docs(assets): add NS-506 session DB durability infographic

A beta tester on a small Fly machine hit a corrupted session database
(state.db). The instance was memory/disk constrained — the agent was even
trying to add a swapfile (blocked by Fly seccomp), and SIGTERM-under-s6
mid-write plus a disk filling with a large npm cache are exactly the
conditions that tear a SQLite file.

The session DB opened with WAL (good) but never set `synchronous` or an
explicit `busy_timeout`, so it ran at SQLite's default durability and a
1s Python-level timeout. This commit pins the SQLite-recommended WAL
durability settings:

- WAL  → `synchronous=NORMAL`: crash-safe against OS crash / power loss /
  process kill (the DB file is never corrupted; only the last
  un-checkpointed transaction can be lost), without FULL's per-write fsync
  cost on the hot session-write path.
- DELETE fallback (NFS/SMB/FUSE, where WAL is unavailable) → `synchronous=
  FULL`, since without WAL only FULL is crash-safe.
- explicit `busy_timeout=2000` so a checkpoint/contention spike surfaces
  as a brief wait, not an immediate "database is locked".

The existing malformed-schema detection + timestamped backup + auto-repair
(`is_malformed_db_error` / `repair_state_db_schema`, surfaced by
`hermes doctor`) already covers *recovery*; this closes the *prevention*
gap that let the corruption happen in the first place.

Tests: 4 new pragma assertions (WAL→NORMAL, busy_timeout, never-OFF,
foreign_keys preserved) that fail without the fix. Plus a real E2E:
SIGKILL a child mid-write, reopen → `PRAGMA integrity_check` returns ok
with all rows intact. Full hermes_state suite (37) green.

Reported via beta (NS-506).

agent/agent_init.py

@@ -599,6 +599,7 @@ def init_agent(
     # (e.g. CLI voice mode adds a temporary prefix for the live call only).
     agent._persist_user_message_idx = None
     agent._persist_user_message_override = None
+    agent._persist_user_message_timestamp = None
 
     # Cache anthropic image-to-text fallbacks per image payload/URL so a
     # single tool loop does not repeatedly re-run auxiliary vision on the

agent/conversation_loop.py

@@ -474,6 +474,7 @@ def run_conversation(
     task_id: str = None,
     stream_callback: Optional[callable] = None,
     persist_user_message: Optional[str] = None,
+    persist_user_timestamp: Optional[float] = None,
 ) -> Dict[str, Any]:
     """
     Run a complete conversation with tool calling until completion.
@@ -489,6 +490,8 @@ def run_conversation(
         persist_user_message: Optional clean user message to store in
             transcripts/history when user_message contains API-only
             synthetic prefixes.
+        persist_user_timestamp: Optional platform event timestamp to store
+            as metadata on that persisted user message.
                 or queuing follow-up prefetch work.
 
     Returns:
@@ -510,6 +513,7 @@ def run_conversation(
         task_id,
         stream_callback,
         persist_user_message,
+        persist_user_timestamp,
         restore_or_build_system_prompt=_restore_or_build_system_prompt,
         install_safe_stdio=_install_safe_stdio,
         sanitize_surrogates=_sanitize_surrogates,

agent/turn_context.py

@@ -69,6 +69,7 @@ def build_turn_context(
     task_id: Optional[str],
     stream_callback,
     persist_user_message: Optional[str],
+    persist_user_timestamp: Optional[float] = None,
     *,
     restore_or_build_system_prompt,
     install_safe_stdio,
@@ -121,6 +122,7 @@ def build_turn_context(
     agent._stream_callback = stream_callback
     agent._persist_user_message_idx = None
     agent._persist_user_message_override = persist_user_message
+    agent._persist_user_message_timestamp = persist_user_timestamp
     # Generate unique task_id if not provided to isolate VMs between tasks.
     effective_task_id = task_id or str(uuid.uuid4())
     agent._current_task_id = effective_task_id

apps/desktop/src/app/settings/model-settings.test.tsx

@@ -16,6 +16,8 @@ const getAuxiliaryModels = vi.fn()
 const setModelAssignment = vi.fn()
 const getRecommendedDefaultModel = vi.fn()
 const setEnvVar = vi.fn()
+const getHermesConfigRecord = vi.fn()
+const saveHermesConfig = vi.fn()
 const startManualProviderOAuth = vi.fn()
 
 vi.mock('@/hermes', () => ({
@@ -24,7 +26,9 @@ vi.mock('@/hermes', () => ({
   getAuxiliaryModels: () => getAuxiliaryModels(),
   setModelAssignment: (body: unknown) => setModelAssignment(body),
   getRecommendedDefaultModel: (slug: string) => getRecommendedDefaultModel(slug),
-  setEnvVar: (key: string, value: string) => setEnvVar(key, value)
+  setEnvVar: (key: string, value: string) => setEnvVar(key, value),
+  getHermesConfigRecord: () => getHermesConfigRecord(),
+  saveHermesConfig: (config: unknown) => saveHermesConfig(config)
 }))
 
 vi.mock('@/store/onboarding', () => ({
@@ -35,7 +39,13 @@ beforeEach(() => {
   getGlobalModelInfo.mockResolvedValue({ provider: 'nous', model: 'hermes-4' })
   getGlobalModelOptions.mockResolvedValue({
     providers: [
-      { name: 'Nous', slug: 'nous', models: ['hermes-4', 'hermes-4-mini'], authenticated: true },
+      {
+        name: 'Nous',
+        slug: 'nous',
+        models: ['hermes-4', 'hermes-4-mini'],
+        authenticated: true,
+        capabilities: { 'hermes-4': { reasoning: true, fast: true } }
+      },
       // An unconfigured api_key provider — surfaced by the full-universe payload.
       { name: 'DeepSeek', slug: 'deepseek', models: [], authenticated: false, auth_type: 'api_key', key_env: 'DEEPSEEK_API_KEY' }
     ]
@@ -47,6 +57,8 @@ beforeEach(() => {
   setModelAssignment.mockResolvedValue({ provider: 'nous', model: 'hermes-4', gateway_tools: [] })
   getRecommendedDefaultModel.mockResolvedValue({ provider: 'deepseek', model: 'deepseek-chat', free_tier: null })
   setEnvVar.mockResolvedValue({ ok: true })
+  getHermesConfigRecord.mockResolvedValue({ agent: { reasoning_effort: 'medium', service_tier: 'normal' } })
+  saveHermesConfig.mockResolvedValue({ ok: true })
 })
 
 afterEach(() => {
@@ -100,6 +112,31 @@ describe('ModelSettings', () => {
     await waitFor(() => expect(setEnvVar).toHaveBeenCalledWith('DEEPSEEK_API_KEY', 'sk-test-123'))
   })
 
+  it('writes the profile default speed (service_tier) when the fast switch is toggled', async () => {
+    await renderModelSettings()
+    await waitFor(() => expect(getHermesConfigRecord).toHaveBeenCalled())
+
+    const fastSwitch = await screen.findByRole('switch')
+    fireEvent.click(fastSwitch)
+
+    await waitFor(() =>
+      expect(saveHermesConfig).toHaveBeenCalledWith(
+        expect.objectContaining({ agent: expect.objectContaining({ service_tier: 'fast' }) })
+      )
+    )
+  })
+
+  it('hides the reasoning/speed defaults when the main model reports no capabilities', async () => {
+    getGlobalModelOptions.mockResolvedValueOnce({
+      providers: [{ name: 'Nous', slug: 'nous', models: ['hermes-4'], authenticated: true, capabilities: { 'hermes-4': { reasoning: false, fast: false } } }]
+    })
+
+    await renderModelSettings()
+    await waitFor(() => expect(getHermesConfigRecord).toHaveBeenCalled())
+
+    expect(screen.queryByRole('switch')).toBeNull()
+  })
+
   it('renders the auxiliary task rows', async () => {
     await renderModelSettings()
 

apps/desktop/src/app/settings/model-settings.tsx

@@ -3,11 +3,14 @@ import { useCallback, useEffect, useMemo, useState } from 'react'
 import { Button } from '@/components/ui/button'
 import { Input } from '@/components/ui/input'
 import { Select, SelectContent, SelectItem, SelectTrigger, SelectValue } from '@/components/ui/select'
+import { Switch } from '@/components/ui/switch'
 import {
   getAuxiliaryModels,
   getGlobalModelInfo,
   getGlobalModelOptions,
+  getHermesConfigRecord,
   getRecommendedDefaultModel,
+  saveHermesConfig,
   setEnvVar,
   setModelAssignment
 } from '@/hermes'
@@ -15,11 +18,26 @@ import type { AuxiliaryModelsResponse, ModelOptionProvider, StaleAuxAssignment }
 import { useI18n } from '@/i18n'
 import { AlertTriangle, Cpu, Loader2 } from '@/lib/icons'
 import { cn } from '@/lib/utils'
+import { notifyError } from '@/store/notifications'
 import { startManualLocalEndpoint, startManualProviderOAuth } from '@/store/onboarding'
+import type { HermesConfigRecord } from '@/types/hermes'
 
 import { CONTROL_TEXT } from './constants'
+import { getNested, setNested } from './helpers'
 import { ListRow, LoadingState, Pill, SectionHeading } from './primitives'
 
+// Hermes' reasoning levels (VALID_REASONING_EFFORTS); `none` = thinking off.
+// Empty config = Hermes default (medium), shown as Medium.
+const EFFORT_VALUES = ['none', 'minimal', 'low', 'medium', 'high', 'xhigh'] as const
+
+// agent.service_tier stores "fast"/"priority"/"on" for fast; anything else is
+// normal (mirrors tui_gateway _load_service_tier).
+const isFastTier = (tier: unknown): boolean =>
+  ['fast', 'priority', 'on'].includes(String(tier ?? '').trim().toLowerCase())
+
+// Reuse the composer's effort labels (`xhigh` shows as "Max", else 1:1).
+const effortLabelKey = (v: string) => (v === 'xhigh' ? 'max' : v) as 'high' | 'low' | 'max' | 'medium' | 'minimal'
+
 // A provider row is "ready" to pick a model from when it reports models. The
 // backend now surfaces the full `hermes model` universe (every canonical
 // provider), so unconfigured providers come back with `authenticated:false`
@@ -97,6 +115,9 @@ export function ModelSettings({ onMainModelChanged }: ModelSettingsProps) {
   const [selectedProvider, setSelectedProvider] = useState('')
   const [selectedModel, setSelectedModel] = useState('')
   const [auxiliary, setAuxiliary] = useState<AuxiliaryModelsResponse | null>(null)
+  // Full profile config, kept so the reasoning/speed defaults round-trip
+  // (read agent.* → write back the whole record) like the generic config page.
+  const [config, setConfig] = useState<HermesConfigRecord | null>(null)
   const [applying, setApplying] = useState(false)
   const [editingAuxTask, setEditingAuxTask] = useState<null | string>(null)
   const [auxDraft, setAuxDraft] = useState<{ model: string; provider: string }>({ model: '', provider: '' })
@@ -113,10 +134,11 @@ export function ModelSettings({ onMainModelChanged }: ModelSettingsProps) {
     setError('')
 
     try {
-      const [modelInfo, modelOptions, auxiliaryModels] = await Promise.all([
+      const [modelInfo, modelOptions, auxiliaryModels, cfg] = await Promise.all([
         getGlobalModelInfo(),
         getGlobalModelOptions(),
-        getAuxiliaryModels()
+        getAuxiliaryModels(),
+        getHermesConfigRecord()
       ])
 
       setMainModel({ model: modelInfo.model, provider: modelInfo.provider })
@@ -124,6 +146,7 @@ export function ModelSettings({ onMainModelChanged }: ModelSettingsProps) {
       setSelectedProvider(prev => prev || modelInfo.provider)
       setSelectedModel(prev => prev || modelInfo.model)
       setAuxiliary(auxiliaryModels)
+      setConfig(cfg)
     } catch (err) {
       setError(err instanceof Error ? err.message : String(err))
     } finally {
@@ -181,6 +204,42 @@ export function ModelSettings({ onMainModelChanged }: ModelSettingsProps) {
       .map(entry => ({ task: entry.task, provider: entry.provider, model: entry.model }))
   }, [auxiliary, mainModel])
 
+  // Capabilities of the APPLIED main model — gates the profile-default
+  // reasoning/speed controls the same way the composer picker gates per-model
+  // edits (reasoning defaults on, fast defaults off when unreported).
+  const mainCaps = useMemo(() => {
+    const row = providers.find(provider => provider.slug === mainModel?.provider)
+
+    return mainModel ? row?.capabilities?.[mainModel.model] : undefined
+  }, [providers, mainModel])
+
+  const reasoningSupported = mainCaps?.reasoning ?? true
+  const fastSupported = mainCaps?.fast ?? false
+  const effortValue = String(getNested(config ?? {}, 'agent.reasoning_effort') ?? '').trim().toLowerCase() || 'medium'
+  const fastOn = isFastTier(getNested(config ?? {}, 'agent.service_tier'))
+
+  // Persist a single agent.* default by round-tripping the whole config record
+  // (PUT /api/config replaces it) — optimistic, with rollback on failure.
+  const writeAgentDefault = useCallback(
+    async (key: string, value: string) => {
+      if (!config) {
+        return
+      }
+
+      const prev = config
+      const next = setNested(config, key, value)
+      setConfig(next)
+
+      try {
+        await saveHermesConfig(next)
+      } catch (err) {
+        setConfig(prev)
+        notifyError(err, m.defaultsFailed)
+      }
+    },
+    [config, m.defaultsFailed]
+  )
+
   // Paste an API key for the selected `api_key` provider, persist it, then
   // refresh so the now-authenticated provider's models populate. Auto-selects
   // the recommended default model so the user can Apply in one more click.
@@ -433,6 +492,38 @@ export function ModelSettings({ onMainModelChanged }: ModelSettingsProps) {
               : `${selectedProviderRow?.name} signs in through your browser — Hermes runs the flow for you.`}
           </p>
         )}
+        {config && mainModel && (reasoningSupported || fastSupported) && (
+          <div className="mt-3 flex flex-wrap items-center gap-x-6 gap-y-3">
+            <span className="text-xs text-muted-foreground">{m.defaultsLabel}</span>
+            {reasoningSupported && (
+              <div className="flex items-center gap-2 text-xs">
+                {m.reasoning}
+                <Select onValueChange={value => void writeAgentDefault('agent.reasoning_effort', value)} value={effortValue}>
+                  <SelectTrigger className={cn('min-w-28', CONTROL_TEXT)}>
+                    <SelectValue />
+                  </SelectTrigger>
+                  <SelectContent>
+                    {EFFORT_VALUES.map(value => (
+                      <SelectItem key={value} value={value}>
+                        {value === 'none' ? m.reasoningOff : t.shell.modelOptions[effortLabelKey(value)]}
+                      </SelectItem>
+                    ))}
+                  </SelectContent>
+                </Select>
+              </div>
+            )}
+            {fastSupported && (
+              <label className="flex items-center gap-2 text-xs">
+                {t.shell.modelOptions.fast}
+                <Switch
+                  checked={fastOn}
+                  onCheckedChange={checked => void writeAgentDefault('agent.service_tier', checked ? 'fast' : 'normal')}
+                  size="xs"
+                />
+              </label>
+            )}
+          </div>
+        )}
         {error && <div className="mt-2 text-xs text-destructive">{error}</div>}
         {switchStaleAux.length > 0 && (
           <div className="mt-2">

apps/desktop/src/app/shell/model-menu-panel.tsx

@@ -18,7 +18,7 @@ import { Skeleton } from '@/components/ui/skeleton'
 import type { HermesGateway } from '@/hermes'
 import { getGlobalModelOptions } from '@/hermes'
 import { useI18n } from '@/i18n'
-import { displayModelName, modelDisplayParts, reasoningEffortLabel } from '@/lib/model-status-label'
+import { currentPickerSelection, displayModelName, modelDisplayParts, reasoningEffortLabel } from '@/lib/model-status-label'
 import { cn } from '@/lib/utils'
 import { $modelPresets, applyModelPreset, modelPresetKey } from '@/store/model-presets'
 import {
@@ -84,8 +84,12 @@ export function ModelMenuPanel({ gateway, onSelectModel, requestGateway }: Model
     }
   })
 
-  const optionsModel = String(modelOptions.data?.model ?? currentModel ?? '')
-  const optionsProvider = String(modelOptions.data?.provider ?? currentProvider ?? '')
+  const { model: optionsModel, provider: optionsProvider } = currentPickerSelection(
+    !!activeSessionId,
+    { model: currentModel, provider: currentProvider },
+    modelOptions.data
+  )
+
   const loading = modelOptions.isPending && !modelOptions.data
 
   const error = modelOptions.error

apps/desktop/src/components/model-picker.tsx

@@ -2,6 +2,7 @@ import { useQuery } from '@tanstack/react-query'
 import { useState } from 'react'
 
 import { useI18n } from '@/i18n'
+import { currentPickerSelection } from '@/lib/model-status-label'
 import type { ModelOptionProvider, ModelOptionsResponse, ModelPricing } from '@/types/hermes'
 
 import type { HermesGateway } from '../hermes'
@@ -66,8 +67,13 @@ export function ModelPickerDialog({
   })
 
   const providers = modelOptions.data?.providers ?? []
-  const optionsModel = String(modelOptions.data?.model ?? currentModel ?? '')
-  const optionsProvider = String(modelOptions.data?.provider ?? currentProvider ?? '')
+
+  const { model: optionsModel, provider: optionsProvider } = currentPickerSelection(
+    !!sessionId,
+    { model: currentModel, provider: currentProvider },
+    modelOptions.data
+  )
+
   const loading = modelOptions.isPending && !modelOptions.data
 
   const error = modelOptions.error

apps/desktop/src/i18n/en.ts

@@ -538,6 +538,10 @@ export const en: Translations = {
       provider: 'Provider',
       model: 'Model',
       applying: 'Applying...',
+      defaultsLabel: 'Defaults',
+      reasoning: 'Reasoning',
+      reasoningOff: 'Off',
+      defaultsFailed: 'Failed to save model defaults',
       auxiliaryTitle: 'Auxiliary models',
       resetAllToMain: 'Reset all to main',
       auxiliaryDesc: 'Helper tasks run on the main model by default. Assign a dedicated model to any task to override.',

apps/desktop/src/i18n/types.ts

@@ -430,6 +430,10 @@ export interface Translations {
       provider: string
       model: string
       applying: string
+      defaultsLabel: string
+      reasoning: string
+      reasoningOff: string
+      defaultsFailed: string
       auxiliaryTitle: string
       resetAllToMain: string
       auxiliaryDesc: string

apps/desktop/src/i18n/zh.ts

@@ -733,6 +733,10 @@ export const zh: Translations = {
       provider: '提供方',
       model: '模型',
       applying: '应用中...',
+      defaultsLabel: '默认值',
+      reasoning: '推理',
+      reasoningOff: '关闭',
+      defaultsFailed: '保存模型默认值失败',
       auxiliaryTitle: '辅助模型',
       resetAllToMain: '全部重置为主模型',
       auxiliaryDesc: '辅助任务默认使用主模型。你可以为任意任务指定专用模型。',

apps/desktop/src/lib/model-status-label.test.ts

@@ -1,6 +1,6 @@
 import { describe, expect, it } from 'vitest'
 
-import { displayModelName, formatModelStatusLabel, reasoningEffortLabel } from './model-status-label'
+import { currentPickerSelection, displayModelName, formatModelStatusLabel, reasoningEffortLabel } from './model-status-label'
 
 describe('model-status-label', () => {
   it('formats display names consistently', () => {
@@ -35,4 +35,25 @@ describe('model-status-label', () => {
   it('returns just the placeholder name when there is no model', () => {
     expect(formatModelStatusLabel('')).toBe('No model')
   })
+
+  describe('currentPickerSelection', () => {
+    const store = { model: 'opus', provider: 'anthropic' }
+    const options = { model: 'hermes-4', provider: 'nous' }
+
+    it('prefers the sticky composer pick over the profile default pre-session', () => {
+      expect(currentPickerSelection(false, store, options)).toEqual(store)
+    })
+
+    it('lets the live session model.options win when a session exists', () => {
+      expect(currentPickerSelection(true, store, options)).toEqual(options)
+    })
+
+    it('falls back to options when the store is empty', () => {
+      expect(currentPickerSelection(false, { model: '', provider: '' }, options)).toEqual(options)
+    })
+
+    it('falls back to the store while options are still loading', () => {
+      expect(currentPickerSelection(true, store, undefined)).toEqual(store)
+    })
+  })
 })

apps/desktop/src/lib/model-status-label.ts

@@ -17,6 +17,22 @@ export function reasoningEffortLabel(effort: string): string {
   return REASONING_LABELS[key] ?? effort
 }
 
+/** Which model/provider a picker should mark "current". With a live session the
+ *  gateway's `model.options` is authoritative; pre-session there is no server
+ *  "current", so the sticky composer pick wins over the profile default the
+ *  global options query returns — else the checkmark snaps back to the default
+ *  and the pick looks ignored. */
+export function currentPickerSelection(
+  hasSession: boolean,
+  store: { model: string; provider: string },
+  options?: { model?: string; provider?: string }
+): { model: string; provider: string } {
+  return {
+    model: String((hasSession && options?.model) || store.model || options?.model || ''),
+    provider: String((hasSession && options?.provider) || store.provider || options?.provider || '')
+  }
+}
+
 /** Strip provider prefix and normalize for display. */
 export function modelBaseId(model: string): string {
   const trimmed = model.trim()

gateway/message_timestamps.py

@@ -0,0 +1,166 @@
+"""Helpers for rendering gateway message timestamps exactly once.
+
+Gateway messages need timestamps in the LLM context for temporal awareness, but
+persisted message content should stay clean so replay does not accumulate
+``[timestamp] [timestamp] ...`` prefixes across turns.
+"""
+
+from __future__ import annotations
+
+import re
+from datetime import datetime
+from typing import Any, Optional, Tuple
+
+
+# Current gateway format: [Tue 2026-04-28 13:40:53 CEST]
+_HUMAN_TIMESTAMP_RE = re.compile(
+    r"^\[(?P<dow>[A-Z][a-z]{2}) "
+    r"(?P<date>\d{4}-\d{2}-\d{2}) "
+    r"(?P<time>\d{2}:\d{2}:\d{2})"
+    r"(?: (?P<tz>[A-Za-z0-9_+\-/:]+))?\]\s*"
+)
+
+# Older gateway format: [2026-04-13T17:02:06+0200] or [+02:00]
+_ISO_TIMESTAMP_RE = re.compile(
+    r"^\[(?P<iso>\d{4}-\d{2}-\d{2}T[^\]]+)\]\s*"
+)
+
+
+def coerce_message_timestamp(ts_value: Any, tz=None) -> Optional[float]:
+    """Coerce a timestamp-like value to Unix epoch seconds.
+
+    Accepts Unix epoch numbers, datetime objects, ISO strings, and the gateway's
+    bracketed human-readable timestamp format. Returns ``None`` when the value
+    cannot be interpreted.
+    """
+    if ts_value is None:
+        return None
+
+    if isinstance(ts_value, (int, float)):
+        return float(ts_value)
+
+    if hasattr(ts_value, "timestamp"):
+        try:
+            return float(ts_value.timestamp())
+        except Exception:
+            return None
+
+    if isinstance(ts_value, str):
+        text = ts_value.strip()
+        if not text:
+            return None
+        parsed = _parse_timestamp_prefix(text, tz=tz)
+        if parsed is not None:
+            return parsed
+        try:
+            return float(text)
+        except (TypeError, ValueError):
+            pass
+        try:
+            dt = datetime.fromisoformat(text)
+        except (TypeError, ValueError):
+            try:
+                dt = datetime.strptime(text, "%Y-%m-%dT%H:%M:%S%z")
+            except (TypeError, ValueError):
+                return None
+        if dt.tzinfo is None:
+            if tz is not None:
+                dt = dt.replace(tzinfo=tz)
+            else:
+                dt = dt.astimezone()
+        return float(dt.timestamp())
+
+    return None
+
+
+def format_message_timestamp(ts_value: Any, tz=None) -> str:
+    """Format a timestamp value as ``[Tue 2026-04-28 13:40:53 CEST]``."""
+    epoch = coerce_message_timestamp(ts_value, tz=tz)
+    if epoch is None:
+        return ""
+    if tz is not None:
+        dt = datetime.fromtimestamp(epoch, tz=tz)
+    else:
+        dt = datetime.fromtimestamp(epoch).astimezone()
+    return "[" + dt.strftime("%a %Y-%m-%d %H:%M:%S %Z") + "]"
+
+
+def strip_leading_message_timestamps(content: str, tz=None) -> Tuple[str, Optional[float]]:
+    """Strip one or more leading gateway timestamp prefixes from ``content``.
+
+    Returns ``(clean_content, embedded_epoch)``.  If multiple timestamp prefixes
+    are present, the timestamp closest to the actual message text wins.  That
+    preserves the original platform-send time for legacy contaminated rows like
+    ``[processing time] [platform time] [sender] message``.
+    """
+    if not isinstance(content, str) or not content:
+        return content, None
+
+    text = content
+    embedded_epoch: Optional[float] = None
+
+    while True:
+        match = _HUMAN_TIMESTAMP_RE.match(text) or _ISO_TIMESTAMP_RE.match(text)
+        if not match:
+            break
+        parsed = _parse_timestamp_match(match, tz=tz)
+        if parsed is not None:
+            embedded_epoch = parsed
+        text = text[match.end():]
+
+    return text, embedded_epoch
+
+
+def render_user_content_with_timestamp(content: str, ts_value: Any = None, tz=None) -> str:
+    """Render a user message for LLM context with exactly one timestamp prefix.
+
+    Existing leading timestamp prefixes are removed first.  If such a prefix was
+    present, its parsed time wins over ``ts_value``; otherwise ``ts_value`` is
+    formatted and prepended.  If no timestamp is available, the cleaned content is
+    returned unchanged.
+    """
+    clean_content, embedded_epoch = strip_leading_message_timestamps(content, tz=tz)
+    effective_ts = embedded_epoch if embedded_epoch is not None else ts_value
+    prefix = format_message_timestamp(effective_ts, tz=tz)
+    if not prefix:
+        return clean_content
+    if clean_content:
+        return f"{prefix} {clean_content}"
+    return prefix
+
+
+def _parse_timestamp_prefix(text: str, tz=None) -> Optional[float]:
+    match = _HUMAN_TIMESTAMP_RE.match(text) or _ISO_TIMESTAMP_RE.match(text)
+    if not match:
+        return None
+    return _parse_timestamp_match(match, tz=tz)
+
+
+def _parse_timestamp_match(match: re.Match, tz=None) -> Optional[float]:
+    if "iso" in match.groupdict() and match.group("iso"):
+        iso_text = match.group("iso")
+        try:
+            dt = datetime.fromisoformat(iso_text)
+        except ValueError:
+            try:
+                dt = datetime.strptime(iso_text, "%Y-%m-%dT%H:%M:%S%z")
+            except ValueError:
+                return None
+        if dt.tzinfo is None:
+            if tz is not None:
+                dt = dt.replace(tzinfo=tz)
+            else:
+                dt = dt.astimezone()
+        return float(dt.timestamp())
+
+    date_part = match.group("date")
+    time_part = match.group("time")
+    try:
+        dt = datetime.strptime(f"{date_part} {time_part}", "%Y-%m-%d %H:%M:%S")
+    except ValueError:
+        return None
+    if tz is not None:
+        dt = dt.replace(tzinfo=tz)
+    else:
+        dt = dt.astimezone()
+    return float(dt.timestamp())

gateway/run.py

@@ -692,10 +692,31 @@ def _uses_telegram_observed_group_context(channel_prompt: Optional[str]) -> bool
     return bool(channel_prompt and _TELEGRAM_OBSERVED_CONTEXT_PROMPT_MARKER in channel_prompt)
 
 
+def _message_timestamps_enabled(user_config: Optional[dict]) -> bool:
+    """True when gateway.message_timestamps.enabled is opted in.
+
+    Default OFF: injecting a ``[Tue 2026-04-28 13:40:53 CEST]`` prefix onto
+    every user message changes what the model sees for all gateway users, so
+    it must be explicitly enabled in config.yaml under
+    ``gateway.message_timestamps.enabled``.
+    """
+    if not isinstance(user_config, dict):
+        return False
+    gw = user_config.get("gateway")
+    if not isinstance(gw, dict):
+        return False
+    mt = gw.get("message_timestamps")
+    if isinstance(mt, dict):
+        return bool(mt.get("enabled", False))
+    # Allow a bare ``message_timestamps: true`` shorthand.
+    return bool(mt)
+
+
 def _build_gateway_agent_history(
     history: List[Dict[str, Any]],
     *,
     channel_prompt: Optional[str] = None,
+    inject_timestamps: bool = False,
 ) -> tuple[List[Dict[str, Any]], Optional[str]]:
     """Convert stored gateway transcript rows into agent replay messages.
 
@@ -704,8 +725,18 @@ def _build_gateway_agent_history(
     turns.  Keeping that context out of ``conversation_history`` avoids
     consecutive-user repair merging it with the live user turn and then hiding
     the current message behind ``history_offset`` during persistence.
+
+    When ``inject_timestamps`` is True (gateway.message_timestamps.enabled),
+    each replayed user message is rendered with a single human-readable
+    timestamp prefix from its stored metadata.
     """
 
+    from hermes_time import get_timezone as _get_msg_tz
+    from gateway.message_timestamps import (
+        render_user_content_with_timestamp as _render_msg_ts,
+    )
+
+    _msg_tz = _get_msg_tz()
     agent_history: List[Dict[str, Any]] = []
     observed_group_context: List[str] = []
     separate_observed_context = _uses_telegram_observed_group_context(channel_prompt)
@@ -725,6 +756,8 @@ def _build_gateway_agent_history(
             continue
 
         content = msg.get("content")
+        if inject_timestamps and role == "user" and isinstance(content, str):
+            content = _render_msg_ts(content, msg.get("timestamp"), tz=_msg_tz)
         if separate_observed_context and msg.get("observed") and role == "user" and content:
             observed_group_context.append(str(content).strip())
             continue
@@ -8378,6 +8411,8 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
         
         # Read privacy.redact_pii from config (re-read per message)
         _redact_pii = False
+        persist_user_message = None
+        persist_user_timestamp = None
         try:
             _pcfg = _load_gateway_config()
             _redact_pii = bool((_pcfg.get("privacy") or {}).get("redact_pii", False))
@@ -8902,6 +8937,42 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
         if message_text is None:
             return
 
+        # Capture the platform event time as message metadata and keep the
+        # persisted transcript clean (strip any leading timestamp prefix).
+        # This runs regardless of the toggle so storage stays clean and the
+        # send-time is preserved. Only the in-context RENDER (prepending the
+        # human-readable prefix the model sees) is gated behind
+        # gateway.message_timestamps.enabled — default OFF.
+        try:
+            from hermes_time import get_timezone as _get_evt_tz
+            from gateway.message_timestamps import (
+                coerce_message_timestamp as _coerce_msg_ts,
+                render_user_content_with_timestamp as _render_msg_ts,
+                strip_leading_message_timestamps as _strip_msg_ts,
+            )
+            _evt_tz = _get_evt_tz()
+            _evt_ts = getattr(event, "timestamp", None)
+            if message_text and isinstance(message_text, str):
+                _clean_message_text, _embedded_ts = _strip_msg_ts(
+                    message_text, tz=_evt_tz)
+                persist_user_message = _clean_message_text
+                _event_epoch = _coerce_msg_ts(_evt_ts, tz=_evt_tz)
+                persist_user_timestamp = (
+                    _event_epoch if _event_epoch is not None else _embedded_ts
+                )
+                if _message_timestamps_enabled(_load_gateway_config()):
+                    message_text = _render_msg_ts(
+                        _clean_message_text,
+                        persist_user_timestamp,
+                        tz=_evt_tz,
+                    )
+                else:
+                    # Toggle off: model sees the clean message; the timestamp
+                    # is still stored as metadata for later opt-in.
+                    message_text = _clean_message_text
+        except Exception as _ts_err:
+            logger.debug("Message timestamp injection failed (non-fatal): %s", _ts_err)
+
         # Bind this gateway run generation to the adapter's active-session
         # event so deferred post-delivery callbacks can be released by the
         # same run that registered them.
@@ -8935,6 +9006,8 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                 run_generation=run_generation,
                 event_message_id=self._reply_anchor_for_event(event),
                 channel_prompt=event.channel_prompt,
+                persist_user_message=persist_user_message,
+                persist_user_timestamp=persist_user_timestamp,
             )
 
             # Stop persistent typing indicator now that the agent is done
@@ -9226,7 +9299,7 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                     "Your next message will start a fresh session."
                 )
 
-            ts = datetime.now().isoformat()
+            ts = time.time()  # Unix epoch float — consistent with DB storage
             
             # If this is a fresh session (no history), write the full tool
             # definitions as the first entry so the transcript is self-describing
@@ -9262,7 +9335,19 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                 # message so the next message can load a transcript that
                 # reflects what was said.  Skip the assistant error text since
                 # it's a gateway-generated hint, not model output. (#7100)
-                _user_entry = {"role": "user", "content": message_text, "timestamp": ts}
+                _user_entry = {
+                    "role": "user",
+                    "content": (
+                        persist_user_message
+                        if persist_user_message is not None
+                        else message_text
+                    ),
+                    "timestamp": (
+                        persist_user_timestamp
+                        if persist_user_timestamp is not None
+                        else ts
+                    ),
+                }
                 if event.message_id:
                     _user_entry["message_id"] = str(event.message_id)
                 self.session_store.append_to_transcript(
@@ -9276,7 +9361,19 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
 
                 # If no new messages found (edge case), fall back to simple user/assistant
                 if not new_messages:
-                    _user_entry = {"role": "user", "content": message_text, "timestamp": ts}
+                    _user_entry = {
+                        "role": "user",
+                        "content": (
+                            persist_user_message
+                            if persist_user_message is not None
+                            else message_text
+                        ),
+                        "timestamp": (
+                            persist_user_timestamp
+                            if persist_user_timestamp is not None
+                            else ts
+                        ),
+                    }
                     if event.message_id:
                         _user_entry["message_id"] = str(event.message_id)
                     self.session_store.append_to_transcript(
@@ -9401,13 +9498,26 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                         _recent_transcript = []
                     for _msg in reversed(_recent_transcript[-10:]):
                         if _msg.get("role") == "user":
-                            _already_persisted = (_msg.get("content") == message_text)
+                            _expected_user_content = (
+                                persist_user_message
+                                if persist_user_message is not None
+                                else message_text
+                            )
+                            _already_persisted = (_msg.get("content") == _expected_user_content)
                             break
                     if not _already_persisted:
                         _user_entry = {
                             "role": "user",
-                            "content": message_text,
-                            "timestamp": datetime.now().isoformat(),
+                            "content": (
+                                persist_user_message
+                                if persist_user_message is not None
+                                else message_text
+                            ),
+                            "timestamp": (
+                                persist_user_timestamp
+                                if persist_user_timestamp is not None
+                                else time.time()
+                            ),
                         }
                         if getattr(event, "message_id", None):
                             _user_entry["message_id"] = str(event.message_id)
@@ -13602,6 +13712,8 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
         _interrupt_depth: int = 0,
         event_message_id: Optional[str] = None,
         channel_prompt: Optional[str] = None,
+        persist_user_message: Optional[str] = None,
+        persist_user_timestamp: Optional[float] = None,
     ) -> Dict[str, Any]:
         """
         Run the agent with the given message and context.
@@ -14912,6 +15024,7 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
             agent_history, observed_group_context = _build_gateway_agent_history(
                 history,
                 channel_prompt=channel_prompt,
+                inject_timestamps=_message_timestamps_enabled(_load_gateway_config()),
             )
             
             # Collect MEDIA paths already in history so we can exclude them
@@ -15028,7 +15141,8 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
             # Keep real user text separate from API-only recovery guidance.  If
             # an auto-continue note is prepended below, persist the original
             # message so stale guidance never replays as user-authored text.
-            _persist_user_message_override: Optional[Any] = None
+            _persist_user_message_override: Optional[Any] = persist_user_message
+            _persist_user_timestamp_override: Optional[float] = persist_user_timestamp
 
             # Prepend pending model switch note so the model knows about the switch
             _pending_notes = getattr(self, '_pending_model_notes', {})
@@ -15168,6 +15282,8 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                     _conversation_kwargs["persist_user_message"] = _persist_user_message_override
                 elif observed_group_context:
                     _conversation_kwargs["persist_user_message"] = message
+                if _persist_user_timestamp_override is not None:
+                    _conversation_kwargs["persist_user_timestamp"] = _persist_user_timestamp_override
                 result = agent.run_conversation(_api_run_message, **_conversation_kwargs)
             finally:
                 unregister_gateway_notify(_approval_session_key)

gateway/session.py

@@ -1322,6 +1322,7 @@ class SessionStore:
                         message.get("platform_message_id") or message.get("message_id")
                     ),
                     observed=bool(message.get("observed")),
+                    timestamp=message.get("timestamp"),
                 )
             except Exception as e:
                 logger.debug("Session DB operation failed: %s", e)

hermes_cli/config.py

@@ -2270,6 +2270,17 @@ DEFAULT_CONFIG = {
     # Gateway settings — control how messaging platforms (Telegram, Discord,
     # Slack, etc.) deliver agent-produced files as native attachments.
     "gateway": {
+        # Inject a human-readable timestamp prefix (e.g.
+        # "[Tue 2026-04-28 13:40:53 CEST]") onto user messages IN THE MODEL'S
+        # CONTEXT so the agent has temporal awareness of when each message was
+        # sent. Off by default — when off, the model sees clean message text.
+        # Persisted transcripts always stay clean (the timestamp is stored as
+        # message metadata regardless of this toggle), so turning it on later
+        # surfaces send-times for past messages too.
+        "message_timestamps": {
+            "enabled": False,
+        },
+
         # When false (default), any file path the agent emits is delivered
         # as a native attachment as long as it isn't under the credential /
         # system-path denylist (/etc, /proc, ~/.ssh, ~/.aws, ~/.hermes/.env,

hermes_constants.py

@@ -461,11 +461,21 @@ _container_detected: bool | None = None
 
 
 def is_container() -> bool:
-    """Return True when running inside a Docker/Podman container.
+    """Return True when running inside a container.
 
-    Checks ``/.dockerenv`` (Docker), ``/run/.containerenv`` (Podman),
-    and ``/proc/1/cgroup`` for container runtime markers.  Result is
-    cached for the process lifetime.  Import-safe — no heavy deps.
+    Recognizes Docker (``/.dockerenv``), Podman (``/run/.containerenv``),
+    and — via ``/proc/1/cgroup`` — the docker/podman/lxc cgroup-v1 markers.
+
+    cgroup v2 collapses ``/proc/1/cgroup`` to a single ``0::/`` line with no
+    runtime marker, so containerd/CRI-O runtimes (the common case on
+    Kubernetes/k3s) were previously missed. To cover those, also check:
+      * ``KUBERNETES_SERVICE_HOST`` env var — set in every Kubernetes pod.
+      * ``kubepods`` / ``containerd`` / ``crio`` markers in ``/proc/1/cgroup``.
+      * the same markers in ``/proc/self/mountinfo`` (cgroup-v2 fallback).
+
+    Result is cached for the process lifetime.  Import-safe — no heavy deps.
+
+    See: NousResearch/hermes-agent#47111
     """
     global _container_detected
     if _container_detected is not None:
@@ -476,10 +486,26 @@ def is_container() -> bool:
     if os.path.exists("/run/.containerenv"):
         _container_detected = True
         return True
+    # Kubernetes always injects this into pod containers; absent on hosts.
+    if os.environ.get("KUBERNETES_SERVICE_HOST"):
+        _container_detected = True
+        return True
+    _CGROUP_MARKERS = ("docker", "podman", "/lxc/", "kubepods", "containerd", "crio")
     try:
         with open("/proc/1/cgroup", "r", encoding="utf-8") as f:
             cgroup = f.read()
-            if "docker" in cgroup or "podman" in cgroup or "/lxc/" in cgroup:
+            if any(marker in cgroup for marker in _CGROUP_MARKERS):
+                _container_detected = True
+                return True
+    except OSError:
+        pass
+    # cgroup v2: /proc/1/cgroup is just "0::/" with no marker. The container
+    # runtime still shows up in the mount table (overlay rootfs, runtime mount
+    # paths), so scan mountinfo as a last resort.
+    try:
+        with open("/proc/self/mountinfo", "r", encoding="utf-8") as f:
+            mountinfo = f.read()
+            if any(marker in mountinfo for marker in ("kubepods", "containerd", "crio")):
                 _container_detected = True
                 return True
     except OSError:

hermes_state.py

@@ -722,7 +722,24 @@ class SessionDB:
                     isolation_level=None,
                 )
                 self._conn.row_factory = sqlite3.Row
-                apply_wal_with_fallback(self._conn, db_label="state.db")
+                journal_mode = apply_wal_with_fallback(self._conn, db_label="state.db")
+                # Durability hardening (NS-506). On memory/disk-constrained
+                # hosts (e.g. a small Fly machine that OOM-kills or SIGTERMs
+                # the process mid-write, or fills the disk with a large npm
+                # cache), an interrupted write can tear the DB. With WAL,
+                # ``synchronous=NORMAL`` fsyncs the WAL at each checkpoint and
+                # is crash-safe against OS crash / power loss / process kill
+                # (only the very last un-checkpointed transaction can be lost,
+                # never the database file itself) — the SQLite-recommended
+                # setting for WAL. On the DELETE fallback (NFS/SMB/FUSE) we use
+                # FULL, since without WAL only FULL is crash-safe. We also set
+                # an explicit ``busy_timeout`` so a checkpoint/contention spike
+                # doesn't surface as an immediate "database is locked".
+                if journal_mode == "wal":
+                    self._conn.execute("PRAGMA synchronous=NORMAL")
+                else:
+                    self._conn.execute("PRAGMA synchronous=FULL")
+                self._conn.execute("PRAGMA busy_timeout=2000")
                 self._conn.execute("PRAGMA foreign_keys=ON")
                 self._init_schema()
 
@@ -2379,6 +2396,7 @@ class SessionDB:
         codex_message_items: Any = None,
         platform_message_id: str = None,
         observed: bool = False,
+        timestamp: Any = None,
     ) -> int:
         """
         Append a message to a session. Returns the message row ID.
@@ -2410,6 +2428,16 @@ class SessionDB:
         # cannot bind list/dict parameters directly.
         stored_content = self._encode_content(content)
 
+        message_timestamp = time.time()
+        if timestamp is not None:
+            try:
+                if hasattr(timestamp, "timestamp"):
+                    message_timestamp = float(timestamp.timestamp())
+                else:
+                    message_timestamp = float(timestamp)
+            except (TypeError, ValueError):
+                logger.debug("Ignoring invalid explicit message timestamp: %r", timestamp)
+
         # Pre-compute tool call count
         num_tool_calls = 0
         if tool_calls is not None:
@@ -2429,7 +2457,7 @@ class SessionDB:
                     tool_call_id,
                     tool_calls_json,
                     tool_name,
-                    time.time(),
+                    message_timestamp,
                     token_count,
                     finish_reason,
                     reasoning,
@@ -2482,6 +2510,16 @@ class SessionDB:
             for msg in messages:
                 role = msg.get("role", "unknown")
                 tool_calls = msg.get("tool_calls")
+                message_timestamp = now_ts
+                if msg.get("timestamp") is not None:
+                    try:
+                        ts_value = msg.get("timestamp")
+                        if hasattr(ts_value, "timestamp"):
+                            message_timestamp = float(ts_value.timestamp())
+                        else:
+                            message_timestamp = float(ts_value)
+                    except (TypeError, ValueError):
+                        logger.debug("Ignoring invalid explicit message timestamp: %r", msg.get("timestamp"))
                 reasoning_details = msg.get("reasoning_details") if role == "assistant" else None
                 codex_reasoning_items = (
                     msg.get("codex_reasoning_items") if role == "assistant" else None
@@ -2519,7 +2557,7 @@ class SessionDB:
                         msg.get("tool_call_id"),
                         tool_calls_json,
                         msg.get("tool_name"),
-                        now_ts,
+                        message_timestamp,
                         msg.get("token_count"),
                         msg.get("finish_reason"),
                         msg.get("reasoning") if role == "assistant" else None,
@@ -2536,7 +2574,7 @@ class SessionDB:
                     total_tool_calls += (
                         len(tool_calls) if isinstance(tool_calls, list) else 1
                     )
-                now_ts += 1e-6
+                now_ts = max(now_ts + 1e-6, message_timestamp + 1e-6)
 
             conn.execute(
                 "UPDATE sessions SET message_count = ?, tool_call_count = ? WHERE id = ?",
@@ -2867,9 +2905,9 @@ class SessionDB:
             rows = self._conn.execute(
                 "SELECT role, content, tool_call_id, tool_calls, tool_name, "
                 "finish_reason, reasoning, reasoning_content, reasoning_details, "
-                "codex_reasoning_items, codex_message_items, platform_message_id, observed "
+                "codex_reasoning_items, codex_message_items, platform_message_id, observed, timestamp "
                 f"FROM messages WHERE session_id IN ({placeholders})"
-                f"{active_clause} ORDER BY id",
+                f"{active_clause} ORDER BY timestamp, id",
                 tuple(session_ids),
             ).fetchall()
 
@@ -2879,6 +2917,8 @@ class SessionDB:
             if row["role"] in {"user", "assistant"} and isinstance(content, str):
                 content = sanitize_context(content).strip()
             msg = {"role": row["role"], "content": content}
+            if row["timestamp"]:
+                msg["timestamp"] = row["timestamp"]
             if row["tool_call_id"]:
                 msg["tool_call_id"] = row["tool_call_id"]
             if row["tool_name"]:

run_agent.py

@@ -1472,16 +1472,21 @@ class AIAgent:
         that synthetic text leak into persisted transcripts or resumed session
         history. When an override is configured for the active turn, mutate the
         in-memory messages list in place so both persistence and returned
-        history stay clean.
+        history stay clean.  A paired timestamp override preserves the platform
+        event time as message metadata, rather than embedding it in content.
         """
         idx = getattr(self, "_persist_user_message_idx", None)
         override = getattr(self, "_persist_user_message_override", None)
-        if override is None or idx is None:
+        timestamp = getattr(self, "_persist_user_message_timestamp", None)
+        if idx is None or (override is None and timestamp is None):
             return
         if 0 <= idx < len(messages):
             msg = messages[idx]
             if isinstance(msg, dict) and msg.get("role") == "user":
-                msg["content"] = override
+                if override is not None:
+                    msg["content"] = override
+                if timestamp is not None:
+                    msg["timestamp"] = timestamp
 
     def _persist_session(self, messages: List[Dict], conversation_history: List[Dict] = None):
         """Save session state to both JSON log and SQLite on any exit path.
@@ -1639,6 +1644,7 @@ class AIAgent:
                     reasoning_details=msg.get("reasoning_details") if role == "assistant" else None,
                     codex_reasoning_items=msg.get("codex_reasoning_items") if role == "assistant" else None,
                     codex_message_items=msg.get("codex_message_items") if role == "assistant" else None,
+                    timestamp=msg.get("timestamp"),
                 )
                 flushed_ids.add(msg_id)
             self._last_flushed_db_idx = len(messages)
@@ -5218,10 +5224,20 @@ class AIAgent:
         task_id: str = None,
         stream_callback: Optional[callable] = None,
         persist_user_message: Optional[str] = None,
+        persist_user_timestamp: Optional[float] = None,
     ) -> Dict[str, Any]:
         """Forwarder — see ``agent.conversation_loop.run_conversation``."""
         from agent.conversation_loop import run_conversation
-        return run_conversation(self, user_message, system_message, conversation_history, task_id, stream_callback, persist_user_message)
+        return run_conversation(
+            self,
+            user_message,
+            system_message,
+            conversation_history,
+            task_id,
+            stream_callback,
+            persist_user_message,
+            persist_user_timestamp,
+        )
 
     def chat(self, message: str, stream_callback: Optional[callable] = None) -> str:
         """

tests/acp/test_session.py

@@ -211,7 +211,10 @@ class TestListAndCleanup:
 
         db = manager._get_db()
         messages = db.get_messages_as_conversation(state.session_id)
-        assert messages == [{"role": "user", "content": "original"}]
+        assert len(messages) == 1
+        assert messages[0]["role"] == "user"
+        assert messages[0]["content"] == "original"
+        assert isinstance(messages[0].get("timestamp"), (int, float))
 
     def test_cleanup_clears_all(self, manager):
         s1 = manager.create_session()
@@ -501,6 +504,8 @@ class TestPersistence:
 
         restored = manager.get_session(state.session_id)
         assert restored is not None
+        msg = restored.history[0]
+        assert isinstance(msg.pop("timestamp", None), (int, float))
         assert restored.history == [{
             "role": "assistant",
             "content": "hello",

tests/gateway/test_fast_command.py

@@ -23,12 +23,20 @@ class _CapturingAgent:
         type(self).last_init = dict(kwargs)
         self.tools = []
 
-    def run_conversation(self, user_message, conversation_history=None, task_id=None, persist_user_message=None):
+    def run_conversation(
+        self,
+        user_message,
+        conversation_history=None,
+        task_id=None,
+        persist_user_message=None,
+        persist_user_timestamp=None,
+    ):
         type(self).last_run = {
             "user_message": user_message,
             "conversation_history": conversation_history,
             "task_id": task_id,
             "persist_user_message": persist_user_message,
+            "persist_user_timestamp": persist_user_timestamp,
         }
         return {
             "final_response": "ok",

tests/gateway/test_message_timestamps.py

@@ -0,0 +1,137 @@
+from datetime import datetime
+from zoneinfo import ZoneInfo
+
+from gateway.message_timestamps import (
+    coerce_message_timestamp,
+    render_user_content_with_timestamp,
+    strip_leading_message_timestamps,
+)
+from run_agent import AIAgent
+
+
+BERLIN = ZoneInfo("Europe/Berlin")
+
+
+def _epoch(year, month, day, hour, minute, second):
+    return datetime(year, month, day, hour, minute, second, tzinfo=BERLIN).timestamp()
+
+
+def test_render_user_content_adds_single_context_timestamp():
+    ts = _epoch(2026, 4, 28, 13, 40, 53)
+
+    rendered = render_user_content_with_timestamp(
+        "[Example User] Timestamp should be in context",
+        ts,
+        tz=BERLIN,
+    )
+
+    assert rendered == (
+        "[Tue 2026-04-28 13:40:53 CEST] "
+        "[Example User] Timestamp should be in context"
+    )
+
+
+def test_render_user_content_deduplicates_existing_timestamp_and_preserves_embedded_time():
+    db_processing_ts = _epoch(2026, 4, 27, 15, 55, 36)
+    stored_content = (
+        "[Mon 2026-04-27 15:54:44 CEST] "
+        "[Example User] This should go on our todo list"
+    )
+
+    rendered = render_user_content_with_timestamp(
+        stored_content,
+        db_processing_ts,
+        tz=BERLIN,
+    )
+
+    assert rendered == stored_content
+    assert rendered.count("2026-04-27") == 1
+
+
+def test_strip_leading_message_timestamps_removes_multiple_prefixes_and_prefers_inner_time():
+    content = (
+        "[Mon 2026-04-27 15:55:36 CEST] "
+        "[Mon 2026-04-27 15:54:44 CEST] "
+        "[Example User] This should go on our todo list"
+    )
+
+    stripped, embedded_ts = strip_leading_message_timestamps(content, tz=BERLIN)
+
+    assert stripped == "[Example User] This should go on our todo list"
+    assert embedded_ts == _epoch(2026, 4, 27, 15, 54, 44)
+
+
+def test_coerce_message_timestamp_accepts_datetime_and_epoch():
+    dt = datetime(2026, 4, 28, 13, 40, 53, tzinfo=BERLIN)
+
+    assert coerce_message_timestamp(dt, tz=BERLIN) == dt.timestamp()
+    assert coerce_message_timestamp(dt.timestamp(), tz=BERLIN) == dt.timestamp()
+
+
+def test_persist_user_message_override_keeps_clean_content_and_timestamp_metadata():
+    agent = AIAgent.__new__(AIAgent)
+    agent._persist_user_message_idx = 0
+    agent._persist_user_message_override = "[Example User] Clean content"
+    agent._persist_user_message_timestamp = _epoch(2026, 4, 28, 13, 40, 53)
+    messages = [
+        {
+            "role": "user",
+            "content": "[Tue 2026-04-28 13:40:53 CEST] [Example User] Clean content",
+        }
+    ]
+
+    agent._apply_persist_user_message_override(messages)
+
+    assert messages == [
+        {
+            "role": "user",
+            "content": "[Example User] Clean content",
+            "timestamp": _epoch(2026, 4, 28, 13, 40, 53),
+        }
+    ]
+
+
+# ---------------------------------------------------------------------------
+# Opt-in gate: gateway.message_timestamps.enabled (default OFF)
+# ---------------------------------------------------------------------------
+
+
+def test_message_timestamps_enabled_defaults_off():
+    from gateway.run import _message_timestamps_enabled
+
+    assert _message_timestamps_enabled(None) is False
+    assert _message_timestamps_enabled({}) is False
+    assert _message_timestamps_enabled({"gateway": {}}) is False
+    assert (
+        _message_timestamps_enabled({"gateway": {"message_timestamps": {}}}) is False
+    )
+
+
+def test_message_timestamps_enabled_when_opted_in():
+    from gateway.run import _message_timestamps_enabled
+
+    assert _message_timestamps_enabled(
+        {"gateway": {"message_timestamps": {"enabled": True}}}
+    ) is True
+    # Bare shorthand also accepted.
+    assert _message_timestamps_enabled({"gateway": {"message_timestamps": True}}) is True
+
+
+def test_build_history_injects_only_when_enabled():
+    from gateway.run import _build_gateway_agent_history
+
+    history = [
+        {"role": "user", "content": "hello", "timestamp": _epoch(2026, 4, 28, 13, 40, 53)},
+        {"role": "assistant", "content": "hi"},
+    ]
+
+    # Default (off): user content stays clean, no timestamp prefix.
+    agent_history, _ = _build_gateway_agent_history(history)
+    assert agent_history[0]["content"] == "hello"
+
+    # Enabled: user content gets exactly one timestamp prefix.
+    agent_history, _ = _build_gateway_agent_history(history, inject_timestamps=True)
+    assert agent_history[0]["content"].startswith("[")
+    assert agent_history[0]["content"].endswith("hello")
+    # Assistant message is never timestamped.
+    assert agent_history[1]["content"] == "hi"

tests/gateway/test_session_api.py

@@ -241,7 +241,11 @@ async def test_session_chat_loads_history_and_preserves_session_headers(auth_ada
     assert kwargs["session_id"] == session_id
     assert kwargs["gateway_session_key"] == "client-42"
     assert kwargs["ephemeral_system_prompt"] == "stay focused"
-    assert kwargs["conversation_history"] == [
+    history = kwargs["conversation_history"]
+    assert len(history) == 2
+    assert isinstance(history[0].pop("timestamp"), (int, float))
+    assert isinstance(history[1].pop("timestamp"), (int, float))
+    assert history == [
         {"role": "user", "content": "earlier"},
         {"role": "assistant", "content": "prior answer"},
     ]

tests/hermes_state/test_session_db_durability.py

@@ -0,0 +1,58 @@
+"""NS-506: session DB durability pragmas.
+
+On memory/disk-constrained hosts an interrupted write (OOM kill, SIGTERM
+mid-write, full disk) can tear the SQLite session DB. These tests pin the
+durability settings the connection must apply so a regression that drops
+them is caught.
+"""
+
+import sqlite3
+
+import pytest
+
+from hermes_state import SessionDB
+
+
+@pytest.fixture
+def db(tmp_path):
+    database = SessionDB(tmp_path / "state.db")
+    try:
+        yield database
+    finally:
+        database.close()
+
+
+def _pragma(conn: sqlite3.Connection, name: str):
+    return conn.execute(f"PRAGMA {name}").fetchone()[0]
+
+
+def test_wal_mode_uses_synchronous_normal(db):
+    """On a normal local filesystem the DB runs WAL + synchronous=NORMAL.
+
+    NORMAL is the SQLite-recommended WAL setting: crash-safe against OS
+    crash / power loss / process kill (the DB file is never corrupted, only
+    the last un-checkpointed txn can be lost), without the per-write fsync
+    cost of FULL.
+    """
+    conn = db._conn
+    assert _pragma(conn, "journal_mode").lower() == "wal"
+    # 0=OFF, 1=NORMAL, 2=FULL, 3=EXTRA
+    assert _pragma(conn, "synchronous") == 1
+
+
+def test_busy_timeout_is_set(db):
+    """An explicit busy_timeout keeps a checkpoint/contention spike from
+    surfacing as an immediate 'database is locked'."""
+    assert _pragma(db._conn, "busy_timeout") == 2000
+
+
+def test_synchronous_is_never_off(db):
+    """The corruption-prone setting (synchronous=OFF) must never be in
+    effect for the session store, regardless of journal mode."""
+    assert _pragma(db._conn, "synchronous") >= 1
+
+
+def test_foreign_keys_still_enabled(db):
+    """Regression guard: the durability pragmas must not displace the
+    existing foreign_keys=ON."""
+    assert _pragma(db._conn, "foreign_keys") == 1

tests/test_hermes_constants.py

@@ -139,12 +139,66 @@ class TestIsContainer:
         """Returns False on a regular Linux host."""
         import builtins
         self._reset_cache(monkeypatch)
+        monkeypatch.delenv("KUBERNETES_SERVICE_HOST", raising=False)
         monkeypatch.setattr(os.path, "exists", lambda p: False)
         cgroup_file = tmp_path / "cgroup"
         cgroup_file.write_text("12:memory:/\n")
+        mountinfo_file = tmp_path / "mountinfo"
+        mountinfo_file.write_text("22 21 0:20 / /sys rw shared:7 - sysfs sysfs rw\n")
+        _real_open = builtins.open
+
+        def _fake_open(p, *a, **kw):
+            if p == "/proc/1/cgroup":
+                return _real_open(str(cgroup_file), *a, **kw)
+            if p == "/proc/self/mountinfo":
+                return _real_open(str(mountinfo_file), *a, **kw)
+            return _real_open(p, *a, **kw)
+
+        monkeypatch.setattr("builtins.open", _fake_open)
+        assert is_container() is False
+
+    def test_detects_kubernetes_env(self, monkeypatch):
+        """KUBERNETES_SERVICE_HOST env var triggers detection (k8s/k3s pod)."""
+        self._reset_cache(monkeypatch)
+        monkeypatch.setattr(os.path, "exists", lambda p: False)
+        monkeypatch.setenv("KUBERNETES_SERVICE_HOST", "10.43.0.1")
+        assert is_container() is True
+
+    def test_detects_cgroup_kubepods(self, monkeypatch, tmp_path):
+        """/proc/1/cgroup containing 'kubepods' triggers detection."""
+        import builtins
+        self._reset_cache(monkeypatch)
+        monkeypatch.delenv("KUBERNETES_SERVICE_HOST", raising=False)
+        monkeypatch.setattr(os.path, "exists", lambda p: False)
+        cgroup_file = tmp_path / "cgroup"
+        cgroup_file.write_text("12:memory:/kubepods/besteffort/podabc\n")
         _real_open = builtins.open
         monkeypatch.setattr("builtins.open", lambda p, *a, **kw: _real_open(str(cgroup_file), *a, **kw) if p == "/proc/1/cgroup" else _real_open(p, *a, **kw))
-        assert is_container() is False
+        assert is_container() is True
+
+    def test_detects_cgroup_v2_via_mountinfo(self, monkeypatch, tmp_path):
+        """cgroup v2 (0::/ only) falls back to containerd marker in mountinfo."""
+        import builtins
+        self._reset_cache(monkeypatch)
+        monkeypatch.delenv("KUBERNETES_SERVICE_HOST", raising=False)
+        monkeypatch.setattr(os.path, "exists", lambda p: False)
+        cgroup_file = tmp_path / "cgroup"
+        cgroup_file.write_text("0::/\n")  # cgroup v2 — no runtime marker
+        mountinfo_file = tmp_path / "mountinfo"
+        mountinfo_file.write_text(
+            "1234 1233 0:42 /containerd/.../rootfs / rw - overlay overlay rw\n"
+        )
+        _real_open = builtins.open
+
+        def _fake_open(p, *a, **kw):
+            if p == "/proc/1/cgroup":
+                return _real_open(str(cgroup_file), *a, **kw)
+            if p == "/proc/self/mountinfo":
+                return _real_open(str(mountinfo_file), *a, **kw)
+            return _real_open(p, *a, **kw)
+
+        monkeypatch.setattr("builtins.open", _fake_open)
+        assert is_container() is True
 
     def test_caches_result(self, monkeypatch):
         """Second call uses cached value without re-probing."""

tests/test_hermes_state.py

@@ -347,6 +347,15 @@ class TestMessageStorage:
         assert messages[0]["content"] == "Hello"
         assert messages[1]["role"] == "assistant"
 
+    def test_append_message_accepts_explicit_timestamp(self, db):
+        db.create_session(session_id="s1", source="telegram")
+        event_ts = 1777383653.0
+
+        db.append_message("s1", role="user", content="Hello", timestamp=event_ts)
+
+        messages = db.get_messages_as_conversation("s1")
+        assert messages[0]["timestamp"] == event_ts
+
     def test_message_increments_session_count(self, db):
         db.create_session(session_id="s1", source="cli")
         db.append_message("s1", role="user", content="Hello")
@@ -370,11 +379,10 @@ class TestMessageStorage:
         assert messages[1]["observed"] == 0
 
         conversation = db.get_messages_as_conversation("s1")
-        assert conversation[0] == {
-            "role": "user",
-            "content": "[Alice|111]\nside chatter",
-            "observed": True,
-        }
+        assert conversation[0]["role"] == "user"
+        assert conversation[0]["content"] == "[Alice|111]\nside chatter"
+        assert conversation[0]["observed"] is True
+        assert isinstance(conversation[0].get("timestamp"), float)
         assert "observed" not in conversation[1]
 
     def test_tool_response_does_not_increment_tool_count(self, db):
@@ -458,7 +466,9 @@ class TestMessageStorage:
         # get_messages_as_conversation decodes back to the original list
         conv = db.get_messages_as_conversation("s1")
         assert len(conv) == 1
-        assert conv[0] == {"role": "user", "content": content}
+        assert conv[0]["role"] == "user"
+        assert conv[0]["content"] == content
+        assert isinstance(conv[0].get("timestamp"), float)
 
     def test_dict_content_round_trip(self, db):
         """Dict-shaped content (e.g. provider wrappers) also round-trips."""
@@ -529,8 +539,12 @@ class TestMessageStorage:
 
         conv = db.get_messages_as_conversation("s1")
         assert len(conv) == 2
-        assert conv[0] == {"role": "user", "content": "Hello"}
-        assert conv[1] == {"role": "assistant", "content": "Hi!"}
+        assert conv[0]["role"] == "user"
+        assert conv[0]["content"] == "Hello"
+        assert isinstance(conv[0]["timestamp"], float)
+        assert conv[1]["role"] == "assistant"
+        assert conv[1]["content"] == "Hi!"
+        assert isinstance(conv[1]["timestamp"], float)
 
     def test_platform_message_id_round_trips(self, db):
         """Platform-side message ids (yuanbao msg_id, telegram update_id, …)
@@ -620,7 +634,10 @@ class TestMessageStorage:
         )
 
         conv = db.get_messages_as_conversation("s1")
-        assert conv == [{"role": "assistant", "content": "Visible answer"}]
+        assert len(conv) == 1
+        assert conv[0]["role"] == "assistant"
+        assert conv[0]["content"] == "Visible answer"
+        assert isinstance(conv[0].get("timestamp"), float)
 
     def test_reasoning_persisted_and_restored(self, db):
         """Reasoning text is stored for assistant messages and restored by

website/docs/user-guide/messaging/index.md

@@ -327,6 +327,24 @@ display:
   tool_progress_grouping: accumulate   # accumulate | separate
 ```
 
+### Message timestamps in model context
+
+Off by default. When enabled, Hermes prepends a human-readable timestamp
+(e.g. `[Tue 2026-04-28 13:40:53 CEST]`) onto each **user** message *in the
+model's context* so the agent knows when messages were sent — useful for
+temporal reasoning ("you asked this morning…", noticing a long gap). It is
+**not** added to assistant messages or the system prompt.
+
+```yaml
+gateway:
+  message_timestamps:
+    enabled: false   # set true to show send-times to the model
+```
+
+Persisted transcripts always stay clean — the timestamp is stored as message
+metadata regardless of this toggle, so enabling it later also surfaces
+send-times for past messages, and replay never accumulates duplicate prefixes.
+
 When enabled, the bot sends status messages as it works:
 
 ```text