fix(agent): scope Ollama/GLM stop-to-length heuristic to Ollama only

The _is_ollama_glm_backend() function was too broad: any local endpoint
running a GLM model was treated as Ollama, triggering the stop->length
misreport heuristic introduced in 8011aa3. This caused false truncation
detection on sglang, vLLM, LM Studio, and other non-Ollama servers that
correctly report finish_reason.

When a GLM model on sglang/vLLM returned finish_reason='stop', the agent
mistakenly reclassified it as 'length' if the response didn't end with
a whitelisted punctuation character (ASCII or CJK). This particularly
affected Chinese-language responses and Markdown-formatted text.

Root cause: the is_local_endpoint() fallback assumed any local GLM
endpoint = Ollama. But many non-Ollama servers also run on localhost.

Fix: remove the is_local_endpoint() catch-all. Only detect Ollama via
its distinctive signatures (port 11434, 'ollama' in URL). All other
local servers are assumed to report finish_reason correctly.

This is the correct tradeoff because:
- False negatives (Ollama at custom port, heuristic not triggered) only
  mean the user sees a truncated response — same as having no heuristic
- False positives (non-Ollama server, heuristic wrongly triggered) inject
  spurious continuation messages into the conversation — strictly worse

Adds two tests:
- sglang GLM response is NOT reclassified as truncated
- Ollama GLM on port 11434 still triggers the heuristic as before

Co-authored-by: Hermes Agent <hermes@nousresearch.com>

run_agent.py

@@ -1367,14 +1367,26 @@ class AIAgent:
         return False
 
     def _is_ollama_glm_backend(self) -> bool:
-        """Detect the narrow backend family affected by Ollama/GLM stop misreports."""
+        """Detect the narrow backend family affected by Ollama/GLM stop misreports.
+
+        Only returns True for backends that are known to be Ollama, which
+        can misreport truncated output as finish_reason='stop'.  Other local
+        servers (sglang, vLLM, LM Studio, etc.) report finish_reason correctly
+        and must NOT be subjected to the stop->length heuristic.
+
+        Detection relies on explicit Ollama signatures:
+        - Port 11434 (Ollama default)
+        - "ollama" in the base URL (e.g. ollama.local, /ollama/ path)
+
+        The previous is_local_endpoint() fallback was too broad and caused
+        false truncation detection on non-Ollama local servers hosting GLM
+        models (sglang, vLLM, etc.).
+        """
         model_lower = (self.model or "").lower()
         provider_lower = (self.provider or "").lower()
         if "glm" not in model_lower and provider_lower != "zai":
             return False
-        if "ollama" in self._base_url_lower or ":11434" in self._base_url_lower:
-            return True
-        return bool(self.base_url and is_local_endpoint(self.base_url))
+        return "ollama" in self._base_url_lower or ":11434" in self._base_url_lower
 
     def _should_treat_stop_as_truncated(
         self,