fix: make vision_analyze timeout configurable via config.yaml (#2480)

Reads auxiliary.vision.timeout from config.yaml (default: 30s) and
passes it to async_call_llm. Useful for slow local vision models
that need more than 30 seconds.

Setting is in config.yaml (not .env) since it's not a secret:

  auxiliary:
    vision:
      timeout: 120

Based on PR #2306.

Co-authored-by: kshitijk4poor <kshitijk4poor@users.noreply.github.com>

hermes_cli/config.py

@@ -182,6 +182,7 @@ 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
         },
         "web_extract": {
             "provider": "auto",

tools/vision_tools.py

@@ -298,12 +298,23 @@ async def vision_analyze_tool(
         
         logger.info("Processing image with vision model...")
         
-        # Call the vision API via centralized router
+        # Call the vision API via centralized router.
+        # Read timeout from config.yaml (auxiliary.vision.timeout), default 30s.
+        vision_timeout = 30.0
+        try:
+            from hermes_cli.config import load_config
+            _cfg = load_config()
+            _vt = _cfg.get("auxiliary", {}).get("vision", {}).get("timeout")
+            if _vt is not None:
+                vision_timeout = float(_vt)
+        except Exception:
+            pass
         call_kwargs = {
             "task": "vision",
             "messages": messages,
             "temperature": 0.1,
             "max_tokens": 2000,
+            "timeout": vision_timeout,
         }
         if model:
             call_kwargs["model"] = model

website/docs/user-guide/configuration.md

@@ -907,6 +907,7 @@ 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
 
   # Web page summarization + browser page text extraction
   web_extract: