Merge branch 'main' into setup-scratch-agent-cleanup

container/agent-runner/src/providers/claude.ts

@@ -226,8 +226,12 @@ function createPreCompactHook(assistantName?: string): HookCallback {
 /**
  * Claude Code auto-compacts context at this window (tokens). Kept here so
  * the generic bootstrap doesn't need to know about Claude-specific env vars.
+ *
+ * Operator override: set CLAUDE_CODE_AUTO_COMPACT_WINDOW in the host env to
+ * raise or lower the threshold without editing source — useful when running
+ * with a 1M-context model variant or when emergency-tuning a deployment.
  */
-const CLAUDE_CODE_AUTO_COMPACT_WINDOW = '165000';
+const CLAUDE_CODE_AUTO_COMPACT_WINDOW = process.env.CLAUDE_CODE_AUTO_COMPACT_WINDOW || '165000';
 
 /**
  * Stale-session detection. Matches Claude Code's error text when a

package.json

@@ -1,6 +1,6 @@
 {
   "name": "nanoclaw",
-  "version": "2.0.15",
+  "version": "2.0.17",
   "description": "Personal Claude assistant. Lightweight, secure, customizable.",
   "type": "module",
   "packageManager": "pnpm@10.33.0",

repo-tokens/badge.svg

@@ -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="133k tokens, 67% of context window">
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="90" height="20" role="img" aria-label="135k tokens, 67% of context window">
-  <title>133k tokens, 67% of context window</title>
+  <title>135k tokens, 67% 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">133k</text>
+        <text aria-hidden="true" x="71" y="15" fill="#010101" fill-opacity=".3">135k</text>
-        <text x="71" y="14">133k</text>
+        <text x="71" y="14">135k</text>
       </g>
     </g>
   </a>

src/container-runner.ts

@@ -58,7 +58,7 @@ const activeContainers = new Map<string, { process: ChildProcess; containerName:
  * a duplicate container against the same session directory, producing
  * racy double-replies.
  */
-const wakePromises = new Map<string, Promise<void>>();
+const wakePromises = new Map<string, Promise<boolean>>();
 
 export function getActiveContainerCount(): number {
   return activeContainers.size;
@@ -73,20 +73,32 @@ export function isContainerRunning(sessionId: string): boolean {
  * (the in-flight wake promise is reused).
  *
  * The container runs the v2 agent-runner which polls the session DB.
+ *
+ * Contract: never throws. Returns `true` on successful spawn, `false` on
+ * transient spawn failure (e.g. OneCLI gateway unreachable). Callers don't
+ * need to wrap — the inbound row stays pending and host-sweep retries on
+ * its next tick. Callers that care (e.g. the router's typing indicator)
+ * can branch on the boolean.
  */
-export function wakeContainer(session: Session): Promise<void> {
+export function wakeContainer(session: Session): Promise<boolean> {
   if (activeContainers.has(session.id)) {
     log.debug('Container already running', { sessionId: session.id });
-    return Promise.resolve();
+    return Promise.resolve(true);
   }
   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(() => {
+  const promise = spawnContainer(session)
-    wakePromises.delete(session.id);
+    .then(() => true)
-  });
+    .catch((err) => {
+      log.warn('wakeContainer failed — host-sweep will retry', { sessionId: session.id, err });
+      return false;
+    })
+    .finally(() => {
+      wakePromises.delete(session.id);
+    });
   wakePromises.set(session.id, promise);
   return promise;
 }
@@ -435,20 +447,18 @@ async function buildContainerArgs(
   }
 
   // OneCLI gateway — injects HTTPS_PROXY + certs so container API calls
-  // are routed through the agent vault for credential injection.
+  // are routed through the agent vault for credential injection. Treated as
-  try {
+  // a transient hard failure: if we can't wire the gateway, we don't spawn.
-    if (agentIdentifier) {
+  // The caller (router or host-sweep) catches the throw, leaves the inbound
-      await onecli.ensureAgent({ name: agentGroup.name, identifier: agentIdentifier });
+  // message pending, and the next sweep tick retries.
-    }
+  if (agentIdentifier) {
-    const onecliApplied = await onecli.applyContainerConfig(args, { addHostMapping: false, agent: agentIdentifier });
+    await onecli.ensureAgent({ name: agentGroup.name, identifier: agentIdentifier });
-    if (onecliApplied) {
-      log.info('OneCLI gateway applied', { containerName });
-    } else {
-      log.warn('OneCLI gateway not applied — container will have no credentials', { containerName });
-    }
-  } catch (err) {
-    log.warn('OneCLI gateway error — container will have no credentials', { containerName, err });
   }
+  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 });
 
   // Host gateway
   args.push(...hostGatewayArgs());

src/host-sweep.ts

@@ -168,6 +168,8 @@ async function sweepSession(session: Session): Promise<void> {
     const dueCount = countDueMessages(inDb);
     if (dueCount > 0 && !isContainerRunning(session.id)) {
       log.info('Waking container for due messages', { sessionId: session.id, count: dueCount });
+      // wakeContainer never throws — transient spawn failures (OneCLI down,
+      // etc.) return false and leave messages pending for the next tick.
       await wakeContainer(session);
     }
 

src/router.ts

@@ -27,7 +27,7 @@ import {
   getMessagingGroupWithAgentCount,
 } from './db/messaging-groups.js';
 import { findSessionForAgent } from './db/sessions.js';
-import { startTypingRefresh } from './modules/typing/index.js';
+import { startTypingRefresh, stopTypingRefresh } from './modules/typing/index.js';
 import { log } from './log.js';
 import { resolveSession, writeSessionMessage, writeOutboundDirect } from './session-manager.js';
 import { wakeContainer } from './container-runner.js';
@@ -457,7 +457,11 @@ async function deliverToAgent(
     startTypingRefresh(session.id, session.agent_group_id, event.channelType, event.platformId, event.threadId);
     const freshSession = getSession(session.id);
     if (freshSession) {
-      await wakeContainer(freshSession);
+      const woke = await wakeContainer(freshSession);
+      // wakeContainer never throws — it returns false on transient spawn
+      // failure (host-sweep retries). Stop the typing indicator we just
+      // started so it doesn't leak; the inbound row stays pending.
+      if (!woke) stopTypingRefresh(freshSession.id);
     }
   }
 }