Fix adaptive mode: model list + synthesizer dropdown were never populated

Two bugs preventing adaptive mode from working:
- ml-adaptive was missing from ML_IDS array (line 3160) — model checkboxes
  never rendered, so no models were selected
- adaptive-synthesizer was missing from populateAllSelects() ids array
  (line 3733) — synthesizer/judge dropdown was always empty

Both are single-line fixes. The backend pipeline (run_adaptive) was
complete and correct — self-eval, RAG retrieval, escalation, quality
scoring, KB storage all work. The UI just never wired the config.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

llm_team_ui.py

@@ -3157,7 +3157,7 @@ let availableModels = [];
 let currentMode = 'brainstorm';
 
 const modelSets = {};
-const ML_IDS = ['ml-brainstorm','ml-validator','ml-roundrobin','ml-consensus','ml-ladder','ml-tournament','ml-evolution','ml-blindassembly','ml-mesh','ml-hallucination','ml-research','ml-eval','ml-refine'];
+const ML_IDS = ['ml-brainstorm','ml-validator','ml-roundrobin','ml-consensus','ml-ladder','ml-tournament','ml-evolution','ml-blindassembly','ml-mesh','ml-hallucination','ml-research','ml-eval','ml-refine','ml-adaptive'];
 
 const MODE_DESCS = {
   brainstorm: 'All models answer in parallel, then one synthesizes the best parts.',
@@ -3736,6 +3736,7 @@ function populateAllSelects() {
     'staircase-challenger','drift-target','drift-analyzer','mesh-synthesizer','halluc-answerer',
     'timeloop-answerer','timeloop-chaos',
     'research-scout','research-checker','research-synth',
+    'adaptive-synthesizer',
     'eval-judge','extract-model','extract-verifier','refine-orchestrator'];
   ids.forEach(id => {
     const el = document.getElementById(id);