Otel: dedupe LLM span error/status + traceparent helpers (#130 follow-up)

Addresses the P2 refactoring follow-ups parked on issue #130:

- otel::with_traceparent(builder, &SpanContext) — one shared W3C
  traceparent injector. Replaces the 4-line inline header loop in
  llamacpp (3x) and openrouter (3x) and removes ollama's private
  inject_traceparent method (4 call sites now use the shared helper).
  Takes &SpanContext (not &dyn Span) because the Span trait is not dyn
  compatible in opentelemetry 0.31.

- otel::record_http_failure(span, status, message) and
  otel::set_http_status(span, status) — collapse the repeated
  'set http.status_code attribute + set_status(Status::error)'
  boilerplate across all three clients (~10 sites).

Net -45 lines. The remaining if-let-Some(span.as_mut()) guards (token
attributes, parse-failure status) stay inline rather than growing a
SpanHandle wrapper type for a pattern that's already readable.

src/ai/openrouter.rs

@@ -5,7 +5,7 @@
 use anyhow::Context as _;
 use anyhow::{Result, anyhow, bail};
 use async_trait::async_trait;
-use opentelemetry::trace::{Span, Status, TraceContextExt};
+use opentelemetry::trace::{Span, Status};
 use opentelemetry::{Context, KeyValue};
 use reqwest::Client;
 use serde::Deserialize;
@@ -397,11 +397,7 @@ impl LlmClient for OpenRouterClient {
         let mut request = self
             .authed(self.client.post(&url))
             .json(&Value::Object(body));
-        for (k, v) in crate::otel::traceparent_headers(
-            &Context::new().with_remote_span_context(span.span_context().clone()),
-        ) {
-            request = request.header(k, v);
-        }
+        request = crate::otel::with_traceparent(request, span.span_context());
         let resp = request
             .send()
             .await
@@ -409,17 +405,15 @@ impl LlmClient for OpenRouterClient {
 
         if !resp.status().is_success() {
             let status = resp.status();
-            span.set_attribute(KeyValue::new("http.status_code", status.as_u16() as i64));
-            span.set_status(Status::error(format!(
-                "OpenRouter stream request failed: {status}"
-            )));
+            crate::otel::record_http_failure(
+                Some(&mut span),
+                status.as_u16(),
+                &format!("OpenRouter stream request failed: {status}"),
+            );
             let body = resp.text().await.unwrap_or_default();
             bail!("OpenRouter stream request failed: {} — {}", status, body);
         }
-        span.set_attribute(KeyValue::new(
-            "http.status_code",
-            resp.status().as_u16() as i64,
-        ));
+        crate::otel::set_http_status(Some(&mut span), resp.status().as_u16());
 
         // OpenAI-compat SSE stream. Each event is `data: <json>\n\n`, with
         // `data: [DONE]` signalling completion. Tool calls arrive as
@@ -612,11 +606,7 @@ impl LlmClient for OpenRouterClient {
         });
 
         let mut request = self.authed(self.client.post(&url)).json(&body);
-        for (k, v) in crate::otel::traceparent_headers(
-            &Context::new().with_remote_span_context(span.span_context().clone()),
-        ) {
-            request = request.header(k, v);
-        }
+        request = crate::otel::with_traceparent(request, span.span_context());
         let resp = request
             .send()
             .await
@@ -627,17 +617,15 @@ impl LlmClient for OpenRouterClient {
 
         if !resp.status().is_success() {
             let status = resp.status();
-            span.set_attribute(KeyValue::new("http.status_code", status.as_u16() as i64));
-            span.set_status(Status::error(format!(
-                "OpenRouter embedding request failed: {status}"
-            )));
+            crate::otel::record_http_failure(
+                Some(&mut span),
+                status.as_u16(),
+                &format!("OpenRouter embedding request failed: {status}"),
+            );
             let body = resp.text().await.unwrap_or_default();
             bail!("OpenRouter embedding request failed: {} — {}", status, body);
         }
-        span.set_attribute(KeyValue::new(
-            "http.status_code",
-            resp.status().as_u16() as i64,
-        ));
+        crate::otel::set_http_status(Some(&mut span), resp.status().as_u16());
 
         #[derive(Deserialize)]
         struct EmbedResponse {
@@ -764,11 +752,7 @@ impl OpenRouterClient {
             .authed(self.client.post(&url))
             .json(&Value::Object(body));
         if let Some(s) = span.as_mut() {
-            for (k, v) in crate::otel::traceparent_headers(
-                &Context::new().with_remote_span_context(s.span_context().clone()),
-            ) {
-                request = request.header(k, v);
-            }
+            request = crate::otel::with_traceparent(request, s.span_context());
         }
         let resp = match request.send().await {
             Ok(r) => r,
@@ -782,21 +766,15 @@ impl OpenRouterClient {
 
         if !resp.status().is_success() {
             let status = resp.status();
-            if let Some(s) = span.as_mut() {
-                s.set_attribute(KeyValue::new("http.status_code", status.as_u16() as i64));
-                s.set_status(Status::error(format!(
-                    "OpenRouter chat request failed: {status}"
-                )));
-            }
+            crate::otel::record_http_failure(
+                span.as_deref_mut(),
+                status.as_u16(),
+                &format!("OpenRouter chat request failed: {status}"),
+            );
             let body = resp.text().await.unwrap_or_default();
             bail!("OpenRouter chat request failed: {} — {}", status, body);
         }
-        if let Some(s) = span.as_mut() {
-            s.set_attribute(KeyValue::new(
-                "http.status_code",
-                resp.status().as_u16() as i64,
-            ));
-        }
+        crate::otel::set_http_status(span.as_deref_mut(), resp.status().as_u16());
 
         let parsed: Value = match resp.json().await {
             Ok(v) => v,