agent turn also receives a system-event warning so the main agent does not blindly rewrite the restored config. Promotion to last-known-good is skipped when a candidate contains redacted secret placeholders such as ***.

​
Common tasks

Each channel has its own config section under channels.<provider>. See the dedicated channel page for setup steps:All channels share the same DM policy pattern:
{
  channels: {
    telegram: {
      enabled: true,
      botToken: "123:abc",
      dmPolicy: "pairing",   // pairing | allowlist | open | disabled
      allowFrom: ["tg:123"], // only for allowlist/open
    },
  },
}
Set the primary model and optional fallbacks:
{
  agents: {
    defaults: {
      model: {
        primary: "anthropic/claude-sonnet-4-6",
        fallbacks: ["openai/gpt-5.4"],
      },
      models: {
        "anthropic/claude-sonnet-4-6": { alias: "Sonnet" },
        "openai/gpt-5.4": { alias: "GPT" },
      },
    },
  },
}
  • agents.defaults.models defines the model catalog and acts as the allowlist for /model.
  • Use fluffbuzz config set agents.defaults.models '<json>' --strict-json --merge to add allowlist entries without removing existing models. Plain replacements that would remove entries are rejected unless you pass --replace.
  • Model refs use provider/model format (e.g. anthropic/claude-opus-4-6).
  • agents.defaults.imageMaxDimensionPx controls transcript/tool image downscaling (default 1200); lower values usually reduce vision-token usage on screenshot-heavy runs.
  • See Models CLI for switching models in chat and Model Failover for auth rotation and fallback behavior.
  • For custom/self-hosted providers, see Custom providers in the reference.
DM access is controlled per channel via dmPolicy:
  • "pairing" (default): unknown senders get a one-time pairing code to approve
  • "allowlist": only senders in allowFrom (or the paired allow store)
  • "open": allow all inbound DMs (requires allowFrom: ["*"])
  • "disabled": ignore all DMs
For groups, use groupPolicy + groupAllowFrom or channel-specific allowlists.See the full reference for per-channel details.
Group messages default to require mention. Configure patterns per agent:
{
  agents: {
    list: [
      {
        id: "main",
        groupChat: {
          mentionPatterns: ["@fluffbuzz", "fluffbuzz"],
        },
      },
    ],
  },
  channels: {
    whatsapp: {
      groups: { "*": { requireMention: true } },
    },
  },
}
  • Metadata mentions: native @-mentions (WhatsApp tap-to-mention, Telegram @bot, etc.)
  • Text patterns: safe regex patterns in mentionPatterns
  • See full reference for per-channel overrides and self-chat mode.
Use agents.defaults.skills for a shared baseline, then override specific agents with agents.list[].skills:
{
  agents: {
    defaults: {
      skills: ["github", "weather"],
    },
    list: [
      { id: "writer" }, // inherits github, weather
      { id: "docs", skills: ["docs-search"] }, // replaces defaults
      { id: "locked-down", skills: [] }, // no skills
    ],
  },
}
  • Omit agents.defaults.skills for unrestricted skills by default.
  • Omit agents.list[].skills to inherit the defaults.
  • Set agents.list[].skills: [] for no skills.
  • See Skills, Skills config, and the Configuration Reference.
Control how aggressively the gateway restarts channels that look stale:
{
  gateway: {
    channelHealthCheckMinutes: 5,
    channelStaleEventThresholdMinutes: 30,
    channelMaxRestartsPerHour: 10,
  },
  channels: {
    telegram: {
      healthMonitor: { enabled: false },
      accounts: {
        alerts: {
          healthMonitor: { enabled: true },
        },
      },
    },
  },
}
  • Set gateway.channelHealthCheckMinutes: 0 to disable health-monitor restarts globally.
  • channelStaleEventThresholdMinutes should be greater than or equal to the check interval.
  • Use channels.<provider>.healthMonitor.enabled or channels.<provider>.accounts.<id>.healthMonitor.enabled to disable auto-restarts for one channel or account without disabling the global monitor.
  • See Health Checks for operational debugging and the full reference for all fields.
Sessions control conversation continuity and isolation:
{
  session: {
    dmScope: "per-channel-peer",  // recommended for multi-user
    threadBindings: {
      enabled: true,
      idleHours: 24,
      maxAgeHours: 0,
    },
    reset: {
      mode: "daily",
      atHour: 4,
      idleMinutes: 120,
    },
  },
}
  • dmScope: main (shared) | per-peer | per-channel-peer | per-account-channel-peer
  • threadBindings: global defaults for thread-bound session routing (Discord supports /focus, /unfocus, /agents, /session idle, and /session max-age).
  • See Session Management for scoping, identity links, and send policy.
  • See full reference for all fields.
Run agent sessions in isolated sandbox runtimes:
{
  agents: {
    defaults: {
      sandbox: {
        mode: "non-main",  // off | non-main | all
        scope: "agent",    // session | agent | shared
      },
    },
  },
}
Build the image first: scripts/sandbox-setup.shSee Sandboxing for the full guide and full reference for all options.
Relay-backed push is configured in fluffbuzz.json.Set this in gateway config:
{
  gateway: {
    push: {
      apns: {
        relay: {
          baseUrl: "https://relay.example.com",
          // Optional. Default: 10000
          timeoutMs: 10000,
        },
      },
    },
  },
}
CLI equivalent:
fluffbuzz config set gateway.push.apns.relay.baseUrl https://relay.example.com
What this does:
  • Lets the gateway send push.test, wake nudges, and reconnect wakes through the external relay.
  • Uses a registration-scoped send grant forwarded by the paired iOS app. The gateway does not need a deployment-wide relay token.
  • Binds each relay-backed registration to the gateway identity that the iOS app paired with, so another gateway cannot reuse the stored registration.
  • Keeps local/manual iOS builds on direct APNs. Relay-backed sends apply only to official distributed builds that registered through the relay.
  • Must match the relay base URL baked into the official/TestFlight iOS build, so registration and send traffic reach the same relay deployment.
End-to-end flow:
  1. Install an official/TestFlight iOS build that was compiled with the same relay base URL.
  2. Configure gateway.push.apns.relay.baseUrl on the gateway.
  3. Pair the iOS app to the gateway and let both node and operator sessions connect.
  4. The iOS app fetches the gateway identity, registers with the relay using App Attest plus the app receipt, and then publishes the relay-backed push.apns.register payload to the paired gateway.
  5. The gateway stores the relay handle and send grant, then uses them for push.test, wake nudges, and reconnect wakes.
Operational notes:
  • If you switch the iOS app to a different gateway, reconnect the app so it can publish a new relay registration bound to that gateway.
  • If you ship a new iOS build that points at a different relay deployment, the app refreshes its cached relay registration instead of reusing the old relay origin.
Compatibility note:
  • FLUFFBUZZ_APNS_RELAY_BASE_URL and FLUFFBUZZ_APNS_RELAY_TIMEOUT_MS still work as temporary env overrides.
  • FLUFFBUZZ_APNS_RELAY_ALLOW_HTTP=true remains a loopback-only development escape hatch; do not persist HTTP relay URLs in config.
See iOS App for the end-to-end flow and Authentication and trust flow for the relay security model.
{
  agents: {
    defaults: {
      heartbeat: {
        every: "30m",
        target: "last",
      },
    },
  },
}
  • every: duration string (30m, 2h). Set 0m to disable.
  • target: last | none | <channel-id> (for example discord, matrix, telegram, or whatsapp)
  • directPolicy: allow (default) or block for DM-style heartbeat targets
  • See Heartbeat for the full guide.
{
  cron: {
    enabled: true,
    maxConcurrentRuns: 2,
    sessionRetention: "24h",
    runLog: {
      maxBytes: "2mb",
      keepLines: 2000,
    },
  },
}
  • sessionRetention: prune completed isolated run sessions from sessions.json (default 24h; set false to disable).
  • runLog: prune cron/runs/<jobId>.jsonl by size and retained lines.
  • See Cron jobs for feature overview and CLI examples.
Enable HTTP webhook endpoints on the Gateway:
{
  hooks: {
    enabled: true,
    token: "shared-secret",
    path: "/hooks",
    defaultSessionKey: "hook:ingress",
    allowRequestSessionKey: false,
    allowedSessionKeyPrefixes: ["hook:"],
    mappings: [
      {
        match: { path: "gmail" },
        action: "agent",
        agentId: "main",
        deliver: true,
      },
    ],
  },
}
Security note:
  • Treat all hook/webhook payload content as untrusted input.
  • Use a dedicated hooks.token; do not reuse the shared Gateway token.
  • Hook auth is header-only (Authorization: Bearer ... or x-fluffbuzz-token); query-string tokens are rejected.
  • hooks.path cannot be /; keep webhook ingress on a dedicated subpath such as /hooks.
  • Keep unsafe-content bypass flags disabled (hooks.gmail.allowUnsafeExternalContent, hooks.mappings[].allowUnsafeExternalContent) unless doing tightly scoped debugging.
  • If you enable hooks.allowRequestSessionKey, also set hooks.allowedSessionKeyPrefixes to bound caller-selected session keys.
  • For hook-driven agents, prefer strong modern model tiers and strict tool policy (for example messaging-only plus sandboxing where possible).
See full reference for all mapping options and Gmail integration.
Run multiple isolated agents with separate workspaces and sessions:
{
  agents: {
    list: [
      { id: "home", default: true, workspace: "~/.fluffbuzz/workspace-home" },
      { id: "work", workspace: "~/.fluffbuzz/workspace-work" },
    ],
  },
  bindings: [
    { agentId: "home", match: { channel: "whatsapp", accountId: "personal" } },
    { agentId: "work", match: { channel: "whatsapp", accountId: "biz" } },
  ],
}
See Multi-Agent and full reference for binding rules and per-agent access profiles.
Use $include to organize large configs:
// ~/.fluffbuzz/fluffbuzz.json
{
  gateway: { port: 18789 },
  agents: { $include: "./agents.json5" },
  broadcast: {
    $include: ["./clients/a.json5", "./clients/b.json5"],
  },
}
  • Single file: replaces the containing object
  • Array of files: deep-merged in order (later wins)
  • Sibling keys: merged after includes (override included values)
  • Nested includes: supported up to 10 levels deep
  • Relative paths: resolved relative to the including file
  • FluffBuzz-owned writes: when a write changes only one top-level section backed by a single-file include such as plugins: { $include: "./plugins.json5" }, FluffBuzz updates that included file and leaves fluffbuzz.json intact
  • Unsupported write-through: root includes, include arrays, and includes with sibling overrides fail closed for FluffBuzz-owned writes instead of flattening the config
  • Error handling: clear errors for missing files, parse errors, and circular includes

​
Config hot reload

The Gateway watches ~/.fluffbuzz/fluffbuzz.json and applies changes automatically — no manual restart needed for most settings. Direct file edits are treated as untrusted until they validate. The watcher waits for editor temp-write/rename churn to settle, reads the final file, and rejects invalid external edits by restoring the last-known-good config. FluffBuzz-owned config writes use the same schema gate before writing; destructive clobbers such as dropping gateway.mode or shrinking the file by more than half are rejected and saved as .rejected.* for inspection. If you see Config auto-restored from last-known-good or config reload restored last-known-good config in logs, inspect the matching .clobbered.* file next to fluffbuzz.json, fix the rejected payload, then run fluffbuzz config validate. See Gateway troubleshooting for the recovery checklist.

​
Reload modes

ModeBehavior
hybrid (default)Hot-applies safe changes instantly. Automatically restarts for critical ones.
hotHot-applies safe changes only. Logs a warning when a restart is needed — you handle it.
restartRestarts the Gateway on any config change, safe or not.
offDisables file watching. Changes take effect on the next manual restart.
{
  gateway: {
    reload: { mode: "hybrid", debounceMs: 300 },
  },
}

​
What hot-applies vs what needs a restart

Most fields hot-apply without downtime. In hybrid mode, restart-required changes are handled automatically.
CategoryFieldsRestart needed?
Channelschannels.*, web (WhatsApp) — all built-in and plugin channelsNo
Agent & modelsagent, agents, models, routingNo
Automationhooks, cron, agent.heartbeatNo
Sessions & messagessession, messagesNo
Tools & mediatools, browser, skills, audio, talkNo
UI & miscui, logging, identity, bindingsNo
Gateway servergateway.* (port, bind, auth, tailscale, TLS, HTTP)Yes
Infrastructurediscovery, canvasHost, pluginsYes
gateway.reload and gateway.remote are exceptions — changing them does not trigger a restart.

​
Reload planning

When you edit a source file that is referenced through $include, FluffBuzz plans the reload from the source-authored layout, not the flattened in-memory view. That keeps hot-reload decisions (hot-apply vs restart) predictable even when a single top-level section lives in its own included file such as plugins: { $include: "./plugins.json5" }. Reload planning fails closed if the source layout is ambiguous.

​
Config RPC (programmatic updates)

For tooling that writes config over the gateway API, prefer this flow:
  • config.schema.lookup to inspect one subtree (shallow schema node + child summaries)
  • config.get to fetch the current snapshot plus hash
  • config.patch for partial updates (JSON merge patch: objects merge, null deletes, arrays replace)
  • config.apply only when you intend to replace the entire config
  • update.run for explicit self-update plus restart
Control-plane writes (config.apply, config.patch, update.run) are rate-limited to 3 requests per 60 seconds per deviceId+clientIp. Restart requests coalesce and then enforce a 30-second cooldown between restart cycles.
Example partial patch: 
fluffbuzz gateway call config.get --params '{}'  # capture payload.hash
fluffbuzz gateway call config.patch --params '{
  "raw": "{ channels: { telegram: { groups: { \"*\": { requireMention: false } } } } }",
  "baseHash": "<hash>"
}'
Both config.apply and config.patch accept raw, baseHash, sessionKey, note, and restartDelayMs. baseHash is required for both methods when a config already exists.

​
Environment variables

FluffBuzz reads env vars from the parent process plus:
  • .env from the current working directory (if present)
  • ~/.fluffbuzz/.env (global fallback)
Neither file overrides existing env vars. You can also set inline env vars in config: 
{
  env: {
    OPENROUTER_API_KEY: "sk-or-...",
    vars: { GROQ_API_KEY: "gsk-..." },
  },
}
If enabled and expected keys aren’t set, FluffBuzz runs your login shell and imports only the missing keys:
{
  env: {
    shellEnv: { enabled: true, timeoutMs: 15000 },
  },
}
Env var equivalent: FLUFFBUZZ_LOAD_SHELL_ENV=1
Reference env vars in any config string value with ${VAR_NAME}:
{
  gateway: { auth: { token: "${FLUFFBUZZ_GATEWAY_TOKEN}" } },
  models: { providers: { custom: { apiKey: "${CUSTOM_API_KEY}" } } },
}
Rules:
  • Only uppercase names matched: [A-Z_][A-Z0-9_]*
  • Missing/empty vars throw an error at load time
  • Escape with $${VAR} for literal output
  • Works inside $include files
  • Inline substitution: "${BASE}/v1" → "https://api.example.com/v1"
For fields that support SecretRef objects, you can use:
{
  models: {
    providers: {
      openai: { apiKey: { source: "env", provider: "default", id: "OPENAI_API_KEY" } },
    },
  },
  skills: {
    entries: {
      "image-lab": {
        apiKey: {
          source: "file",
          provider: "filemain",
          id: "/skills/entries/image-lab/apiKey",
        },
      },
    },
  },
  channels: {
    googlechat: {
      serviceAccountRef: {
        source: "exec",
        provider: "vault",
        id: "channels/googlechat/serviceAccount",
      },
    },
  },
}
SecretRef details (including secrets.providers for env/file/exec) are in Secrets Management. Supported credential paths are listed in SecretRef Credential Surface.
See Environment for full precedence and sources.

​
Full reference

For the complete field-by-field reference, see Configuration Reference.
Related: Configuration Examples · Configuration Reference · Doctor