fix(planner): the other four server-side calls were still on the metered key

The test that was supposed to prevent this grepped for the literal
`runtime.complete(` and passed while the phase planner (`mission_plan.rs`),
both swarm calls, and a second enhance path in `claws.rs` still billed the
pay-as-you-go account. They spell the receiver `state.runtime` or wrap the
call across lines, so the receiver name was never the thing to match. The
test now matches the METHOD, and covers all five files.

`complete_or` gains the rule that makes it safe to apply everywhere: a
`name:model` spec is an operator's explicit provider choice — the swarm
worker model is configured exactly that way — and is passed straight to
`Runtime::resolve_provider` untouched. Only a bare name is ambiguous, and a
bare name is precisely what resolves to the default provider. Hijacking a
chosen Kimi or GLM model onto Anthropic would be the same silent-substitution
bug pointed the other way.

`validator_preflight` and the evaluator judge keep calling the runtime
directly, on purpose: both exist to exercise the CONFIGURED spec.

Co-Authored-By: Claude Opus 5 <[email protected]>

crates/cm-api/src/routes/claws.rs

@@ -660,9 +660,15 @@ pub(crate) async fn enhance_and_publish(
     let user_prompt = format!(
         "ROLE CONTEXT: {role_context}\n\nBRAIN: {reference}\n\n=== SYSTEM PROMPT ===\n{sp}\n\n=== AGENTS.md ===\n{agent_md}\n\n=== PERSONA ===\n{persona}\n\n=== SKILLS ===\n{skills}"
     );
-    let raw = runtime
-        .complete(ENHANCE_SYSTEM, &user_prompt, "claude-opus-4-8", 16000, true)
-        .await?;
+    let raw = crate::subscription::complete_or(
+        runtime,
+        ENHANCE_SYSTEM,
+        &user_prompt,
+        "claude-opus-4-8",
+        16000,
+        true,
+    )
+    .await?;
     let v = extract_json(&raw).ok_or_else(|| "unparseable enhance output".to_string())?;
     let enh = v.get("enhanced").cloned().unwrap_or(Value::Null);
     let field = |k: &str| {