Improve AI provider model configuration

app/src/ai/acp/launch.rs

@@ -1,4 +1,7 @@
-use galaxy_acp::{AcpAgentPreset, AcpLaunchConfig, CODEX_ACP_NPM_VERSION, OPENCODE_NPM_VERSION};
+use galaxy_acp::{
+    resolve_known_acp_agent, AcpAgentPreset, AcpLaunchConfig, CODEX_ACP_NPM_VERSION,
+    OPENCODE_NPM_VERSION,
+};
 use sha2::{Digest as _, Sha256};
 
 use crate::persistence::model::AcpConversationData;
@@ -215,9 +218,11 @@ pub(crate) fn resolve_acp_launch(
     match agent_id.trim().to_ascii_lowercase().as_str() {
         "codex" => AcpAgentPreset::Codex.resolve_launch_config(),
         "opencode" => AcpAgentPreset::OpenCode.resolve_launch_config(),
-        unknown => Err(format!(
-            "Unknown ACP agent preset {unknown:?}; choose \"codex\" or \"opencode\", or configure a custom ACP executable"
-        )),
+        _ => resolve_known_acp_agent(agent_id).map_err(|error| {
+            format!(
+                "{error} Configure a custom ACP executable if this client uses a different command."
+            )
+        }),
     }
 }
 

app/src/ai/acp/launch_tests.rs

@@ -4,7 +4,7 @@ use super::*;
 fn unknown_builtin_agent_ids_are_rejected() {
     let error = resolve_acp_launch("mystery-agent", "", &[]).unwrap_err();
 
-    assert!(error.contains("Unknown ACP agent preset"));
+    assert!(error.contains("Unknown ACP agent"));
 }
 
 #[test]

app/src/ai/llms.rs

@@ -509,7 +509,7 @@ fn default_computer_use_llms() -> AvailableLLMs {
             },
             description: None,
             disable_reason: None,
-            vision_supported: true,
+            vision_supported: false,
             spec: None,
             provider: LLMProvider::Unknown,
             host_configs: HashMap::new(),
@@ -1164,7 +1164,7 @@ impl LLMPreferences {
                         },
                         description: Some(provider_name.clone()),
                         disable_reason: None,
-                        vision_supported: model.vision_supported,
+                        vision_supported: model.effective_vision_supported(),
                         spec: None,
                         provider: LLMProvider::LiteLLM,
                         host_configs: HashMap::from([(
@@ -1670,13 +1670,14 @@ impl LLMPreferences {
             .map(|model| OpenAIModelConfig {
                 model_id: model.id,
                 display_name: model.display_name,
-                vision_supported: false,
+                vision_supported: true,
                 context_size: model.context_size.unwrap_or(128_000),
                 max_input_tokens: model.context_size,
                 max_output_tokens: None,
                 provider: None,
                 use_rig: true,
                 supports_system_messages: Some(true),
+                capability_overrides: std::collections::HashMap::new(),
                 reasoning_efforts: Vec::new(),
                 enabled: true,
             })
@@ -2594,7 +2595,7 @@ async fn fetch_from_litellm_model_info(
                 .and_then(|v| u32::try_from(v).ok());
             let context_size = max_input_tokens.unwrap_or(200_000);
 
-            let vision_supported = model_info["supports_vision"].as_bool().unwrap_or(false);
+            let vision_supported = model_info["supports_vision"].as_bool().unwrap_or(true);
 
             let display_name = model_name.replace(['-', '_'], " ");
             let display_name = display_name
@@ -2651,6 +2652,7 @@ async fn fetch_from_litellm_model_info(
                 } else {
                     model_info["supports_system_messages"].as_bool()
                 },
+                capability_overrides: std::collections::HashMap::new(),
                 reasoning_efforts: Vec::new(),
                 enabled: true,
             })
@@ -2769,7 +2771,7 @@ async fn fetch_from_openai_models(
                 vision_supported: m["supports_vision"]
                     .as_bool()
                     .or_else(|| m["vision_support"].as_bool())
-                    .unwrap_or(false),
+                    .unwrap_or(true),
                 context_size,
                 max_input_tokens,
                 max_output_tokens,
@@ -2780,6 +2782,7 @@ async fn fetch_from_openai_models(
                 } else {
                     m["supports_system_messages"].as_bool()
                 },
+                capability_overrides: std::collections::HashMap::new(),
                 reasoning_efforts: Vec::new(),
                 enabled: true,
             })

app/src/ai/llms_tests.rs

@@ -152,6 +152,7 @@ fn openai_model(model_id: &str) -> OpenAIModelConfig {
         provider: None,
         use_rig: false,
         supports_system_messages: None,
+        capability_overrides: std::collections::HashMap::new(),
         reasoning_efforts: Vec::new(),
         enabled: true,
     }