feat: add Docker entrypoints, LLM providers, pipeline hardening, workbench pages

Phase 9 — four parallel workstreams:

- Stream A: 14 Docker entrypoints for containerized deployment
- Stream B: Pipeline hardening — robust JSON parsing, LLM retry logic,
  consumer negative-ack, FalkorDB test import fix
- Stream C: Azure OpenAI, OpenAI-compatible, and Mistral LLM providers
- Stream D: Workbench Prompts, Token Cost, Knowledge Cores pages +
  Settings feature switches

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

ts/scripts/run-llm-openai-compatible.ts

@@ -0,0 +1,17 @@
+/**
+ * Start the OpenAI-compatible text-completion service.
+ *
+ * Usage: OPENAI_COMPAT_URL=http://localhost:1234/v1 pnpm tsx scripts/run-llm-openai-compatible.ts
+ *
+ * Env:
+ *   NATS_URL            (default: nats://localhost:4222)
+ *   OPENAI_COMPAT_URL   (required)
+ *   OPENAI_COMPAT_KEY   (default: sk-no-key-required)
+ *   OPENAI_COMPAT_MODEL (default: default)
+ */
+import { run } from "../packages/flow/src/model/text-completion/openai-compatible.js";
+
+run().catch((err) => {
+  console.error("OpenAI-compatible LLM service failed:", err);
+  process.exit(1);
+});