feat: add family-based chat templates

autoresearch-dashboard.md

@@ -1,14 +1,9 @@
-# Autoresearch Dashboard: latency-p95-chat-completions
+# Autoresearch Dashboard: dynamic-chat-templates
 
-**Runs:** 6 | **Kept:** 2 | **Discarded:** 4 | **Crashed:** 0
-**Baseline:** p95_ms: 941.252ms (#1)
-**Best:** p95_ms: 925.587ms (#6, -1.7%)
+**Runs:** 1 | **Kept:** 1 | **Discarded:** 0 | **Crashed:** 0
+**Baseline:** template_score: 20.0% (#7)
+**Best:** template_score: 20.0% (#7, +0.0%)
 
-| # | commit | p95_ms | status | description |
-|---|--------|--------|--------|-------------|
-| 1 | ceed0e5 | 941.252ms (+0.0%) | keep | baseline |
-| 2 | 5269f43 | 1032.315ms (+9.7%) | discard | use stack buffer for token detokenization |
-| 3 | 994e607 | 1004.435ms (+6.7%) | discard | slim turbo4b runtime profile |
-| 4 | db92212 | 3027.145ms (+221.6%) | discard | switch to qwen-style chat template |
-| 5 | caf4654 | 965.663ms (+2.6%) | discard | stop generation on default turn boundaries |
-| 6 | e8402d2 | 925.587ms (-1.7%) | keep | disable llama perf counters in hot path |
+| # | commit | template_score | status | description |
+|---|--------|----------------|--------|-------------|
+| 7 | 89ef220 | 20.0% (+0.0%) | keep | baseline |