Merge pull request #75890 from NousResearch/bb/disk-full-toast

Toast when a send fails because the disk is full

agent/turn_finalizer.py

@@ -647,6 +647,13 @@ def finalize_turn(
     }
     if agent._tool_guardrail_halt_decision is not None:
         result["guardrail"] = agent._tool_guardrail_halt_decision.to_metadata()
+    # Persistence failures already set failed=True + an explanation in
+    # final_response; also stamp `error` so gateway surfaces status="error"
+    # (and desktop can toast disk-full) instead of a quiet complete frame.
+    if failed and str(_turn_exit_reason) == "session_persistence_failed":
+        result["error"] = final_response or (
+            "session storage could not be written — free disk space and try again"
+        )
     # Surface any post-loop cleanup failures so the caller can distinguish a
     # clean turn from one whose trajectory/session/resource teardown raised
     # (the response is still returned either way — #8049).

apps/desktop/src/app/session/hooks/use-message-stream/gateway-event.ts

@@ -34,7 +34,7 @@ import {
   setChangeEventsAvailable
 } from '@/store/live-sync'
 import { dispatchNativeNotification } from '@/store/native-notifications'
-import { notify } from '@/store/notifications'
+import { isDiskFullErrorMessage, notify, notifyError } from '@/store/notifications'
 import { requestDesktopOnboarding, requestDesktopOnboardingForCredentialWarning } from '@/store/onboarding'
 import { revealDesktopPane } from '@/store/pane-focus'
 import { flashPetActivity, markPetUnread, setPetActivity } from '@/store/pet'
@@ -1161,6 +1161,8 @@ export function useGatewayEventHandler(deps: GatewayEventDeps) {
 
         if (looksLikeProviderSetup) {
           requestDesktopOnboarding(errorMessage)
+        } else if (isDiskFullErrorMessage(errorMessage)) {
+          notifyError(new Error(errorMessage), translateNow('notifications.errors.diskFull'))
         } else {
           // Toast globally, not just when the failing thread is focused: a
           // turn-ending error (e.g. out of funds) blocks every thread, so the

apps/desktop/src/app/session/hooks/use-message-stream/index.ts

@@ -22,6 +22,7 @@ import {
 } from '@/lib/generated-images'
 import { parseTodos } from '@/lib/todos'
 import { dispatchNativeNotification } from '@/store/native-notifications'
+import { isDiskFullErrorMessage, notifyError } from '@/store/notifications'
 import { broadcastSessionsChanged } from '@/store/session-sync'
 import { upsertSubagent } from '@/store/subagents'
 import { setSessionTodos } from '@/store/todos'
@@ -599,6 +600,16 @@ export function useMessageStream({
         }
       })
 
+      // Persistence / mid-turn disk-full failures land as a terminal frame with
+      // an error string, not a rejected prompt.submit. Toast them here so a
+      // full disk never looks like a silent no-reply. Only fire on actual
+      // failure signals — never on a healthy reply that happens to say
+      // "disk full".
+      const diskFullSignal = failure?.error || (failure ? text : '')
+      if (diskFullSignal && isDiskFullErrorMessage(diskFullSignal)) {
+        notifyError(new Error(diskFullSignal), translateNow('notifications.errors.diskFull'))
+      }
+
       scheduleSessionsRefresh()
 
       if (compactedTurnRef.current.delete(sessionId)) {

apps/desktop/src/i18n/ar.ts

@@ -117,6 +117,7 @@ export const ar = defineLocale({
     errors: {
       elevenLabsNeedsKey: 'يتطلب ElevenLabs STT المفتاح ELEVENLABS_API_KEY.',
       elevenLabsRejectedKey: 'رفض ElevenLabs مفتاح API (401).',
+      diskFull: 'القرص ممتلئ — حرّر مساحة ثم أعد المحاولة.',
       methodNotAllowed: 'رفضت خلفية سطح المكتب هذا الطلب (405 Method Not Allowed). جرب إعادة تشغيل Hermes Desktop.',
       microphonePermission: 'تم رفض إذن الميكروفون.',
       openaiRejectedApiKey: 'رفض OpenAI مفتاح API.',

apps/desktop/src/i18n/en.ts

@@ -132,6 +132,7 @@ export const en: Translations = {
     errors: {
       elevenLabsNeedsKey: 'ElevenLabs STT needs ELEVENLABS_API_KEY.',
       elevenLabsRejectedKey: 'ElevenLabs rejected the API key (401).',
+      diskFull: 'Disk full — free some space, then try again.',
       gatewayAuthFailed: 'Gateway authentication failed — check your API_SERVER_KEY.',
       methodNotAllowed:
         'The desktop backend rejected that request (405 Method Not Allowed). Try restarting Hermes Desktop.',

apps/desktop/src/i18n/ja.ts

@@ -133,6 +133,7 @@ export const ja = defineLocale({
     errors: {
       elevenLabsNeedsKey: 'ElevenLabs STT には ELEVENLABS_API_KEY が必要です。',
       elevenLabsRejectedKey: 'ElevenLabs が API キーを拒否しました (401)。',
+      diskFull: 'ディスク容量不足です — 空きを作ってからもう一度お試しください。',
       gatewayAuthFailed: 'ゲートウェイ認証に失敗しました — API_SERVER_KEY を確認してください。',
       methodNotAllowed:
         'デスクトップバックエンドがそのリクエストを拒否しました (405 Method Not Allowed)。Hermes Desktop を再起動してください。',

apps/desktop/src/i18n/types.ts

@@ -174,6 +174,7 @@ export interface Translations {
     errors: {
       elevenLabsNeedsKey: string
       elevenLabsRejectedKey: string
+      diskFull: string
       gatewayAuthFailed: string
       methodNotAllowed: string
       microphonePermission: string

apps/desktop/src/i18n/zh-hant.ts

@@ -129,6 +129,7 @@ export const zhHant = defineLocale({
     errors: {
       elevenLabsNeedsKey: 'ElevenLabs STT 需要 ELEVENLABS_API_KEY。',
       elevenLabsRejectedKey: 'ElevenLabs 拒絕了該 API 金鑰 (401)。',
+      diskFull: '磁碟已滿 — 請騰出一些空間後再試。',
       gatewayAuthFailed: '閘道認證失敗 — 請檢查你的 API_SERVER_KEY。',
       methodNotAllowed: '桌面後端拒絕了該請求 (405 Method Not Allowed)。請嘗試重新啟動 Hermes Desktop。',
       microphonePermission: '麥克風權限已被拒絕。',

apps/desktop/src/i18n/zh.ts

@@ -129,6 +129,7 @@ export const zh: Translations = {
     errors: {
       elevenLabsNeedsKey: 'ElevenLabs STT 需要 ELEVENLABS_API_KEY。',
       elevenLabsRejectedKey: 'ElevenLabs 拒绝了该 API key (401)。',
+      diskFull: '磁盘已满 — 请腾出一些空间后再试。',
       gatewayAuthFailed: '网关认证失败 — 请检查你的 API_SERVER_KEY。',
       methodNotAllowed: '桌面后端拒绝了该请求 (405 Method Not Allowed)。请尝试重启 Hermes Desktop。',
       microphonePermission: '麦克风权限已被拒绝。',

apps/desktop/src/store/notifications.test.ts

@@ -1,6 +1,6 @@
 import { beforeEach, expect, test } from 'vitest'
 
-import { $notifications, clearNotifications, notifyError } from './notifications'
+import { $notifications, clearNotifications, isDiskFullErrorMessage, notifyError } from './notifications'
 
 beforeEach(() => {
   clearNotifications()
@@ -32,3 +32,26 @@ test('provider invalid_api_key error still maps to the OpenAI summary', () => {
 
   expect(lastMessage()).toMatch(/OpenAI rejected the API key/i)
 })
+
+test('disk-full / ENOSPC errors toast a free-space message', () => {
+  expect(isDiskFullErrorMessage('OSError: [Errno 28] No space left on device')).toBe(true)
+  expect(isDiskFullErrorMessage('sqlite3.OperationalError: database or disk is full')).toBe(true)
+  expect(isDiskFullErrorMessage('disk full: session storage could not be written — free some disk space')).toBe(true)
+  expect(isDiskFullErrorMessage('This is often a full disk — free some space')).toBe(true)
+  expect(isDiskFullErrorMessage('session storage could not be written: permission denied')).toBe(false)
+  expect(isDiskFullErrorMessage('network timeout')).toBe(false)
+
+  notifyError(new Error('OSError: [Errno 28] No space left on device: state.db'), 'Prompt failed')
+
+  expect(lastMessage()).toMatch(/Disk full/i)
+  expect(lastMessage()).toMatch(/free some space/i)
+})
+
+test('session storage write failure is treated as disk-full class', () => {
+  notifyError(
+    new Error('disk full: session storage could not be written — free some disk space and try again'),
+    'Prompt failed'
+  )
+
+  expect(lastMessage()).toMatch(/Disk full/i)
+})

apps/desktop/src/store/notifications.ts

@@ -76,7 +76,27 @@ function cleanErrorText(value: string) {
   return value.replace(/^Error:\s*/, '').trim()
 }
 
+/** True when an error string is a disk-full / ENOSPC / SQLITE_FULL failure. */
+export function isDiskFullErrorMessage(message: string): boolean {
+  return (
+    /no space left on device/i.test(message) ||
+    /not enough space/i.test(message) ||
+    /database or disk is full/i.test(message) ||
+    /\bENOSPC\b/i.test(message) ||
+    /disk full/i.test(message) ||
+    /full disk/i.test(message)
+  )
+}
+
 const ERROR_SUMMARIES: { test: (msg: string) => boolean; summarize: (msg: string) => string }[] = [
+  {
+    // Disk full / ENOSPC — session DB write, backend crash, or any path that
+    // bubbles "no space left" / SQLITE_FULL through notifyError. Match before
+    // generic length truncation so the user gets a clear "free space" toast
+    // instead of a silent send or a raw errno dump.
+    test: isDiskFullErrorMessage,
+    summarize: () => translateNow('notifications.errors.diskFull')
+  },
   {
     test: msg => /['"]code['"]\s*:\s*['"]gateway_auth_failed['"]/i.test(msg),
     summarize: () => translateNow('notifications.errors.gatewayAuthFailed')

hermes_state.py

@@ -16,6 +16,7 @@ Key design decisions:
 
 import asyncio
 import atexit
+import errno
 import json
 import logging
 import os
@@ -939,6 +940,36 @@ def is_malformed_db_error(exc: BaseException) -> bool:
     return any(marker in str(exc).lower() for marker in _MALFORMED_SCHEMA_MARKERS)
 
 
+# Markers that mean the host filesystem cannot accept another write. Kept as
+# plain substrings so OSError, sqlite3.OperationalError, and wrapped RPC
+# error strings all match the same helper.
+_DISK_FULL_MARKERS = (
+    "no space left on device",
+    "not enough space",
+    "database or disk is full",  # SQLITE_FULL
+    "disk full",
+    "full disk",
+    "enospc",
+)
+
+
+def is_disk_full_error(exc: BaseException | str | None) -> bool:
+    """True when *exc* (or a stringified error) is a disk-full / ENOSPC failure.
+
+    Covers:
+      * ``OSError`` with ``errno.ENOSPC``
+      * SQLite ``OperationalError: database or disk is full`` (SQLITE_FULL)
+      * Plain English / errno strings that survive RPC wrapping
+    """
+    if exc is None:
+        return False
+    if isinstance(exc, OSError) and getattr(exc, "errno", None) == errno.ENOSPC:
+        return True
+    text = exc if isinstance(exc, str) else str(exc)
+    lowered = text.lower()
+    return any(marker in lowered for marker in _DISK_FULL_MARKERS)
+
+
 def _claim_repair_attempt(db_path: Path) -> bool:
     """Claim the one-shot repair attempt for *db_path* in this process.
 

run_agent.py

@@ -3530,8 +3530,8 @@ class AIAgent:
                 prefix
                 + "the turn was stopped because session storage could not be "
                 "written (the transcript would have been lost on restart). "
-                "Check disk space / permissions for the state DB, then send "
-                "your message again."
+                "This is often a full disk — free some space (or fix state.db "
+                "permissions), then send your message again."
             )
         # Unknown/diagnostic-only reasons (e.g. "unknown", guardrail_halt
         # which already surfaces its own message) — don't second-guess.

tests/state/test_disk_full_error.py

@@ -0,0 +1,30 @@
+"""is_disk_full_error classifies ENOSPC / SQLITE_FULL failures."""
+
+from __future__ import annotations
+
+import errno
+import sqlite3
+
+from hermes_state import is_disk_full_error
+
+
+def test_enospc_oserror():
+    assert is_disk_full_error(OSError(errno.ENOSPC, "No space left on device")) is True
+
+
+def test_sqlite_full_operational_error():
+    assert is_disk_full_error(sqlite3.OperationalError("database or disk is full")) is True
+
+
+def test_string_markers():
+    assert is_disk_full_error("disk full: session storage could not be written") is True
+    assert is_disk_full_error("ENOSPC writing state.db") is True
+    assert is_disk_full_error("This is often a full disk — free some space") is True
+
+
+def test_unrelated_errors():
+    assert is_disk_full_error(None) is False
+    assert is_disk_full_error(OSError(errno.EACCES, "Permission denied")) is False
+    assert is_disk_full_error(RuntimeError("network timeout")) is False
+    assert is_disk_full_error("session not found") is False
+    assert is_disk_full_error("session storage could not be written: permission denied") is False

tui_gateway/methods_prompt.py

@@ -233,10 +233,32 @@ def _(rid, params: dict) -> dict:
         )
 
     # Persist the DB row lazily, now that the user has actually sent a message.
-    _ensure_session_db_row(session)
-    # A branch becomes real here: copy its parent's transcript into the row so it
-    # resumes with full context (the agent won't persist the seed itself).
-    _persist_branch_seed(session)
+    # Disk-full must fail the RPC (not stream silently): desktop maps the error
+    # string to a "disk full" toast so the user knows why the send vanished.
+    try:
+        _ensure_session_db_row(session)
+        # A branch becomes real here: copy its parent's transcript into the row so it
+        # resumes with full context (the agent won't persist the seed itself).
+        _persist_branch_seed(session)
+    except Exception as exc:
+        from hermes_state import is_disk_full_error
+
+        with session["history_lock"]:
+            session["running"] = False
+            session["last_active"] = time.time()
+            _clear_inflight_turn(session)
+        if is_disk_full_error(exc):
+            return _err(
+                rid,
+                5070,
+                "disk full: session storage could not be written — free some disk space and try again",
+            )
+        logger.warning("prompt.submit: session persist failed: %s", exc, exc_info=True)
+        return _err(
+            rid,
+            5071,
+            f"session storage could not be written: {exc}",
+        )
     _start_agent_build(sid, session)
 
     def run_after_agent_ready() -> None:

tui_gateway/server.py

@@ -2518,7 +2518,14 @@ def _ensure_session_db_row(session: dict) -> None:
             # means the launch/default profile (matches run_agent's convention).
             profile_name=Path(profile_home).name if profile_home else None,
         )
-    except Exception:
+    except Exception as exc:
+        # Disk-full is not a soft failure: if we swallow it here, prompt.submit
+        # returns {"status":"streaming"} and the user's message vanishes with
+        # no toast. Re-raise so the submit handler can return a real RPC error.
+        from hermes_state import is_disk_full_error
+
+        if is_disk_full_error(exc):
+            raise
         logger.debug("failed to persist desktop session row", exc_info=True)
     finally:
         if close_db:
@@ -2561,7 +2568,11 @@ def _persist_branch_seed(session: dict) -> None:
                     timestamp=msg.get("timestamp"),
                 )
             session["_branch_seed_persisted"] = True
-        except Exception:
+        except Exception as exc:
+            from hermes_state import is_disk_full_error
+
+            if is_disk_full_error(exc):
+                raise
             logger.debug("branch seed persist failed", exc_info=True)