Merge main: compose 016 (channel instances) with 017 (idle timeout) in the migrations barrel

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
fix(db): renumber idle-timeout migration to 017 — 016 is taken by #2733 's instance migration
2026-06-18 18:29:35 +08:00 · 2026-06-11 20:11:42 +03:00 · 2026-06-11 14:08:35 +03:00 · 2026-06-11 14:03:57 +03:00
40 changed files with 547 additions and 1142 deletions
@@ -33,7 +33,7 @@ Run `/update-nanoclaw` in Claude Code.

 **Validation**: runs `pnpm run build` and `pnpm test`. If container files changed, also runs the container typecheck and `./container/build.sh`.

-**Breaking changes check**: after validation, reads CHANGELOG.md for any `[BREAKING]` entries introduced by the update and diffs `versions.json` for moved component pins. Each entry carries its migration path — a skill to run or a `docs/` page to follow (per CONTRIBUTING.md, "Breaking Changes") — and the skill walks you through them.
+**Breaking changes check**: after validation, reads CHANGELOG.md for any `[BREAKING]` entries introduced by the update. If found, shows each breaking change and offers to run the recommended skill to migrate.

 ## Rollback

@@ -221,31 +221,24 @@ After validation succeeds, check if the update introduced any breaking changes.
 Determine which CHANGELOG entries are new by diffing against the backup tag:
 - `git diff <backup-tag-from-step-1>..HEAD -- CHANGELOG.md`

-Parse the diff output for lines that contain `[BREAKING]` anywhere in the line. Each such line is one breaking change entry, and per CONTRIBUTING.md ("Breaking Changes") it references its migration path in one of two forms:
+Parse the diff output for lines that contain `[BREAKING]` anywhere in the line. Each such line is one breaking change entry. The format is:
 ```
 [BREAKING] <description>. Run `/<skill-name>` to <action>.
-[BREAKING] <description>. **Migration:** follow [docs/<page>.md](docs/<page>.md) ...
 ```

-Also diff the component version pins:
- `git diff <backup-tag-from-step-1>..HEAD -- versions.json`
-
-Each changed pin is a breaking component update (e.g. `onecli-gateway` moving means the OneCLI gateway must be upgraded). Its migration path is the `[BREAKING]` CHANGELOG entry covering it; if no new entry mentions it, search `docs/` for the pin name (convention: `docs/<component>-upgrades.md`) and treat that doc as the migration path.
-
-If no `[BREAKING]` lines are found and `versions.json` did not change:
+If no `[BREAKING]` lines are found:
 - Skip this step silently. Proceed to Step 7 (skill updates check).

-Otherwise:
+If one or more `[BREAKING]` lines are found:
 - Display a warning header to the user: "This update includes breaking changes that may require action:"
- For each breaking change, display the full description (for a moved pin without its own entry: the component name, old → new version, and the doc that covers it).
- Use AskUserQuestion to ask the user which migrations to run now. Options:
+- For each breaking change, display the full description.
+- Collect all skill names referenced in the breaking change entries (the `/<skill-name>` part).
+- Use AskUserQuestion to ask the user which migration skills they want to run now. Options:
  - One option per referenced skill (e.g., "Run /add-whatsapp to re-add WhatsApp channel")
-  - One option per referenced doc (e.g., "Upgrade the OneCLI gateway (docs/onecli-upgrades.md)")
  - "Skip — I'll handle these manually"
- Set `multiSelect: true` so the user can pick multiple migrations if there are several breaking changes.
+- Set `multiSelect: true` so the user can pick multiple skills if there are several breaking changes.
 - For each skill the user selects, invoke it using the Skill tool.
- For each doc the user selects, read the doc and execute it top to bottom — these docs are written to be executed verbatim by a coding agent (detect → fix → verify → rollback). Stop and report if a verify step fails.
- After all selected migrations complete (or if user chose Skip), proceed to Step 7 (skill updates check).
+- After all selected skills complete (or if user chose Skip), proceed to Step 7 (skill updates check).

 # Step 7: Check for skill and channel/provider updates

@@ -2,11 +2,6 @@

 All notable changes to NanoClaw will be documented in this file.

-## [Unreleased]
-
- [BREAKING] **`@onecli-sh/sdk` 0.5.0 -> 2.2.1 — requires a OneCLI server with the `/v1` API** (older servers 404 every SDK call). The sanctioned gateway and CLI versions are pinned in `versions.json`; the `onecli` setup step enforces them. **Migration:** [docs/onecli-upgrades.md](docs/onecli-upgrades.md).
- **Slash commands now interrupt an in-flight turn.** A runner-handled command (`/clear`, `/compact`, `/cost`, …) arriving mid-turn aborts the active stream and runs immediately instead of waiting out the turn.
-
 ## [2.1.0] - 2026-06-07

 - [BREAKING] **Startup now requires an upgrade marker.** The host refuses to boot unless `data/upgrade-state.json` records that this install reached the current version through a sanctioned path (`/setup`, `/update-nanoclaw`, `/migrate-nanoclaw`). After this update completes — and before restarting the service — stamp the marker by running `pnpm exec tsx scripts/upgrade-state.ts set`. If the host has already tripped on restart with "update did not go through the supported path", that same command clears it. See [docs/upgrade-recovery.md](docs/upgrade-recovery.md).
@@ -19,13 +19,6 @@

 **Not accepted:** Features, capabilities, compatibility, enhancements. These should be skills.

-## Breaking Changes
-
-Breaking changes are allowed; **silent** ones are not. NanoClaw does not migrate user installs at runtime — the user's coding agent is the migrator, so every breaking change must ship a migration path that agent can execute without a human reverse-engineering the diff:
-
-1. **Every `[BREAKING]` CHANGELOG entry must reference its migration path** — either a skill to run (`Run /<skill-name> to <action>`) or a `docs/` page covering **detect / why / fix / verify / rollback** (see [docs/onecli-upgrades.md](docs/onecli-upgrades.md) for the shape). `/update-nanoclaw` surfaces these entries after every update and walks the user through them.
-2. **If the change moves an external component's sanctioned version** (gateway, pinned CLI binary, …), update its pin in [`versions.json`](versions.json). The changelog stays human-narrative; `versions.json` is the machine-checkable signal — `/update-nanoclaw` diffs it across the update and routes the user to the linked doc for any pin that moved.
-
 ## Skills

 NanoClaw uses [Claude Code skills](https://code.claude.com/docs/en/skills) — markdown files with optional supporting files that teach Claude how to do something. There are four types of skills in NanoClaw, each serving a different purpose.
@@ -15,6 +15,8 @@ export interface RunnerConfig {
  groupName: string;
  agentGroupId: string;
  maxMessagesPerPrompt: number;
+  /** Idle window in ms after which the poll loop exits cleanly. 0 = disabled. */
+  idleTimeoutMs: number;
  mcpServers: Record<string, { command: string; args: string[]; env: Record<string, string> }>;
  model?: string;
  effort?: string;
@@ -44,6 +46,7 @@ export function loadConfig(): RunnerConfig {
    groupName: (raw.groupName as string) || '',
    agentGroupId: (raw.agentGroupId as string) || '',
    maxMessagesPerPrompt: (raw.maxMessagesPerPrompt as number) || DEFAULT_MAX_MESSAGES,
+    idleTimeoutMs: (raw.idleTimeoutMs as number) || 0,
    mcpServers: (raw.mcpServers as RunnerConfig['mcpServers']) || {},
    model: (raw.model as string) || undefined,
    effort: (raw.effort as string) || undefined,
@@ -0,0 +1,193 @@
+/**
+ * Idle-timeout guard — the machinery that lets ephemeral sessions exit
+ * cleanly instead of riding until host-sweep's absolute ceiling.
+ *
+ * Behavior leg: the idle tracker with an injected clock (markActivity /
+ * shouldExit semantics, including the hasProcessedAtLeastOne gate and the
+ * idleTimeoutMs <= 0 disable).
+ *
+ * AST legs (runPollLoop is an infinite loop — not invocable in a test):
+ *   - runPollLoop destructures idleTimeoutMs from loadConfig() (the
+ *     destructure may carry other keys; this only pins idleTimeoutMs);
+ *   - the empty-poll branch exits via process.exit(0) gated on
+ *     idle.shouldExit();
+ *   - idle.markActivity() runs after the batch-completion
+ *     markCompleted(processingIds) so the idle window restarts per batch;
+ *   - the processQuery call site threads idleTimeoutMs as the 5th argument;
+ *   - the 'result' event arm calls query.end() gated on
+ *     `idleTimeoutMs > 0 && !hasUnwrapped` — never unconditionally, or the
+ *     unwrapped-output re-send nudge would be cut off mid-stream;
+ *   - loadConfig()'s returned literal carries the idleTimeoutMs field
+ *     (RunnerConfig's type is covered by the typecheck leg).
+ */
+import fs from 'fs';
+import path from 'path';
+
+import { describe, expect, it } from 'bun:test';
+import ts from 'typescript';
+
+import { createIdleTracker } from './idle-tracker.js';
+
+describe('idle tracker behavior', () => {
+  it('never exits before the first processed batch, regardless of elapsed time', () => {
+    let clock = 0;
+    const tracker = createIdleTracker(1000, () => clock);
+    clock = 1_000_000;
+    expect(tracker.shouldExit()).toBe(false);
+  });
+
+  it('exits only after the idle window elapses past the last activity', () => {
+    let clock = 0;
+    const tracker = createIdleTracker(1000, () => clock);
+
+    tracker.markActivity(); // first batch completes at t=0
+    clock = 900;
+    expect(tracker.shouldExit()).toBe(false);
+    clock = 1001;
+    expect(tracker.shouldExit()).toBe(true);
+
+    // New activity re-arms the window.
+    tracker.markActivity();
+    clock = 1900;
+    expect(tracker.shouldExit()).toBe(false);
+    clock = 2002;
+    expect(tracker.shouldExit()).toBe(true);
+  });
+
+  it('idleTimeoutMs <= 0 disables idle exit entirely', () => {
+    let clock = 0;
+    const tracker = createIdleTracker(0, () => clock);
+    tracker.markActivity();
+    clock = 10_000_000;
+    expect(tracker.shouldExit()).toBe(false);
+  });
+});
+
+// ── AST legs ──
+
+function parse(file: string): ts.SourceFile {
+  const source = fs.readFileSync(path.join(import.meta.dir, file), 'utf8');
+  return ts.createSourceFile(file, source, ts.ScriptTarget.Latest, true);
+}
+
+function findAll<T extends ts.Node>(root: ts.Node, pred: (n: ts.Node) => n is T): T[] {
+  const out: T[] = [];
+  const visit = (n: ts.Node): void => {
+    if (pred(n)) out.push(n);
+    n.forEachChild(visit);
+  };
+  visit(root);
+  return out;
+}
+
+function hasAncestor(node: ts.Node, pred: (n: ts.Node) => boolean): boolean {
+  let cur: ts.Node | undefined = node.parent;
+  while (cur) {
+    if (pred(cur)) return true;
+    cur = cur.parent;
+  }
+  return false;
+}
+
+describe('poll-loop.ts idle wiring', () => {
+  const sf = parse('poll-loop.ts');
+  const runPollLoop = findAll(sf, ts.isFunctionDeclaration).find((f) => f.name?.text === 'runPollLoop');
+
+  it('destructures idleTimeoutMs from loadConfig()', () => {
+    const decls = findAll(runPollLoop!, ts.isVariableDeclaration).filter(
+      (d) =>
+        d.initializer !== undefined &&
+        ts.isCallExpression(d.initializer) &&
+        ts.isIdentifier(d.initializer.expression) &&
+        d.initializer.expression.text === 'loadConfig' &&
+        ts.isObjectBindingPattern(d.name),
+    );
+    expect(decls.length).toBeGreaterThanOrEqual(1);
+    const hasKey = decls.some((d) =>
+      (d.name as ts.ObjectBindingPattern).elements.some(
+        (e) => ts.isIdentifier(e.name) && e.name.text === 'idleTimeoutMs',
+      ),
+    );
+    expect(hasKey).toBe(true);
+  });
+
+  it('the empty-poll branch exits 0 gated on idle.shouldExit()', () => {
+    const exits = findAll(runPollLoop!, ts.isCallExpression).filter(
+      (c) =>
+        ts.isPropertyAccessExpression(c.expression) &&
+        c.expression.getText(sf) === 'process.exit' &&
+        c.arguments[0]?.getText(sf) === '0',
+    );
+    const gated = exits.filter((c) =>
+      hasAncestor(
+        c,
+        (n) => ts.isIfStatement(n) && n.expression.getText(sf).replace(/\s+/g, '') === 'idle.shouldExit()',
+      ),
+    );
+    expect(gated.length).toBe(1);
+    // And the gate itself sits inside the messages.length === 0 branch.
+    expect(
+      hasAncestor(gated[0], (n) => ts.isIfStatement(n) && n.expression.getText(sf).includes('messages.length === 0')),
+    ).toBe(true);
+  });
+
+  it('marks activity after markCompleted so the idle window restarts per batch', () => {
+    const marks = findAll(runPollLoop!, ts.isCallExpression).filter(
+      (c) => c.expression.getText(sf).replace(/\s+/g, '') === 'idle.markActivity',
+    );
+    expect(marks.length).toBe(1);
+    // The batch-completion call is markCompleted(processingIds) — the others
+    // handle command/skip bookkeeping and must not arm the idle window.
+    const completed = findAll(runPollLoop!, ts.isCallExpression).filter(
+      (c) =>
+        ts.isIdentifier(c.expression) &&
+        c.expression.text === 'markCompleted' &&
+        c.arguments[0]?.getText(sf) === 'processingIds',
+    );
+    expect(completed.length).toBe(1);
+    expect(marks[0].getStart(sf)).toBeGreaterThan(completed[0].getStart(sf));
+  });
+
+  it("threads idleTimeoutMs as processQuery's 5th argument", () => {
+    const calls = findAll(runPollLoop!, ts.isCallExpression).filter(
+      (c) => ts.isIdentifier(c.expression) && c.expression.text === 'processQuery',
+    );
+    expect(calls.length).toBe(1);
+    expect(calls[0].arguments.length).toBe(5);
+    expect(calls[0].arguments[4].getText(sf)).toBe('idleTimeoutMs');
+  });
+
+  it("the 'result' event arm ends the stream gated on idleTimeoutMs > 0 && !hasUnwrapped", () => {
+    const processQuery = findAll(sf, ts.isFunctionDeclaration).find((f) => f.name?.text === 'processQuery');
+    expect(processQuery).toBeDefined();
+    const ends = findAll(processQuery!, ts.isCallExpression).filter(
+      (c) => c.expression.getText(sf).replace(/\s+/g, '') === 'query.end',
+    );
+    // The !hasUnwrapped half of the gate is load-bearing: an unconditional
+    // (or idleTimeoutMs-only) end would close the stream right after the
+    // unwrapped-output nudge was pushed, stranding the re-sent response.
+    const gated = ends.filter((c) =>
+      hasAncestor(
+        c,
+        (n) =>
+          ts.isIfStatement(n) && n.expression.getText(sf).replace(/\s+/g, '') === 'idleTimeoutMs>0&&!hasUnwrapped',
+      ),
+    );
+    expect(gated.length).toBe(1);
+  });
+});
+
+describe('config.ts idle wiring', () => {
+  const sf = parse('config.ts');
+
+  it('loadConfig returns an idleTimeoutMs field', () => {
+    const loadConfig = findAll(sf, ts.isFunctionDeclaration).find((f) => f.name?.text === 'loadConfig');
+    expect(loadConfig).toBeDefined();
+    const props = findAll(loadConfig!, ts.isPropertyAssignment).filter(
+      (p) => ts.isIdentifier(p.name) && p.name.text === 'idleTimeoutMs',
+    );
+    expect(props.length).toBe(1);
+    // Reads the raw container.json key with a 0 default (0 = disabled).
+    expect(props[0].initializer.getText(sf).replace(/\s+/g, '')).toContain('raw.idleTimeoutMs');
+  });
+});
@@ -0,0 +1,40 @@
+/**
+ * Idle-exit tracker for ephemeral sessions.
+ *
+ * The poll loop creates one tracker per run and makes two one-line calls:
+ *
+ *   - `markActivity()` after a batch completes — records the last time the
+ *     agent did real work and arms the tracker (an agent that never processed
+ *     anything must not idle-exit before its first trigger arrives).
+ *   - `shouldExit()` in the empty-poll branch — true once idleTimeoutMs > 0,
+ *     at least one batch has been processed, and the idle window has elapsed.
+ *
+ * `idleTimeoutMs` comes from the group's container.json (RunnerConfig),
+ * materialized from the `container_configs.idle_timeout_ms` column. A value
+ * of 0 (the default) disables idle exit entirely — the container then rides
+ * until host-sweep's absolute ceiling, exactly as before this tracker existed.
+ */
+
+export interface IdleTracker {
+  /** Record activity: arms the tracker and resets the idle window. */
+  markActivity(): void;
+  /** True when the session has been idle past the timeout and may exit 0. */
+  shouldExit(): boolean;
+}
+
+export function createIdleTracker(idleTimeoutMs: number, now: () => number = Date.now): IdleTracker {
+  let lastActivityAt = now();
+  let hasProcessedAtLeastOne = false;
+
+  return {
+    markActivity(): void {
+      lastActivityAt = now();
+      hasProcessedAtLeastOne = true;
+    },
+    shouldExit(): boolean {
+      if (idleTimeoutMs <= 0) return false;
+      if (!hasProcessedAtLeastOne) return false;
+      return now() - lastActivityAt > idleTimeoutMs;
+    },
+  };
+}
@@ -27,7 +27,6 @@ import { fileURLToPath } from 'url';

 import { loadConfig } from './config.js';
 import { buildSystemPromptAddendum } from './destinations.js';
-import { ensureMemoryScaffold } from './memory-scaffold.js';
 // Providers barrel — each enabled provider self-registers on import.
 // Provider skills append imports to providers/index.ts.
 import './providers/index.js';
@@ -96,12 +95,6 @@ async function main(): Promise<void> {
    effort: config.effort,
  });

-  // Providers that lack native memory opt in via `usesMemoryScaffold`; for them
-  // the runner creates a persistent memory/ tree in its host-backed workspace at
-  // boot (idempotent). Default off — the trunk default (Claude) omits the flag
-  // and keeps its native memory untouched.
-  if (provider.usesMemoryScaffold) ensureMemoryScaffold();
-
  await runPollLoop({
    provider,
    providerName,
@@ -5,7 +5,6 @@ import { getUndeliveredMessages } from './db/messages-out.js';
 import { getPendingMessages } from './db/messages-in.js';
 import { getContinuation, setContinuation } from './db/session-state.js';
 import { MockProvider } from './providers/mock.js';
-import type { ProviderExchange } from './providers/types.js';
 import { runPollLoop } from './poll-loop.js';

 beforeEach(() => {
@@ -305,7 +304,6 @@ async function runPollLoopWithTimeout(provider: MockProvider, signal: AbortSigna
      provider,
      providerName: 'mock',
      cwd: '/tmp',
-      signal,
    }),
    new Promise<void>((_, reject) => {
      signal.addEventListener('abort', () => reject(new Error('aborted')));
@@ -326,86 +324,6 @@ function sleep(ms: number): Promise<void> {
  return new Promise((resolve) => setTimeout(resolve, ms));
 }

-describe('poll loop — exchange hook (onExchangeComplete)', () => {
-  // A provider that declares the per-exchange hook. The hook call is the
-  // wiring under test — these tests go red if the poll-loop seam is severed.
-  // What the provider DOES with an exchange (e.g. write markdown into
-  // conversations/) ships with the provider, not the runner.
-  class HookedMockProvider extends MockProvider {
-    readonly exchanges: ProviderExchange[] = [];
-    onExchangeComplete(exchange: ProviderExchange): void {
-      this.exchanges.push(exchange);
-    }
-  }
-
-  it('reports each exchange to a provider that declares the hook', async () => {
-    insertMessage('m1', { sender: 'Alice', text: 'please archive this' }, { platformId: 'chan-1', channelType: 'discord' });
-
-    const provider = new HookedMockProvider({}, () => '<message to="discord-test">archived answer</message>');
-    const controller = new AbortController();
-    const loopPromise = runPollLoopWithTimeout(provider, controller.signal, 2000);
-
-    await waitFor(() => provider.exchanges.length > 0, 2000);
-    controller.abort();
-
-    expect(provider.exchanges.length).toBe(1);
-    const exchange = provider.exchanges[0];
-    expect(exchange.prompt).toContain('please archive this');
-    expect(exchange.result).toContain('archived answer');
-    expect(exchange.continuation).toStartWith('mock-session-');
-    expect(exchange.status).toBe('completed');
-
-    await loopPromise.catch(() => {});
-  });
-
-  it('does not report the internal wrapping-retry nudge as a user prompt', async () => {
-    insertMessage('m1', { sender: 'Alice', text: 'wrap this later' }, { platformId: 'chan-1', channelType: 'discord' });
-
-    let calls = 0;
-    const provider = new HookedMockProvider({}, () => {
-      calls += 1;
-      // First result is unwrapped (triggers the retry nudge), second is wrapped.
-      return calls === 1 ? 'unwrapped text' : '<message to="discord-test">wrapped now</message>';
-    });
-    const controller = new AbortController();
-    const loopPromise = runPollLoopWithTimeout(provider, controller.signal, 3000);
-
-    await waitFor(() => provider.exchanges.length >= 2, 3000);
-    controller.abort();
-
-    // Both exchanges attribute themselves to the real user prompt, never the nudge.
-    for (const exchange of provider.exchanges) {
-      expect(exchange.prompt).not.toContain('Your response was not delivered');
-      expect(exchange.prompt).toContain('wrap this later');
-    }
-    expect(provider.exchanges.map((e) => e.status)).toEqual(['undelivered', 'completed']);
-
-    await loopPromise.catch(() => {});
-  });
-
-  it('a throwing hook never breaks delivery', async () => {
-    insertMessage('m1', { sender: 'Alice', text: 'still deliver this' }, { platformId: 'chan-1', channelType: 'discord' });
-
-    class ThrowingHookProvider extends MockProvider {
-      onExchangeComplete(): void {
-        throw new Error('hook exploded');
-      }
-    }
-    const provider = new ThrowingHookProvider({}, () => '<message to="discord-test">delivered anyway</message>');
-    const controller = new AbortController();
-    const loopPromise = runPollLoopWithTimeout(provider, controller.signal, 2000);
-
-    await waitFor(() => getUndeliveredMessages().length > 0, 2000);
-    controller.abort();
-
-    const out = getUndeliveredMessages();
-    expect(out.length).toBe(1);
-    expect(out[0].content).toContain('delivered anyway');
-
-    await loopPromise.catch(() => {});
-  });
-});
-
 describe('poll loop — provider error recovery', () => {
  it('writes error to outbound and continues loop on provider throw', async () => {
    insertMessage('m1', { sender: 'Alice', text: 'trigger error' }, { platformId: 'chan-1', channelType: 'discord' });
@@ -544,76 +462,3 @@ class InvalidSessionProvider {
    };
  }
 }
-
-describe('poll loop — slash command during active query', () => {
-  it('aborts the active query when /clear arrives as a follow-up', async () => {
-    insertMessage('m-active', { sender: 'Alice', text: 'long running request' }, { platformId: 'chan-1', channelType: 'discord' });
-
-    const provider = new BlockingProvider();
-    const controller = new AbortController();
-    const loopPromise = runPollLoopWithTimeout(provider as unknown as MockProvider, controller.signal, 3000);
-
-    await waitFor(() => provider.queries === 1, 2000);
-    insertMessage('m-clear-active', { sender: 'Alice', text: '/clear' }, { platformId: 'chan-1', channelType: 'discord' });
-
-    await waitFor(() => provider.aborts === 1, 2000);
-    await waitFor(
-      () => getUndeliveredMessages().some((msg) => JSON.parse(msg.content).text === 'Session cleared.'),
-      2000,
-    );
-    controller.abort();
-
-    expect(provider.ends).toBe(0);
-    expect(getContinuation('mock')).toBeUndefined();
-    expect(getPendingMessages()).toHaveLength(0);
-
-    await loopPromise.catch(() => {});
-  });
-});
-
-/**
- * Provider whose query never completes until ended/aborted — for testing how
- * the loop interrupts an active stream.
- */
-class BlockingProvider {
-  readonly supportsNativeSlashCommands = false;
-  queries = 0;
-  aborts = 0;
-  ends = 0;
-
-  isSessionInvalid(): boolean {
-    return false;
-  }
-
-  query() {
-    const owner = this;
-    this.queries += 1;
-    let wake: (() => void) | null = null;
-    let ended = false;
-    let aborted = false;
-
-    return {
-      push() {},
-      end: () => {
-        owner.ends += 1;
-        ended = true;
-        wake?.();
-      },
-      abort: () => {
-        owner.aborts += 1;
-        aborted = true;
-        wake?.();
-      },
-      events: (async function* () {
-        yield { type: 'activity' as const };
-        yield { type: 'init' as const, continuation: 'blocking-session' };
-        while (!ended && !aborted) {
-          await new Promise<void>((resolve) => {
-            wake = resolve;
-          });
-          wake = null;
-        }
-      })(),
-    };
-  }
-}
@@ -1,37 +0,0 @@
-import { describe, expect, it } from 'bun:test';
-import fs from 'fs';
-import os from 'os';
-import path from 'path';
-
-import { ensureMemoryScaffold } from './memory-scaffold.js';
-
-describe('ensureMemoryScaffold', () => {
-  it('deterministically creates the memory tree', () => {
-    const base = fs.mkdtempSync(path.join(os.tmpdir(), 'nanoclaw-mem-'));
-    try {
-      ensureMemoryScaffold(base);
-
-      expect(fs.existsSync(path.join(base, 'memory', 'index.md'))).toBe(true);
-      expect(fs.existsSync(path.join(base, 'memory', 'system', 'definition.md'))).toBe(true);
-      expect(fs.existsSync(path.join(base, 'memory', 'memories'))).toBe(true);
-      expect(fs.existsSync(path.join(base, 'memory', 'data'))).toBe(true);
-    } finally {
-      fs.rmSync(base, { recursive: true, force: true });
-    }
-  });
-
-  it('is idempotent and never clobbers the agent edits', () => {
-    const base = fs.mkdtempSync(path.join(os.tmpdir(), 'nanoclaw-mem-'));
-    try {
-      ensureMemoryScaffold(base);
-      const indexFile = path.join(base, 'memory', 'index.md');
-      fs.writeFileSync(indexFile, '# my own index\n');
-
-      ensureMemoryScaffold(base);
-
-      expect(fs.readFileSync(indexFile, 'utf-8')).toBe('# my own index\n');
-    } finally {
-      fs.rmSync(base, { recursive: true, force: true });
-    }
-  });
-});
@@ -1,39 +0,0 @@
-import fs from 'fs';
-import path from 'path';
-import { fileURLToPath } from 'url';
-
-/**
- * Create the agent's persistent memory scaffold, container-side, at boot.
- *
- * The runner owns its own workspace: it writes the memory tree straight into
- * `/workspace/agent` (the host-backed, RW group dir, so it persists across the
- * ephemeral container). No host-side step, nothing mounted in.
- *
- * The default `definition.md` / `index.md` live as real markdown templates next
- * to this module (under `memory-templates/`) — not as strings in code — so the
- * doctrine is editable as markdown and the agent receives an unescaped copy.
- * They ship in the mounted `/app/src` tree, so no image change is needed.
- *
- * Idempotent — only writes what's missing, so the agent's own edits and
- * accumulated memory are never clobbered on a later wake. Provider-agnostic:
- * the runner makes no assumption about which harness is running — a provider
- * opts in via `usesMemoryScaffold`.
- */
-const TEMPLATES_DIR = path.join(path.dirname(fileURLToPath(import.meta.url)), 'memory-templates');
-
-export function ensureMemoryScaffold(baseDir = '/workspace/agent'): void {
-  const memoryDir = path.join(baseDir, 'memory');
-  const systemDir = path.join(memoryDir, 'system');
-
-  for (const dir of [systemDir, path.join(memoryDir, 'memories'), path.join(memoryDir, 'data')]) {
-    fs.mkdirSync(dir, { recursive: true });
-  }
-
-  copyTemplateIfMissing('definition.md', path.join(systemDir, 'definition.md'));
-  copyTemplateIfMissing('index.md', path.join(memoryDir, 'index.md'));
-}
-
-function copyTemplateIfMissing(template: string, dest: string): void {
-  if (fs.existsSync(dest)) return;
-  fs.copyFileSync(path.join(TEMPLATES_DIR, template), dest);
-}
@@ -1,22 +0,0 @@
-import { describe, expect, it } from 'bun:test';
-import fs from 'fs';
-import path from 'path';
-
-// Wiring guard for the memory-scaffold seam: the boot gate in index.ts
-// (`if (provider.usesMemoryScaffold) ensureMemoryScaffold()`) is the seam's
-// single functional reach-in. The unit tests in memory-scaffold.test.ts drive
-// ensureMemoryScaffold directly and stay green if the gate is deleted — this
-// test goes red. main() can't be driven in-process (it reads
-// /workspace/agent/container.json and enters the poll loop), so the guard is
-// structural: gate + import must both be present in the real entry point.
-describe('memory scaffold boot wiring', () => {
-  const indexSrc = fs.readFileSync(path.join(import.meta.dir, 'index.ts'), 'utf-8');
-
-  it('gates the scaffold on the provider capability in main()', () => {
-    expect(indexSrc).toContain('if (provider.usesMemoryScaffold) ensureMemoryScaffold()');
-  });
-
-  it('imports ensureMemoryScaffold from the seam module', () => {
-    expect(indexSrc).toContain("import { ensureMemoryScaffold } from './memory-scaffold.js'");
-  });
-});
@@ -1,23 +0,0 @@
-# Agent Memory System
-
-This editable file defines how your persistent memory works. It is a starting
-point, not a contract — reorganize it as the work demands. If the user or another
-memory system replaces this definition, follow the replacement.
-
-Start every memory task at `memory/index.md`, then follow the narrowest relevant index.
-Treat indexes as core data: keep them accurate and concise.
-Every folder of durable memory has its own `index.md` describing its contents.
-When an index grows past roughly 20 entries, group related items into subfolders,
-and give each new subfolder its own `index.md` linked from the parent.
-
-Use `memory/memories/` for durable facts, project context, people, decisions, and entity notes.
-Use `memory/data/` for structured reference data, datasets, tables, and reusable records.
-Use entity folders for things that matter: projects, people, places, organizations, decisions.
-
-When the user shares something that should survive future turns, store it in the
-smallest useful file; prefer updating an existing file over creating duplicates.
-Write concise, source-aware notes; include dates when timing matters.
-If a fact is corrected, update the memory and keep only useful history.
-When you add, move, or remove memory, update the nearest index.
-Before answering from memory, read the relevant index or file instead of guessing;
-if memory is missing or uncertain, say so and verify when it matters.
@@ -1,5 +0,0 @@
-# Memory Index
-
- [Memory system definition](system/definition.md)
- [Memories](memories/) - durable facts, people, projects, decisions
- [Data](data/) - structured reference data
@@ -4,6 +4,8 @@ import { writeMessageOut } from './db/messages-out.js';
 import { getInboundDb, touchHeartbeat, clearStaleProcessingAcks } from './db/connection.js';
 import { clearContinuation, migrateLegacyContinuation, setContinuation } from './db/session-state.js';
 import { clearCurrentInReplyTo, setCurrentInReplyTo } from './current-batch.js';
+import { loadConfig } from './config.js';
+import { createIdleTracker } from './idle-tracker.js';
 import {
  formatMessages,
  extractRouting,
@@ -14,7 +16,7 @@ import {
  type RoutingContext,
 } from './formatter.js';
 import { isUploadTraceCommand, uploadTrace } from './upload-trace.js';
-import type { AgentProvider, AgentQuery, ProviderEvent, ProviderExchange } from './providers/types.js';
+import type { AgentProvider, AgentQuery, ProviderEvent } from './providers/types.js';

 const POLL_INTERVAL_MS = 1000;
 const ACTIVE_POLL_INTERVAL_MS = 500;
@@ -63,12 +65,6 @@ export interface PollLoopConfig {
  systemContext?: {
    instructions?: string;
  };
-  /**
-   * Optional stop signal. In production the loop runs until the container
-   * dies; tests pass a signal so an abandoned loop actually exits instead of
-   * polling forever and stealing messages from the next test's DB.
-   */
-  signal?: AbortSignal;
 }

 /**
@@ -110,10 +106,15 @@ export async function runPollLoop(config: PollLoopConfig): Promise<void> {
  // This lets the new container re-process those messages.
  clearStaleProcessingAcks();

+  // Idle exit: when the group's container config sets idle_timeout_ms, an
+  // idle container exits 0 after the window elapses instead of riding until
+  // host-sweep's absolute ceiling kills it. Unset/0 = disabled (default).
+  const { idleTimeoutMs } = loadConfig();
+  const idle = createIdleTracker(idleTimeoutMs);
+
  let pollCount = 0;
  let isFirstPoll = true;
  while (true) {
-    if (config.signal?.aborted) return;
    // Skip system messages — they're responses for MCP tools (e.g., ask_user_question)
    const messages = getPendingMessages(isFirstPoll).filter((m) => m.kind !== 'system');
    isFirstPoll = false;
@@ -125,6 +126,10 @@ export async function runPollLoop(config: PollLoopConfig): Promise<void> {
    }

    if (messages.length === 0) {
+      if (idle.shouldExit()) {
+        log(`Idle timeout (${idleTimeoutMs}ms) — exiting`);
+        process.exit(0);
+      }
      await sleep(POLL_INTERVAL_MS);
      continue;
    }
@@ -239,15 +244,7 @@ export async function runPollLoop(config: PollLoopConfig): Promise<void> {
    // can stamp it on outbound rows — needed for a2a return-path routing.
    setCurrentInReplyTo(routing.inReplyTo);
    try {
-      const result = await processQuery(
-        query,
-        routing,
-        processingIds,
-        config.providerName,
-        config.provider.onExchangeComplete?.bind(config.provider),
-        prompt,
-        continuation,
-      );
+      const result = await processQuery(query, routing, processingIds, config.providerName, idleTimeoutMs);
      if (result.continuation && result.continuation !== continuation) {
        continuation = result.continuation;
        setContinuation(config.providerName, continuation);
@@ -281,6 +278,7 @@ export async function runPollLoop(config: PollLoopConfig): Promise<void> {
    // Ensure completed even if processQuery ended without a result event
    // (e.g. stream closed unexpectedly).
    markCompleted(processingIds);
+    idle.markActivity();
    log(`Completed ${ids.length} message(s)`);
  }
 }
@@ -328,18 +326,11 @@ async function processQuery(
  routing: RoutingContext,
  initialBatchIds: string[],
  providerName: string,
-  onExchangeComplete: ((exchange: ProviderExchange) => void) | undefined,
-  initialPrompt: string,
-  initialContinuation: string | undefined,
+  idleTimeoutMs: number = 0,
 ): Promise<QueryResult> {
  let queryContinuation: string | undefined;
  let done = false;
  let unwrappedNudged = false;
-  // Prompt queue for the exchange hook — each result event consumes the
-  // oldest unanswered prompt, except a wrapping-retry result, which answers
-  // the same prompt again. Unused (and unmaintained) when the provider
-  // doesn't implement `onExchangeComplete`.
-  const archivePrompts: string[] = [initialPrompt];

  // Concurrent polling: push follow-ups into the active query as they arrive.
  // We do NOT force-end the stream on silence — keeping the query open avoids
@@ -365,16 +356,13 @@ async function processQuery(
        // resume id (fixed at sdkQuery() time); admin/passthrough commands
        // (/compact, /cost, …) only dispatch when they're the first input
        // of a query — pushed mid-stream they arrive as plain text and
-        // the SDK never runs them. Abort the active stream and leave the
-        // rows pending; the outer loop handles them on next iteration via
-        // the canonical command path + formatMessagesWithCommands. Abort,
-        // not end: end() lets an in-flight turn run to completion, which
-        // can block the command (e.g. /clear during a long task) for as
-        // long as the turn takes.
+        // the SDK never runs them. End the stream and leave the rows
+        // pending; the outer loop handles them on next iteration via the
+        // canonical command path + formatMessagesWithCommands.
        if (pending.some((m) => isRunnerCommand(m))) {
-          log('Pending slash command — aborting active stream so outer loop can process');
+          log('Pending slash command — ending stream so outer loop can process');
          endedForCommand = true;
-          query.abort();
+          query.end();
          return;
        }

@@ -419,7 +407,6 @@ async function processQuery(
        log(`Pushing ${keep.length} follow-up message(s) into active query`);
        unwrappedNudged = false;
        query.push(prompt);
-        archivePrompts.push(prompt);
        markCompleted(keptIds);
      } catch (err) {
        // Without this catch the rejection escapes the void IIFE and Node
@@ -481,16 +468,10 @@ async function processQuery(
        // (send_message) mid-turn, or the message may not need a response
        // at all — either way the turn is finished.
        markCompleted(initialBatchIds);
+        let hasUnwrapped = false;
        if (event.text) {
-          const { hasUnwrapped } = dispatchResultText(event.text, routing);
-          const willRetryWrapping = hasUnwrapped && !unwrappedNudged;
-          notifyExchangeComplete(onExchangeComplete, {
-            prompt: archivePrompts[0] ?? initialPrompt,
-            result: event.text,
-            continuation: queryContinuation ?? initialContinuation,
-            status: hasUnwrapped ? 'undelivered' : 'completed',
-          });
-          if (willRetryWrapping) {
+          ({ hasUnwrapped } = dispatchResultText(event.text, routing));
+          if (hasUnwrapped && !unwrappedNudged) {
            unwrappedNudged = true;
            const destinations = getAllDestinations();
            const names = destinations.map((d) => d.name).join(', ');
@@ -501,23 +482,16 @@ async function processQuery(
                `Please re-send your response with the correct wrapping.</system>`,
            );
          }
-          // The wrapping-retry result answers the SAME user prompt — keep it
-          // queued so the retry archives against it, not the nudge text.
-          if (!willRetryWrapping) archivePrompts.shift();
-        } else {
-          archivePrompts.shift();
+        }
+        // When idleTimeoutMs is set, end the stream once the turn completes
+        // so the outer loop can evaluate the idle window. Skipped while the
+        // turn's output was unwrapped — the re-send nudge pushed above needs
+        // the stream to stay open for the corrected response.
+        if (idleTimeoutMs > 0 && !hasUnwrapped) {
+          query.end();
        }
      }
    }
-  } catch (err) {
-    const errMsg = err instanceof Error ? err.message : String(err);
-    notifyExchangeComplete(onExchangeComplete, {
-      prompt: archivePrompts[0] ?? initialPrompt,
-      result: `Error: ${errMsg}`,
-      continuation: queryContinuation ?? initialContinuation,
-      status: 'error',
-    });
-    throw err;
  } finally {
    done = true;
    clearInterval(pollHandle);
@@ -526,18 +500,6 @@ async function processQuery(
  return { continuation: queryContinuation };
 }

-function notifyExchangeComplete(
-  hook: ((exchange: ProviderExchange) => void) | undefined,
-  exchange: ProviderExchange,
-): void {
-  if (!hook) return;
-  try {
-    hook(exchange);
-  } catch (err) {
-    log(`onExchangeComplete failed: ${err instanceof Error ? err.message : String(err)}`);
-  }
-}
-
 function handleEvent(event: ProviderEvent, _routing: RoutingContext): void {
  switch (event.type) {
    case 'init':
@@ -6,25 +6,6 @@ export interface AgentProvider {
   */
  readonly supportsNativeSlashCommands: boolean;

-  /**
-   * Optional. When true, the runner scaffolds a persistent `memory/` tree in the
-   * agent's workspace at boot. Providers with their own native memory (e.g.
-   * Claude's `CLAUDE.local.md`) omit this and get nothing — memory is opt-in per
-   * provider, never gated on a provider name.
-   */
-  readonly usesMemoryScaffold?: boolean;
-
-  /**
-   * Optional. Called by the poll-loop after each completed exchange (a
-   * result, a wrapping retry, or an error). Providers whose harness keeps no
-   * on-disk transcript implement this to persist exchanges themselves (e.g.
-   * markdown into the agent's `conversations/` dir); providers that persist
-   * and archive their own transcript (e.g. the Claude Agent SDK's `.jsonl`)
-   * omit it. Best-effort: the loop catches and logs anything it throws. The
-   * implementation lives with the provider, never in the runner.
-   */
-  onExchangeComplete?(exchange: ProviderExchange): void;
-
  /** Start a new query. Returns a handle for streaming input and output. */
  query(input: QueryInput): AgentQuery;

@@ -50,16 +31,6 @@ export interface AgentProvider {
  maybeRotateContinuation?(continuation: string, cwd: string): string | null;
 }

-/** One prompt/result round-trip, as reported to `onExchangeComplete`. */
-export interface ProviderExchange {
-  /** The user prompt this exchange answers (never an internal retry nudge). */
-  prompt: string;
-  result: string | null;
-  /** Continuation/thread id in effect for the exchange, if any. */
-  continuation?: string;
-  status: 'completed' | 'undelivered' | 'error';
-}
-
 /**
 * Options passed to provider constructors. Fields are common to most
 * providers; individual providers may ignore any they don't need.
@@ -310,6 +310,7 @@ CREATE TABLE container_configs (
  image_tag              TEXT,
  assistant_name         TEXT,
  max_messages_per_prompt INTEGER,
+  idle_timeout_ms        INTEGER,                         -- idle-exit window (ms); NULL/0 = disabled
  skills                 TEXT NOT NULL DEFAULT '"all"',
  mcp_servers            TEXT NOT NULL DEFAULT '{}',
  packages_apt           TEXT NOT NULL DEFAULT '[]',
@@ -344,6 +345,7 @@ Migrations live in `src/db/migrations/`, one file per migration. Runner: `runMig
 | 009 | `009-drop-pending-credentials.ts` | Drop the defunct `pending_credentials` table |
 | 014 | `014-container-configs.ts` | `container_configs` — per-agent-group container runtime config |
 | 015 | `015-cli-scope.ts` | `ALTER TABLE container_configs ADD COLUMN cli_scope` |
+| 016 | `016-container-idle-timeout.ts` | `ALTER TABLE container_configs ADD COLUMN idle_timeout_ms` |

 Numbers 005 and 006 are intentionally absent — migrations were renumbered during early development.

@@ -1,83 +0,0 @@
-# Upgrading the OneCLI gateway
-
-NanoClaw talks to the OneCLI gateway (credential vault + egress proxy) through `@onecli-sh/sdk`. The gateway is an external component with its own release line, so NanoClaw pins the **sanctioned gateway version** in [`versions.json`](../versions.json) under `onecli-gateway`. When an update moves that pin, the gateway must be upgraded — this doc is the migration path. It is written to be handed to a coding agent verbatim: detect → upgrade → verify → rollback.
-
-There is deliberately **no runtime version check, and setup does not migrate the gateway for you**: the gateway is a separate out-of-band component, and the migrator is your coding agent running `/update-nanoclaw` — it diffs `versions.json` across the update and routes you here when the `onecli-gateway` pin moved. (Setup detects a pre-`/v1` gateway and points at this doc, but never upgrades it.) Run the steps below verbatim.
-
-## 1. Detect
-
-Find out what is running and what is required:
-
-```bash
-cat versions.json                                   # the sanctioned pin
-curl -s http://127.0.0.1:10254/api/health           # reports the running gateway version
-curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:10254/v1/health
-```
-
-If the last command prints `404`, the server predates the `/v1` API that `@onecli-sh/sdk` 2.x requires — every SDK call will fail with 404s that look transient but are permanent. If your gateway is remote, substitute its host for `127.0.0.1` (it's in `.env` as `ONECLI_URL` / `NANOCLAW_ONECLI_API_HOST`).
-
-Why gateways fall behind: the OneCLI installer's docker-compose tracks the `latest` image tag, but Docker never re-pulls a tag — the server freezes at whatever `latest` meant on install day.
-
-## 2. Upgrade
-
-The gateway runs as a Docker service in `~/.onecli`. Upgrade just that container to the pinned `onecli-gateway` version — vault data lives in named Docker volumes and survives. This upgrades only the gateway; the CLI binary is pinned separately (see below).
-
-**Local gateway (the common case):**
-
-```bash
-cd ~/.onecli && ONECLI_VERSION=<onecli-gateway pin from versions.json> docker compose pull onecli && docker compose up -d
-```
-
-**Remote gateway** — run the same command on the gateway's host (NanoClaw can't reach it over SSH).
-
-## 3. Verify
-
-Host-side health is necessary but **not sufficient**:
-
-```bash
-curl -s http://127.0.0.1:10254/v1/health     # must return {"status":"ok",...}
-```
-
-**Verify the bind interface (container reachability).** Agent containers reach the gateway over the docker bridge (`host.docker.internal` → e.g. `172.17.0.1`), so a server bound only to `127.0.0.1` boots clean host-side while every credentialed call from containers dies at the proxy:
-
-```bash
-docker run --rm --add-host=host.docker.internal:host-gateway \
-  curlimages/curl -s -o /dev/null -w '%{http_code}' http://host.docker.internal:10254/v1/health
-```
-
-This must print `200`. If it can't connect while the host-side check passed, set the bind address in `~/.onecli/.env` to the docker-bridge IP (or `0.0.0.0` on a host with a closed firewall) and `cd ~/.onecli && docker compose up -d`. Symptom if skipped: host log clean, agents fail all API calls.
-
-Finally, restart the NanoClaw service (per-install names — derive with `setup/lib/install-slug.sh`):
-
-```bash
-# macOS
-source setup/lib/install-slug.sh && launchctl kickstart -k gui/$(id -u)/$(launchd_label)
-# Linux
-source setup/lib/install-slug.sh && systemctl --user restart $(systemd_unit)
-```
-
-## 4. Rollback
-
-```bash
-cd ~/.onecli && ONECLI_VERSION=<old-version> docker compose up -d
-```
-
-If the NanoClaw update itself is being rolled back, also pin `@onecli-sh/sdk` back to its previous version in `package.json` and run `pnpm install`. Vault data is unaffected in both directions.
-
-## The CLI binary (`onecli-cli` pin)
-
-The `onecli` host CLI is pinned the same way, under `onecli-cli` in `versions.json`. Setup installs exactly that version by direct release download — it never resolves "latest". When an update moves this pin, replace the binary with the pinned release:
-
-```bash
-onecli --version                                            # detect: what is installed
-V=<onecli-cli pin from versions.json>
-OS=$(uname -s | tr '[:upper:]' '[:lower:]')                 # darwin | linux
-ARCH=$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/')   # amd64 | arm64
-curl -fsSL -o /tmp/onecli.tgz \
-  "https://github.com/onecli/onecli-cli/releases/download/v${V}/onecli_${V}_${OS}_${ARCH}.tar.gz"
-tar -xzf /tmp/onecli.tgz -C /tmp
-install -m 0755 /tmp/onecli "$(command -v onecli || echo ~/.local/bin/onecli)"
-onecli --version                                            # verify: must match versions.json
-```
-
-To roll back, run the same block after reverting `versions.json` (or checking out the previous NanoClaw version). The CLI is stateless — vault data lives in the gateway, so swapping the binary in either direction loses nothing.
@@ -1,6 +1,6 @@
 {
  "name": "nanoclaw",
-  "version": "2.1.13",
+  "version": "2.1.10",
  "description": "Personal Claude assistant. Lightweight, secure, customizable.",
  "type": "module",
  "packageManager": "pnpm@10.33.0",
@@ -30,7 +30,7 @@
  "dependencies": {
    "@clack/core": "^1.2.0",
    "@clack/prompts": "^1.2.0",
-    "@onecli-sh/sdk": "2.2.1",
+    "@onecli-sh/sdk": "^0.5.0",
    "better-sqlite3": "11.10.0",
    "chat": "^4.24.0",
    "cron-parser": "5.5.0",
@@ -15,8 +15,8 @@ importers:
        specifier: ^1.2.0
        version: 1.2.0
      '@onecli-sh/sdk':
-        specifier: 2.2.1
-        version: 2.2.1
+        specifier: ^0.5.0
+        version: 0.5.0
      better-sqlite3:
        specifier: 11.10.0
        version: 11.10.0
@@ -303,8 +303,8 @@ packages:
      '@emnapi/core': ^1.7.1
      '@emnapi/runtime': ^1.7.1

-  '@onecli-sh/sdk@2.2.1':
-    resolution: {integrity: sha512-q2mCW4ZsARlLEoTxz/P0NQ4MiCh7Z2n28pxkSc7srS+tozyw40PdTnWYW7NI8hfSYplZTx5856Adq1iPi4KN3Q==}
+  '@onecli-sh/sdk@0.5.0':
+    resolution: {integrity: sha512-oe5Yx9o98v6N1PgzcCR7nULHHqcqKWNJIDOHGOSNX+l20mLlZpFUqfKPeFmsojBNRQMoqbvZQKUlFMp6gVuYBA==}
    engines: {node: '>=20'}

  '@oxc-project/types@0.124.0':
@@ -1665,7 +1665,7 @@ snapshots:
      '@tybys/wasm-util': 0.10.1
    optional: true

-  '@onecli-sh/sdk@2.2.1': {}
+  '@onecli-sh/sdk@0.5.0': {}

  '@oxc-project/types@0.124.0': {}

@@ -1,5 +1,5 @@
-<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="90" height="20" role="img" aria-label="192k tokens, 96% of context window">
-  <title>192k tokens, 96% of context window</title>
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="90" height="20" role="img" aria-label="190k tokens, 95% of context window">
+  <title>190k tokens, 95% of context window</title>
  <linearGradient id="s" x2="0" y2="100%">
    <stop offset="0" stop-color="#bbb" stop-opacity=".1"/>
    <stop offset="1" stop-opacity=".1"/>
@@ -15,8 +15,8 @@
      <g fill="#fff" text-anchor="middle" font-family="Verdana,Geneva,DejaVu Sans,sans-serif" font-size="11">
        <text aria-hidden="true" x="26" y="15" fill="#010101" fill-opacity=".3">tokens</text>
        <text x="26" y="14">tokens</text>
-        <text aria-hidden="true" x="71" y="15" fill="#010101" fill-opacity=".3">192k</text>
-        <text x="71" y="14">192k</text>
+        <text aria-hidden="true" x="71" y="15" fill="#010101" fill-opacity=".3">190k</text>
+        <text x="71" y="14">190k</text>
      </g>
    </g>
  </a>
@@ -1,48 +0,0 @@
-/**
- * versions.json is the machine-checkable source for sanctioned component
- * versions: setup steps read it, /update-nanoclaw diffs it across updates.
- * These tests go red if the file, the pin, or the onecli-step wiring is
- * deleted — the pin moving back to a hardcoded constant is the regression
- * this guards against.
- */
-import fs from 'fs';
-import path from 'path';
-import { fileURLToPath } from 'url';
-
-import { describe, expect, it } from 'vitest';
-
-import { readVersionPin } from './version-pins.js';
-
-const here = path.dirname(fileURLToPath(import.meta.url));
-
-describe('readVersionPin', () => {
-  it('resolves the onecli-gateway pin from the real versions.json', () => {
-    expect(readVersionPin('onecli-gateway')).toMatch(/^\d+\.\d+\.\d+$/);
-  });
-
-  it('resolves the onecli-cli pin from the real versions.json', () => {
-    expect(readVersionPin('onecli-cli')).toMatch(/^\d+\.\d+\.\d+$/);
-  });
-
-  it('throws for a component with no pin', () => {
-    expect(() => readVersionPin('no-such-component')).toThrow(/no pin/);
-  });
-});
-
-describe('onecli step wiring', () => {
-  it('reads its gateway pin from versions.json, not a hardcoded constant', () => {
-    const source = fs.readFileSync(path.join(here, '..', 'onecli.ts'), 'utf-8');
-    expect(source).toContain("readVersionPin('onecli-gateway')");
-    expect(source).not.toMatch(/ONECLI_GATEWAY_VERSION = '\d/);
-  });
-
-  it('reads its CLI pin from versions.json and never resolves "latest"', () => {
-    const source = fs.readFileSync(path.join(here, '..', 'onecli.ts'), 'utf-8');
-    expect(source).toContain("readVersionPin('onecli-cli')");
-    expect(source).not.toMatch(/ONECLI_CLI(?:_FALLBACK)?_VERSION = '\d/);
-    // The upstream installer and the /releases/latest redirect probe both
-    // chase "latest" — reintroducing either bypasses the sanctioned pin.
-    expect(source).not.toContain('onecli.sh/cli/install');
-    expect(source).not.toContain('/releases/latest');
-  });
-});
@@ -1,31 +0,0 @@
-/**
- * Sanctioned version pins for external components (`versions.json` at the
- * repo root) — the single machine-checkable source. Setup steps read their
- * pin here; `/update-nanoclaw` diffs the file across an update and routes
- * the user to the migration doc for any pin that moved (see CONTRIBUTING.md,
- * "Breaking changes").
- */
-import fs from 'fs';
-import path from 'path';
-import { fileURLToPath } from 'url';
-
-const VERSIONS_FILE = path.resolve(
-  path.dirname(fileURLToPath(import.meta.url)),
-  '..',
-  '..',
-  'versions.json',
-);
-
-/**
- * Returns the pinned version for a component, e.g.
- * `readVersionPin('onecli-gateway')`. Throws when the file or the pin is
- * missing — a missing pin is an install-tree defect, not a runtime condition.
- */
-export function readVersionPin(component: string): string {
-  const pins: unknown = JSON.parse(fs.readFileSync(VERSIONS_FILE, 'utf-8'));
-  const value = (pins as Record<string, unknown>)[component];
-  if (typeof value !== 'string' || value.length === 0) {
-    throw new Error(`versions.json has no pin for "${component}"`);
-  }
-  return value;
-}
@@ -1,29 +0,0 @@
-/**
- * The step DETECTS gateway /v1 compatibility and warns (pointing at
- * docs/onecli-upgrades.md) — it does not migrate the gateway; that's the
- * agent's job via /update-nanoclaw. The verify helper must distinguish
- * incompatible (pre-/v1 server: warn) from unreachable (transient: nothing to
- * say) so the warning only fires on a real pre-/v1 server.
- */
-import { describe, expect, it } from 'vitest';
-
-import { verifyGatewayV1 } from './onecli.js';
-
-function fakeFetch(behavior: 'ok' | '404' | 'down'): typeof fetch {
-  return (async () => {
-    if (behavior === 'down') throw new Error('ECONNREFUSED');
-    return { ok: behavior === 'ok' } as Response;
-  }) as unknown as typeof fetch;
-}
-
-describe('verifyGatewayV1', () => {
-  it('ok when /v1/health answers', async () => {
-    expect(await verifyGatewayV1('http://x', fakeFetch('ok'))).toBe('ok');
-  });
-  it('incompatible when the server answers HTTP without /v1', async () => {
-    expect(await verifyGatewayV1('http://x', fakeFetch('404'))).toBe('incompatible');
-  });
-  it('unreachable on connection failure', async () => {
-    expect(await verifyGatewayV1('http://x', fakeFetch('down'))).toBe('unreachable');
-  });
-});
@@ -17,7 +17,6 @@ import os from 'os';
 import path from 'path';

 import { log } from '../src/log.js';
-import { readVersionPin } from './lib/version-pins.js';
 import { emitStatus } from './status.js';

 const LOCAL_BIN = path.join(os.homedir(), '.local', 'bin');
@@ -103,18 +102,20 @@ function writeEnvOnecliUrl(url: string): void {
  writeEnvVar('ONECLI_URL', url);
 }

-// The SANCTIONED gateway version: fresh installs pin to it. Upgrading an
-// existing gateway is NOT done here — the gateway is a separate out-of-band
-// component, and the migrator is the user's coding agent following
-// docs/onecli-upgrades.md during /update-nanoclaw. The pin lives in
-// versions.json ("onecli-gateway") so that flow can diff it across updates and
-// route the agent to the doc; bump it there deliberately on a new release.
-const ONECLI_GATEWAY_VERSION = readVersionPin('onecli-gateway');
-// The CLI binary follows the same convention: installed at its pin
-// ("onecli-cli" in versions.json), never at whatever "latest" means today.
-const ONECLI_CLI_VERSION = readVersionPin('onecli-cli');
+// Last-known-good CLI release. Used only if BOTH the upstream installer
+// and the redirect-based version probe fail. Bump deliberately when a
+// new CLI release ships.
+const ONECLI_GATEWAY_VERSION = '1.23.0';
+const ONECLI_CLI_FALLBACK_VERSION = '1.3.0';
 const ONECLI_CLI_REPO = 'onecli/onecli-cli';

+function installOnecliCliOnly(): { stdout: string; ok: boolean } {
+  const upstream = runInstall('curl -fsSL onecli.sh/cli/install | sh');
+  if (upstream.ok) return { stdout: upstream.stdout, ok: true };
+  const fallback = installOnecliCliDirect();
+  return { stdout: upstream.stdout + (upstream.stderr ?? '') + '\n' + fallback.stdout, ok: fallback.ok };
+}
+
 // Remove containers in the "onecli" compose project whose service name isn't
 // in the v2 set. Pre-v2 OneCLI used service "app" (container onecli-app-1);
 // v2 uses "onecli". Compose flags the old container as an orphan but won't
@@ -160,10 +161,24 @@ function installOnecli(): { stdout: string; ok: boolean } {
    return { stdout: stdout + (gw.stderr ?? ''), ok: false };
  }

-  const cli = installOnecliCliDirect();
-  stdout += cli.stdout;
-  if (!cli.ok) {
-    log.error('OneCLI CLI install failed');
+  // CLI install. The upstream script calls the GitHub releases API
+  // (api.github.com) to resolve the latest tag — which 403s anonymous
+  // callers after 60 requests/hour per IP. Try upstream first; on failure
+  // resolve the version ourselves (via HTTP redirect, which isn't
+  // API-throttled) and download the release archive directly.
+  const upstream = runInstall('curl -fsSL onecli.sh/cli/install | sh');
+  stdout += upstream.stdout;
+  if (upstream.ok) return { stdout, ok: true };
+
+  log.warn('Upstream CLI installer failed — falling back to direct download', {
+    stderr: upstream.stderr,
+  });
+  stdout += (upstream.stderr ?? '') + '\n';
+
+  const fallback = installOnecliCliDirect();
+  stdout += fallback.stdout;
+  if (!fallback.ok) {
+    log.error('OneCLI CLI install failed (both upstream and direct fallback)');
    return { stdout, ok: false };
  }
  return { stdout, ok: true };
@@ -183,11 +198,11 @@ function runInstall(cmd: string): { stdout: string; stderr?: string; ok: boolean
 }

 /**
- * Install the OneCLI CLI at the sanctioned pin by downloading the release
- * archive straight from GitHub. Deliberately no "latest" resolution — the
- * upstream installer script always chases the newest release, which would
- * drift from the pin. PATH setup is not lost by skipping it:
- * ensureShellProfilePath() in run() covers it.
+ * Reinstate the OneCLI CLI install without hitting GitHub's rate-limited
+ * releases API. Resolves the version via the HTTP redirect from
+ * /releases/latest → /releases/tag/vX.Y.Z, then downloads the archive
+ * directly. Falls back to ONECLI_CLI_FALLBACK_VERSION if the redirect
+ * probe also fails.
 */
 function installOnecliCliDirect(): { stdout: string; ok: boolean } {
  const lines: string[] = [];
@@ -206,7 +221,24 @@ function installOnecliCliDirect(): { stdout: string; ok: boolean } {
    return { stdout: lines.join('\n'), ok: false };
  }

-  const version = ONECLI_CLI_VERSION;
+  let version: string | null = null;
+  try {
+    const redirect = execSync(
+      `curl -fsSL -o /dev/null -w '%{url_effective}' https://github.com/${ONECLI_CLI_REPO}/releases/latest`,
+      { encoding: 'utf-8', stdio: ['ignore', 'pipe', 'pipe'] },
+    ).trim();
+    const m = redirect.match(/\/tag\/v?([^/]+)$/);
+    if (m) version = m[1];
+  } catch {
+    // redirect probe failed — we'll pin the fallback
+  }
+  if (!version) {
+    version = ONECLI_CLI_FALLBACK_VERSION;
+    append(`Version probe failed; installing pinned fallback ${version}.`);
+  } else {
+    append(`Resolved onecli CLI ${version} via release redirect.`);
+  }
+
  const archive = `onecli_${version}_${osName}_${arch}.tar.gz`;
  const url = `https://github.com/${ONECLI_CLI_REPO}/releases/download/v${version}/${archive}`;
  const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'onecli-'));
@@ -243,39 +275,6 @@ function installOnecliCliDirect(): { stdout: string; ok: boolean } {
  }
 }

-/**
- * /v1 API compatibility check. @onecli-sh/sdk 2.x requires the server's /v1
- * API; servers older than the cutover answer 404 on every SDK call (permanent,
- * but presents as transient per-spawn failures). This is detect-only — setup
- * does not migrate the gateway. The upgrade is an out-of-band action on a
- * separate component that the agent runs via docs/onecli-upgrades.md during
- * /update-nanoclaw, so this step only surfaces the condition and points there.
- */
-export async function verifyGatewayV1(
-  url: string,
-  fetchImpl: typeof fetch = fetch,
-): Promise<'ok' | 'incompatible' | 'unreachable'> {
-  try {
-    const res = await fetchImpl(`${url}/v1/health`, { signal: AbortSignal.timeout(5000) });
-    return res.ok ? 'ok' : 'incompatible';
-  } catch {
-    return 'unreachable';
-  }
-}
-
-/**
- * Detect-and-warn helper: returns a status HINT (and logs) when the gateway is
- * pre-/v1, else null. Never fails the step or auto-upgrades — the agent owns
- * the upgrade via docs/onecli-upgrades.md.
- */
-function gatewayV1Hint(result: 'ok' | 'incompatible' | 'unreachable'): string | null {
-  if (result !== 'incompatible') return null;
-  log.warn('OneCLI gateway lacks the /v1 API @onecli-sh/sdk 2.x requires', {
-    pin: ONECLI_GATEWAY_VERSION,
-  });
-  return 'OneCLI gateway lacks the /v1 API @onecli-sh/sdk 2.x requires — upgrade it: docs/onecli-upgrades.md';
-}
-
 export async function pollHealth(url: string, timeoutMs: number): Promise<boolean> {
  // `/api/health` matches the path probe.sh uses — keep them aligned.
  const deadline = Date.now() + timeoutMs;
@@ -301,7 +300,7 @@ export async function run(args: string[]): Promise<void> {
    // Remote-mode: install only the CLI, point it at the remote gateway, and
    // record the URL in .env. No local gateway is started.
    log.info('Installing OneCLI CLI for remote gateway', { remoteUrl });
-    const res = installOnecliCliDirect();
+    const res = installOnecliCliOnly();
    if (!res.ok || !onecliVersion()) {
      emitStatus('ONECLI', {
        INSTALLED: false,
@@ -340,14 +339,12 @@ export async function run(args: string[]): Promise<void> {
      log.info('Wrote ONECLI_API_KEY to .env');
    }
    const healthy = await pollHealth(remoteUrl, 5000);
-    const v1Hint = healthy ? gatewayV1Hint(await verifyGatewayV1(remoteUrl)) : null;
    emitStatus('ONECLI', {
      INSTALLED: true,
      REMOTE: true,
      ONECLI_URL: remoteUrl,
      HEALTHY: healthy,
      STATUS: 'success',
-      ...(v1Hint ? { GATEWAY_HINT: v1Hint } : {}),
      LOG: 'logs/setup.log',
    });
    return;
@@ -381,14 +378,12 @@ export async function run(args: string[]): Promise<void> {
    writeEnvOnecliUrl(url);
    log.info('Reusing existing OneCLI', { url });
    const healthy = await pollHealth(url, 5000);
-    const v1Hint = healthy ? gatewayV1Hint(await verifyGatewayV1(url)) : null;
    emitStatus('ONECLI', {
      INSTALLED: true,
      REUSED: true,
      ONECLI_URL: url,
      HEALTHY: healthy,
      STATUS: 'success',
-      ...(v1Hint ? { GATEWAY_HINT: v1Hint } : {}),
      LOG: 'logs/setup.log',
    });
    return;
@@ -441,7 +436,6 @@ export async function run(args: string[]): Promise<void> {
  log.info('Wrote ONECLI_URL to .env', { url });

  const healthy = await pollHealth(url, 15000);
-  const v1Hint = healthy ? gatewayV1Hint(await verifyGatewayV1(url)) : null;

  emitStatus('ONECLI', {
    INSTALLED: true,
@@ -452,7 +446,6 @@ export async function run(args: string[]): Promise<void> {
    // The next step (auth) will surface a genuinely broken gateway via
    // `onecli secrets list`, so don't trigger rescue attempts from here.
    STATUS: 'success',
-    ...(v1Hint ? { GATEWAY_HINT: v1Hint } : {}),
    ...(healthy
      ? {}
      : {
@@ -59,6 +59,7 @@ export function backfillContainerConfigs(): void {
      image_tag: legacy.imageTag ?? null,
      assistant_name: legacy.assistantName ?? null,
      max_messages_per_prompt: legacy.maxMessagesPerPrompt ?? null,
+      idle_timeout_ms: null,
      skills: JSON.stringify(legacy.skills ?? 'all'),
      mcp_servers: JSON.stringify(legacy.mcpServers ?? {}),
      packages_apt: JSON.stringify(legacy.packages?.apt ?? []),
@@ -22,6 +22,7 @@ function presentConfig(row: ContainerConfigRow): Record<string, unknown> {
    image_tag: row.image_tag,
    assistant_name: row.assistant_name,
    max_messages_per_prompt: row.max_messages_per_prompt,
+    idle_timeout_ms: row.idle_timeout_ms,
    skills: JSON.parse(row.skills),
    mcp_servers: JSON.parse(row.mcp_servers),
    packages_apt: JSON.parse(row.packages_apt),
@@ -213,7 +214,7 @@ registerResource({
      access: 'approval',
      description:
        'Update container config scalar fields. Changes are saved but do NOT take effect until you run `ncl groups restart`. ' +
-        'Use --id <group-id> and any of: --provider, --model, --effort, --image-tag, --assistant-name, --max-messages-per-prompt, --cli-scope.',
+        'Use --id <group-id> and any of: --provider, --model, --effort, --image-tag, --assistant-name, --max-messages-per-prompt, --idle-timeout-ms, --cli-scope.',
      handler: async (args) => {
        const id = args.id as string;
        if (!id) throw new Error('--id is required');
@@ -223,7 +224,14 @@ registerResource({
        const updates: Partial<
          Pick<
            ContainerConfigRow,
-            'provider' | 'model' | 'effort' | 'image_tag' | 'assistant_name' | 'max_messages_per_prompt' | 'cli_scope'
+            | 'provider'
+            | 'model'
+            | 'effort'
+            | 'image_tag'
+            | 'assistant_name'
+            | 'max_messages_per_prompt'
+            | 'idle_timeout_ms'
+            | 'cli_scope'
          >
        > = {};
        if (args.provider !== undefined) updates.provider = args.provider as string;
@@ -233,6 +241,7 @@ registerResource({
        if (args.assistant_name !== undefined) updates.assistant_name = args.assistant_name as string;
        if (args.max_messages_per_prompt !== undefined)
          updates.max_messages_per_prompt = Number(args.max_messages_per_prompt);
+        if (args.idle_timeout_ms !== undefined) updates.idle_timeout_ms = Number(args.idle_timeout_ms);
        if (args['cli-scope'] !== undefined || args.cli_scope !== undefined) {
          const scope = (args['cli-scope'] ?? args.cli_scope) as string;
          if (!['disabled', 'group', 'global'].includes(scope)) {
@@ -243,7 +252,7 @@ registerResource({

        if (Object.keys(updates).length === 0) {
          throw new Error(
-            'Nothing to update — provide at least one of: --provider, --model, --effort, --image-tag, --assistant-name, --max-messages-per-prompt, --cli-scope',
+            'Nothing to update — provide at least one of: --provider, --model, --effort, --image-tag, --assistant-name, --max-messages-per-prompt, --idle-timeout-ms, --cli-scope',
          );
        }

@@ -0,0 +1,82 @@
+/**
+ * idle_timeout_ms threading — migration 016 column → `ContainerConfigRow` →
+ * `configFromDb()` → `materializeContainerJson()` → `container.json`.
+ *
+ * The default leg is load-bearing: a NULL column must keep `idleTimeoutMs`
+ * out of container.json entirely, so groups that never set the value get
+ * today's behavior byte-identical (the container-side loadConfig then
+ * defaults to 0 = idle exit disabled).
+ */
+import fs from 'fs';
+import path from 'path';
+import { describe, expect, it, beforeEach, afterEach, vi } from 'vitest';
+
+vi.mock('./config.js', async () => {
+  const actual = await vi.importActual('./config.js');
+  return { ...actual, GROUPS_DIR: '/tmp/nanoclaw-test-container-config/groups' };
+});
+
+const TEST_DIR = '/tmp/nanoclaw-test-container-config';
+const GROUPS_DIR = path.join(TEST_DIR, 'groups');
+
+import { initTestDb, closeDb, runMigrations } from './db/index.js';
+import { createAgentGroup, getAgentGroup } from './db/agent-groups.js';
+import { ensureContainerConfig, getContainerConfig, updateContainerConfigScalars } from './db/container-configs.js';
+import { configFromDb, materializeContainerJson } from './container-config.js';
+
+const GID = 'ag-idle';
+
+function now(): string {
+  return new Date().toISOString();
+}
+
+describe('container config idle_timeout_ms threading', () => {
+  beforeEach(() => {
+    if (fs.existsSync(TEST_DIR)) fs.rmSync(TEST_DIR, { recursive: true });
+    fs.mkdirSync(GROUPS_DIR, { recursive: true });
+
+    const db = initTestDb();
+    runMigrations(db);
+
+    createAgentGroup({ id: GID, name: 'idle-group', folder: 'idle-group', agent_provider: null, created_at: now() });
+    ensureContainerConfig(GID);
+  });
+
+  afterEach(() => {
+    closeDb();
+    if (fs.existsSync(TEST_DIR)) fs.rmSync(TEST_DIR, { recursive: true });
+  });
+
+  it('updateContainerConfigScalars persists idle_timeout_ms and configFromDb threads it', () => {
+    updateContainerConfigScalars(GID, { idle_timeout_ms: 300000 });
+
+    const row = getContainerConfig(GID)!;
+    expect(row.idle_timeout_ms).toBe(300000);
+
+    const config = configFromDb(row, getAgentGroup(GID)!);
+    expect(config.idleTimeoutMs).toBe(300000);
+  });
+
+  it('materializeContainerJson writes idleTimeoutMs into container.json', () => {
+    updateContainerConfigScalars(GID, { idle_timeout_ms: 300000 });
+
+    const config = materializeContainerJson(GID);
+    expect(config.idleTimeoutMs).toBe(300000);
+
+    const written = JSON.parse(fs.readFileSync(path.join(GROUPS_DIR, 'idle-group', 'container.json'), 'utf8'));
+    expect(written.idleTimeoutMs).toBe(300000);
+  });
+
+  it('NULL column (the default) keeps idleTimeoutMs out of container.json — feature off', () => {
+    const row = getContainerConfig(GID)!;
+    expect(row.idle_timeout_ms).toBeNull();
+
+    const config = configFromDb(row, getAgentGroup(GID)!);
+    expect(config.idleTimeoutMs).toBeUndefined();
+
+    materializeContainerJson(GID);
+    const written = JSON.parse(fs.readFileSync(path.join(GROUPS_DIR, 'idle-group', 'container.json'), 'utf8'));
+    // JSON.stringify drops undefined — the key must be absent, not null/0.
+    expect('idleTimeoutMs' in written).toBe(false);
+  });
+});
@@ -41,6 +41,8 @@ export interface ContainerConfig {
  assistantName?: string;
  agentGroupId?: string;
  maxMessagesPerPrompt?: number;
+  /** Idle window in ms after which an idle container exits cleanly. Unset/0 = disabled. */
+  idleTimeoutMs?: number;
  model?: string;
  effort?: string;
 }
@@ -61,6 +63,7 @@ export function configFromDb(row: ContainerConfigRow, group: AgentGroup): Contai
    assistantName: row.assistant_name ?? group.name,
    agentGroupId: group.id,
    maxMessagesPerPrompt: row.max_messages_per_prompt ?? undefined,
+    idleTimeoutMs: row.idle_timeout_ms ?? undefined,
    model: row.model ?? undefined,
    effort: row.effort ?? undefined,
  };
@@ -1,5 +1,3 @@
-import fs from 'fs';
-import path from 'path';
 import { describe, expect, it } from 'vitest';

 import { resolveProviderName } from './container-runner.js';
@@ -27,22 +25,3 @@ describe('resolveProviderName', () => {
    expect(resolveProviderName(null, '')).toBe('claude');
  });
 });
-
-describe('buildContainerArgs ordering invariant (structural)', () => {
-  // The OneCLI gateway apply (SDK applyContainerConfig) appends credential-stub
-  // mounts — e.g. the codex auth.json sentinel nested INSIDE our RW
-  // /home/node/.codex mount. Docker applies binds in argument order, so the
-  // stub must land AFTER its parent mount or the parent shadows it and the
-  // agent silently degrades to loginless auth. Driving the real
-  // buildContainerArgs needs a live gateway + container runtime, so this
-  // guards the invariant structurally: the gateway apply must appear after
-  // the volume-mounts loop in the source.
-  it('applies the OneCLI gateway after the volume mounts', () => {
-    const src = fs.readFileSync(path.join(process.cwd(), 'src', 'container-runner.ts'), 'utf-8');
-    const mountsLoop = src.indexOf('for (const mount of mounts)');
-    const gatewayApply = src.indexOf('onecli.applyContainerConfig');
-    expect(mountsLoop).toBeGreaterThan(-1);
-    expect(gatewayApply).toBeGreaterThan(-1);
-    expect(gatewayApply).toBeGreaterThan(mountsLoop);
-  });
-});
@@ -36,7 +36,6 @@ import { validateAdditionalMounts } from './modules/mount-security/index.js';
 import './providers/index.js';
 import {
  getProviderContainerConfig,
-  providerProvidesAgentSurfaces,
  type ProviderContainerContribution,
  type VolumeMount,
 } from './providers/provider-container-registry.js';
@@ -128,19 +127,12 @@ async function spawnContainer(session: Session): Promise<void> {
  // and buildContainerArgs so we don't re-read.
  const containerConfig = materializeContainerJson(agentGroup.id);

-  // Per-group filesystem state lives forever after first creation. Init is
-  // idempotent: it only writes paths that don't already exist, so this call
-  // is a no-op for groups that have spawned before. Runs before the provider
-  // contribution so a surfaces-providing provider finds the group dir ready.
-  const providerName = resolveProviderName(session.agent_provider, containerConfig.provider);
-  initGroupFilesystem(agentGroup, { provider: providerName });
-
  // Resolve the effective provider + any host-side contribution it declares
  // (extra mounts, env passthrough). Computed once and threaded through both
  // buildMounts and buildContainerArgs so side effects (mkdir, etc.) fire once.
  const { provider, contribution } = resolveProviderContribution(session, agentGroup, containerConfig);

-  const mounts = buildMounts(agentGroup, session, containerConfig, provider, contribution);
+  const mounts = buildMounts(agentGroup, session, containerConfig, contribution);
  const containerName = `nanoclaw-v2-${agentGroup.folder}-${Date.now()}`;
  // OneCLI agent identifier is always the agent group id — stable across
  // sessions and reversible via getAgentGroup() for approval routing.
@@ -242,37 +234,32 @@ function resolveProviderContribution(
    ? fn({
        sessionDir: sessionDir(agentGroup.id, session.id),
        agentGroupId: agentGroup.id,
-        groupDir: path.resolve(GROUPS_DIR, agentGroup.folder),
-        selectedSkills: selectedSkillNames(containerConfig),
        hostEnv: process.env,
      })
    : {};
  return { provider, contribution };
 }

-export function buildMounts(
+function buildMounts(
  agentGroup: AgentGroup,
  session: Session,
  containerConfig: import('./container-config.js').ContainerConfig,
-  provider: string,
  providerContribution: ProviderContainerContribution,
 ): VolumeMount[] {
  const projectRoot = process.cwd();

-  // Default agent surfaces (composed project doc, skill links, provider state
-  // dir) apply unless the provider's registration declares it provides its
-  // own — a capability, never a provider name. See provider-container-registry.
-  const defaultSurfaces = !providerProvidesAgentSurfaces(provider);
+  // Per-group filesystem state lives forever after first creation. Init is
+  // idempotent: it only writes paths that don't already exist, so this call
+  // is a no-op for groups that have spawned before.
+  initGroupFilesystem(agentGroup);

+  // Sync skill symlinks based on container.json selection before mounting.
  const claudeDir = path.join(DATA_DIR, 'v2-sessions', agentGroup.id, '.claude-shared');
-  if (defaultSurfaces) {
-    // Sync skill symlinks based on container.json selection before mounting.
-    syncSkillSymlinks(claudeDir, containerConfig);
+  syncSkillSymlinks(claudeDir, containerConfig);

-    // Compose CLAUDE.md fresh every spawn from the shared base, enabled skill
-    // fragments, and MCP server instructions. See `claude-md-compose.ts`.
-    composeGroupClaudeMd(agentGroup);
-  }
+  // Compose CLAUDE.md fresh every spawn from the shared base, enabled skill
+  // fragments, and MCP server instructions. See `claude-md-compose.ts`.
+  composeGroupClaudeMd(agentGroup);

  const mounts: VolumeMount[] = [];
  const sessDir = sessionDir(agentGroup.id, session.id);
@@ -299,11 +286,11 @@ export function buildMounts(
  // already RO-mounted, so writes through it fail regardless — no need for
  // a nested mount there.
  const composedClaudeMd = path.join(groupDir, 'CLAUDE.md');
-  if (defaultSurfaces && fs.existsSync(composedClaudeMd)) {
+  if (fs.existsSync(composedClaudeMd)) {
    mounts.push({ hostPath: composedClaudeMd, containerPath: '/workspace/agent/CLAUDE.md', readonly: true });
  }
  const fragmentsDir = path.join(groupDir, '.claude-fragments');
-  if (defaultSurfaces && fs.existsSync(fragmentsDir)) {
+  if (fs.existsSync(fragmentsDir)) {
    mounts.push({ hostPath: fragmentsDir, containerPath: '/workspace/agent/.claude-fragments', readonly: true });
  }

@@ -316,15 +303,13 @@ export function buildMounts(
  // Shared CLAUDE.md — read-only, imported by the composed entry point via
  // the `.claude-shared.md` symlink inside the group dir.
  const sharedClaudeMd = path.join(process.cwd(), 'container', 'CLAUDE.md');
-  if (defaultSurfaces && fs.existsSync(sharedClaudeMd)) {
+  if (fs.existsSync(sharedClaudeMd)) {
    mounts.push({ hostPath: sharedClaudeMd, containerPath: '/app/CLAUDE.md', readonly: true });
  }

  // Per-group .claude-shared at /home/node/.claude (Claude state, settings,
  // skill symlinks)
-  if (defaultSurfaces) {
-    mounts.push({ hostPath: claudeDir, containerPath: '/home/node/.claude', readonly: false });
-  }
+  mounts.push({ hostPath: claudeDir, containerPath: '/home/node/.claude', readonly: false });

  // Shared agent-runner source — read-only, same code for all groups.
  const agentRunnerSrc = path.join(projectRoot, 'container', 'agent-runner', 'src');
@@ -361,7 +346,25 @@ function syncSkillSymlinks(claudeDir: string, containerConfig: import('./contain
    fs.mkdirSync(skillsDir, { recursive: true });
  }

-  const desired = selectedSkillNames(containerConfig);
+  // Determine desired skill set
+  const projectRoot = process.cwd();
+  const sharedSkillsDir = path.join(projectRoot, 'container', 'skills');
+  let desired: string[];
+  if (containerConfig.skills === 'all') {
+    // Recompute from shared dir — newly-added upstream skills appear automatically
+    desired = fs.existsSync(sharedSkillsDir)
+      ? fs.readdirSync(sharedSkillsDir).filter((e) => {
+          try {
+            return fs.statSync(path.join(sharedSkillsDir, e)).isDirectory();
+          } catch {
+            return false;
+          }
+        })
+      : [];
+  } else {
+    desired = containerConfig.skills;
+  }
+
  const desiredSet = new Set(desired);

  // Remove symlinks not in the desired set
@@ -394,24 +397,6 @@ function syncSkillSymlinks(claudeDir: string, containerConfig: import('./contain
  }
 }

-/**
- * Resolve the group's skill selection to concrete names — `'all'` recomputes
- * from `container/skills/` so newly-added upstream skills appear automatically.
- */
-function selectedSkillNames(containerConfig: import('./container-config.js').ContainerConfig): string[] {
-  if (containerConfig.skills !== 'all') return containerConfig.skills;
-  const sharedSkillsDir = path.join(process.cwd(), 'container', 'skills');
-  return fs.existsSync(sharedSkillsDir)
-    ? fs.readdirSync(sharedSkillsDir).filter((e) => {
-        try {
-          return fs.statSync(path.join(sharedSkillsDir, e)).isDirectory();
-        } catch {
-          return false;
-        }
-      })
-    : [];
-}
-
 async function buildContainerArgs(
  mounts: VolumeMount[],
  containerName: string,
@@ -434,6 +419,20 @@ async function buildContainerArgs(
    }
  }

+  // OneCLI gateway — injects HTTPS_PROXY + certs so container API calls
+  // are routed through the agent vault for credential injection. Treated as
+  // a transient hard failure: if we can't wire the gateway, we don't spawn.
+  // The caller (router or host-sweep) catches the throw, leaves the inbound
+  // message pending, and the next sweep tick retries.
+  if (agentIdentifier) {
+    await onecli.ensureAgent({ name: agentGroup.name, identifier: agentIdentifier });
+  }
+  const onecliApplied = await onecli.applyContainerConfig(args, { addHostMapping: false, agent: agentIdentifier });
+  if (!onecliApplied) {
+    throw new Error('OneCLI gateway not applied — refusing to spawn container without credentials');
+  }
+  log.info('OneCLI gateway applied', { containerName });
+
  // Egress lockdown when enabled — throws if it can't be established, aborting
  // the spawn rather than running with open egress. Otherwise the host gateway.
  if (ensureEgressNetwork()) {
@@ -460,24 +459,6 @@ async function buildContainerArgs(
    }
  }

-  // OneCLI gateway — injects HTTPS_PROXY + certs so container API calls
-  // are routed through the agent vault for credential injection, and mounts
-  // any credential stubs the gateway serves (e.g. a sentinel auth file).
-  // Runs AFTER the volume mounts so a stub nested inside one of our mounts
-  // (a parent dir mounted RW above it) lands later in the args and isn't
-  // shadowed by it. Treated as a transient hard failure: if we can't wire
-  // the gateway, we don't spawn. The caller (router or host-sweep) catches
-  // the throw, leaves the inbound message pending, and the next sweep tick
-  // retries.
-  if (agentIdentifier) {
-    await onecli.ensureAgent({ name: agentGroup.name, identifier: agentIdentifier });
-  }
-  const onecliApplied = await onecli.applyContainerConfig(args, { addHostMapping: false, agent: agentIdentifier });
-  if (!onecliApplied) {
-    throw new Error('OneCLI gateway not applied — refusing to spawn container without credentials');
-  }
-  log.info('OneCLI gateway applied', { containerName });
-
  // Override entrypoint: run v2 entry point directly via Bun (no tsc, no stdin).
  args.push('--entrypoint', 'bash');

@@ -8,6 +8,7 @@ const SCALAR_COLUMNS = new Set([
  'image_tag',
  'assistant_name',
  'max_messages_per_prompt',
+  'idle_timeout_ms',
  'cli_scope',
 ]);
 const JSON_COLUMNS = new Set(['skills', 'mcp_servers', 'packages_apt', 'packages_npm', 'additional_mounts']);
@@ -55,7 +56,14 @@ export function updateContainerConfigScalars(
  updates: Partial<
    Pick<
      ContainerConfigRow,
-      'provider' | 'model' | 'effort' | 'image_tag' | 'assistant_name' | 'max_messages_per_prompt' | 'cli_scope'
+      | 'provider'
+      | 'model'
+      | 'effort'
+      | 'image_tag'
+      | 'assistant_name'
+      | 'max_messages_per_prompt'
+      | 'idle_timeout_ms'
+      | 'cli_scope'
    >
  >,
 ): void {
@@ -0,0 +1,13 @@
+import type Database from 'better-sqlite3';
+import type { Migration } from './index.js';
+
+export const migration017: Migration = {
+  version: 17,
+  name: 'container-idle-timeout',
+  up(db: Database.Database) {
+    // Idle-exit window in ms for the agent container. NULL (the default) or 0
+    // disables idle exit — existing groups keep today's behavior, where an
+    // idle container rides until host-sweep's absolute ceiling kills it.
+    db.prepare('ALTER TABLE container_configs ADD COLUMN idle_timeout_ms INTEGER').run();
+  },
+};
@@ -13,6 +13,7 @@ import { migration013 } from './013-approval-render-metadata.js';
 import { migration014 } from './014-container-configs.js';
 import { migration015 } from './015-cli-scope.js';
 import { migration016 } from './016-messaging-group-instance.js';
+import { migration017 } from './017-container-idle-timeout.js';
 import { moduleApprovalsPendingApprovals } from './module-approvals-pending-approvals.js';
 import { moduleApprovalsTitleOptions } from './module-approvals-title-options.js';

@@ -46,6 +47,7 @@ export const migrations: Migration[] = [
  migration014,
  migration015,
  migration016,
+  migration017,
 ];

 /** Row shape of PRAGMA foreign_key_check. Child rowids are stable across a
@@ -4,7 +4,6 @@ import path from 'path';
 import { DATA_DIR, GROUPS_DIR } from './config.js';
 import { ensureContainerConfig } from './db/container-configs.js';
 import { log } from './log.js';
-import { providerProvidesAgentSurfaces } from './providers/provider-container-registry.js';
 import type { AgentGroup } from './types.js';

 const DEFAULT_SETTINGS_JSON =
@@ -47,18 +46,9 @@ const DEFAULT_SETTINGS_JSON =
 * spawn by `composeGroupClaudeMd()` (see `claude-md-compose.ts`). Initial
 * per-group instructions (if provided) seed `CLAUDE.local.md`.
 */
-export function initGroupFilesystem(
-  group: AgentGroup,
-  opts?: { instructions?: string; provider?: string | null },
-): void {
+export function initGroupFilesystem(group: AgentGroup, opts?: { instructions?: string }): void {
  const initialized: string[] = [];

-  // Default agent surfaces apply unless the group's provider declares (at
-  // registration) that it provides its own. Callers that don't know the
-  // provider omit it — unregistered/unknown names report no capabilities,
-  // so the default surfaces are written, exactly as before this seam.
-  const defaultSurfaces = !providerProvidesAgentSurfaces(opts?.provider);
-
  // 1. groups/<folder>/ — group memory + working dir
  const groupDir = path.resolve(GROUPS_DIR, group.folder);
  if (!fs.existsSync(groupDir)) {
@@ -69,7 +59,7 @@ export function initGroupFilesystem(
  // groups/<folder>/CLAUDE.local.md — per-group agent memory, auto-loaded by
  // Claude Code. Seeded with caller-provided instructions on first creation.
  const claudeLocalFile = path.join(groupDir, 'CLAUDE.local.md');
-  if (defaultSurfaces && !fs.existsSync(claudeLocalFile)) {
+  if (!fs.existsSync(claudeLocalFile)) {
    const body = opts?.instructions ? opts.instructions + '\n' : '';
    fs.writeFileSync(claudeLocalFile, body);
    initialized.push('CLAUDE.local.md');
@@ -81,28 +71,26 @@ export function initGroupFilesystem(
  initialized.push('container_configs');

  // 2. data/v2-sessions/<id>/.claude-shared/ — Claude state + per-group skills
-  if (defaultSurfaces) {
-    const claudeDir = path.join(DATA_DIR, 'v2-sessions', group.id, '.claude-shared');
-    if (!fs.existsSync(claudeDir)) {
-      fs.mkdirSync(claudeDir, { recursive: true });
-      initialized.push('.claude-shared');
-    }
+  const claudeDir = path.join(DATA_DIR, 'v2-sessions', group.id, '.claude-shared');
+  if (!fs.existsSync(claudeDir)) {
+    fs.mkdirSync(claudeDir, { recursive: true });
+    initialized.push('.claude-shared');
+  }

-    const settingsFile = path.join(claudeDir, 'settings.json');
-    if (!fs.existsSync(settingsFile)) {
-      fs.writeFileSync(settingsFile, DEFAULT_SETTINGS_JSON);
-      initialized.push('settings.json');
-    } else {
-      ensurePreCompactHook(settingsFile, initialized);
-    }
+  const settingsFile = path.join(claudeDir, 'settings.json');
+  if (!fs.existsSync(settingsFile)) {
+    fs.writeFileSync(settingsFile, DEFAULT_SETTINGS_JSON);
+    initialized.push('settings.json');
+  } else {
+    ensurePreCompactHook(settingsFile, initialized);
+  }

-    // Skills directory — created empty here; symlinks are synced at spawn
-    // time by container-runner.ts based on container.json skills selection.
-    const skillsDst = path.join(claudeDir, 'skills');
-    if (!fs.existsSync(skillsDst)) {
-      fs.mkdirSync(skillsDst, { recursive: true });
-      initialized.push('skills/');
-    }
+  // Skills directory — created empty here; symlinks are synced at spawn
+  // time by container-runner.ts based on container.json skills selection.
+  const skillsDst = path.join(claudeDir, 'skills');
+  if (!fs.existsSync(skillsDst)) {
+    fs.mkdirSync(skillsDst, { recursive: true });
+    initialized.push('skills/');
  }

  if (initialized.length > 0) {
@@ -1,143 +0,0 @@
-import fs from 'fs';
-import path from 'path';
-import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
-
-const TEST_ROOT = '/tmp/nanoclaw-provider-surfaces-test';
-const GROUPS_DIR = path.join(TEST_ROOT, 'groups');
-const DATA_DIR = path.join(TEST_ROOT, 'data');
-
-vi.mock('./config.js', async (importOriginal) => ({
-  ...(await importOriginal<typeof import('./config.js')>()),
-  DATA_DIR: '/tmp/nanoclaw-provider-surfaces-test/data',
-  GROUPS_DIR: '/tmp/nanoclaw-provider-surfaces-test/groups',
-}));
-
-vi.mock('./log.js', () => ({
-  log: {
-    debug: vi.fn(),
-    info: vi.fn(),
-    warn: vi.fn(),
-    error: vi.fn(),
-    fatal: vi.fn(),
-  },
-}));
-
-import { buildMounts } from './container-runner.js';
-import { closeDb, createAgentGroup, initTestDb, runMigrations } from './db/index.js';
-import { ensureContainerConfig } from './db/container-configs.js';
-import { initGroupFilesystem } from './group-init.js';
-import { registerProviderContainerConfig } from './providers/provider-container-registry.js';
-import type { ContainerConfig } from './container-config.js';
-import type { AgentGroup, Session } from './types.js';
-
-// A provider that declares (at registration) that it owns its agent surfaces.
-// Registered once — the registry is module-global and rejects duplicates.
-registerProviderContainerConfig('surfaces-test-provider', () => ({}), { providesAgentSurfaces: true });
-
-function group(id: string, folder: string): AgentGroup {
-  return { id, name: folder, folder, agent_provider: null, created_at: new Date().toISOString() } as AgentGroup;
-}
-
-function session(id: string, agentGroupId: string): Session {
-  return { id, agent_group_id: agentGroupId } as Session;
-}
-
-function containerConfig(): ContainerConfig {
-  return { mcpServers: {}, packages: { apt: [], npm: [] }, additionalMounts: [], skills: [] };
-}
-
-beforeEach(() => {
-  fs.rmSync(TEST_ROOT, { recursive: true, force: true });
-  fs.mkdirSync(TEST_ROOT, { recursive: true });
-  runMigrations(initTestDb());
-});
-
-afterEach(() => {
-  closeDb();
-  fs.rmSync(TEST_ROOT, { recursive: true, force: true });
-});
-
-describe('initGroupFilesystem agent surfaces', () => {
-  it('writes the default surfaces when no provider is given (today’s behavior)', () => {
-    const ag = group('ag-default', 'default-group');
-    createAgentGroup(ag);
-
-    initGroupFilesystem(ag, { instructions: 'hello' });
-
-    const groupDir = path.join(GROUPS_DIR, ag.folder);
-    const claudeDir = path.join(DATA_DIR, 'v2-sessions', ag.id, '.claude-shared');
-    expect(fs.readFileSync(path.join(groupDir, 'CLAUDE.local.md'), 'utf-8')).toBe('hello\n');
-    expect(fs.existsSync(path.join(claudeDir, 'settings.json'))).toBe(true);
-    expect(fs.existsSync(path.join(claudeDir, 'skills'))).toBe(true);
-  });
-
-  it('skips the default surfaces for a provider that provides its own', () => {
-    const ag = group('ag-surfy', 'surfy-group');
-    createAgentGroup(ag);
-
-    initGroupFilesystem(ag, { instructions: 'hello', provider: 'surfaces-test-provider' });
-
-    const groupDir = path.join(GROUPS_DIR, ag.folder);
-    const sessionRoot = path.join(DATA_DIR, 'v2-sessions', ag.id);
-    expect(fs.existsSync(groupDir)).toBe(true);
-    expect(fs.existsSync(path.join(groupDir, 'CLAUDE.local.md'))).toBe(false);
-    expect(fs.existsSync(path.join(sessionRoot, '.claude-shared'))).toBe(false);
-  });
-
-  it('treats an unregistered provider name as default surfaces', () => {
-    const ag = group('ag-unknown', 'unknown-group');
-    createAgentGroup(ag);
-
-    initGroupFilesystem(ag, { provider: 'not-registered' });
-
-    expect(fs.existsSync(path.join(GROUPS_DIR, ag.folder, 'CLAUDE.local.md'))).toBe(true);
-  });
-});
-
-describe('buildMounts agent surfaces', () => {
-  it('mounts the default surfaces for an unregistered provider (today’s behavior)', () => {
-    const ag = group('ag-mounts-default', 'mounts-default');
-    createAgentGroup(ag);
-    ensureContainerConfig(ag.id);
-    initGroupFilesystem(ag, {});
-
-    const mounts = buildMounts(ag, session('s1', ag.id), containerConfig(), 'claude', {});
-
-    const byContainerPath = new Map(mounts.map((m) => [m.containerPath, m]));
-    expect(byContainerPath.has('/home/node/.claude')).toBe(true);
-    expect(byContainerPath.has('/app/CLAUDE.md')).toBe(true);
-    expect(byContainerPath.has('/workspace/agent/CLAUDE.md')).toBe(true);
-    // Composer ran: the generated project doc exists on disk.
-    expect(fs.existsSync(path.join(GROUPS_DIR, ag.folder, 'CLAUDE.md'))).toBe(true);
-  });
-
-  it('suppresses the default surfaces and keeps contributed mounts for a surfaces-providing provider', () => {
-    const ag = group('ag-mounts-surfy', 'mounts-surfy');
-    createAgentGroup(ag);
-    ensureContainerConfig(ag.id);
-    initGroupFilesystem(ag, { provider: 'surfaces-test-provider' });
-
-    const contributed = {
-      mounts: [
-        {
-          hostPath: path.join(GROUPS_DIR, ag.folder),
-          containerPath: '/workspace/agent/OWN-DOC.md',
-          readonly: true,
-        },
-      ],
-    };
-    const mounts = buildMounts(ag, session('s2', ag.id), containerConfig(), 'surfaces-test-provider', contributed);
-
-    const containerPaths = mounts.map((m) => m.containerPath);
-    expect(containerPaths).not.toContain('/home/node/.claude');
-    expect(containerPaths).not.toContain('/app/CLAUDE.md');
-    expect(containerPaths).not.toContain('/workspace/agent/CLAUDE.md');
-    // Composer did NOT run for this group.
-    expect(fs.existsSync(path.join(GROUPS_DIR, ag.folder, 'CLAUDE.md'))).toBe(false);
-    // Core mounts and the provider's own contribution are intact.
-    expect(containerPaths).toContain('/workspace');
-    expect(containerPaths).toContain('/workspace/agent');
-    expect(containerPaths).toContain('/app/src');
-    expect(containerPaths).toContain('/workspace/agent/OWN-DOC.md');
-  });
-});
@@ -27,19 +27,6 @@ export interface ProviderContainerContext {
  sessionDir: string;
  /** Agent group ID, for any per-group logic. */
  agentGroupId: string;
-  /**
-   * Per-group host directory: `<GROUPS_DIR>/<folder>` (mounted RW at
-   * `/workspace/agent`). Exists by the time the config fn runs — group
-   * filesystem init happens first. Surfaces-providing providers compose
-   * their project doc and skill links here.
-   */
-  groupDir: string;
-  /**
-   * Skill names selected by the group's container config, with `'all'`
-   * already resolved against `container/skills/`. Surfaces-providing
-   * providers use this to sync their own skill-discovery links.
-   */
-  selectedSkills: string[];
  /** `process.env` at spawn time — pull passthrough values from here. */
  hostEnv: NodeJS.ProcessEnv;
 }
@@ -51,56 +38,19 @@ export interface ProviderContainerContribution {
  env?: Record<string, string>;
 }

-/**
- * Static capabilities a provider declares at registration time — knowable
- * without a spawn context, so any host path (group init, spawn, creation
- * flows) can consult them by name.
- */
-export interface ProviderHostCapabilities {
-  /**
-   * Optional. When true, this provider owns its agent-facing surfaces — the
-   * composed project doc, skill-discovery links, and provider state dir —
-   * and the host must NOT compose or mount the default ones (composed
-   * CLAUDE.md, `.claude-fragments`, `/app/CLAUDE.md`, `/home/node/.claude`,
-   * `CLAUDE.local.md` seeding). The provider's config fn does its own
-   * composing and returns its own mounts. Default off — providers that omit
-   * this get the default surfaces, which is today's behavior.
-   */
-  readonly providesAgentSurfaces?: boolean;
-}
-
 export type ProviderContainerConfigFn = (ctx: ProviderContainerContext) => ProviderContainerContribution;

-interface RegistryEntry {
-  fn: ProviderContainerConfigFn;
-  capabilities: ProviderHostCapabilities;
-}
+const registry = new Map<string, ProviderContainerConfigFn>();

-const registry = new Map<string, RegistryEntry>();
-
-export function registerProviderContainerConfig(
-  name: string,
-  fn: ProviderContainerConfigFn,
-  capabilities: ProviderHostCapabilities = {},
-): void {
+export function registerProviderContainerConfig(name: string, fn: ProviderContainerConfigFn): void {
  if (registry.has(name)) {
    throw new Error(`Provider container config already registered: ${name}`);
  }
-  registry.set(name, { fn, capabilities });
+  registry.set(name, fn);
 }

 export function getProviderContainerConfig(name: string): ProviderContainerConfigFn | undefined {
-  return registry.get(name)?.fn;
-}
-
-/**
- * Capability lookup by provider name. Unregistered providers (including the
- * baked-in default) report no capabilities — the host applies its default
- * surfaces, exactly as before this seam existed.
- */
-export function providerProvidesAgentSurfaces(name: string | null | undefined): boolean {
-  if (!name) return false;
-  return registry.get(name)?.capabilities.providesAgentSurfaces === true;
+  return registry.get(name);
 }

 export function listProviderContainerConfigNames(): string[] {
@@ -19,6 +19,7 @@ export interface ContainerConfigRow {
  image_tag: string | null;
  assistant_name: string | null;
  max_messages_per_prompt: number | null;
+  idle_timeout_ms: number | null; // idle-exit window (ms); NULL/0 = disabled
  skills: string; // JSON: '"all"' | '["skill1","skill2"]'
  mcp_servers: string; // JSON: Record<string, McpServerConfig>
  packages_apt: string; // JSON: string[]
@@ -1,97 +0,0 @@
-/**
- * Guard for the raw-route half of src/webhook-server.ts —
- * registerWebhookHandler + the rawRoutes dispatch branch.
- *
- * Drives the REAL shared HTTP server on an ephemeral WEBHOOK_PORT (no
- * mocking of the routing layer): a registered raw route must dispatch,
- * unknown paths must 404, a throwing handler must surface as 500,
- * raw routes must coexist with Chat SDK adapter routes on the same
- * server, and stopWebhookServer must clear them.
- */
-import { afterAll, describe, expect, it, vi } from 'vitest';
-
-import type { Chat } from 'chat';
-
-import { registerWebhookAdapter, registerWebhookHandler, stopWebhookServer } from './webhook-server.js';
-
-const PORT = 21000 + Math.floor(Math.random() * 20000);
-
-async function post(path: string, body = '{}'): Promise<globalThis.Response> {
-  for (let attempt = 0; ; attempt++) {
-    try {
-      return await fetch(`http://127.0.0.1:${PORT}/webhook/${path}`, { method: 'POST', body });
-    } catch (err) {
-      if (attempt >= 40) throw err;
-      await new Promise((r) => setTimeout(r, 50));
-    }
-  }
-}
-
-afterAll(async () => {
-  await stopWebhookServer();
-  delete process.env.WEBHOOK_PORT;
-});
-
-describe('webhook server raw routes', () => {
-  it('dispatches a registered raw route to its handler', async () => {
-    process.env.WEBHOOK_PORT = String(PORT);
-    const methods: string[] = [];
-    registerWebhookHandler('ping', (req, res) => {
-      methods.push(req.method || '');
-      res.writeHead(200, { 'Content-Type': 'text/plain' });
-      res.end('pong');
-    });
-
-    const res = await post('ping');
-    expect(res.status).toBe(200);
-    expect(await res.text()).toBe('pong');
-    expect(methods).toEqual(['POST']);
-  });
-
-  it('returns 404 for paths with no registered route', async () => {
-    const res = await post('nope');
-    expect(res.status).toBe(404);
-  });
-
-  it('turns a throwing handler into a 500 response', async () => {
-    registerWebhookHandler('boom', () => {
-      throw new Error('handler exploded');
-    });
-
-    const res = await post('boom');
-    expect(res.status).toBe(500);
-    expect(await res.text()).toBe('Internal Server Error');
-  });
-
-  it('coexists with Chat SDK adapter routes on the same server', async () => {
-    const handler = vi.fn(async () => new Response('ok-chat', { status: 200 }));
-    const chat = { webhooks: { fake: handler } } as unknown as Chat;
-    registerWebhookAdapter(chat, 'fake');
-
-    const chatRes = await post('fake');
-    expect(chatRes.status).toBe(200);
-    expect(await chatRes.text()).toBe('ok-chat');
-    expect(handler).toHaveBeenCalledTimes(1);
-
-    // The raw route registered earlier is still live alongside it.
-    const rawRes = await post('ping');
-    expect(rawRes.status).toBe(200);
-  });
-
-  it('clears raw routes on stopWebhookServer', async () => {
-    await stopWebhookServer();
-
-    // Restart the server with a fresh route; the old raw routes must be gone.
-    registerWebhookHandler('fresh', (_req, res) => {
-      res.writeHead(200, { 'Content-Type': 'text/plain' });
-      res.end('fresh');
-    });
-
-    const stale = await post('ping');
-    expect(stale.status).toBe(404);
-
-    const fresh = await post('fresh');
-    expect(fresh.status).toBe(200);
-    expect(await fresh.text()).toBe('fresh');
-  });
-});
@@ -3,12 +3,9 @@
 *
 * Starts lazily on first adapter registration. Routes requests by path:
 *   /webhook/{adapterName} → chat.webhooks[adapterName](request)
- *   /webhook/{path}        → raw handler from registerWebhookHandler(path, ...)
 *
 * Multiple Chat instances can register adapters — each adapter name maps
- * to its owning Chat instance. Raw routes let modules receive non-Chat-SDK
- * webhooks (GitHub, payment providers, health checks) on the same server
- * without editing this file or opening a second port.
+ * to its owning Chat instance.
 */
 import http from 'http';

@@ -23,11 +20,7 @@ interface WebhookEntry {
  adapterName: string;
 }

-/** Node-style handler for raw (non-Chat-SDK) webhook routes. */
-export type RawWebhookHandler = (req: http.IncomingMessage, res: http.ServerResponse) => void | Promise<void>;
-
 const routes = new Map<string, WebhookEntry>();
-const rawRoutes = new Map<string, RawWebhookHandler>();
 let server: http.Server | null = null;

 /** Convert Node.js IncomingMessage to a Web API Request. */
@@ -91,22 +84,6 @@ export function registerWebhookAdapter(chat: Chat, adapterName: string, routingP
  log.info('Webhook adapter registered', { adapter: adapterName, path: `/webhook/${routingPath}` });
 }

-/**
- * Register a raw Node-style handler at /webhook/{path} on the shared server.
- *
- * For webhooks that don't flow through a Chat SDK adapter (GitHub, payment
- * providers, health checks): modules register their endpoint here instead of
- * editing this file or standing up a second HTTP server on another port.
- * The handler owns the request/response directly.
- *
- * Starts the server lazily on first call.
- */
-export function registerWebhookHandler(path: string, handler: RawWebhookHandler): void {
-  rawRoutes.set(path, handler);
-  ensureServer();
-  log.info('Webhook handler registered', { path: `/webhook/${path}` });
-}
-
 function ensureServer(): void {
  if (server) return;

@@ -124,22 +101,14 @@ function ensureServer(): void {
    }

    const adapterName = match[1];
+    const entry = routes.get(adapterName);
+    if (!entry) {
+      res.writeHead(404, { 'Content-Type': 'text/plain' });
+      res.end(`Unknown adapter: ${adapterName}`);
+      return;
+    }

    try {
-      // Raw routes take priority — the handler writes the response itself.
-      const rawHandler = rawRoutes.get(adapterName);
-      if (rawHandler) {
-        await rawHandler(req, res);
-        return;
-      }
-
-      const entry = routes.get(adapterName);
-      if (!entry) {
-        res.writeHead(404, { 'Content-Type': 'text/plain' });
-        res.end(`Unknown adapter: ${adapterName}`);
-        return;
-      }
-
      const webReq = await toWebRequest(req);
      // eslint-disable-next-line @typescript-eslint/no-explicit-any
      const webhooks = entry.chat.webhooks as Record<string, (r: Request, opts?: any) => Promise<Response>>;
@@ -152,10 +121,8 @@ function ensureServer(): void {
      await fromWebResponse(webRes, res);
    } catch (err) {
      log.error('Webhook handler error', { adapter: adapterName, url: req.url, err });
-      if (!res.headersSent) {
-        res.writeHead(500, { 'Content-Type': 'text/plain' });
-        res.end('Internal Server Error');
-      }
+      res.writeHead(500, { 'Content-Type': 'text/plain' });
+      res.end('Internal Server Error');
    }
  });

@@ -170,7 +137,6 @@ export async function stopWebhookServer(): Promise<void> {
    await new Promise<void>((resolve) => server!.close(() => resolve()));
    server = null;
    routes.clear();
-    rawRoutes.clear();
    log.info('Webhook server stopped');
  }
 }
@@ -1,4 +0,0 @@
-{
-  "onecli-gateway": "1.36.0",
-  "onecli-cli": "2.2.5"
-}