Merge remote-tracking branch 'origin/main' into feat/opentui-native-engine

agent/auxiliary_client.py

@@ -3079,23 +3079,20 @@ def _try_configured_fallback_chain(
         if not fb_provider or fb_provider.lower() == skip:
             continue
         fb_model = str(entry.get("model", "")).strip() or None
-        fb_base_url = str(entry.get("base_url", "")).strip() or None
-        fb_api_key = str(entry.get("api_key", "")).strip() or None
 
         label = f"fallback_chain[{i}]({fb_provider})"
 
         try:
-            fb_client = _resolve_single_provider(
-                fb_provider, fb_model, fb_base_url, fb_api_key)
+            fb_client, resolved_model = _resolve_fallback_entry(entry)
         except Exception:
-            fb_client = None
+            fb_client, resolved_model = None, None
 
         if fb_client is not None:
             logger.info(
                 "Auxiliary %s: %s on %s — configured fallback to %s (%s)",
-                task, reason, failed_provider, label, fb_model or "default",
+                task, reason, failed_provider, label, resolved_model or fb_model or "default",
             )
-            return fb_client, fb_model, label
+            return fb_client, resolved_model or fb_model, label
         tried.append(label)
 
     if tried:
@@ -3106,6 +3103,103 @@ def _try_configured_fallback_chain(
     return None, None, ""
 
 
+def _fallback_entry_api_key(entry: Dict[str, Any]) -> Optional[str]:
+    """Resolve inline or env-backed API key from a fallback-chain entry."""
+    explicit = str(entry.get("api_key") or "").strip()
+    if explicit:
+        return explicit
+    key_env = str(entry.get("key_env") or entry.get("api_key_env") or "").strip()
+    if key_env:
+        return os.getenv(key_env, "").strip() or None
+    return None
+
+
+def _resolve_fallback_entry(entry: Dict[str, Any]) -> Tuple[Optional[Any], Optional[str]]:
+    """Resolve one fallback entry through the central provider router."""
+    provider = str(entry.get("provider") or "").strip()
+    model = str(entry.get("model") or "").strip() or None
+    if not provider or not model:
+        return None, None
+    base_url = str(entry.get("base_url") or "").strip() or None
+    api_key = _fallback_entry_api_key(entry)
+    api_mode = str(entry.get("api_mode") or entry.get("transport") or "").strip() or None
+    return resolve_provider_client(
+        provider,
+        model=model,
+        explicit_base_url=base_url,
+        explicit_api_key=api_key,
+        api_mode=api_mode,
+    )
+
+
+def _try_main_fallback_chain(
+    task: Optional[str],
+    failed_provider: str = "",
+    reason: str = "error",
+) -> Tuple[Optional[Any], Optional[str], str]:
+    """Try the top-level main-agent fallback chain for an auxiliary call.
+
+    ``provider: auto`` auxiliary tasks should respect the user's declared
+    main fallback policy before dropping into Hermes' built-in discovery
+    chain. The top-level chain is read through ``get_fallback_chain`` so
+    both modern ``fallback_providers`` and legacy ``fallback_model`` entries
+    participate in the same order as the main agent.
+    """
+    try:
+        from hermes_cli.config import load_config
+        from hermes_cli.fallback_config import get_fallback_chain
+
+        chain = get_fallback_chain(load_config())
+    except Exception as exc:
+        logger.debug("Auxiliary %s: could not load main fallback chain: %s", task or "call", exc)
+        return None, None, ""
+
+    if not chain:
+        return None, None, ""
+
+    failed_norm = (failed_provider or "").strip().lower()
+    main_norm = (_read_main_provider() or "").strip().lower()
+    skip = {p for p in (failed_norm, main_norm, "auto") if p}
+    tried: List[str] = []
+
+    for i, entry in enumerate(chain):
+        if not isinstance(entry, dict):
+            continue
+        fb_provider = str(entry.get("provider") or "").strip()
+        fb_model = str(entry.get("model") or "").strip()
+        if not fb_provider or not fb_model:
+            continue
+        fb_norm = fb_provider.lower()
+        label = f"fallback_providers[{i}]({fb_provider})"
+        if fb_norm in skip:
+            tried.append(f"{label} (skipped)")
+            continue
+        if _is_provider_unhealthy(fb_norm):
+            _log_skip_unhealthy(fb_norm, task)
+            tried.append(f"{label} (unhealthy)")
+            continue
+        try:
+            fb_client, resolved_model = _resolve_fallback_entry(entry)
+        except Exception as exc:
+            logger.debug("Auxiliary %s: main fallback %s failed to resolve: %s", task or "call", label, exc)
+            fb_client, resolved_model = None, None
+        if fb_client is not None:
+            logger.info(
+                "Auxiliary %s: %s on %s — main fallback chain to %s (%s)",
+                task or "call", reason, failed_provider or "auto", label,
+                resolved_model or fb_model,
+            )
+            return fb_client, resolved_model or fb_model, fb_provider
+        tried.append(label)
+
+    if tried:
+        logger.debug(
+            "Auxiliary %s: main fallback chain exhausted (tried: %s)",
+            task or "call", ", ".join(tried),
+        )
+    return None, None, ""
+
+
 def _resolve_single_provider(
     provider: str,
     model: Optional[str] = None,
@@ -3116,16 +3210,19 @@ def _resolve_single_provider(
 
     Uses the existing provider resolution infrastructure where possible.
     """
-    # Reuse resolve_provider_client which handles provider→client mapping
+    # Reuse resolve_provider_client which handles provider→client mapping.
     client, resolved_model = resolve_provider_client(
         provider=provider,
         model=model,
-        base_url=base_url,
-        api_key=api_key,
+        explicit_base_url=base_url,
+        explicit_api_key=api_key,
     )
     return client
 
-def _resolve_auto(main_runtime: Optional[Dict[str, Any]] = None) -> Tuple[Optional[OpenAI], Optional[str]]:
+def _resolve_auto(
+    main_runtime: Optional[Dict[str, Any]] = None,
+    task: Optional[str] = None,
+) -> Tuple[Optional[OpenAI], Optional[str]]:
     """Full auto-detection chain.
 
     Priority:
@@ -3223,7 +3320,22 @@ def _resolve_auto(main_runtime: Optional[Dict[str, Any]] = None) -> Tuple[Option
                             main_provider, resolved or main_model)
                 return client, resolved or main_model
 
-    # ── Step 2: aggregator / fallback chain ──────────────────────────────
+    # ── Step 2: user-configured fallback policy ─────────────────────────
+    # In auto mode, respect the task-specific fallback chain first, then the
+    # main agent's top-level fallback_providers/fallback_model chain. The
+    # hardcoded provider discovery chain below is only the convenience default
+    # for users who have not declared a fallback policy.
+    if task:
+        fb_client, fb_model, _fb_label = _try_configured_fallback_chain(
+            task, main_provider or "auto", reason="main provider unavailable")
+        if fb_client is not None:
+            return fb_client, fb_model
+    fb_client, fb_model, _fb_label = _try_main_fallback_chain(
+        task, main_provider or "auto", reason="main provider unavailable")
+    if fb_client is not None:
+        return fb_client, fb_model
+
+    # ── Step 3: aggregator / fallback chain ──────────────────────────────
     tried = []
     for label, try_fn in _get_provider_chain():
         if _is_provider_unhealthy(label):
@@ -3344,6 +3456,7 @@ def resolve_provider_client(
     api_mode: str = None,
     main_runtime: Optional[Dict[str, Any]] = None,
     is_vision: bool = False,
+    task: Optional[str] = None,
 ) -> Tuple[Optional[Any], Optional[str]]:
     """Central router: given a provider name and optional model, return a
     configured client with the correct auth, base URL, and API format.
@@ -3464,7 +3577,7 @@ def resolve_provider_client(
 
     # ── Auto: try all providers in priority order ────────────────────
     if provider == "auto":
-        client, resolved = _resolve_auto(main_runtime=main_runtime)
+        client, resolved = _resolve_auto(main_runtime=main_runtime, task=task)
         if client is None:
             return None, None
         # When auto-detection lands on a non-OpenRouter provider (e.g. a
@@ -4357,11 +4470,16 @@ def _client_cache_key(
     api_mode: Optional[str] = None,
     main_runtime: Optional[Dict[str, Any]] = None,
     is_vision: bool = False,
+    task: Optional[str] = None,
 ) -> tuple:
     runtime = _normalize_main_runtime(main_runtime)
     runtime_key = tuple(runtime.get(field, "") for field in _MAIN_RUNTIME_FIELDS) if provider == "auto" else ()
+    # `auto` can now resolve through task-specific or main fallback policy,
+    # so the task participates in the cache key. Non-auto providers keep the
+    # old cache shape because the explicit provider/model tuple is sufficient.
+    task_key = (task or "") if provider == "auto" else ""
     pool_hint = _pool_cache_hint(provider, main_runtime=main_runtime)
-    return (provider, async_mode, base_url or "", api_key or "", api_mode or "", runtime_key, is_vision, pool_hint)
+    return (provider, async_mode, base_url or "", api_key or "", api_mode or "", runtime_key, is_vision, task_key, pool_hint)
 
 
 def _store_cached_client(cache_key: tuple, client: Any, default_model: Optional[str], *, bound_loop: Any = None) -> None:
@@ -4554,6 +4672,7 @@ def _get_cached_client(
     api_mode: str = None,
     main_runtime: Optional[Dict[str, Any]] = None,
     is_vision: bool = False,
+    task: Optional[str] = None,
 ) -> Tuple[Optional[Any], Optional[str]]:
     """Get or create a cached client for the given provider.
 
@@ -4591,6 +4710,7 @@ def _get_cached_client(
         api_mode=api_mode,
         main_runtime=main_runtime,
         is_vision=is_vision,
+        task=task,
     )
     with _client_cache_lock:
         if cache_key in _client_cache:
@@ -4635,6 +4755,7 @@ def _get_cached_client(
         api_mode=api_mode,
         main_runtime=runtime,
         is_vision=is_vision,
+        task=task,
     )
     if client is not None:
         # For async clients, remember which loop they were created on so we
@@ -5140,7 +5261,7 @@ def call_llm(
             if not resolved_base_url:
                 logger.info("Auxiliary %s: provider %s unavailable, trying auto-detection chain",
                             task or "call", resolved_provider)
-                client, final_model = _get_cached_client("auto", main_runtime=main_runtime)
+                client, final_model = _get_cached_client("auto", main_runtime=main_runtime, task=task)
         if client is None:
             raise RuntimeError(
                 f"No LLM provider configured for task={task} provider={resolved_provider}. "
@@ -5466,14 +5587,19 @@ def call_llm(
 
             # Fallback order (#26882, #26803):
             #   1. User-configured fallback_chain (per-task) if set
-            #   2. Main agent model (last-resort safety net)
-            # For auto users (no explicit aux provider), use the full
-            # auto-detection chain instead — its Step 1 IS the main agent
-            # model, so users on `auto` already get main-model fallback.
+            #   2. For auto: top-level main fallback_providers/fallback_model
+            #   3. For auto: built-in auxiliary discovery chain
+            #   4. For explicit aux providers: main agent model safety net
             fb_client, fb_model, fb_label = (None, None, "")
             if is_auto:
-                fb_client, fb_model, fb_label = _try_payment_fallback(
-                    resolved_provider, task, reason=reason)
+                fb_client, fb_model, fb_label = _try_configured_fallback_chain(
+                    task, resolved_provider or "auto", reason=reason)
+                if fb_client is None:
+                    fb_client, fb_model, fb_label = _try_main_fallback_chain(
+                        task, resolved_provider or "auto", reason=reason)
+                if fb_client is None:
+                    fb_client, fb_model, fb_label = _try_payment_fallback(
+                        resolved_provider, task, reason=reason)
             else:
                 fb_client, fb_model, fb_label = _try_configured_fallback_chain(
                     task, resolved_provider or "auto", reason=reason)
@@ -5636,7 +5762,7 @@ async def async_call_llm(
             if not resolved_base_url:
                 logger.info("Auxiliary %s: provider %s unavailable, trying auto-detection chain",
                             task or "call", resolved_provider)
-                client, final_model = _get_cached_client("auto", async_mode=True)
+                client, final_model = _get_cached_client("auto", async_mode=True, main_runtime=main_runtime, task=task)
         if client is None:
             raise RuntimeError(
                 f"No LLM provider configured for task={task} provider={resolved_provider}. "
@@ -5904,13 +6030,19 @@ async def async_call_llm(
 
             # Fallback order (#26882, #26803):
             #   1. User-configured fallback_chain (per-task) if set
-            #   2. Main agent model (last-resort safety net)
-            # Auto users get the full auto-detection chain instead — its
-            # Step 1 IS the main agent model.
+            #   2. For auto: top-level main fallback_providers/fallback_model
+            #   3. For auto: built-in auxiliary discovery chain
+            #   4. For explicit aux providers: main agent model safety net
             fb_client, fb_model, fb_label = (None, None, "")
             if is_auto:
-                fb_client, fb_model, fb_label = _try_payment_fallback(
-                    resolved_provider, task, reason=reason)
+                fb_client, fb_model, fb_label = _try_configured_fallback_chain(
+                    task, resolved_provider or "auto", reason=reason)
+                if fb_client is None:
+                    fb_client, fb_model, fb_label = _try_main_fallback_chain(
+                        task, resolved_provider or "auto", reason=reason)
+                if fb_client is None:
+                    fb_client, fb_model, fb_label = _try_payment_fallback(
+                        resolved_provider, task, reason=reason)
             else:
                 fb_client, fb_model, fb_label = _try_configured_fallback_chain(
                     task, resolved_provider or "auto", reason=reason)

apps/desktop/src/app/session/hooks/use-prompt-actions.ts

@@ -58,6 +58,7 @@ import { clearSessionTodos } from '@/store/todos'
 
 import type {
   ClientSessionState,
+  BrowserManageResponse,
   FileAttachResponse,
   HandoffFailResponse,
   HandoffRequestResponse,
@@ -1141,6 +1142,81 @@ export function usePromptActions({
           } catch (err) {
             renderSlashOutput(`error: ${err instanceof Error ? err.message : String(err)}`)
           }
+        },
+        // /browser connect|disconnect|status manages the live CDP connection on
+        // the gateway host, mirroring the TUI's browser.manage RPC. It mutates
+        // BROWSER_CDP_URL (and may launch Chrome) in the gateway process — only
+        // meaningful when that process runs on this machine, so it's gated to
+        // local connections. A remote gateway would act on the wrong host.
+        browser: async ctx => {
+          const resolved = await withSlashOutput(ctx)
+
+          if (!resolved) {
+            return
+          }
+
+          const { render: renderSlashOutput, sessionId } = resolved
+
+          if ($connection.get()?.mode === 'remote') {
+            renderSlashOutput(
+              '/browser manages a Chromium-family browser on the gateway host — only available when connected to a local gateway.'
+            )
+
+            return
+          }
+
+          const [rawAction = 'status', ...rest] = ctx.arg.trim().split(/\s+/).filter(Boolean)
+          const cmdAction = rawAction.toLowerCase()
+
+          if (!['connect', 'disconnect', 'status'].includes(cmdAction)) {
+            renderSlashOutput(
+              'usage: /browser [connect|disconnect|status] [url] · persistent: set browser.cdp_url in config.yaml'
+            )
+
+            return
+          }
+
+          const url = cmdAction === 'connect' ? rest.join(' ').trim() || 'http://127.0.0.1:9222' : undefined
+
+          if (url) {
+            renderSlashOutput(`checking Chromium-family browser remote debugging at ${url}...`)
+          }
+
+          try {
+            const result = await requestGateway<BrowserManageResponse>('browser.manage', {
+              action: cmdAction,
+              session_id: sessionId,
+              ...(url && { url })
+            })
+
+            // Without a streamed session subscription, the gateway bundles its
+            // progress lines into `messages` — flush them inline.
+            result?.messages?.forEach(message => renderSlashOutput(message))
+
+            if (cmdAction === 'status') {
+              renderSlashOutput(
+                result?.connected
+                  ? `browser connected: ${result.url || '(url unavailable)'}`
+                  : 'browser not connected (try /browser connect <url> or set browser.cdp_url in config.yaml)'
+              )
+
+              return
+            }
+
+            if (cmdAction === 'disconnect') {
+              renderSlashOutput('browser disconnected')
+
+              return
+            }
+
+            if (result?.connected) {
+              renderSlashOutput('Browser connected to live Chromium-family browser via CDP')
+              renderSlashOutput(`Endpoint: ${result.url || '(url unavailable)'}`)
+              renderSlashOutput('next browser tool call will use this CDP endpoint')
+            }
+          } catch (err) {
+            renderSlashOutput(`error: ${err instanceof Error ? err.message : String(err)}`)
+          }
         }
       }
 

apps/desktop/src/app/types.ts

@@ -46,6 +46,12 @@ export interface SlashExecResponse {
   warning?: string
 }
 
+export interface BrowserManageResponse {
+  connected?: boolean
+  url?: string
+  messages?: string[]
+}
+
 export interface SessionSteerResponse {
   // 'queued' == accepted into the live turn's steer slot (injected at the next
   // tool-result boundary); 'rejected' == no live tool window, caller queues.

apps/desktop/src/lib/desktop-slash-commands.test.ts

@@ -52,6 +52,17 @@ describe('desktop slash command curation', () => {
     expect(desktopSlashUnavailableMessage('/personality')).toBeNull()
   })
 
+  it('treats /browser as an executable action command (local-gateway connect)', () => {
+    // /browser used to be terminal-only; it now resolves to a desktop action
+    // handler that routes browser.manage RPC when the gateway is local.
+    expect(isDesktopSlashCommand('/browser')).toBe(true)
+    expect(isDesktopSlashSuggestion('/browser')).toBe(true)
+    expect(desktopSlashUnavailableMessage('/browser')).toBeNull()
+    expect(resolveDesktopCommand('/browser')?.surface).toEqual({ kind: 'action', action: 'browser' })
+    // Bare /browser expands to its sub-action options in the popover.
+    expect(resolveDesktopCommand('/browser')?.args).toBe(true)
+  })
+
   it('allows aliases to execute without cluttering the popover', () => {
     expect(isDesktopSlashSuggestion('/reset')).toBe(false)
     expect(isDesktopSlashCommand('/reset')).toBe(true)

apps/desktop/src/lib/desktop-slash-commands.ts

@@ -30,6 +30,7 @@ export interface DesktopThemeCommandOption {
  */
 export type DesktopActionId =
   | 'branch'
+  | 'browser'
   | 'handoff'
   | 'help'
   | 'new'
@@ -103,6 +104,12 @@ const DESKTOP_COMMAND_SPECS: readonly DesktopCommandSpec[] = [
   { name: '/skin', description: 'Switch desktop theme or cycle to the next one', surface: action('skin'), args: true },
   { name: '/title', description: 'Rename the current session', surface: action('title') },
   { name: '/help', description: 'Show desktop slash commands', aliases: ['/commands'], surface: action('help') },
+  {
+    name: '/browser',
+    description: 'Manage browser CDP connection [connect|disconnect|status] (local gateway only)',
+    surface: action('browser'),
+    args: true
+  },
 
   // Overlay pickers
   { name: '/model', description: 'Switch the model for this session', surface: picker('model'), hidden: true },
@@ -142,7 +149,7 @@ const DESKTOP_COMMAND_SPECS: readonly DesktopCommandSpec[] = [
 // per reason beats 40 identical object literals.
 const NO_DESKTOP_SURFACE: Record<DesktopUnavailableReason, readonly string[]> = {
   terminal: [
-    '/browser', '/busy', '/clear', '/compact', '/config', '/copy', '/cron', '/details',
+    '/busy', '/clear', '/compact', '/config', '/copy', '/cron', '/details',
     '/exit', '/footer', '/gateway', '/gquota', '/history', '/image', '/indicator', '/logs',
     '/mouse', '/paste', '/platforms', '/plugins', '/quit', '/redraw', '/reload', '/restart',
     '/sb', '/set-home', '/sethome', '/snap', '/snapshot', '/statusbar', '/toolsets', '/update', '/verbose'

gateway/platforms/base.py

@@ -77,6 +77,13 @@ def _thread_metadata_for_source(source, reply_to_message_id: str | None = None)
     return metadata
 
 
+def _mark_notify_metadata(metadata: dict | None) -> dict:
+    """Clone metadata and mark a user-visible reply as notify-worthy."""
+    notify_metadata = dict(metadata) if metadata else {}
+    notify_metadata["notify"] = True
+    return notify_metadata
+
+
 def _reply_anchor_for_event(event) -> str | None:
     """Return reply_to id for platforms that need reply semantics.
 
@@ -3889,7 +3896,7 @@ class BasePlatformAdapter(ABC):
                     chat_id=event.source.chat_id,
                     content=_text,
                     reply_to=_reply_anchor_for_event(event),
-                    metadata=thread_meta,
+                    metadata=_mark_notify_metadata(thread_meta),
                 )
                 if _eph_ttl > 0 and _r.success and _r.message_id:
                     self._schedule_ephemeral_delete(
@@ -3995,7 +4002,7 @@ class BasePlatformAdapter(ABC):
                             chat_id=event.source.chat_id,
                             content=_text,
                             reply_to=_reply_anchor_for_event(event),
-                            metadata=_thread_meta,
+                            metadata=_mark_notify_metadata(_thread_meta),
                         )
                         if _eph_ttl > 0 and _r.success and _r.message_id:
                             self._schedule_ephemeral_delete(
@@ -4045,7 +4052,7 @@ class BasePlatformAdapter(ABC):
                                 chat_id=event.source.chat_id,
                                 content=_text,
                                 reply_to=_reply_anchor_for_event(event),
-                                metadata=_thread_meta,
+                                metadata=_mark_notify_metadata(_thread_meta),
                             )
                             if _eph_ttl > 0 and _r.success and _r.message_id:
                                 self._schedule_ephemeral_delete(
@@ -4268,6 +4275,12 @@ class BasePlatformAdapter(ABC):
                         )
                         text_content = _recovered
 
+                # Final user-visible content (text, TTS, media, files) gets
+                # the existing notify=True marker. Clone once so typing/status
+                # metadata stays unmarked and progress bubbles remain
+                # thread-strict.
+                _final_thread_metadata = _mark_notify_metadata(_thread_metadata)
+
                 # Auto-TTS: if voice message, generate audio FIRST (before sending text)
                 # Gated via ``_should_auto_tts_for_chat``: fires when the chat has
                 # an explicit ``/voice on|tts`` opt-in OR when ``voice.auto_tts`` is
@@ -4307,7 +4320,7 @@ class BasePlatformAdapter(ABC):
                             chat_id=event.source.chat_id,
                             audio_path=_tts_path,
                             caption=telegram_tts_caption,
-                            metadata=_thread_metadata,
+                            metadata=_final_thread_metadata,
                         )
                         _tts_caption_delivered = bool(
                             telegram_tts_caption and getattr(tts_result, "success", False)
@@ -4322,23 +4335,11 @@ class BasePlatformAdapter(ABC):
                 if text_content and not _tts_caption_delivered:
                     logger.info("[%s] Sending response (%d chars) to %s", self.name, len(text_content), event.source.chat_id)
                     _reply_anchor = _reply_anchor_for_event(event)
-                    # Mark final response messages for notification delivery.
-                    # Platform adapters that support per-message notification
-                    # control (e.g. Telegram's disable_notification) use this
-                    # flag to override silent-mode and ensure the final
-                    # response triggers a push notification.
-                    # Clone to avoid mutating the metadata shared with the
-                    # typing-indicator task (which must remain unmarked).
-                    if _thread_metadata is not None:
-                        _thread_metadata = dict(_thread_metadata)
-                        _thread_metadata["notify"] = True
-                    else:
-                        _thread_metadata = {"notify": True}
                     result = await self._send_with_retry(
                         chat_id=event.source.chat_id,
                         content=text_content,
                         reply_to=_reply_anchor,
-                        metadata=_thread_metadata,
+                        metadata=_final_thread_metadata,
                     )
                     _record_delivery(result)
 
@@ -4367,7 +4368,7 @@ class BasePlatformAdapter(ABC):
                         await self.send_multiple_images(
                             chat_id=event.source.chat_id,
                             images=images,
-                            metadata=_thread_metadata,
+                            metadata=_final_thread_metadata,
                             human_delay=human_delay,
                         )
                     except Exception as batch_err:
@@ -4409,7 +4410,7 @@ class BasePlatformAdapter(ABC):
                         await self.send_multiple_images(
                             chat_id=event.source.chat_id,
                             images=_batch,
-                            metadata=_thread_metadata,
+                            metadata=_final_thread_metadata,
                             human_delay=human_delay,
                         )
                     except Exception as batch_err:
@@ -4424,19 +4425,19 @@ class BasePlatformAdapter(ABC):
                             media_result = await self.send_voice(
                                 chat_id=event.source.chat_id,
                                 audio_path=media_path,
-                                metadata=_thread_metadata,
+                                metadata=_final_thread_metadata,
                             )
                         elif ext in _VIDEO_EXTS:
                             media_result = await self.send_video(
                                 chat_id=event.source.chat_id,
                                 video_path=media_path,
-                                metadata=_thread_metadata,
+                                metadata=_final_thread_metadata,
                             )
                         else:
                             media_result = await self.send_document(
                                 chat_id=event.source.chat_id,
                                 file_path=media_path,
-                                metadata=_thread_metadata,
+                                metadata=_final_thread_metadata,
                             )
 
                         if not media_result.success:
@@ -4454,13 +4455,13 @@ class BasePlatformAdapter(ABC):
                             await self.send_video(
                                 chat_id=event.source.chat_id,
                                 video_path=file_path,
-                                metadata=_thread_metadata,
+                                metadata=_final_thread_metadata,
                             )
                         else:
                             await self.send_document(
                                 chat_id=event.source.chat_id,
                                 file_path=file_path,
-                                metadata=_thread_metadata,
+                                metadata=_final_thread_metadata,
                             )
                     except Exception as file_err:
                         logger.error("[%s] Error sending local file %s: %s", self.name, file_path, file_err)

gateway/platforms/email.py

@@ -678,8 +678,13 @@ class EmailAdapter(BasePlatformAdapter):
         image_url: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
-        """Send an image URL as part of an email body."""
+        """Send an image URL as part of an email body.
+
+        ``metadata`` is accepted to honor the base-class contract; the
+        email body send doesn't use it.
+        """
         text = caption or ""
         text += f"\n\nImage: {image_url}"
         return await self.send(chat_id, text.strip(), reply_to)

gateway/platforms/whatsapp.py

@@ -846,13 +846,20 @@ class WhatsAppAdapter(WhatsAppBehaviorMixin, BasePlatformAdapter):
         image_url: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
-        """Download image URL to cache, send natively via bridge."""
+        """Download image URL to cache, send natively via bridge.
+
+        ``metadata`` is accepted to honor the base-class contract — the
+        batch sender ``send_multiple_images`` passes it through to every
+        send path. The bridge media call doesn't use it, matching the
+        sibling overrides (send_video / send_voice / send_document).
+        """
         try:
             local_path = await cache_image_from_url(image_url)
             return await self._send_media_to_bridge(chat_id, local_path, "image", caption)
         except Exception:
-            return await super().send_image(chat_id, image_url, caption, reply_to)
+            return await super().send_image(chat_id, image_url, caption, reply_to, metadata)
 
     async def send_image_file(
         self,
@@ -1136,6 +1143,15 @@ class WhatsAppAdapter(WhatsAppBehaviorMixin, BasePlatformAdapter):
             body = data.get("body", "")
             if data.get("isGroup"):
                 body = self._clean_bot_mention_text(body, data)
+
+            # If this is a reply, include the quoted message text so the agent
+            # knows exactly what the user is responding to (fixes "approve" context issue)
+            quoted_text = str(data.get("quotedText") or "").strip()
+            if quoted_text and data.get("hasQuotedMessage"):
+                # Truncate long quoted text to keep prompts reasonable
+                if len(quoted_text) > 300:
+                    quoted_text = quoted_text[:297] + "..."
+                body = f"[Replying to: \"{quoted_text}\"]\n{body}"
             MAX_TEXT_INJECT_BYTES = 100 * 1024
             if msg_type == MessageType.DOCUMENT and cached_urls:
                 for doc_path in cached_urls:

gateway/run.py

@@ -413,6 +413,57 @@ def _resolve_progress_thread_id(platform: Any, source_thread_id: Any, event_mess
     return None
 
 
+def _has_platform_display_override(user_config: dict, platform_key: str, setting: str) -> bool:
+    """Return True when display.platforms.<platform> explicitly sets setting."""
+    display = user_config.get("display") if isinstance(user_config, dict) else None
+    if not isinstance(display, dict):
+        return False
+    platforms = display.get("platforms")
+    if not isinstance(platforms, dict):
+        return False
+    platform_cfg = platforms.get(platform_key)
+    return isinstance(platform_cfg, dict) and setting in platform_cfg
+
+
+def _resolve_gateway_display_bool(
+    user_config: dict,
+    platform_key: str,
+    setting: str,
+    *,
+    default: bool = False,
+    platform: Any = None,
+    require_platform_override_for: set[Any] | None = None,
+) -> bool:
+    """Resolve a boolean display setting with optional platform-only opt-in.
+
+    Some display features expose assistant scratch text rather than deliberate
+    user-facing output.  For high-noise threaded chat surfaces such as
+    Mattermost, a global opt-in is too broad: they must be enabled with an
+    explicit display.platforms.<platform>.<setting> override.
+    """
+    current_platform = _gateway_platform_value(platform or platform_key)
+    platform_only = {
+        _gateway_platform_value(candidate)
+        for candidate in (require_platform_override_for or set())
+    }
+    if (
+        current_platform in platform_only
+        and not _has_platform_display_override(user_config, platform_key, setting)
+    ):
+        return False
+
+    from gateway.display_config import resolve_display_setting
+
+    value = resolve_display_setting(user_config, platform_key, setting, default)
+    if isinstance(value, bool):
+        return value
+    if isinstance(value, str):
+        return value.strip().lower() in {"true", "yes", "1", "on"}
+    if value is None:
+        return bool(default)
+    return bool(value)
+
+
 def _telegramize_command_mentions(text: str, platform: Any) -> str:
     """Rewrite slash-command mentions to Telegram-valid command names.
 
@@ -8989,17 +9040,24 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                     source, session_entry, reason="agent-result-compression",
                 )
 
-            # Prepend reasoning/thinking if display is enabled (per-platform)
+            # Prepend reasoning/thinking if display is enabled (per-platform).
+            # Mattermost requires explicit per-platform opt-in because this is
+            # scratch text, not ordinary final-answer content.
             try:
-                from gateway.display_config import resolve_display_setting as _rds
-                _show_reasoning_effective = _rds(
+                _show_reasoning_effective = _resolve_gateway_display_bool(
                     _load_gateway_config(),
                     _platform_config_key(source.platform),
                     "show_reasoning",
-                    getattr(self, "_show_reasoning", False),
+                    default=bool(getattr(self, "_show_reasoning", False)),
+                    platform=source.platform,
+                    require_platform_override_for={Platform.MATTERMOST},
                 )
             except Exception:
-                _show_reasoning_effective = getattr(self, "_show_reasoning", False)
+                _show_reasoning_effective = (
+                    False
+                    if source.platform == Platform.MATTERMOST
+                    else getattr(self, "_show_reasoning", False)
+                )
             if _show_reasoning_effective and response and not _intentional_silence:
                 last_reasoning = agent_result.get("last_reasoning")
                 if last_reasoning:
@@ -13635,18 +13693,32 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
         # in chat platforms while opting into concise mid-turn updates.
         interim_assistant_messages_enabled = (
             source.platform != Platform.WEBHOOK
-            and bool(
-                resolve_display_setting(
-                    user_config,
-                    platform_key,
-                    "interim_assistant_messages",
-                    True,
-                )
+            and _resolve_gateway_display_bool(
+                user_config,
+                platform_key,
+                "interim_assistant_messages",
+                default=True,
+                platform=source.platform,
+                require_platform_override_for={Platform.MATTERMOST},
             )
         )
-        
+        # thinking_progress is independent — if enabled, we need the progress
+        # queue even when tool_progress is off (thinking relay uses same infra).
+        # Mattermost requires a per-platform opt-in: global scratch-text display
+        # is too easy to leak into busy public threads.
+        _thinking_enabled = _resolve_gateway_display_bool(
+            user_config,
+            platform_key,
+            "thinking_progress",
+            default=False,
+            platform=source.platform,
+            require_platform_override_for={Platform.MATTERMOST},
+        )
+        needs_progress_queue = tool_progress_enabled or _thinking_enabled
+
+
         # Queue for progress messages (thread-safe)
-        progress_queue = queue.Queue() if tool_progress_enabled else None
+        progress_queue = queue.Queue() if needs_progress_queue else None
         last_tool = [None]  # Mutable container for tracking in closure
         last_progress_msg = [None]  # Track last message for dedup
         repeat_count = [0]  # How many times the same message repeated
@@ -13752,6 +13824,24 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                     logger.debug("tool-progress onboarding hint failed: %s", _hint_err)
                 return
 
+            # "_thinking" is assistant scratch text between tool calls.  It
+            # is never ordinary tool progress: only relay it when the platform
+            # explicitly opted into thinking_progress.  Handle both legacy
+            # callback shapes: ("_thinking", text) and
+            # ("reasoning.available", "_thinking", text, ...).
+            if event_type == "_thinking" or tool_name == "_thinking":
+                if not _thinking_enabled:
+                    return
+                thinking_text = preview if tool_name == "_thinking" else tool_name
+                msg = f"💬 {thinking_text}" if thinking_text else None
+                if msg:
+                    progress_queue.put(msg)
+                return
+
+            # If tool_progress is off, only _thinking passes through (above).
+            # Regular tool calls are suppressed.
+            if not tool_progress_enabled:
+                return
 
             # Only act on tool.started events (ignore tool.completed, reasoning.available, etc.)
             if event_type not in {"tool.started",}:
@@ -14783,6 +14873,10 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
 
             agent.clarify_callback = _clarify_callback_sync
 
+            # Show assistant thinking between tool calls — independent of
+            # tool_progress mode. Mattermost needs an explicit per-platform
+            # opt-in so global scratch-text display does not leak into threads.
+            agent.thinking_progress = _thinking_enabled
             # Store agent reference for interrupt support
             agent_holder[0] = agent
             # Capture the full tool definitions for transcript logging

gateway/stream_consumer.py

@@ -197,6 +197,30 @@ class GatewayStreamConsumer:
         # this response and route through edit-based for graceful degradation.
         self._draft_failures = 0
 
+    def _metadata_for_send(
+        self,
+        *,
+        final: bool = False,
+        expect_edits: bool = False,
+    ) -> dict | None:
+        """Return per-send metadata for stream-created messages.
+
+        Mattermost treats notify-worthy sends as user-visible final content
+        when deciding whether a broken thread root may fall back flat.  Preview
+        and progress sends keep their original metadata and remain thread-strict.
+
+        ``expect_edits`` preserves the upstream Telegram streaming contract:
+        preview messages that may be edited later must stay on the editable
+        legacy send path, while fresh/fallback final sends can still use richer
+        final-message delivery.
+        """
+        meta = dict(self.metadata) if self.metadata else {}
+        if expect_edits:
+            meta["expect_edits"] = True
+        if final:
+            meta["notify"] = True
+        return meta or None
+
     @property
     def already_sent(self) -> bool:
         """True if at least one message was sent or edited during the run."""
@@ -513,7 +537,11 @@ class GatewayStreamConsumer:
                         chunks_delivered = False
                         reply_to = self._message_id or self._initial_reply_to_id
                         for chunk in chunks:
-                            new_id = await self._send_new_chunk(chunk, reply_to)
+                            new_id = await self._send_new_chunk(
+                                chunk,
+                                reply_to,
+                                final=got_done,
+                            )
                             if new_id is not None and new_id != reply_to:
                                 chunks_delivered = True
                         self._accumulated = ""
@@ -749,7 +777,13 @@ class GatewayStreamConsumer:
         # Strip trailing whitespace/newlines but preserve leading content
         return cleaned.rstrip()
 
-    async def _send_new_chunk(self, text: str, reply_to_id: Optional[str]) -> Optional[str]:
+    async def _send_new_chunk(
+        self,
+        text: str,
+        reply_to_id: Optional[str],
+        *,
+        final: bool = False,
+    ) -> Optional[str]:
         """Send a new message chunk, optionally threaded to a previous message.
 
         Returns the message_id so callers can thread subsequent chunks.
@@ -758,15 +792,11 @@ class GatewayStreamConsumer:
         if not text.strip():
             return reply_to_id
         try:
-            meta = dict(self.metadata) if self.metadata else {}
-            # This chunk becomes the next edit target — adapters that support
-            # rich final sends (Telegram) must keep it on the editable path.
-            meta["expect_edits"] = True
             result = await self.adapter.send(
                 chat_id=self.chat_id,
                 content=text,
                 reply_to=reply_to_id,
-                metadata=meta,
+                metadata=self._metadata_for_send(final=final, expect_edits=True),
             )
             if result.success and result.message_id:
                 self._message_id = str(result.message_id)
@@ -885,7 +915,7 @@ class GatewayStreamConsumer:
                 result = await self.adapter.send(
                     chat_id=self.chat_id,
                     content=chunk,
-                    metadata=self.metadata,
+                    metadata=self._metadata_for_send(final=True),
                 )
                 if result.success:
                     break
@@ -1242,7 +1272,7 @@ class GatewayStreamConsumer:
             result = await self.adapter.send(
                 chat_id=self.chat_id,
                 content=text,
-                metadata=self.metadata,
+                metadata=self._metadata_for_send(final=True),
             )
         except Exception as e:
             logger.debug("Fresh-final send failed, falling back to edit: %s", e)
@@ -1532,7 +1562,10 @@ class GatewayStreamConsumer:
                     chat_id=self.chat_id,
                     content=text,
                     reply_to=self._initial_reply_to_id,
-                    metadata={**(self.metadata or {}), "expect_edits": True},
+                    metadata=self._metadata_for_send(
+                        final=finalize,
+                        expect_edits=True,
+                    ),
                 )
                 if result.success:
                     if result.message_id:

scripts/release.py

@@ -90,6 +90,7 @@ AUTHOR_MAP = {
     "290859878+synapsesx@users.noreply.github.com": "synapsesx",
     "157689911+itsflownium@users.noreply.github.com": "itsflownium",
     "dirtyren@users.noreply.github.com": "dirtyren",
+    "evansrory@gmail.com": "zimigit2020",
     "237263164+ft-ioxcs@users.noreply.github.com": "ft-ioxcs",
     "tharushkadinujaya05@gmail.com": "0xneobyte",
     "138671361+Veritas-7@users.noreply.github.com": "Veritas-7",

tests/agent/test_auxiliary_client.py

@@ -1653,6 +1653,37 @@ class TestAuxiliaryFallbackLayering:
         exc.status_code = 402
         return exc
 
+    def test_auto_provider_uses_task_then_main_chain_before_builtin_chain(self, monkeypatch):
+        """Auto aux call failures try per-task then top-level fallback before built-ins."""
+        primary_client = MagicMock()
+        primary_client.chat.completions.create.side_effect = self._make_payment_err()
+
+        main_chain_client = MagicMock()
+        main_chain_client.chat.completions.create.return_value = MagicMock(choices=[
+            MagicMock(message=MagicMock(content="from main fallback chain"))
+        ])
+
+        with patch("agent.auxiliary_client._get_cached_client",
+                   return_value=(primary_client, "qwen/qwen3.5-122b-a10b")), \
+             patch("agent.auxiliary_client._resolve_task_provider_model",
+                   return_value=("auto", None, None, None, None)), \
+             patch("agent.auxiliary_client._try_configured_fallback_chain",
+                   return_value=(None, None, "")) as mock_task_chain, \
+             patch("agent.auxiliary_client._try_main_fallback_chain",
+                   return_value=(main_chain_client, "inclusionai/ring-2.6-1t:free", "openrouter")) as mock_main_chain, \
+             patch("agent.auxiliary_client._try_payment_fallback") as mock_builtin_chain:
+            result = call_llm(
+                task="title_generation",
+                messages=[{"role": "user", "content": "hello"}],
+            )
+
+        assert main_chain_client.chat.completions.create.called
+        mock_task_chain.assert_called_once_with(
+            "title_generation", "auto", reason="payment error")
+        mock_main_chain.assert_called_once_with(
+            "title_generation", "auto", reason="payment error")
+        mock_builtin_chain.assert_not_called()
+
     def test_explicit_provider_uses_configured_chain_first(self, monkeypatch, caplog):
         """When a user has fallback_chain configured, it's tried BEFORE the main agent model."""
         monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")

tests/agent/test_auxiliary_main_first.py

@@ -118,6 +118,64 @@ class TestResolveAutoMainFirst:
         assert client is chain_client
         assert model == "google/gemini-3-flash-preview"
 
+    def test_main_unavailable_uses_task_fallback_chain_before_builtin_chain(self):
+        """Auto aux resolution honors auxiliary.<task>.fallback_chain before built-ins."""
+        task_client = MagicMock()
+        with patch(
+            "agent.auxiliary_client._read_main_provider", return_value="nvidia",
+        ), patch(
+            "agent.auxiliary_client._read_main_model", return_value="qwen/qwen3.5-122b-a10b",
+        ), patch(
+            "agent.auxiliary_client.resolve_provider_client",
+            return_value=(None, None),  # main provider has no client
+        ), patch(
+            "agent.auxiliary_client._try_configured_fallback_chain",
+            return_value=(task_client, "task-free-model", "fallback_chain[0](openrouter)"),
+        ) as mock_task_chain, patch(
+            "agent.auxiliary_client._try_main_fallback_chain",
+        ) as mock_main_chain, patch(
+            "agent.auxiliary_client._try_openrouter",
+        ) as mock_openrouter:
+            from agent.auxiliary_client import _resolve_auto
+
+            client, model = _resolve_auto(task="title_generation")
+
+        assert client is task_client
+        assert model == "task-free-model"
+        mock_task_chain.assert_called_once_with(
+            "title_generation", "nvidia", reason="main provider unavailable")
+        mock_main_chain.assert_not_called()
+        mock_openrouter.assert_not_called()
+
+    def test_main_unavailable_uses_main_fallback_chain_before_builtin_chain(self):
+        """Auto aux resolution honors top-level fallback_providers before built-ins."""
+        main_fallback_client = MagicMock()
+        with patch(
+            "agent.auxiliary_client._read_main_provider", return_value="nvidia",
+        ), patch(
+            "agent.auxiliary_client._read_main_model", return_value="qwen/qwen3.5-122b-a10b",
+        ), patch(
+            "agent.auxiliary_client.resolve_provider_client",
+            return_value=(None, None),  # main provider has no client
+        ), patch(
+            "agent.auxiliary_client._try_configured_fallback_chain",
+            return_value=(None, None, ""),
+        ), patch(
+            "agent.auxiliary_client._try_main_fallback_chain",
+            return_value=(main_fallback_client, "inclusionai/ring-2.6-1t:free", "openrouter"),
+        ) as mock_main_chain, patch(
+            "agent.auxiliary_client._try_openrouter",
+        ) as mock_openrouter:
+            from agent.auxiliary_client import _resolve_auto
+
+            client, model = _resolve_auto(task="title_generation")
+
+        assert client is main_fallback_client
+        assert model == "inclusionai/ring-2.6-1t:free"
+        mock_main_chain.assert_called_once_with(
+            "title_generation", "nvidia", reason="main provider unavailable")
+        mock_openrouter.assert_not_called()
+
     def test_no_main_config_uses_chain_directly(self):
         """No main provider configured → skip step 1, use chain (no regression)."""
         chain_client = MagicMock()

tests/gateway/test_mattermost.py

@@ -6,7 +6,10 @@ import pytest
 from unittest.mock import MagicMock, patch, AsyncMock
 
 from gateway.config import Platform, PlatformConfig
-from gateway.run import _resolve_progress_thread_id
+from gateway.run import (
+    _resolve_gateway_display_bool,
+    _resolve_progress_thread_id,
+)
 
 
 class TestMattermostProgressThreadRouting:
@@ -32,6 +35,97 @@ class TestMattermostProgressThreadRouting:
         ) is None
 
 
+class TestMattermostDisplayHygiene:
+    def test_mattermost_requires_platform_opt_in_for_interim_assistant_messages(self):
+        """Global interim commentary must not make Mattermost leak scratch notes."""
+        user_config = {"display": {"interim_assistant_messages": True}}
+
+        assert _resolve_gateway_display_bool(
+            user_config,
+            "mattermost",
+            "interim_assistant_messages",
+            default=True,
+            platform=Platform.MATTERMOST,
+            require_platform_override_for={Platform.MATTERMOST},
+        ) is False
+
+    def test_mattermost_platform_opt_in_can_enable_interim_assistant_messages(self):
+        """Mattermost can still opt into commentary explicitly per platform."""
+        user_config = {
+            "display": {
+                "interim_assistant_messages": False,
+                "platforms": {
+                    "mattermost": {"interim_assistant_messages": True},
+                },
+            }
+        }
+
+        assert _resolve_gateway_display_bool(
+            user_config,
+            "mattermost",
+            "interim_assistant_messages",
+            default=True,
+            platform=Platform.MATTERMOST,
+            require_platform_override_for={Platform.MATTERMOST},
+        ) is True
+
+    def test_mattermost_requires_platform_opt_in_for_thinking_progress(self):
+        """Global thinking_progress must not surface internal analysis in Mattermost."""
+        user_config = {"display": {"thinking_progress": True}}
+
+        assert _resolve_gateway_display_bool(
+            user_config,
+            "mattermost",
+            "thinking_progress",
+            default=False,
+            platform=Platform.MATTERMOST,
+            require_platform_override_for={Platform.MATTERMOST},
+        ) is False
+
+    def test_mattermost_requires_platform_opt_in_for_show_reasoning(self):
+        """Global show_reasoning must not prepend scratch reasoning in Mattermost."""
+        user_config = {"display": {"show_reasoning": True}}
+
+        assert _resolve_gateway_display_bool(
+            user_config,
+            "mattermost",
+            "show_reasoning",
+            default=False,
+            platform=Platform.MATTERMOST,
+            require_platform_override_for={Platform.MATTERMOST},
+        ) is False
+
+    def test_mattermost_platform_opt_in_can_enable_show_reasoning(self):
+        user_config = {
+            "display": {
+                "show_reasoning": False,
+                "platforms": {"mattermost": {"show_reasoning": True}},
+            }
+        }
+
+        assert _resolve_gateway_display_bool(
+            user_config,
+            "mattermost",
+            "show_reasoning",
+            default=False,
+            platform=Platform.MATTERMOST,
+            require_platform_override_for={Platform.MATTERMOST},
+        ) is True
+
+    def test_global_thinking_progress_still_applies_to_other_platforms(self):
+        """The Mattermost guard must not silently neuter Telegram/other chats."""
+        user_config = {"display": {"thinking_progress": True}}
+
+        assert _resolve_gateway_display_bool(
+            user_config,
+            "telegram",
+            "thinking_progress",
+            default=False,
+            platform=Platform.TELEGRAM,
+            require_platform_override_for={Platform.MATTERMOST},
+        ) is True
+
+
 # ---------------------------------------------------------------------------
 # Platform & Config
 # ---------------------------------------------------------------------------
@@ -347,6 +441,24 @@ class TestMattermostSend:
         payload = self.adapter._api_post.call_args_list[0][0][1]
         assert payload["root_id"] == "root_post"
 
+    @pytest.mark.asyncio
+    async def test_progress_send_with_invalid_thread_root_never_falls_back_flat(self):
+        """Tool/status/progress bubbles must stay quiet when the thread is broken."""
+        self.adapter._reply_mode = "thread"
+        self.adapter._api_get = AsyncMock(return_value={"id": "bad_root", "root_id": ""})
+        self.adapter._api_post = AsyncMock(return_value={})
+
+        result = await self.adapter.send(
+            "channel_1",
+            "⚙️ terminal...",
+            metadata={"thread_id": "bad_root"},
+        )
+
+        assert result.success is False
+        assert self.adapter._api_post.call_count == 1
+        payload = self.adapter._api_post.call_args_list[0][0][1]
+        assert payload["root_id"] == "bad_root"
+
     @pytest.mark.asyncio
     async def test_send_api_failure(self):
         """When API returns error, send should return failure."""

tests/gateway/test_media_metadata_contract.py

@@ -0,0 +1,80 @@
+"""Contract: media-send overrides must accept the ``metadata`` kwarg.
+
+``BasePlatformAdapter.send_multiple_images`` passes ``metadata=metadata``
+to ``send_image`` / ``send_image_file`` / ``send_animation`` on every send.
+An override whose signature stops at ``reply_to`` raises ``TypeError:
+send_image() got an unexpected keyword argument 'metadata'`` at runtime —
+which is exactly how image delivery broke on WhatsApp and email.
+
+This mirrors ``test_discord_media_metadata.py`` but covers the two
+adapters that previously slipped, plus a best-effort sweep over every
+adapter that imports cleanly so the next slip is caught at test time.
+"""
+
+from __future__ import annotations
+
+import importlib
+import inspect
+
+import pytest
+
+
+def _accepts_metadata(method) -> bool:
+    params = inspect.signature(method).parameters
+    if "metadata" in params:
+        return True
+    # A ``**kwargs`` catch-all also absorbs metadata (the convention used by
+    # WhatsApp's send_video / send_voice / send_document overrides).
+    return any(p.kind is inspect.Parameter.VAR_KEYWORD for p in params.values())
+
+
+# (module, class) for the two adapters this fix targeted. These must import
+# in CI, so assert directly rather than skipping.
+@pytest.mark.parametrize(
+    "module_name, class_name",
+    [
+        ("gateway.platforms.whatsapp", "WhatsAppAdapter"),
+        ("gateway.platforms.email", "EmailAdapter"),
+    ],
+)
+def test_send_image_accepts_metadata(module_name, class_name):
+    cls = getattr(importlib.import_module(module_name), class_name)
+    assert _accepts_metadata(cls.send_image), (
+        f"{class_name}.send_image must accept 'metadata' (or **kwargs) — "
+        f"send_multiple_images passes it on every send"
+    )
+
+
+# Best-effort sweep across all shipped adapters. Modules whose optional
+# platform SDK isn't installed are skipped; an adapter that imports but
+# whose override drops metadata is a hard failure.
+_ALL_ADAPTERS = [
+    ("gateway.platforms.bluebubbles", "BlueBubblesAdapter"),
+    ("gateway.platforms.dingtalk", "DingTalkAdapter"),
+    ("gateway.platforms.discord", "DiscordAdapter"),
+    ("gateway.platforms.email", "EmailAdapter"),
+    ("gateway.platforms.feishu", "FeishuAdapter"),
+    ("gateway.platforms.matrix", "MatrixAdapter"),
+    ("gateway.platforms.mattermost", "MattermostAdapter"),
+    ("gateway.platforms.signal", "SignalAdapter"),
+    ("gateway.platforms.slack", "SlackAdapter"),
+    ("gateway.platforms.telegram", "TelegramAdapter"),
+    ("gateway.platforms.wecom", "WeComAdapter"),
+    ("gateway.platforms.weixin", "WeixinAdapter"),
+    ("gateway.platforms.whatsapp", "WhatsAppAdapter"),
+    ("gateway.platforms.yuanbao", "YuanbaoAdapter"),
+]
+
+
+@pytest.mark.parametrize("module_name, class_name", _ALL_ADAPTERS)
+def test_all_adapters_send_image_metadata_sweep(module_name, class_name):
+    try:
+        module = importlib.import_module(module_name)
+    except Exception as exc:  # optional platform dep not installed
+        pytest.skip(f"{module_name} not importable: {exc}")
+    cls = getattr(module, class_name, None)
+    if cls is None or "send_image" not in cls.__dict__:
+        pytest.skip(f"{class_name} has no send_image override")
+    assert _accepts_metadata(cls.send_image), (
+        f"{class_name}.send_image drops the 'metadata' kwarg"
+    )

tests/gateway/test_stream_consumer_thread_routing.py

@@ -106,6 +106,42 @@ class TestInitialReplyToId:
         assert call_kwargs["metadata"] == {**metadata, "expect_edits": True}
         assert metadata == {"thread_id": "omt_topic789"}
 
+    @pytest.mark.asyncio
+    async def test_final_first_send_marks_metadata_notify_true(self):
+        """Final streaming sends should use the existing notify=True marker."""
+        adapter = _make_adapter()
+        consumer = GatewayStreamConsumer(
+            adapter,
+            "chat_123",
+            metadata={"thread_id": "root_post_123"},
+            initial_reply_to_id="reply_post_456",
+        )
+
+        await consumer._send_or_edit("Final answer", finalize=True)
+
+        call_kwargs = adapter.send.call_args[1]
+        metadata = call_kwargs["metadata"]
+        assert metadata["thread_id"] == "root_post_123"
+        assert metadata["notify"] is True
+        assert "delivery_kind" not in metadata
+        assert "allow_flat_fallback" not in metadata
+
+    @pytest.mark.asyncio
+    async def test_nonfinal_first_send_does_not_mark_notify(self):
+        """Preview/interim streaming sends must not be notify-worthy."""
+        adapter = _make_adapter()
+        consumer = GatewayStreamConsumer(
+            adapter,
+            "chat_123",
+            metadata={"thread_id": "root_post_123"},
+            initial_reply_to_id="reply_post_456",
+        )
+
+        await consumer._send_or_edit("Preview", finalize=False)
+
+        metadata = adapter.send.call_args[1]["metadata"]
+        assert metadata == {"thread_id": "root_post_123", "expect_edits": True}
+
 
 class TestOverflowFirstMessage:
     """Verify thread routing is preserved when the first message overflows."""

tests/gateway/test_telegram_overflow_partial.py

@@ -134,7 +134,7 @@ async def test_stream_consumer_fallback_sends_tail_after_partial_overflow():
 
     adapter.send.assert_awaited_once()
     assert adapter.send.await_args.kwargs["content"] == "world"
-    assert adapter.send.await_args.kwargs["metadata"] == {"thread_id": "77"}
+    assert adapter.send.await_args.kwargs["metadata"] == {"thread_id": "77", "notify": True}
     adapter.delete_message.assert_not_awaited()
     assert consumer.final_response_sent is True
     assert consumer.final_content_delivered is True

tests/gateway/test_tts_media_routing.py

@@ -76,7 +76,7 @@ async def test_base_adapter_routes_telegram_flac_media_tag_to_document_sender(tm
     adapter.send_document.assert_awaited_once_with(
         chat_id="chat-1",
         file_path=str(media_file),
-        metadata=None,
+        metadata={"notify": True},
     )
     adapter.send_voice.assert_not_awaited()
 
@@ -95,7 +95,7 @@ async def test_base_adapter_routes_non_voice_telegram_ogg_media_tag_to_document_
     adapter.send_document.assert_awaited_once_with(
         chat_id="chat-1",
         file_path=str(media_file),
-        metadata=None,
+        metadata={"notify": True},
     )
     adapter.send_voice.assert_not_awaited()
 
@@ -116,7 +116,7 @@ async def test_base_adapter_routes_voice_tagged_telegram_ogg_media_tag_to_voice_
     adapter.send_voice.assert_awaited_once_with(
         chat_id="chat-1",
         audio_path=str(media_file),
-        metadata=None,
+        metadata={"notify": True},
     )
     adapter.send_document.assert_not_awaited()
 

tests/run_agent/test_async_httpx_del_neuter.py

@@ -176,11 +176,16 @@ class TestClientCacheBoundedGrowth:
         """When the loop changes, the old entry should be replaced, not duplicated."""
         from agent.auxiliary_client import (
             _client_cache,
+            _client_cache_key,
             _client_cache_lock,
             _get_cached_client,
         )
 
-        key = ("test_replace", True, "", "", "", (), False, "")
+        key = _client_cache_key(
+            "test_replace",
+            async_mode=True,
+            task="",
+        )
 
         # Simulate a stale entry from a closed loop
         old_loop = asyncio.new_event_loop()

website/docs/reference/environment-variables.md

@@ -687,7 +687,7 @@ For task-specific direct endpoints, Hermes uses the task's configured API key or
 
 ## Fallback Providers (config.yaml only)
 
-The primary model fallback chain is configured exclusively through `config.yaml` — there are no environment variables for it. Add a top-level `fallback_providers` list with `provider` and `model` keys to enable automatic failover when your main model encounters errors.
+The primary model fallback chain is configured exclusively through `config.yaml` — there are no environment variables for it. Add a top-level `fallback_providers` list with `provider` and `model` keys to enable automatic failover when your main model encounters errors. Auxiliary tasks whose provider is `auto` also consult this chain before Hermes' built-in auxiliary discovery chain.
 
 ```yaml
 fallback_providers:
@@ -695,7 +695,7 @@ fallback_providers:
     model: anthropic/claude-sonnet-4
 ```
 
-The older top-level `fallback_model` single-provider shape is still read for backward compatibility, but new configuration should use `fallback_providers`.
+The older top-level `fallback_model` single-provider shape is still read for backward compatibility, but new configuration should use `fallback_providers`. For task-specific auxiliary policy, use `auxiliary.<task>.fallback_chain` in `config.yaml`; there is no environment variable equivalent.
 
 See [Fallback Providers](/user-guide/features/fallback-providers) for full details.
 

website/docs/user-guide/configuring-models.md

@@ -53,7 +53,7 @@ Click **Show auxiliary** to reveal the 11 task slots:
 
 ![Auxiliary panel expanded](/img/docs/dashboard-models/auxiliary-expanded.png)
 
-Every auxiliary task defaults to `auto` — meaning Hermes uses your main model for that job too. Override a specific task when you want a cheaper or faster model for a side-job.
+Every auxiliary task defaults to `auto` — meaning Hermes tries your main model for that job too. If that route is unavailable or hits a capacity-style failure, `auto` follows any task-specific `auxiliary.<task>.fallback_chain`, then the main `fallback_providers` / `fallback_model` chain, then Hermes' built-in auxiliary discovery chain. Override a specific task when you want a cheaper or faster model for a side-job.
 
 ### Common override patterns
 
@@ -129,7 +129,21 @@ auxiliary:
     # ... other fields unchanged
 ```
 
-`provider: auto` with `model: ''` tells Hermes to use the main model for that task.
+`provider: auto` with `model: ''` tells Hermes to use the main model for that task, while still honoring fallback policy if the main route cannot serve the auxiliary call.
+
+Optional task-specific fallback chains live under the same auxiliary task:
+
+```yaml
+auxiliary:
+  title_generation:
+    provider: auto
+    model: ''
+    fallback_chain:
+      - provider: openrouter
+        model: inclusionai/ring-2.6-1t:free
+```
+
+When `fallback_chain` is absent, `auto` uses the top-level `fallback_providers` chain before the built-in auxiliary discovery chain.
 
 ## When does it take effect?
 

website/docs/user-guide/features/fallback-providers.md

@@ -168,7 +168,7 @@ fallback_providers:
 | Messaging gateway (Telegram, Discord, etc.) | ✔ |
 | Subagent delegation | ✔ (subagents inherit the parent fallback chain) |
 | Cron jobs | ✔ (cron agents inherit configured fallback providers) |
-| Auxiliary tasks (vision, compression) | ✘ (use their own provider chain — see below) |
+| Auxiliary tasks on `provider: auto` | ✔ (try per-task fallback, then the main fallback chain before built-in aux discovery) |
 
 :::tip
 There are no environment variables for the primary fallback chain — configure it exclusively through `config.yaml` or `hermes fallback`. This is intentional: fallback configuration is a deliberate choice, not something a stale shell export should override.
@@ -195,23 +195,30 @@ Hermes uses separate lightweight models for side tasks. Each task has its own pr
 
 ### Auto-Detection Chain
 
-When a task's provider is set to `"auto"` (the default), Hermes tries providers in order until one works:
+When a task's provider is set to `"auto"` (the default), Hermes first tries the main provider + main model for that auxiliary task. If that route is unavailable or later fails with a capacity-style error, Hermes now honors user-configured fallback policy before using the built-in discovery chain:
 
-**For text tasks (compression, web extract, etc.):**
+```text
+Main provider + main model → auxiliary.<task>.fallback_chain →
+fallback_providers / fallback_model → built-in auxiliary discovery chain
+```
+
+The task-specific chain is most precise and wins when present. The top-level `fallback_providers` chain is the same policy the main agent uses, so free-only or same-provider fallback rules apply to auxiliary tasks on `auto` as well.
+
+**Built-in text discovery chain (compression, web extract, title generation, etc.):**
 
 ```text
 OpenRouter → Nous Portal → Custom endpoint → Codex OAuth →
 API-key providers (z.ai, Kimi, MiniMax, Xiaomi MiMo, Hugging Face, Anthropic) → give up
 ```
 
-**For vision tasks:**
+**Built-in vision discovery chain:**
 
 ```text
 Main provider (if vision-capable) → OpenRouter → Nous Portal →
 Codex OAuth → Anthropic → Custom endpoint → give up
 ```
 
-If the resolved provider fails at call time, Hermes also has an internal retry: if the provider is not OpenRouter and no explicit `base_url` is set, it tries OpenRouter as a last-resort fallback.
+Those built-in chains are a convenience fallback for users who have not declared a task-specific or main fallback policy.
 
 ### Configuring Auxiliary Providers
 
@@ -232,6 +239,9 @@ auxiliary:
   compression:
     provider: "auto"
     model: ""
+    fallback_chain:              # optional, task-specific fallback policy
+      - provider: openrouter
+        model: inclusionai/ring-2.6-1t:free
 
   skills_hub:
     provider: "auto"
@@ -242,7 +252,9 @@ auxiliary:
     model: ""
 ```
 
-Every task above follows the same **provider / model / base_url** pattern. Context compression is configured under `auxiliary.compression`:
+Every task above follows the same **provider / model / base_url** pattern. Each task can also declare its own `fallback_chain`; if omitted, `provider: auto` uses the top-level `fallback_providers` chain before Hermes' built-in auxiliary discovery chain.
+
+Context compression is configured under `auxiliary.compression`:
 
 ```yaml
 auxiliary: