feat(v2): OneCLI 0.3.1 — approvals, credential collection, threaded routing

Three features built on top of @onecli-sh/sdk 0.3.1, landed together because
they share wiring surfaces (session DB schema, delivery dispatcher, Chat SDK
bridge, channel adapter contract).

## OneCLI manual-approval handler

* `src/onecli-approvals.ts` — long-polls OneCLI via the SDK's
  `configureManualApproval`; on each request, delivers an `ask_question` card
  to the admin agent group's first messaging group, persists a
  `pending_approvals` row, and waits on an in-memory Promise resolved by the
  admin's button click or an expiry timer. Expired cards are edited to
  "Expired (...)" and a startup sweep flushes any rows left over from a
  previous process.
* Short 11-byte approval id (`oa-<8 base36>`) instead of the SDK's UUID so the
  Telegram 64-byte `callback_data` limit is respected; the OneCLI UUID stays
  in the persisted payload for audit.
* Migration 003 consolidated: `pending_approvals` now has the OneCLI-aware
  columns from the start (`agent_group_id`, `channel_type`, `platform_id`,
  `platform_message_id`, `expires_at`, `status`), `session_id` relaxed to
  nullable so cross-session approvals fit.
* `handleQuestionResponse` in `src/index.ts` now routes OneCLI approvals
  through `resolveOneCLIApproval` before falling back to the
  session-bound approval path.

## Credential collection from chat

New `trigger_credential_collection` MCP tool — the agent researches a
third-party API, calls the tool with `{name, hostPattern, headerName,
valueFormat, description}`, and blocks until the host reports saved, rejected,
or failed. The credential value never enters the agent's context: the user
submits it into a Chat SDK Modal on the host side, the host writes it to
OneCLI via a thin facade (`src/onecli-secrets.ts` — shells out to
`onecli secrets create`, shape mirrors the SDK we expect upstream), and only
the status string flows back to the container via a system message.

* `src/credentials.ts` — host-side handler: delivers the card to the
  conversation's own channel (not the admin channel — credential collection
  is a user-facing flow, distinct from admin approval), persists a
  `pending_credentials` row, drives the submit → `createSecret` → notify
  pipeline. Falls back gracefully when the channel doesn't support modals.
* `src/db/credentials.ts` + migration 005: `pending_credentials` table.
* `src/channels/chat-sdk-bridge.ts`: renders a `credential_request` card,
  handles the `nccr:` action prefix by opening a Modal with a TextInput,
  registers an `onModalSubmit` handler for the `nccm:` callback prefix.
* `container/agent-runner/src/mcp-tools/credentials.ts`: the blocking MCP
  tool, mirroring the `ask_user_question` polling pattern.
* `container/agent-runner/src/db/messages-in.ts`: `findCredentialResponse`
  helper to pick up the system message the host writes back.

## Threaded adapter routing

The destination layer previously didn't carry thread context, so agent replies
to Discord always landed in the root channel regardless of which thread the
inbound came from.

* `ChannelAdapter.supportsThreads: boolean` — declared by every channel skill
  at `createChatSdkBridge`. Threaded: Discord, Slack, Teams, Google Chat,
  Linear, GitHub, Webex. Non-threaded: Telegram, WhatsApp Cloud, Matrix,
  Resend, iMessage.
* `src/router.ts`: non-threaded adapters strip `threadId` at ingest (threads
  collapse to channel-level sessions). Threaded adapters override the
  wiring's `session_mode` to `'per-thread'` so each thread = a session
  (except `agent-shared`, which is preserved as a cross-channel intent the
  adapter can't know about).
* `session_routing` table in `inbound.db` — single-row default reply routing
  written by the host on every container wake from
  `session.messaging_group_id` + `session.thread_id`. Forward-compat
  `CREATE TABLE IF NOT EXISTS` handles older session DBs lazily.
* `container/agent-runner/src/db/session-routing.ts` — container-side reader.
* `send_message` / `send_file` / `ask_user_question` / `send_card` /
  scheduling tools all default their routing (channel, platform, **and**
  thread) from the session when no explicit `to` is given. Explicit `to`
  uses the destination's channel with `thread_id = null` (cross-destination
  sends start a new conversation elsewhere).
* `poll-loop.ts::sendToDestination` (the final-text single-destination
  shortcut) now inherits `thread_id` from `RoutingContext` too — this was
  the root cause of Discord replies landing in the root channel even after
  `send_message` was wired correctly.

## Related cleanups

* `src/container-runner.ts`: OneCLI agent identifier switched from the lossy
  folder-derived string to `agent_group.id`, making `getAgentGroup(externalId)`
  a trivial reverse lookup for per-agent scoping.
* `wakeContainer` race fix via an in-flight promise map — concurrent wakes
  during the async buildContainerArgs / OneCLI `applyContainerConfig` window
  no longer double-spawn containers against the same session directory.
* `src/db/db-v2.test.ts`: dropped the brittle `expect(row.v).toBe(N)` schema
  version assertion — it had to be bumped on every migration addition.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/container-runner.ts

@@ -21,6 +21,7 @@ import {
   markContainerStopped,
   sessionDir,
   writeDestinations,
+  writeSessionRouting,
 } from './session-manager.js';
 import type { AgentGroup, Session } from './types.js';
 
@@ -35,6 +36,16 @@ interface VolumeMount {
 /** Active containers tracked by session ID. */
 const activeContainers = new Map<string, { process: ChildProcess; containerName: string }>();
 
+/**
+ * In-flight wake promises, keyed by session id. Deduplicates concurrent
+ * `wakeContainer` calls while the first spawn is still mid-setup (async
+ * buildContainerArgs, OneCLI gateway apply, etc.) — otherwise a second
+ * wake in that window passes the `activeContainers.has` check and spawns
+ * a duplicate container against the same session directory, producing
+ * racy double-replies.
+ */
+const wakePromises = new Map<string, Promise<void>>();
+
 export function getActiveContainerCount(): number {
   return activeContainers.size;
 }
@@ -44,27 +55,47 @@ export function isContainerRunning(sessionId: string): boolean {
 }
 
 /**
- * Wake up a container for a session. If already running, no-op.
+ * Wake up a container for a session. If already running or mid-spawn, no-op
+ * (the in-flight wake promise is reused).
+ *
  * The container runs the v2 agent-runner which polls the session DB.
  */
-export async function wakeContainer(session: Session): Promise<void> {
+export function wakeContainer(session: Session): Promise<void> {
   if (activeContainers.has(session.id)) {
     log.debug('Container already running', { sessionId: session.id });
-    return;
+    return Promise.resolve();
   }
+  const existing = wakePromises.get(session.id);
+  if (existing) {
+    log.debug('Container wake already in-flight — joining existing promise', { sessionId: session.id });
+    return existing;
+  }
+  const promise = spawnContainer(session).finally(() => {
+    wakePromises.delete(session.id);
+  });
+  wakePromises.set(session.id, promise);
+  return promise;
+}
 
+async function spawnContainer(session: Session): Promise<void> {
   const agentGroup = getAgentGroup(session.agent_group_id);
   if (!agentGroup) {
     log.error('Agent group not found', { agentGroupId: session.agent_group_id });
     return;
   }
 
-  // Refresh the destination map so any admin changes take effect on wake
+  // Refresh the destination map and default reply routing so any admin
+  // changes take effect on wake.
   writeDestinations(agentGroup.id, session.id);
+  writeSessionRouting(agentGroup.id, session.id);
 
   const mounts = buildMounts(agentGroup, session);
   const containerName = `nanoclaw-v2-${agentGroup.folder}-${Date.now()}`;
-  const agentIdentifier = agentGroup.is_admin ? undefined : agentGroup.folder.toLowerCase().replace(/_/g, '-');
+  // OneCLI agent identifier is the agent group id. The admin group uses OneCLI's
+  // default agent (undefined), so unscoped credentials apply. Non-admin groups
+  // use their stable ag-xxx id, which is reversible via getAgentGroup() for
+  // approval-request routing.
+  const agentIdentifier = agentGroup.is_admin ? undefined : agentGroup.id;
   const args = await buildContainerArgs(mounts, containerName, session, agentGroup, agentIdentifier);
 
   log.info('Spawning container', { sessionId: session.id, agentGroup: agentGroup.name, containerName });