π The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
feat(ruflo-console): Claude can read the console by default β modelControl read, modelConfirm ask (0.33.18)
ruve8384b5e5690
diff --git a/plugins/ruflo-console/.claude-plugin/plugin.json b/plugins/ruflo-console/.claude-plugin/plugin.jsonindex 3846d6c94c..eb88a4854c 100644--- a/plugins/ruflo-console/.claude-plugin/plugin.json+++ b/plugins/ruflo-console/.claude-plugin/plugin.json@@ -1,7 +1,7 @@{"name": "ruflo-console","description": "ruflo's cockpit inside Claude Code and the one /ruflo command for every ruflo mod (function hooks, early access). Views: overview with health alerts, swarm topology graph, claims flow with TTL rings, federation map, plugin health matrix, learning curve and pipeline, MetaHarness radar and audit trend, memory, cost gauge, agent timeline, approvals queue, event stream, a main menu, an x.ruv.io federation board, an AI terminal (codex, claude or both in remembered sessions, streamed), Skills (npx skills), a Hive-Mind view, a MetaHarness lab, agent drill-down; a command palette for confirm-gated actions through the ruflo CLI; a band above the prompt. Reads ruflo's files and the CLI's local JSON; anything not measured reads n/a. The one network call it makes by itself is a daily read of the published plugin.json at github.com/ruvnet/ruflo to offer an update (Settings β Updates: ask, auto, or off); it installs only through Claude Code's own claude plugin update, and never a new major version without asking.",- "version": "0.33.17",+ "version": "0.33.18","author": {"name": "ruvnet","url": "https://github.com/ruvnet"diff --git a/plugins/ruflo-console/hooks/settings.ts b/plugins/ruflo-console/hooks/settings.tsindex 57b38efc99..c0c49990da 100644--- a/plugins/ruflo-console/hooks/settings.ts+++ b/plugins/ruflo-console/hooks/settings.ts@@ -61,7 +61,7 @@ export const CLAUDE_MODELS = ['default', 'haiku', 'sonnet', 'opus'] as constexport const AI_BUDGETS = [0.25, 0.5, 1, 2] as const/** `autoAccept`: claude, codex and swarm turns go straight out with no confirm (they stay read-only, in plan mode, under the budget); ruflo commands still ask. */export type AiPrefs = { claudeModel: (typeof CLAUDE_MODELS)[number]; budgetUsd: (typeof AI_BUDGETS)[number]; autoAccept: boolean; /** Claude writes guidance after a mission goal is entered. */ guidance: boolean; /** ADR-443: the active mission and task ride in Claude's prompt (changes only when the task changes). */ missionContext: boolean; /** ADR-443: the person's own gate commands, one per line or `\n`-separated (parseGates validates). */ loopGates: string; /** ADR-443: a USD cap for one mission's spend ('' none). */ missionCapUsd: string; /** ADR-444: how far Claude may drive the console with its console_* tools (they exist only when not off). */ modelControl: 'off' | 'read' | 'write' | 'manage' | 'full'; /** ADR-444: a non-read action waits for the person's Yes (ask) or confirms itself (auto). */ modelConfirm: 'ask' | 'auto' } & LoopPrefs-export const DEFAULT_AI: AiPrefs = { claudeModel: 'default', budgetUsd: 1, autoAccept: false, guidance: true, missionContext: true, loopGates: '', missionCapUsd: '', modelControl: 'off', modelConfirm: 'auto', ...DEFAULT_LOOP }+export const DEFAULT_AI: AiPrefs = { claudeModel: 'default', budgetUsd: 1, autoAccept: false, guidance: true, missionContext: true, loopGates: '', missionCapUsd: '', modelControl: 'read', modelConfirm: 'ask', ...DEFAULT_LOOP }const ON_OFF = ['on', 'off'] as constconst onOff = (value: boolean) => (value ? 'on' : 'off')@@ -297,8 +297,9 @@ export async function loadAiPrefs(state: State, host: Host): Promise<void> {budgetUsd: budget ?? DEFAULT_AI.budgetUsd,autoAccept: stored?.autoAccept === true,guidance: stored?.guidance !== false,- modelControl: (['read', 'write', 'manage', 'full'] as const).find(item => item === stored?.modelControl) ?? 'off',- modelConfirm: stored?.modelConfirm === 'ask' ? 'ask' : 'auto',+ // Default `read` (Claude may look, never act), and an explicit saved "off" stays off. A missing confirm mode is `ask`: only a saved "auto" is auto.+ modelControl: stored?.modelControl === 'off' ? 'off' : ((['read', 'write', 'manage', 'full'] as const).find(item => item === stored?.modelControl) ?? DEFAULT_AI.modelControl),+ modelConfirm: stored?.modelConfirm === 'auto' ? 'auto' : 'ask',missionContext: stored?.missionContext !== false,loopGates: typeof stored?.loopGates === 'string' ? stored.loopGates.slice(0, 800) : '',missionCapUsd: typeof stored?.missionCapUsd === 'string' && /^\d{1,5}(\.\d{1,2})?$/.test(stored.missionCapUsd) ? stored.missionCapUsd : '',diff --git a/plugins/ruflo-console/hooks/version.ts b/plugins/ruflo-console/hooks/version.tsindex 105fb63c48..076933a87b 100644--- a/plugins/ruflo-console/hooks/version.ts+++ b/plugins/ruflo-console/hooks/version.ts@@ -2,4 +2,4 @@* The console's version, shown on the header so a person can tell which build is running. Kept equal to the plugin's manifest* (`.claude-plugin/plugin.json`); tests/version.spec.ts fails if the two drift.*/-export const CONSOLE_VERSION = '0.33.17'+export const CONSOLE_VERSION = '0.33.18'diff --git a/plugins/ruflo-console/scripts/smoke.sh b/plugins/ruflo-console/scripts/smoke.shindex 5b3955a276..f922aebbe2 100755--- a/plugins/ruflo-console/scripts/smoke.sh+++ b/plugins/ruflo-console/scripts/smoke.sh@@ -11,9 +11,9 @@ step() { printf "β %s ... " "$1"; }ok() { printf "PASS\n"; PASS=$((PASS+1)); }bad() { printf "FAIL: %s\n" "$1"; FAIL=$((FAIL+1)); }-step "1. plugin.json declares ruflo-console 0.33.17"+step "1. plugin.json declares ruflo-console 0.33.18"grep -q '"name": "ruflo-console"' "$ROOT/.claude-plugin/plugin.json" \- && grep -q '"version": "0.33.17"' "$ROOT/.claude-plugin/plugin.json" && ok || bad "name/version"+ && grep -q '"version": "0.33.18"' "$ROOT/.claude-plugin/plugin.json" && ok || bad "name/version"step "2. hooks.json names exactly one module and no classic hook commands"grep -q '"modules": \["./register.ts"\]' "$HOOKS/hooks.json" && ! grep -q '"command"' "$HOOKS/hooks.json" \diff --git a/plugins/ruflo-console/tests/mission-guidance.spec.ts b/plugins/ruflo-console/tests/mission-guidance.spec.tsindex d3f90d563e..c125d12ecf 100644--- a/plugins/ruflo-console/tests/mission-guidance.spec.ts+++ b/plugins/ruflo-console/tests/mission-guidance.spec.ts@@ -301,6 +301,20 @@ describe('loop-centric missions (ADR-441)', () => {expect(settingsOf(state).ai).toEqual(DEFAULT_AI)})+ it('Claude may read the console by default and never act without asking; a saved off or auto is kept (ADR-444)', async () => {+ const state = newState({})+ const saved = new Map<string, unknown>()+ const host = { invalidate: () => undefined, storeSet: async (key: string, value: unknown) => void saved.set(key, value), storeGet: async (key: string) => saved.get(key) } as unknown as Host++ expect(DEFAULT_AI).toMatchObject({ modelControl: 'read', modelConfirm: 'ask' })+ for (const [stored, level, confirm] of [[undefined, 'read', 'ask'], [{ modelControl: 'off' }, 'off', 'ask'], [{ modelControl: 'write', modelConfirm: 'auto' }, 'write', 'auto'], [{ modelControl: 'root', modelConfirm: 'yes' }, 'read', 'ask'], [{ modelControl: 'full' }, 'full', 'ask']] as const) {+ if (stored === undefined) saved.delete('ai-prefs')+ else saved.set('ai-prefs', stored)+ await loadAiPrefs(state, host)+ expect(settingsOf(state).ai, JSON.stringify(stored)).toMatchObject({ modelControl: level, modelConfirm: confirm })+ }+ })+it('has a Help guide on loop-centric missions, linked from the mission guide', () => {const guide = TOPICS.find(topic => topic.id === 'mission-loop')diff --git a/plugins/ruflo-console/tests/model-tools.spec.ts b/plugins/ruflo-console/tests/model-tools.spec.tsindex 9d67f6d628..af4ed036ff 100644--- a/plugins/ruflo-console/tests/model-tools.spec.ts+++ b/plugins/ruflo-console/tests/model-tools.spec.ts@@ -383,7 +383,7 @@ describe('the dashboard', () => {const show = (state: State) => viewText({ state, nowMs: Date.now(), columns: 100, act: { control: { pause: () => undefined } } as unknown as Actions }, 'overview')it('says control is off and where to turn it on', () => {- const text = show(newState({}))+ const text = show(setup('off').state)expect(text).toContain('Claude control')expect(text).toContain('Settings β Claude control')@@ -409,7 +409,7 @@ describe('the dashboard', () => {await callTool('console_state', {}, deps)const on = show(state).toLowerCase()- const off = show(newState({})).toLowerCase()+ const off = show(setup('off').state).toLowerCase()expect(on.indexOf('claude control')).toBeGreaterThanOrEqual(0)expect(on.indexOf('claude control')).toBeLessThan(on.indexOf('optimizer'))diff --git a/v3/docs/adr/ADR-444-claude-controls-the-console.md b/v3/docs/adr/ADR-444-claude-controls-the-console.mdindex fb41d668bb..ba8e404ff5 100644--- a/v3/docs/adr/ADR-444-claude-controls-the-console.md+++ b/v3/docs/adr/ADR-444-claude-controls-the-console.md@@ -25,7 +25,7 @@ Four tools, `mcp__ruflo-console__` plus:- `console_set {field, value}`: fill a field the pages have (`goal`, `profile`, `rigor`, `research.question|depth|cap`, `dev.<field>`, `cost.budget`).- `console_run {id, text?}`: run a palette entry, the same ids `/ruflo run` takes.-**How much Claude may do is a setting**, off by default:+**How much Claude may do is a setting**, `read` by default since ruflo-console 0.33.18 (it was off; a person who saved "off" stays off):| Level | Claude may ||---|---|@@ -61,3 +61,7 @@ With `ask` as the default, a person who had turned control on found Claude parke## 7. Amendment: auto never answers network, spend or delete (console 0.33.4, ADR-450 T8, T12)`modelConfirm: auto` no longer applies to every class. An action classed `network`, `spend` or `delete` always waits for the person in the console's confirm row, even in `auto`: Claude's call is answered "Waiting for the person to confirm" and it must not retry. `auto` still runs local `write` actions unattended. Text Claude passes to `console_set` (the value) or `console_run` (the text) is screened with the shared secret screen (`hooks/screen.ts`, a copy kept in step by `scripts/sync-mod-screen.mjs`) before it reaches an entry; a match is refused ("that text looks like a secret") and never echoed. `RUFLO_CONSOLE_CONTROL` may only lower the saved level, or force `ask`; it can no longer raise either, so a project's settings `env` cannot give Claude more control than the person saved. For a recording or a test that needs a level, save it in Settings (or the plugin store) instead of the environment.++## Update (2026-10-05): the default is read + ask++Default `modelControl` is now `read` and default `modelConfirm` is `ask`, at the owner's request, so Claude can open pages and read the state of a console without anyone first finding the setting. `read` never acts, so the earlier "parked on every write" problem that moved the confirm default to `auto` cannot arise at the default level; a pending ask is now also shown as a banner in the console. A missing confirm mode is `ask`: only a saved `auto` is auto, and a saved `off` stays off. Raising the level (write and above) remains the person's choice in Settings β Claude control. The four tools now register in every session by default, which adds their few hundred tokens to each request.diff --git a/v3/docs/adr/ADR-450-mod-system-threat-model.md b/v3/docs/adr/ADR-450-mod-system-threat-model.mdindex ee3a8f0d32..8c332522a9 100644--- a/v3/docs/adr/ADR-450-mod-system-threat-model.md+++ b/v3/docs/adr/ADR-450-mod-system-threat-model.md@@ -122,7 +122,7 @@ Status: **fixed** (this change), **held** (attempted, no break), **open** (recom### T8. Autopilot default: the worst action at `write` / `manage` with `confirm=auto` (required item 8)-- Setup: `modelControl` defaults to `off` (`settings.ts:49`); `modelConfirm` defaults to `auto` (`settings.ts:286`), so raising the level also removes the person's Yes. Cap: 40 calls per turn, reset at every `turn.start` (`register.ts:343`).+- Setup: `modelControl` defaults to `read` and `modelConfirm` to `ask` since ruflo-console 0.33.18 (it was `off` and `auto`, so raising the level also removed the person's Yes); a saved `off` or `auto` is kept. Cap: 40 calls per turn, reset at every `turn.start` (`register.ts:343`).- At `write` (after T1): file and store writes: `auto-cfg-set` (rewrites `.claude-flow/config.json`), `auto-ses-save`, `task` / `mission` / `auto-task-new` (text that later agents act on), `store`, `mem-pattern-store`, `nn-pattern-store`, `vec-hooks-remember` (plant memory that is recalled in later sessions: T15), `daemon`, `init`, worker dispatch, `mem-export` (overwrites `.claude-flow/memory-export.json`). No shell, no network, no billed model (these now need more).- At `manage`: everything networked: `x-publish` and `x-bbs-publish` (publish text as the person's own key), `vec-brain-transfer` / `sync-push` (publish to pi.ruv.io under the person's identity), `broadcast`, `federation-join`, `marketplace` and `plugin-install` (install code that runs with Claude Code's access), `dt-update-all` (download and write `node_modules`). **This is the worst reachable level in practice: read a secret with any file tool, then publish it with `x-publish`.** Nothing in the console reads the published text for secrets.- Is the per-turn cap enough? No. It bounds one turn; a `/loop` or any long task gets 40 per turn without limit, and the cap says nothing about class (40 `x-publish` calls fit).@@ -261,6 +261,6 @@ Sections 1-8 are left as written; this section records what happened after. The| T18 | Denial of service by the model | Held for the console; the cap does not span turns (see T8's per-session budgets) | n/a || T19 | `http.fetch` hook sees other plugins' requests | **Recorded, no fix**, by design of the entry. ADR-451 item 4's governor is not built. | #3737 (research), #3740 (this entry) |-**Human decisions still open.** (1) Whether `modelConfirm` should default to `ask`: `DEFAULT_AI` in `ruflo-console/hooks/settings.ts` still has `modelConfirm: 'auto'`, with `modelControl: 'off'` so it matters only after the person raises control; T8's always-ask classes bound it. (2) Whether T9's default becomes `refuse-risky`.+**Human decisions still open.** (1) ~~Whether `modelConfirm` should default to `ask`~~ β resolved 2026-10-05: the default is now `ask`, with `modelControl: 'read'`; T8's always-ask classes still bound `auto`. (2) Whether T9's default becomes `refuse-risky`.**Not verified:** the regression-test counts in section 7 were not re-run for this update; no code or test result was re-measured here, only PR state and the files named above.