Changeset 0.9.1 (#51)

server/providers/anthropic.go

@@ -170,7 +170,7 @@ func (p *AnthropicProvider) ListModels(_ context.Context, _ ProviderConfig) ([]M
 
 	out := make([]Model, 0, len(modelIDs))
 	for _, m := range modelIDs {
-		caps, _ := capabilities.LookupKnownModel(m.id)
+		caps := capabilities.InferCapabilities(m.id)
 		out = append(out, Model{
 			ID:           m.id,
 			Name:         m.name,

server/providers/openai.go

@@ -193,11 +193,8 @@ func (p *OpenAIProvider) ListModels(ctx context.Context, cfg ProviderConfig) ([]
 
 	out := make([]Model, 0, len(result.Data))
 	for _, m := range result.Data {
-		// Try known table first, then heuristic
-		caps, found := capabilities.LookupKnownModel(m.ID)
-		if !found {
-			caps = capabilities.InferCapabilities(m.ID)
-		}
+		// Heuristic inference from model ID
+		caps := capabilities.InferCapabilities(m.ID)
 		// Use context_length from API if available and we don't have it
 		if m.ContextLength > 0 && caps.MaxContext == 0 {
 			caps.MaxContext = m.ContextLength

server/providers/openrouter.go

@@ -69,11 +69,8 @@ func (p *OpenRouterProvider) ListModels(ctx context.Context, cfg ProviderConfig)
 
 	out := make([]Model, 0, len(result.Data))
 	for _, m := range result.Data {
-		// Start with known table, fall back to heuristic
-		caps, found := capabilities.LookupKnownModel(m.ID)
-		if !found {
-			caps = capabilities.InferCapabilities(m.ID)
-		}
+		// Heuristic inference from model ID
+		caps := capabilities.InferCapabilities(m.ID)
 
 		// Overlay context length from OpenRouter metadata
 		if m.ContextLength > 0 && caps.MaxContext == 0 {

server/providers/venice.go

@@ -1,7 +1,6 @@
 package providers
 
 import (
-	"git.gobha.me/xcaliber/chat-switchboard/capabilities"
 	"git.gobha.me/xcaliber/chat-switchboard/models"
 	"context"
 	"encoding/json"
@@ -80,10 +79,7 @@ func (p *VeniceProvider) ListModels(ctx context.Context, cfg ProviderConfig) ([]
 		}
 
 		// Venice doesn't report max output tokens directly.
-		// Try known table, then derive from context.
-		if known, ok := capabilities.LookupKnownModel(m.ID); ok && known.MaxOutputTokens > 0 {
-			caps.MaxOutputTokens = known.MaxOutputTokens
-		}
+		// ResolveMaxOutput will derive from context window at resolution time.
 
 		var pricing *models.ModelPricing
 		if spec.Pricing.Input.USD > 0 {