feat(ai): discover the llama-swap picker and vision from model metadata

/insights/models now lists llama-swap's models live from /v1/models
instead of LLAMA_SWAP_ALLOWED_MODELS: every kind=chat model, with
setParamsByID aliases (:sub / :fast) hidden, filtered by
[llamacpp.picker] exclude and the optional include allowlist. Ids the
include list names but llama-swap no longer serves drop out instead of
showing as dead picker entries.

has_vision and context_window come from each model's config.yaml metadata
(read from meta.llamaswap, where the deployed llama-swap merges it, or from
meta as upstream documents). A model without metadata is text-only chat.
A live served window still wins over the configured ctx.

Agentic insights on llama-swap now ask the chat model's capabilities:
text-only models (e.g. qwen3.8-27b-code, --no-mmproj) get the local vision
model's description inlined, like hybrid, instead of an image they can't
read. If llama-swap can't be asked, images are sent as before.

Drops AppState.llamacpp_allowed_models.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

src/state.rs

@@ -78,10 +78,6 @@ pub struct AppState {
     /// threading through the generator.
     #[allow(dead_code)]
     pub llamacpp: Option<Arc<LlamaCppClient>>,
-    /// Curated list of llama-swap model ids exposed to clients. Sourced from
-    /// `LLAMA_SWAP_ALLOWED_MODELS` (comma-separated). Empty when unset; the
-    /// server then falls back to `LLAMA_SWAP_PRIMARY_MODEL`.
-    pub llamacpp_allowed_models: Vec<String>,
     pub sms_client: SmsApiClient,
     pub insight_generator: InsightGenerator,
     /// Chat continuation service. Hold an Arc so handlers can clone cheaply.
@@ -134,7 +130,6 @@ impl AppState {
         openrouter: Option<Arc<OpenRouterClient>>,
         openrouter_allowed_models: Vec<String>,
         llamacpp: Option<Arc<LlamaCppClient>>,
-        llamacpp_allowed_models: Vec<String>,
         sms_client: SmsApiClient,
         insight_generator: InsightGenerator,
         insight_chat: Arc<InsightChatService>,
@@ -196,7 +191,6 @@ impl AppState {
             openrouter,
             openrouter_allowed_models,
             llamacpp,
-            llamacpp_allowed_models,
             sms_client,
             insight_generator,
             insight_chat,
@@ -232,7 +226,6 @@ impl Default for AppState {
         let openrouter_allowed_models = llm.openrouter.allowed.clone();
 
         let llamacpp = build_llamacpp(llm);
-        let llamacpp_allowed_models = llm.llamacpp.picker.include.clone().unwrap_or_default();
 
         let sms_api_url =
             env::var("SMS_API_URL").unwrap_or_else(|_| "http://localhost:8000".to_string());
@@ -369,7 +362,6 @@ impl Default for AppState {
             openrouter,
             openrouter_allowed_models,
             llamacpp,
-            llamacpp_allowed_models,
             sms_client,
             insight_generator,
             insight_chat,
@@ -548,7 +540,6 @@ impl AppState {
             None,
             Vec::new(),
             None,
-            Vec::new(),
             sms_client,
             insight_generator,
             insight_chat,