Master smith at the dashboard control room, wall of glowing amber screens showing live gauges, charts, and status lights

Chapter 7 · Settings Group

Dashboard — Settings Group

9 purpose-built sub-tabs for platform-wide configuration. Part of Chapter 7: The Dashboard.

Part of Chapter 7, This page covers the Settings top-level group. See The Dashboard for the Forge group tabs (Progress, Runs, Cost, Actions, Replay, etc.), Dashboard — LiveGuard Tabs, and Dashboard — Forge-Master Studio.

Settings Group

The Settings group is a top-level container with 9 purpose-built sub-tabs for platform-wide configuration. It replaced the older single Config tab. Settings is one of four top-level groups in the dashboard nav:

🔨 Forge (default)
Home · Review · Progress · Crucible · Governance · Runs · Cost · Actions · Replay · Traces · Skills · Tempering · Memory · Timeline · Inner Loop · Extensions

🛡 LiveGuard
Health · Incidents · Triage · Security · Env · Watcher · Bug Registry

📋 Forge-Master
Studio (the reasoning orchestrator's home)

⚙ Settings (this section)
9 sub-tabs covering platform-wide configuration

Click Settings in the top nav and you'll see 9 purple-accented sub-tabs. Every tab persists changes to its specific config file via the dashboard's safe-write path (sanitizer drops unknown fields, snaps numbers to safe bounds, no UI bug can corrupt your config).

⚙ General

Project identity: preset, template version, and agent enablement.

Preset, the stack profile applied during setup (dotnet, typescript, python, etc.). Read-only on this tab; change via setup.ps1 -Preset <name>.
Template Version, current framework version applied to your project files. pforge update bumps this.
Agents, toggle which reviewer agents are active. Persists to .forge.json#agents.

Settings → General sub-tab showing project identity fields (preset, template version, agents) with Save Configuration and Reload buttons

⚛ Models

Model routing: default execution model and image generation model selection.

Model Routing: Default, auto (orchestrator picks per slice), or pin to a specific model
Image Generation Model, Grok Aurora (XAI_API_KEY) or DALL-E (OPENAI_API_KEY) for diagrams and chapter heroes via forge_generate_image

Settings → Models sub-tab with Model Routing dropdown set to auto and Image Generation Model dropdown

›_ Execution

Per-slice execution behavior: quorum mode, escalation chain, complexity threshold, retry policy. The most-edited Settings tab during day-to-day work.

⚿ API Keys

Stores API keys in .forge/secrets.json (gitignored). Same precedence as env vars: anything set here is picked up by the orchestrator without restarting the server.

XAI_API_KEY, Grok models + Aurora image generation
OPENAI_API_KEY, GPT models direct + DALL-E (also enables OpenAI fallback for COPILOT_SERVABLE models)
ANTHROPIC_API_KEY, Claude direct (Forge-Master + workers without claude CLI)

Values are masked on display. The "Test" button against each key validates by calling the provider's lightweight endpoint, never the full reasoning model.

Settings → API Keys sub-tab showing masked input fields for XAI, OpenAI, Anthropic keys with per-row Test buttons

↓ Updates

Framework version status + one-click pforge self-update from upstream. Surfaces version drift between your local VERSION and GitHub's latest release.

🗄 Memory

OpenBrain wiring: server URL, MCP credentials, project scope. See Chapter 21 — Memory Architecture for the three-tier model.

🔔 Bridge

Remote Bridge endpoints for Slack / Teams / PagerDuty / OpenClaw / Telegram / Discord. See Chapter 20 — Remote Bridge for the per-channel walkthrough.

🔥 Crucible

Idea-smelting pipeline configuration. Persists to .forge/crucible/config.json.

Default Lane, tweak (4q) / feature (7q) / full (~12q). Lane controls interview length.
Self-Referral Depth, max child smelts a parent can spawn (0–3, default 1)
Auto-approve agent-submitted smelts, when source: agent, finalize without human approval (off by default)
Default-Source Weights, Memory / Principles / Plans (sum to 100). Server normalizes if you don't.
Stale Defaults Warning, hours after which Principles/profile changes flag STALE_PRINCIPLES/STALE_PROFILE in the interview

Settings → Crucible sub-tab showing Default Lane dropdown, Self-Referral Depth, Auto-approve toggle, Default-Source Weights, and Stale Defaults Warning fields

🧠 Brain

Forge-Master reasoning configuration: reasoningModel, routerModel, quorumAdvisory, embeddingFallback, GitHub Models zero-key path. See Forge-Master → Configuration for every field.

Audit-Loop activation isn't on a Settings tab, it lives in .forge.json#audit.mode (off | auto | always) and is toggled via the Audit Loop chapter. Drain results stream into the Tempering tab in the Forge group.

⚒ Forge-Master

Configuration for Forge-Master's autonomous background roles: the Observer (live narration of hub events) and the Auditor (automated post-run health analysis). Both are off by default — enable each role with one click here or by editing .forge.json directly.

Observer

The Observer is a mute-by-default background hub subscriber. When enabled it batches live plan events into 60-second windows and narrates notable patterns via the Forge-Master reasoning loop. Narrations are stored in Brain and stream to the Observer Narrations card on the main dashboard view.

Field ID	Type	Default	Effect
`cfg-observer-enabled`	checkbox	off	Enables/disables the observer process. Maps to `forgeMaster.observer.enabled`.
`cfg-observer-modeltier`	select	`inherit`	Model quality tier for narration calls. `inherit` uses the Brain `reasoningModel`; other options: `flagship`, `mid`, `fast`. See Model tier dropdown below.
`cfg-observer-budget-usd`	number	0.10	Daily USD spending cap. Rejects negative values. Maps to `forgeMaster.observer.maxUsdPerDay`.
`cfg-observer-budget-narrations`	number	6	Hourly narration frequency cap. Rejects negative values. Maps to `forgeMaster.observer.maxNarrationsPerHour`.
`cfg-observer-batch-window-ms`	number	60000	Event batch window in milliseconds. Lower values produce more frequent (and expensive) narrations. Maps to `forgeMaster.observer.batchWindowMs`.
`cfg-observer-brain-capture`	checkbox	on	Whether narrations are written to Brain (via `brain_capture`) in addition to the hub event stream. Disable to reduce Brain storage usage. Maps to `forgeMaster.observer.brainCapture`.

Auditor

The Auditor automatically invokes the Plan-Health Auditor agent after runs, writing reports to .forge/health/latest.md. Results are surfaced on the Auditor Latest Report card.

Field ID	Type	Default	Effect
`cfg-auditor-modeltier`	select	`inherit`	Model quality tier for auditor analysis. Same four canonical tokens as the observer tier. Maps to `forgeMaster.auditor.modelTier`.
`cfg-auditor-on-failure`	checkbox	off	Invoke the auditor automatically whenever a run ends in failure. Maps to `hooks.postRun.invokeAuditor.onFailure`.
`cfg-auditor-every-n-runs`	number	blank (off)	Invoke the auditor periodically every N runs. Leave blank to disable periodic invocation. Values 1–4 are rejected — the minimum opt-in value is 5 (reasonable cadence; see Resolved Decision in Phase-40 plan). Maps to `hooks.postRun.invokeAuditor.everyNRuns`.

Model tier dropdown

Both the Observer and Auditor share the same four canonical model-tier tokens. The UI displays human-friendly labels while the backend stores the canonical token in .forge.json:

UI label	Canonical token	Meaning
Inherit from Brain settings	`null` / `inherit`	Uses the `reasoningModel` configured in Settings → Brain
Flagship (best quality)	`flagship`	Highest-capability model in the configured provider (e.g., Claude Opus, GPT-4o)
Balanced	`mid`	Mid-tier model — good quality at lower cost
Fast (low cost)	`fast`	Fastest, cheapest model — suitable for high-frequency narrations

Cross-references: forgeMaster.observer schema · forgeMaster.auditor schema.