feat(config): rewire model roles to frank-small/frank-large + NPU flm provider

- models.yml: rename frank-default-small -> frank-small (dankserver),
  frank-default-large -> frank-large (dankclaw-gpu, text-only input);
  add 'flm (dankclaw-npu)' provider with gemma4-it:e4b and nuextract3:4b.
- config.yml: point modelRoles at renamed models; vision -> nuextract3:4b:auto,
  tiny/task -> gemma4-it:e4b:off; compaction reorder (snapcompact added,
  idleThresholdTokens 200k->100k, thresholdPercent -1->85); hideThinkingBlock true;
  statusline transparency + compact thinking level; images.urls backends list.

agent/models.yml

@@ -7,12 +7,12 @@ providers:
     api: openai-completions
     auth: none
     models:
-      - id: frank-default-small
-        name: "frank-default-small (Qwen3.6-35B-A3B FP8, FreeToken RTX3090, moe-cache 2048)"
-        contextWindow: 204800
-        maxTokens: 204800
+      - id: frank-small
+        name: "frank-small (dankserver)"
+        contextWindow: 262144
+        maxTokens: 262144
         reasoning: true
-        input: [text, image]
+        input: [text]
         compat:
           reasoningEffortMap:
             max: xhigh
@@ -22,12 +22,34 @@ providers:
     api: openai-completions
     auth: none
     models:
-      - id: frank-default-large
-        name: "frank-default-large (Qwen3.8-Flash-Next Q4_0 ROCmFP4 Strix, froggeric-v22.4.0 template)"
-        contextWindow: 262144
-        maxTokens: 262144
+      - id: frank-large
+        name: "frank-large (dankclaw-gpu)"
+        contextWindow: 200000
+        maxTokens: 200000
+        reasoning: true
+        input: [text]
+        compat:
+          reasoningEffortMap:
+            max: xhigh
+
+  "flm (dankclaw-npu)":
+    baseUrl: http://192.168.0.143:7771/v1
+    api: openai-completions
+    auth: none
+    models:
+      - id: gemma4-it:e4b
+        name: "gemma4-it:e4b (dankclaw-npu)"
+        contextWindow: 131072
+        maxTokens: 131072
         reasoning: true
         input: [text, image]
         compat:
           reasoningEffortMap:
             max: xhigh
+
+      - id: nuextract3:4b
+        name: "nuextract3:4b (dankclaw-npu extraction)"
+        contextWindow: 32768
+        maxTokens: 32768
+        reasoning: false
+        input: [text]