fix: 6 bugs in model metadata, reasoning detection, and delegate tool

Cherry-picked from PR #2169 by @0xbyt4.

1. _strip_provider_prefix: skip Ollama model:tag names (qwen:0.5b)
2. Fuzzy match: remove reverse direction that made claude-sonnet-4
   resolve to 1M instead of 200K
3. _has_content_after_think_block: reuse _strip_think_blocks() to
   handle all tag variants (thinking, reasoning, REASONING_SCRATCHPAD)
4. models.dev lookup: elif→if so nous provider also queries models.dev
5. Disk cache fallback: use 5-min TTL instead of full hour so network
   is retried soon
6. Delegate build: wrap child construction in try/finally so
   _last_resolved_tool_names is always restored on exception

agent/models_dev.py

@@ -107,11 +107,12 @@ def fetch_models_dev(force_refresh: bool = False) -> Dict[str, Any]:
     except Exception as e:
         logger.debug("Failed to fetch models.dev: %s", e)
 
-    # Fall back to disk cache
+    # Fall back to disk cache — use a short TTL (5 min) so we retry
+    # the network fetch soon instead of serving stale data for a full hour.
     if not _models_dev_cache:
         _models_dev_cache = _load_disk_cache()
         if _models_dev_cache:
-            _models_dev_cache_time = time.time()
+            _models_dev_cache_time = time.time() - _MODELS_DEV_CACHE_TTL + 300
             logger.debug("Loaded models.dev from disk cache (%d providers)", len(_models_dev_cache))
 
     return _models_dev_cache