feat(cost_model): add provider field on Price + register qwen3.8-27b (local)

pilot/cost_model.py

@@ -55,13 +55,20 @@ CHARS_PER_TOKEN = 4  # English prose/code rule of thumb; ±15% is normal
 @dataclass(frozen=True)
 class Price:
     """Per-MTok prices. `cache_write` and `cache_read` are absolute rates, not
-    multipliers, so providers with different cache economics stay comparable."""
+    multipliers, so providers with different cache economics stay comparable.
+
+    `provider` is the opencode provider name (`headroom`, `local`, ...). 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.
+    Default `headroom` preserved for the existing roster."""
 
     name: str
     input: float
     output: float
     cache_write: float
     cache_read: float
+    provider: str = "headroom"
 
     @property
     def batch_input(self) -> float:
@@ -91,6 +98,12 @@ 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"),
 }