ai: collapse llamacpp into LLM_BACKEND env switch

Reverts the per-request backend="llamacpp" value. Chat/vision/embedding
backend is now a deploy-time decision (LLM_BACKEND=ollama|llamacpp),
applied globally across chat, vision describe, and embeddings — so
embedding vectors stay in one space across the index.

- Per-request backend whitelist back to "local"|"hybrid". A request
  arriving with backend="llamacpp" is rejected.
- LLM_BACKEND=llamacpp swaps the entire local stack to llama-swap:
  chat hits the chat slot, describe hits the vision slot, embeddings
  hit the embed slot. Hybrid mode still routes chat to OpenRouter
  but uses LLM_BACKEND for the describe pass.
- Drops env vars HYBRID_VISION_BACKEND, LLAMA_SWAP_VISION_MODELS,
  EMBEDDING_BACKEND (the last never shipped). Drops the
  LlamaCppClient.vision_models allowlist — capability inference now
  reports has_vision only for the configured vision_model slot.
- Drops the /insights/llamacpp/models handler. /insights/models is
  the single endpoint; returns Ollama servers under LLM_BACKEND=ollama
  and llama-swap slots (from LLAMA_SWAP_ALLOWED_MODELS) under
  LLM_BACKEND=llamacpp. Same envelope shape either way.
- New ai::embed_one helper routes embeddings through llama-swap when
  LLM_BACKEND=llamacpp (else Ollama). Wires it into the four
  insight_generator embedding sites.
- Cross-replay matrix simplifies to pre-llamacpp shape (local↔local,
  hybrid↔hybrid, hybrid→local allowed; local→hybrid rejected).

src/ai/handlers.rs

@@ -470,7 +470,16 @@ pub async fn generate_agentic_insight_handler(
     }
 }
 
-/// GET /insights/models - List available models from both servers with capabilities
+/// GET /insights/models - Local-backend models with capabilities. Returns
+/// Ollama servers when `LLM_BACKEND=ollama` (default), or llama-swap slots
+/// when `LLM_BACKEND=llamacpp`. Same envelope shape either way so the
+/// client picker doesn't have to branch on backend kind.
+///
+/// For llama-swap: `models` comes verbatim from `LLAMA_SWAP_ALLOWED_MODELS`
+/// (no live `/v1/models` probe), `has_vision` is true only for the
+/// configured `LLAMA_SWAP_VISION_MODEL` slot id, and `has_tool_calling` is
+/// reported as true for every slot (llama-server is launched with `--jinja`
+/// by convention — a misconfigured slot surfaces as a chat-call error).
 #[get("/insights/models")]
 pub async fn get_available_models_handler(
     _claims: Claims,
@@ -478,6 +487,29 @@ pub async fn get_available_models_handler(
 ) -> impl Responder {
     log::debug!("Fetching available models with capabilities");
 
+    if crate::ai::local_backend_is_llamacpp()
+        && let Some(lc) = app_state.llamacpp.as_ref()
+    {
+        let models: Vec<ModelCapabilities> = app_state
+            .llamacpp_allowed_models
+            .iter()
+            .map(|name| ModelCapabilities {
+                name: name.clone(),
+                has_vision: name == &lc.vision_model,
+                has_tool_calling: true,
+            })
+            .collect();
+        let primary = ServerModels {
+            url: lc.base_url.clone(),
+            models,
+            default_model: lc.primary_model.clone(),
+        };
+        return HttpResponse::Ok().json(AvailableModelsResponse {
+            primary,
+            fallback: None,
+        });
+    }
+
     let ollama_client = &app_state.ollama;
 
     // Fetch models with capabilities from primary server
@@ -549,36 +581,6 @@ pub async fn get_openrouter_models_handler(
     HttpResponse::Ok().json(response)
 }
 
-#[derive(serde::Serialize)]
-pub struct LlamaCppModelsResponse {
-    pub models: Vec<String>,
-    pub default_model: Option<String>,
-    pub configured: bool,
-}
-
-/// GET /insights/llamacpp/models - Curated llama-swap model ids exposed
-/// to clients for the llamacpp backend. Returned verbatim from
-/// `LLAMA_SWAP_ALLOWED_MODELS`; no live call to llama-swap. Use
-/// `LLAMA_SWAP_URL` plus `LLAMA_SWAP_PRIMARY_MODEL` on the server side to
-/// pick the actual chat slot.
-#[get("/insights/llamacpp/models")]
-pub async fn get_llamacpp_models_handler(
-    _claims: Claims,
-    app_state: web::Data<crate::state::AppState>,
-) -> impl Responder {
-    let configured = app_state.llamacpp.is_some();
-    let default_model = app_state
-        .llamacpp
-        .as_ref()
-        .map(|c| c.primary_model.clone());
-    let response = LlamaCppModelsResponse {
-        models: app_state.llamacpp_allowed_models.clone(),
-        default_model,
-        configured,
-    };
-    HttpResponse::Ok().json(response)
-}
-
 /// POST /insights/rate - Rate an insight (thumbs up/down for training data)
 #[post("/insights/rate")]
 pub async fn rate_insight_handler(