feat(opencode): configure vllm-qwen38 provider for local Qwen3.8-27B

pilot/cost_model.py

@@ -57,7 +57,7 @@ class Price:
     """Per-MTok prices. `cache_write` and `cache_read` are absolute rates, not
     multipliers, so providers with different cache economics stay comparable.
 
-    `provider` is the opencode provider name (`headroom`, `local`, ...). It
+    `provider` is the opencode provider name (`headroom`, `vllm-qwen38`, ...). It
     doubles as the dispatch key for `.pr-review.json:model` overrides — when
     a per-repo override is set, `_resolve_display_model` returns
     `f"{provider}/{key}"` so the opencode subprocess routes correctly.
@@ -98,12 +98,13 @@ PRICES: dict[str, Price] = {
     # xAI Grok — cache_write = input
     "grok-4.5": Price("Grok 4.5", 2.00, 6.00, 2.00, 0.30),
     "grok-4.3": Price("Grok 4.3", 1.25, 2.50, 1.25, 0.20),
-    # Self-hosted — local AI workstation, no per-token charge. provider="local"
-    # so the opencode subprocess routes via the `local` provider block in
-    # opencode.json (baseURL=http://192.168.1.79:18020/v1). Equivalent-cost
-    # column will read $0 — the cost-comparison signal is that the same work
-    # would bill $X on a paid model.
-    "qwen3.8-27b": Price("Qwen 3.8 27B (local)", 0.0, 0.0, 0.0, 0.0, provider="local"),
+    # Self-hosted — AI workstation RTX 3090, vLLM + DFlash2 spec-decode, no
+    # per-token charge. provider="vllm-qwen38" so the opencode subprocess
+    # routes via the matching provider block in opencode.json
+    # (baseURL=http://192.168.1.79:18020/v1). Equivalent-cost column reads $0
+    # — the cost-comparison signal is that the same work would bill $X on a
+    # paid model.
+    "qwen3.8-27b": Price("Qwen3.8-27B (vLLM, MTP, 150k ctx)", 0.0, 0.0, 0.0, 0.0, provider="vllm-qwen38"),
 }