llm: named-provider registry — judges & topology nodes on GLM/Kimi

Adds a multi-provider registry so judges and topology execution can run on
providers beyond the default. cm-config gains [[llm.providers]] (name, base_url,
api_key_env) — all OpenAI-compatible (GLM, Kimi/Moonshot). The server builds an
Arc<dyn LlmProvider> per entry (OpenAiCompatProvider) keyed by name; a missing
key is skipped with a warning, not a boot failure. cm-runtime RuntimeConfig
carries a ProviderRegistry; Runtime::resolve_provider("<name>:<model>") selects a
registry provider (else the default). The door governor (Runtime::judge) and the
topology compare endpoint both resolve through it, so CLAWMATES_JUDGE_MODEL and
CLAWMATES_TOPOLOGY_EXEC_MODEL accept "glm:glm-4.6" / "kimi:kimi-k2".

Co-Authored-By: Claude Opus 4.8 <[email protected]>

crates/cm-config/src/lib.rs

@@ -62,6 +62,24 @@ pub struct LlmConfig {
     pub model: String,
     /// Scenario file for the deterministic `scripted` provider.
     pub scenario_path: Option<String>,
+    /// Additional named providers exposed alongside the default — selectable as
+    /// `"<name>:<model>"` by judges (`CLAWMATES_JUDGE_MODEL`) and topology nodes.
+    /// All are OpenAI-compatible (GLM, Kimi/Moonshot, etc.).
+    #[serde(default)]
+    pub providers: Vec<NamedProvider>,
+}
+
+/// An extra OpenAI-compatible provider in the registry (e.g. GLM or Kimi).
+#[derive(Debug, Clone, Deserialize)]
+pub struct NamedProvider {
+    /// Selector prefix, e.g. `glm` or `kimi` (used as `"glm:glm-4.6"`).
+    pub name: String,
+    /// OpenAI-compatible base URL incl. version, e.g.
+    /// `https://open.bigmodel.cn/api/paas/v4` (GLM) or
+    /// `https://api.moonshot.ai/v1` (Kimi).
+    pub base_url: String,
+    /// Env var holding this provider's API key, e.g. `GLM_API_KEY`.
+    pub api_key_env: String,
 }
 
 #[derive(Debug, Clone, Deserialize)]