v2.3.0: adaptive Crof self-healing system

- Per-model success/failure tracking with dynamic item limits
- Proactive compaction when above learned limit
- Auto-retry on finish_reason=length with aggressive re-compaction
- Tested: kimi-k2.6 (27 items) and mimo-v2.5-pro both completed
- All previous fixes included: _ts crash, connection reset, timeout, orphaned fco

CHANGELOG.md

@@ -1,5 +1,20 @@
 # Changelog
 
+## v2.3.0 (2026-05-20)
+
+- **Adaptive Crof self-healing system**
+  - Tracks per-model success/failure history with item counts
+  - Dynamically learns max item limit per model (starts at 30, adjusts down on failures)
+  - Proactively compacts input when above learned limit before sending to upstream
+  - Auto-retry on `finish_reason=length` with aggressive re-compaction and resend
+  - Prevents `stream disconnected` and `incomplete` errors on long conversations
+  - All tracking logged to stderr: `[crof-adaptive] model=X items=N OK/FAIL -> limit=N`
+- Fixed `NameError: _ts` crash in debug logging
+- Fixed `ConnectionResetError` crash on client disconnect during streaming
+- Added 180s upstream timeout to prevent hanging connections
+- Compaction now preserves function_call/function_call_output pairs (no orphaned tool outputs)
+- Fixed reasoning control: `reasoning_effort=none` always sends both params
+
 ## v2.2.1 (2026-05-20)
 
 - **Fixed compaction orphaning function_call_output items** — root cause of Crof `incomplete` responses