diff --git a/cli-config.yaml.example b/cli-config.yaml.example
index 504b2178..922807f1 100644
--- a/cli-config.yaml.example
+++ b/cli-config.yaml.example
@@ -324,6 +324,9 @@ compression:
 #   vision:
 #     provider: "auto"
 #     model: ""              # e.g. "google/gemini-2.5-flash", "openai/gpt-4o"
+#     timeout: 30            # LLM API call timeout (seconds)
+#     download_timeout: 30   # Image HTTP download timeout (seconds)
+#                            # Increase for slow connections or self-hosted image servers
 #
 #   # Web page scraping / summarization + browser page text extraction
 #   web_extract:
diff --git a/gateway/run.py b/gateway/run.py
index 3c0ca181..3b519304 100644
--- a/gateway/run.py
+++ b/gateway/run.py
@@ -3891,7 +3891,7 @@ class GatewayRunner:
                 # Send media files
                 for media_path in (media_files or []):
                     try:
-                        await adapter.send_file(
+                        await adapter.send_document(
                             chat_id=source.chat_id,
                             file_path=media_path,
                         )
diff --git a/hermes_cli/config.py b/hermes_cli/config.py
index 69530761..e2503ebe 100644
--- a/hermes_cli/config.py
+++ b/hermes_cli/config.py
@@ -223,7 +223,8 @@ DEFAULT_CONFIG = {
             "model": "",           # e.g. "google/gemini-2.5-flash", "gpt-4o"
             "base_url": "",        # direct OpenAI-compatible endpoint (takes precedence over provider)
             "api_key": "",         # API key for base_url (falls back to OPENAI_API_KEY)
-            "timeout": 30,         # seconds — increase for slow local vision models
+            "timeout": 30,         # seconds — LLM API call timeout; increase for slow local vision models
+            "download_timeout": 30,  # seconds — image HTTP download timeout; increase for slow connections
         },
         "web_extract": {
             "provider": "auto",
diff --git a/tools/vision_tools.py b/tools/vision_tools.py
index 47b40684..404d06a5 100644
--- a/tools/vision_tools.py
+++ b/tools/vision_tools.py
@@ -45,6 +45,28 @@ logger = logging.getLogger(__name__)
 
 _debug = DebugSession("vision_tools", env_var="VISION_TOOLS_DEBUG")
 
+# Configurable HTTP download timeout for _download_image().
+# Separate from auxiliary.vision.timeout which governs the LLM API call.
+# Resolution: config.yaml auxiliary.vision.download_timeout → env var → 30s default.
+def _resolve_download_timeout() -> float:
+    env_val = os.getenv("HERMES_VISION_DOWNLOAD_TIMEOUT", "").strip()
+    if env_val:
+        try:
+            return float(env_val)
+        except ValueError:
+            pass
+    try:
+        from hermes_cli.config import load_config
+        cfg = load_config()
+        val = cfg.get("auxiliary", {}).get("vision", {}).get("download_timeout")
+        if val is not None:
+            return float(val)
+    except Exception:
+        pass
+    return 30.0
+
+_VISION_DOWNLOAD_TIMEOUT = _resolve_download_timeout()
+
 
 def _validate_image_url(url: str) -> bool:
     """
@@ -146,7 +168,7 @@ async def _download_image(image_url: str, destination: Path, max_retries: int =
             # Enable follow_redirects to handle image CDNs that redirect (e.g., Imgur, Picsum)
             # SSRF: event_hooks validates each redirect target against private IP ranges
             async with httpx.AsyncClient(
-                timeout=30.0,
+                timeout=_VISION_DOWNLOAD_TIMEOUT,
                 follow_redirects=True,
                 event_hooks={"response": [_ssrf_redirect_guard]},
             ) as client:
@@ -183,6 +205,10 @@ async def _download_image(image_url: str, destination: Path, max_retries: int =
                     exc_info=True,
                 )
     
+    if last_error is None:
+        raise RuntimeError(
+            f"_download_image exited retry loop without attempting (max_retries={max_retries})"
+        )
     raise last_error
 
 
diff --git a/website/docs/user-guide/configuration.md b/website/docs/user-guide/configuration.md
index 17f15dc5..48d76dd8 100644
--- a/website/docs/user-guide/configuration.md
+++ b/website/docs/user-guide/configuration.md
@@ -1018,7 +1018,8 @@ auxiliary:
     model: ""                  # e.g. "openai/gpt-4o", "google/gemini-2.5-flash"
     base_url: ""               # Custom OpenAI-compatible endpoint (overrides provider)
     api_key: ""                # API key for base_url (falls back to OPENAI_API_KEY)
-    timeout: 30                # seconds — increase for slow local vision models
+    timeout: 30                # seconds — LLM API call; increase for slow local vision models
+    download_timeout: 30       # seconds — image HTTP download; increase for slow connections
 
   # Web page summarization + browser page text extraction
   web_extract:
@@ -1042,7 +1043,7 @@ auxiliary:
 ```
 
 :::tip
-Each auxiliary task has a configurable `timeout` (in seconds). Defaults: vision 30s, web_extract 30s, approval 30s, compression 120s. Increase these if you use slow local models for auxiliary tasks.
+Each auxiliary task has a configurable `timeout` (in seconds). Defaults: vision 30s, web_extract 30s, approval 30s, compression 120s. Increase these if you use slow local models for auxiliary tasks. Vision also has a separate `download_timeout` (default 30s) for the HTTP image download — increase this for slow connections or self-hosted image servers.
 :::
 
 :::info