Add context awareness: token tracker + compaction + 6GB GPU tier

Context management for local models with limited windows:
- Context Tracker (community function): shows tokens used vs available,
  progress bar, percentage remaining — so you see the cliff coming
- Checkpoint Summarization Filter: auto-summarizes old messages when
  context fills up, like Claude's auto-compaction
- Both added as recommended post-install links in setup output
  (Open WebUI Functions install with one click from the UI)

6GB GPU tier (Quadro P3300, GTX 1060, etc.):
- Qwen 3.5 4B at Q4_K_M = ~2.5GB weights, leaves 3.5GB for KV cache
- With Q8 KV cache: ~32K usable context on 6GB
- Better than squeezing 9B into nothing — more context > slightly smarter

https://claude.ai/code/session_01PtYTPherSJaxDEVPgF6Nxu

ubuntu-post-install.sh

@@ -1125,6 +1125,9 @@ elif [[ "$TOTAL_VRAM" -ge 14 ]]; then
 elif [[ "$TOTAL_VRAM" -ge 8 ]]; then
     CHAT_MODEL="qwen3.5:9b";  CODE_MODEL="qwen3.5:9b"
     CTX=32768;  TIER="${TOTAL_VRAM}GB — 9B dense, 32K context"
+elif [[ "$TOTAL_VRAM" -ge 6 ]]; then
+    CHAT_MODEL="qwen3.5:4b";  CODE_MODEL="qwen3.5:4b"
+    CTX=32768;  TIER="${TOTAL_VRAM}GB — 4B + KV quant, 32K context"
 elif [[ "$TOTAL_VRAM" -ge 4 ]]; then
     CHAT_MODEL="qwen3.5:4b";  CODE_MODEL="qwen3.5:4b"
     CTX=16384;  TIER="${TOTAL_VRAM}GB — 4B models, 16K context"