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_client.py

@@ -2472,6 +2472,7 @@ class TestGatewayConformance:
         mem_cfg.fact_confidence_threshold = 0.7
         mem_cfg.injection_enabled = True
         mem_cfg.max_injection_tokens = 2000
+        mem_cfg.token_counting = "tiktoken"
 
         with patch("deerflow.config.memory_config.get_memory_config", return_value=mem_cfg):
             result = client.get_memory_config()
@@ -2479,6 +2480,7 @@ class TestGatewayConformance:
         parsed = MemoryConfigResponse(**result)
         assert parsed.enabled is True
         assert parsed.max_facts == 100
+        assert parsed.token_counting == "tiktoken"
 
     def test_get_memory_status(self, client):
         mem_cfg = MagicMock()
@@ -2489,6 +2491,7 @@ class TestGatewayConformance:
         mem_cfg.fact_confidence_threshold = 0.7
         mem_cfg.injection_enabled = True
         mem_cfg.max_injection_tokens = 2000
+        mem_cfg.token_counting = "tiktoken"
 
         memory_data = {
             "version": "1.0",
@@ -2514,6 +2517,7 @@ class TestGatewayConformance:
 
         parsed = MemoryStatusResponse(**result)
         assert parsed.config.enabled is True
+        assert parsed.config.token_counting == "tiktoken"
         assert parsed.data.version == "1.0"