feat(routing): engage modes + sender scope + accumulate/drop + per-agent fan-out

Replaces the opaque trigger_rules JSON + response_scope enum on
messaging_group_agents with four explicit orthogonal columns:

    engage_mode            'pattern' | 'mention' | 'mention-sticky'
    engage_pattern         regex source; required when mode='pattern';
                           '.' is the "always" sentinel
    sender_scope           'all' | 'known'
    ignored_message_policy 'drop' | 'accumulate'

Inbound routing becomes a fan-out — every wired agent is evaluated
independently. A match gets its own session + container wake. A miss
with accumulate keeps the message as context-only (trigger=0) in that
agent's session, so when the agent does eventually engage it sees the
prior chatter.

## Schema

- Migration 010 (`engage-modes`): adds the 4 new columns, backfills
  from trigger_rules.pattern + requiresTrigger + response_scope, drops
  the legacy columns.
- messages_in gains `trigger INTEGER NOT NULL DEFAULT 1` (session DB
  schema + `migrateMessagesInTable` forward-compat).
- countDueMessages gates waking on `trigger = 1`.

## Routing

- `pickAgent` (returns one) → loop over all wired agents. Per agent:
  evaluate engage_mode; run access gate + sender-scope gate; on full
  match → resolveSession + writeSessionMessage(trigger=1) + wake. On
  miss with accumulate → writeSessionMessage(trigger=0), no wake. On
  miss with drop → skip.
- New `findSessionForAgent(agentGroupId, mgId, threadId)` scopes
  session lookup by agent so fan-out doesn't cross sessions.
- `messageIdForAgent` namespaces inbound message ids by agent_group_id
  so PRIMARY KEY doesn't collide across per-agent session DBs.

## Adapter layer

- `ConversationConfig` replaces `triggerPattern` + `requiresTrigger`
  with `engageMode` + `engagePattern`.
- Chat SDK bridge stores `Map<platformId, ConversationConfig[]>` (multi-
  agent per conversation) and applies union gating pre-onInbound:
    * onSubscribedMessage: engage if any wiring keeps firing in
      subscribed state (mention-sticky or pattern)
    * onNewMention: engage on mention; only subscribes the thread if
      at least one wiring is `mention-sticky`
    * onDirectMessage: engage per mode; sticky follows same rule
- Bridge no longer unconditionally calls `thread.subscribe()`.

## Sender scope

- Permissions module registers a second hook `setSenderScopeGate` that
  runs per-wiring after the existing access gate. `sender_scope='known'`
  requires canAccessAgentGroup(); `'all'` is a no-op. Not installed →
  no-op everywhere (default allow).

## Container side

- Host passes `NANOCLAW_MAX_MESSAGES_PER_PROMPT` (reuses existing
  MAX_MESSAGES_PER_PROMPT config; was dead code from v1).
- `getPendingMessages` queries `ORDER BY seq DESC LIMIT N`, reverses to
  chronological order for the prompt — accumulated context rides along
  with trigger rows up to the cap.
- `MessageInRow` gains `trigger: number` so the container can tell them
  apart in downstream code (container still processes both; only the
  host uses `trigger=0` for don't-wake).

## Defaults (per ACTION-ITEMS item 1 decision)

- DM (is_group=0): `engage_mode='pattern'`, `engage_pattern='.'` (always)
- Threaded group: `engage_mode='mention-sticky'` (seed-discord)
- Non-threaded group / CLI: pattern '.' in bootstrap scripts

## Tests

- src/host-core.test.ts: 3 new cases — fan-out (2 agents, 2 sessions,
  2 wakes), accumulate (trigger=0 + no wake), drop (no session created).
- Existing 10 host-core tests still pass.
- Migration 010 runs on an empty DB in 0-row path — verified.

Closes: ACTION-ITEMS items 1, 4.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

container/agent-runner/src/db/messages-in.ts

@@ -18,16 +18,33 @@ export interface MessageInRow {
   process_after: string | null;
   recurrence: string | null;
   tries: number;
+  /** 1 = wake-eligible (default); 0 = accumulated context only */
+  trigger: number;
   platform_id: string | null;
   channel_type: string | null;
   thread_id: string | null;
   content: string;
 }
 
+// Cap on how many messages reach the agent in one prompt, including any
+// accumulated-but-not-triggered context. Host controls the cap via the
+// NANOCLAW_MAX_MESSAGES_PER_PROMPT env var; default mirrors the host's
+// config.ts default of 10.
+const MAX_MESSAGES_PER_PROMPT = Math.max(
+  1,
+  parseInt(process.env.NANOCLAW_MAX_MESSAGES_PER_PROMPT || '10', 10) || 10,
+);
+
 /**
  * Fetch pending messages that are due for processing.
  * Reads from inbound.db (read-only), filters against processing_ack in outbound.db
  * to skip messages already picked up by this or a previous container run.
+ *
+ * Returns the most recent `MAX_MESSAGES_PER_PROMPT` pending rows in
+ * chronological order, regardless of their `trigger` flag: accumulated
+ * context (trigger=0) rides along with the wake-eligible rows so the agent
+ * sees the prior context it missed. Host's countDueMessages gates waking on
+ * trigger=1 separately (see src/db/session-db.ts).
  */
 export function getPendingMessages(): MessageInRow[] {
   const inbound = getInboundDb();
@@ -38,9 +55,10 @@ export function getPendingMessages(): MessageInRow[] {
       `SELECT * FROM messages_in
        WHERE status = 'pending'
          AND (process_after IS NULL OR datetime(process_after) <= datetime('now'))
-       ORDER BY timestamp ASC`,
+       ORDER BY seq DESC
+       LIMIT ?`,
     )
-    .all() as MessageInRow[];
+    .all(MAX_MESSAGES_PER_PROMPT) as MessageInRow[];
 
   if (pending.length === 0) return [];
 
@@ -51,7 +69,9 @@ export function getPendingMessages(): MessageInRow[] {
     ),
   );
 
-  return pending.filter((m) => !ackedIds.has(m.id));
+  // Reverse: we fetched DESC to take the most recent N, but the agent
+  // should see them in chronological order (oldest first).
+  return pending.filter((m) => !ackedIds.has(m.id)).reverse();
 }
 
 /** Mark messages as processing — writes to processing_ack in outbound.db. */