feat(memory): add memory.token_counting config to avoid tiktoken network dependency (#3429) (#3465)

* feat(memory): add memory.token_counting config to avoid tiktoken network dependency (#3429)

Add a `memory.token_counting` option (`tiktoken` | `char`) so deployments in
network-restricted environments can opt out of tiktoken entirely. In `char`
mode the memory-injection budget uses a network-free character-based estimate
and never triggers the BPE download from openaipublic.blob.core.windows.net,
which could otherwise block for tens of minutes (see #3402).

Also harden the default `tiktoken` path:
- cache an in-flight LOADING sentinel so concurrent callers fall back
  immediately instead of spawning more blocking get_encoding threads when the
  first load is still running (e.g. under the 5s startup warm-up timeout);
- cache failures with a timestamp and retry after a cooldown so a transient
  network outage self-heals back to accurate counting without a restart;
- skip startup warm-up entirely in char mode.

The new config is surfaced via the memory config API and config.example.yaml
(config_version bumped). Default remains `tiktoken`, so existing deployments
are unaffected.

* fix(memory): use CJK-aware char token estimate and address review feedback

- Replace the flat len(text)//4 fallback with a CJK-aware estimate so
  Chinese/Japanese/Korean memory content does not over-fill the injection budget
- Document the internal tiktoken retry cooldown and char-mode escape hatch
- Sync CLAUDE.md / config.example.yaml / MEMORY_IMPROVEMENTS.md wording
- Fix MemoryConfigResponse mocks/assertions and add CJK estimate tests

backend/tests/test_lead_agent_prompt.py

@@ -192,7 +192,7 @@ def test_build_acp_section_uses_explicit_app_config_without_global_config(monkey
 
 def test_get_memory_context_uses_explicit_app_config_without_global_config(monkeypatch):
     explicit_config = SimpleNamespace(
-        memory=SimpleNamespace(enabled=True, injection_enabled=True, max_injection_tokens=1234),
+        memory=SimpleNamespace(enabled=True, injection_enabled=True, max_injection_tokens=1234, token_counting="tiktoken"),
     )
     captured: dict[str, object] = {}
 
@@ -204,9 +204,10 @@ def test_get_memory_context_uses_explicit_app_config_without_global_config(monke
         captured["user_id"] = user_id
         return {"facts": []}
 
-    def fake_format_memory_for_injection(memory_data, *, max_tokens):
+    def fake_format_memory_for_injection(memory_data, *, max_tokens, use_tiktoken=True):
         captured["memory_data"] = memory_data
         captured["max_tokens"] = max_tokens
+        captured["use_tiktoken"] = use_tiktoken
         return "remember this"
 
     monkeypatch.setattr("deerflow.config.memory_config.get_memory_config", fail_get_memory_config)
@@ -223,6 +224,7 @@ def test_get_memory_context_uses_explicit_app_config_without_global_config(monke
         "user_id": "user-1",
         "memory_data": {"facts": []},
         "max_tokens": 1234,
+        "use_tiktoken": True,
     }