feat(qa): remote NIM provider + headless-QA robustness

Enable autonomous QA through a remote OpenAI-compatible provider (NVIDIA NIM)
and harden the tool/approval path so unattended multi-stage runs complete.

- inference: add openai_compat provider (Bearer chat-completions for NIM/OpenAI),
  dispatched by provider type "nim"/"openai"; key via api_key/api_key_env.
- server: bind configured [server] host/port instead of a hardcoded 8080;
  POST /sessions accepts an optional `intent` (WS parity) for intent-driven workflows.
- kernel: thread the bound operator profile's approval_mode into per-tool gating so
  auto/yolo enable unattended approval (engine still consulted; policy/plane-2 BLOCK
  stays terminal); on a recoverable tool failure feed the tool's arg-schema back into
  context so the model self-corrects instead of repeating a malformed call.
- tools: split deletion out of file_write into a separate, explicitly-named file_delete
  tool — a model can no longer delete a file by getting a write-mode parameter wrong.
- server: add GET /metrics/tool-reliability — per-model tool-call validity from the
  event log (measurement groundwork for capability-aware routing).
- docs: update AGENTS.md across kernel, tools, server, inference.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

infrastructure/src/main/kotlin/com/correx/infrastructure/InfrastructureModule.kt

@@ -47,6 +47,7 @@ import com.correx.infrastructure.inference.commons.ResidencyMode
 import com.correx.infrastructure.inference.llama.cpp.DefaultModelManager
 import com.correx.infrastructure.inference.llama.cpp.LlamaCppEmbedder
 import com.correx.infrastructure.inference.llama.cpp.LlamaCppInferenceProvider
+import com.correx.infrastructure.inference.openai.OpenAiCompatInferenceProvider
 import io.ktor.client.HttpClient
 import io.ktor.client.engine.cio.CIO
 import com.correx.infrastructure.router.turbovec.TurboVecL3MemoryStore
@@ -127,6 +128,20 @@ object InfrastructureModule {
         baseUrl = baseUrl,
     )
 
+    fun createOpenAiCompatProvider(
+        modelId: String,
+        baseUrl: String,
+        apiKey: String,
+        idPrefix: String = "openai",
+        capabilities: Set<CapabilityScore> = DEFAULT_LLAMA_CAPABILITIES,
+    ): OpenAiCompatInferenceProvider = OpenAiCompatInferenceProvider(
+        modelId = modelId,
+        baseUrl = baseUrl,
+        apiKey = apiKey,
+        idPrefix = idPrefix,
+        capabilities = capabilities,
+    )
+
     fun createModelManager(
         settings: ModelsSettings,
         eventStore: EventStore,