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/packages/harness/deerflow/config/memory_config.py

@@ -1,5 +1,7 @@
 """Configuration for memory mechanism."""
 
+from typing import Literal
+
 from pydantic import BaseModel, Field
 
 
@@ -60,6 +62,17 @@ class MemoryConfig(BaseModel):
         le=8000,
         description="Maximum tokens to use for memory injection",
     )
+    token_counting: Literal["tiktoken", "char"] = Field(
+        default="tiktoken",
+        description=(
+            "Token counting strategy for memory-injection budgeting. "
+            "'tiktoken' is accurate but the encoding's BPE data may be "
+            "downloaded from a public network endpoint on first use, which "
+            "can block for a long time in network-restricted environments "
+            "(see issue #3402/#3429). 'char' uses a network-free "
+            "CJK-aware character-based estimate and never touches tiktoken."
+        ),
+    )
 
 
 # Global configuration instance