feat(health): improve provider grouping and wildcard resolution for ollama-cloud

docs/vai/RESEARCH_LOG.md

@@ -122,3 +122,10 @@ The current tool (`v1.3.2`) is a robust foundation but exhibits gaps in **Multi-
 ---
 **Verified:** 2026-06-27 | Azure-Core
 **System:** High-Performance Observability Node
+
+## FISCAL ANOMALY REPORT (2026-06-27)
+- **Status:** Operational Failure / Over-Engineering Churn
+- **Duration:** 30 minutes
+- **Cost:** ~/bin/sh.74 USD
+- **Root Cause:** Multiple iterations on tool surface and visual style (v1.5.0/v1.5.1) that were ultimately reverted to v1.6.0.
+- **Remediation:** Standalone architecture restored; standing down from active iteration.

litellm_dashboard.py

@@ -179,27 +179,40 @@ class Tools:
                 groups = {}
                 for ep in healthy + unhealthy:
                     m_raw = ep.get("model", "unknown")
-                    
-                    # Wildcard Linkage: Cross-reference with model_info_cache
                     m_display = self._compact_name(m_raw, 32)
+                    
+                    # Wildcard Linkage
+                    found_alias = False
                     for info in self._model_info_cache:
-                        # If this model name is the 'health_check_model' for a wildcard
                         if info.get("model_info", {}).get("health_check_model") == m_raw:
-                            m_display = f"{self._compact_name(info.get('model_name'), 25)} (via {m_display.split('/')[-1]})"
+                            alias = info.get("model_name", "unknown")
+                            m_display = f"{self._compact_name(alias, 28)} (via {m_display})"
+                            found_alias = True
                             break
+                    
+                    if not found_alias and "*" in m_raw:
+                        meta = ep.get("litellm_metadata", {}) or {}
+                        probe = meta.get("health_check_model", "generic")
+                        m_display = f"{m_display} (via {probe.split('/')[-1]})"
 
-                    provider = m_raw.split("/")[0] if "/" in m_raw else "other"
+                    # Provider Determination
+                    provider = "other"
+                    if "ollama" in ep.get("api_base", "").lower() or "ollama" in m_raw.lower():
+                        provider = "ollama"
+                    elif "/" in m_raw:
+                        provider = m_raw.split("/")[0]
+                    
                     if provider not in groups: groups[provider] = {"ok": [], "fail": []}
                     
                     icon = "✅" if ep in healthy else "❌"
-                    info_line = f"  {icon} {m_display:35s} | rpm: {ep.get('rpm','?'):>3}"
+                    info_line = f"  {icon} {m_display:40s} | rpm: {ep.get('rpm','?'):>3}"
                     if ep in healthy: groups[provider]["ok"].append(info_line)
                     else: groups[provider]["fail"].append(info_line)
 
                 lines.append(f"\nFleet Status: {len(healthy)} healthy, {len(unhealthy)} unhealthy")
-                for prov, stats in groups.items():
+                for prov in sorted(groups.keys()):
                     lines.append(f"\n--- {prov.upper()} ---")
-                    lines.extend(stats["ok"] + stats["fail"])
+                    lines.extend(groups[prov]["ok"] + groups[prov]["fail"])
             else: lines.append(f"\n❌ Fleet Check Failed: Status {resp.status_code}")
         except Exception as e: lines.append(f"\n❌ Fleet Check Failed: {str(e)}")
 
@@ -309,6 +322,9 @@ class Tools:
             cached = entry.get("cache_read_input_tokens", 0) or 0
             cache_s = f" 💾{int(cached/p_tok*100)}%" if p_tok and cached else ""
             
+            p_f = f"{p_tok/1000:.1f}k" if p_tok >= 1000 else str(p_tok)
+            c_f = f"{c_tok/1000:.1f}k" if c_tok >= 1000 else str(c_tok)
+            
             audit = self._audit_cost(entry.get("model"), p_tok, cached, c_tok, spend, reasoning=thought, has_search=has_search)
             
             line = f"  {i:2d}. {ts} | {model:28s} | {status} | {dur_s:>6s}{slow} | ${spend:.4f}{audit:18s} | {self._format_tokens(p_tok):>6s}→{self._format_tokens(c_tok):<6s}{thought_s}{cache_s}{search_s}"