M1/F2+F4: platform registry, Moonshot API-key channel, dynamic model sync

F2 — fixed three-platform registry in kigi-models: kimi-code
(subscription, OAuth bearer, base kigi_env::coding_api_base_url()),
moonshot-cn (https://api.moonshot.cn/v1), moonshot-ai
(https://api.moonshot.ai/v1) with kimi-k model-prefix filtering.
Moonshot API keys via KIGI_MOONSHOT_CN_API_KEY / KIGI_MOONSHOT_AI_API_KEY
(+ KIGI_MOONSHOT_API_KEY shared fallback) or ~/.kigi/config.toml;
values redacted from logs/display.

F4 — model catalog now syncs from GET {base}/models (Bearer auth,
wire shape per official kimi-cli: id/context_length/supports_reasoning/
supports_image_in/supports_video_in/display_name) with the official
capability-derivation rules (thinking / always_thinking-in-name /
kimi-k2 implicit set). Managed keys {platform_id}/{model_id}; default
model = first list entry; default thinking iff capabilities contain
thinking/always_thinking. Sync failure → last cache; no cache →
built-in fallback table seeded from ids sourced in official kimi-cli
(kimi-for-coding, kimi-k2-turbo-preview, kimi-k2-thinking-turbo).
401 during sync forces one token refresh and retries.

Model resolution priority preserved: CLI > env > config > server >
fallback. Grok model artifacts (grok-4*/grok-build catalog, tier
gating remnants) removed from non-test code.

All first-party endpoints re-verified live: device_authorization mints
real codes; /models on all three platforms answers with real API auth
errors when unauthenticated.

Gates: check/clippy --all-targets 0/0, fmt clean, deny ok,
kigi-shell lib 5136 green, kigi-tui lib 6819 green, kigi-models 8.

crates/codegen/kigi-shell/src/agent/server.rs

@@ -166,13 +166,19 @@ async fn handle_connection(ws: WebSocket, state: Arc<ServerState>, peer_addr: So
                 .spawn(move || {
                     // Prefetch models before creating the runtime (blocking is OK here)
                     let auth = agent_config.create_auth_manager().current();
-                    let fetch_auth =
-                        ModelFetchAuth::resolve(&agent_config.endpoints, auth.is_some());
+                    let fetch_auth = ModelFetchAuth::resolve(&agent_config.endpoints);
+                    let platform_keys =
+                        crate::agent::models::PlatformApiKeys::resolve(&agent_config.platforms);
                     let prefetched_models = if auth.is_some()
                         || agent_config.endpoints.has_custom_endpoint()
-                        || fetch_auth != ModelFetchAuth::Session
+                        || platform_keys.any()
                     {
-                        prefetch_models_blocking(&agent_config.endpoints, auth.as_ref(), fetch_auth)
+                        prefetch_models_blocking(
+                            &agent_config.endpoints,
+                            auth.as_ref(),
+                            fetch_auth,
+                            &platform_keys,
+                        )
                     } else {
                         None
                     };