refactor: simplify config resolution and consolidate main.rs init (#287)

* refactor: simplify config resolution and consolidate main.rs init into AppBuilder

- Add parse_bool_env() and parse_string_env() helpers to eliminate repetitive
  5-line optional_env/parse/map_err/unwrap_or boilerplate across 12 config files
- Add EmbeddingsConfig::create_provider() to centralize embeddings construction
  (fixes hardcoded 1536 dimensions and missing Ollama provider in app.rs)
- Extract init_cli_tracing(), setup_wasm_channels(), start_tunnel(),
  run_memory_command(), run_worker(), run_claude_bridge() from main.rs
- Replace ~600 lines of inline init in main.rs with AppBuilder::build_all()
- Expose catalog_entries from AppComponents for gateway registry entries
- Net reduction: ~738 lines across 15 files

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: propagate dev_loaded_tool_names from AppBuilder and add parse_option_env helper

Address PR review feedback:

- Capture dev_loaded_tool_names from WASM loading in init_extensions()
  and expose via AppComponents so bootstrap_hooks receives the actual
  dev tool names instead of an empty slice (fixes silent hook skip)
- Add parse_option_env<T>() helper for Option<T> config fields,
  simplifying max_cost_per_day_cents and max_actions_per_hour in agent.rs

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: fetch real NEAR AI pricing and unify cost calculation path

CostGuard was independently looking up pricing via costs::model_cost(),
falling back to GPT-4o default rates when NEAR AI model names didn't
match the static table — causing ~3x cost overestimates in logs.

- Add pricing map to NearAiChatProvider that fetches real rates from
  /v1/model/list at startup (background, non-blocking)
- Update cost_per_token() to check fetched pricing first, then static
  table, then default
- Add cost_per_token parameter to CostGuard::record_llm_call() so the
  dispatcher passes provider-sourced rates directly

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* chore: update default NEAR AI model to GLM-latest

Replace fireworks llama4-maverick-instruct-basic with zai-org/GLM-latest
as the default model in config and setup wizard.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: align wizard default model name with config

Change "zai/GLM-latest" to "zai-org/GLM-latest" in wizard.rs to match
the default in config/llm.rs.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

---------

Co-authored-by: Claude Opus 4.6 <[email protected]>

src/agent/cost_guard.rs

@@ -151,14 +151,19 @@ impl CostGuard {
     /// Record a completed LLM action: its token costs and the action timestamp.
     ///
     /// Call this AFTER an LLM call completes so that costs are tracked.
+    ///
+    /// When `cost_per_token` is `Some`, those rates are used directly (provider-
+    /// sourced pricing). When `None`, falls back to the static `costs::model_cost`
+    /// lookup table, then `costs::default_cost`.
     pub async fn record_llm_call(
         &self,
         model: &str,
         input_tokens: u32,
         output_tokens: u32,
+        cost_per_token: Option<(Decimal, Decimal)>,
     ) -> Decimal {
-        let (input_rate, output_rate) =
-            costs::model_cost(model).unwrap_or_else(costs::default_cost);
+        let (input_rate, output_rate) = cost_per_token
+            .unwrap_or_else(|| costs::model_cost(model).unwrap_or_else(costs::default_cost));
         let cost =
             input_rate * Decimal::from(input_tokens) + output_rate * Decimal::from(output_tokens);
 
@@ -261,7 +266,9 @@ mod tests {
         assert!(guard.check_allowed().await.is_ok());
 
         // Record a big call, still allowed
-        guard.record_llm_call("gpt-4o", 100_000, 100_000).await;
+        guard
+            .record_llm_call("gpt-4o", 100_000, 100_000, None)
+            .await;
         assert!(guard.check_allowed().await.is_ok());
     }
 
@@ -278,7 +285,7 @@ mod tests {
         // Record a call that costs more than $0.01
         // gpt-4o: input=$0.0000025/tok, output=$0.00001/tok
         // 10000 input + 10000 output = $0.025 + $0.10 = $0.125
-        guard.record_llm_call("gpt-4o", 10_000, 10_000).await;
+        guard.record_llm_call("gpt-4o", 10_000, 10_000, None).await;
 
         // Now should be blocked
         let result = guard.check_allowed().await;
@@ -301,7 +308,7 @@ mod tests {
         // First 3 actions allowed
         for _ in 0..3 {
             assert!(guard.check_allowed().await.is_ok());
-            guard.record_llm_call("gpt-4o", 10, 10).await;
+            guard.record_llm_call("gpt-4o", 10, 10, None).await;
         }
 
         // 4th should be blocked
@@ -322,7 +329,7 @@ mod tests {
 
         assert_eq!(guard.daily_spend().await, Decimal::ZERO);
 
-        let cost = guard.record_llm_call("gpt-4o", 1000, 500).await;
+        let cost = guard.record_llm_call("gpt-4o", 1000, 500, None).await;
         assert!(cost > Decimal::ZERO);
         assert_eq!(guard.daily_spend().await, cost);
     }
@@ -333,8 +340,8 @@ mod tests {
 
         assert_eq!(guard.actions_this_hour().await, 0);
 
-        guard.record_llm_call("gpt-4o", 10, 10).await;
-        guard.record_llm_call("gpt-4o", 10, 10).await;
+        guard.record_llm_call("gpt-4o", 10, 10, None).await;
+        guard.record_llm_call("gpt-4o", 10, 10, None).await;
 
         assert_eq!(guard.actions_this_hour().await, 2);
     }
@@ -371,10 +378,10 @@ mod tests {
         assert!(guard.model_usage().await.is_empty());
 
         // Record calls for two different models
-        guard.record_llm_call("gpt-4o", 1000, 500).await;
-        guard.record_llm_call("gpt-4o", 2000, 1000).await;
+        guard.record_llm_call("gpt-4o", 1000, 500, None).await;
+        guard.record_llm_call("gpt-4o", 2000, 1000, None).await;
         guard
-            .record_llm_call("claude-3-5-sonnet-20241022", 500, 200)
+            .record_llm_call("claude-3-5-sonnet-20241022", 500, 200, None)
             .await;
 
         let usage = guard.model_usage().await;

src/agent/dispatcher.rs

@@ -222,6 +222,7 @@ impl Agent {
                     &model_name,
                     output.usage.input_tokens,
                     output.usage.output_tokens,
+                    Some(self.llm().cost_per_token()),
                 )
                 .await;
             tracing::debug!(