fix(docs): correct provider/strategy/MCP-tools drift (179→177, 13→14)

- ARCHITECTURE.md and CODEBASE_DOCUMENTATION.md: 179 → 177 registered
  providers (canonical from src/shared/constants/providers.ts).
- FEATURES.md and en.json wizard step: 13 → 14 routing strategies; lists
  all 14 explicitly including reset-aware (the missing one).
- llm.txt root: combo strategy count corrected in 3 places (UI tree,
  dashboard summary, fallback semantics).
- MCP-SERVER.md: 37 tool count was already correct; added a "Related
  Frameworks (v3.8.0)" section pointing to Cloud Agents
  (docs/frameworks/CLOUD_AGENT.md) and Guardrails
  (docs/security/GUARDRAILS.md), both sibling frameworks intentionally
  outside the MCP tool catalog.
- scripts/i18n/sync-llm-mirrors.mjs (new): idempotent helper to push
  root llm.txt body into the 40 docs/i18n/<locale>/llm.txt mirrors
  while preserving each locale's heading + language bar prefix; ran
  it to refresh all 40 mirrors so `check:docs-sync` is green.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

docs/frameworks/MCP-SERVER.md

@@ -131,6 +131,36 @@ Defined in `open-sse/mcp-server/tools/skillTools.ts`. Backed by `src/lib/skills/
 | `omniroute_skills_execute`    | Execute a skill with provided input and return the execution record               |
 | `omniroute_skills_executions` | List recent skill execution history                                               |
 
+## Related Frameworks (v3.8.0)
+
+The MCP tool inventory above (37 tools = 30 base + 3 memory + 4 skills) is intentionally
+scoped to runtime routing/cache/compression/memory/skills/proxy operations. Two adjacent
+frameworks ship alongside the MCP server in v3.8.0 and are documented separately:
+
+### Cloud Agents
+
+Cloud Agents are out-of-process AI coding agents (codex-cloud, devin, jules) wired into
+OmniRoute through the same connection model used for LLM providers. They are exposed via
+their own REST surface (`/api/v1/agents/*`) and are **not** part of the MCP tool catalog
+— calling a Cloud Agent does not consume an MCP scope.
+
+- Implementation: `src/lib/cloudAgent/` (`registry.ts`, `agents/codex-cloud.ts`, `agents/devin.ts`, `agents/jules.ts`).
+- Lifecycle: `createTask`, `getStatus`, `approvePlan`, `sendMessage`, `listSources`.
+- Documentation: [docs/frameworks/CLOUD_AGENT.md](./CLOUD_AGENT.md).
+
+### Guardrails
+
+Guardrails are pre/post-execution filters (vision-bridge, pii-masker, prompt-injection)
+applied inside the chat pipeline. They run before the MCP tool/route layer is reached
+and emit structured violations to the audit pipeline; they are not invoked as MCP tools.
+
+- Implementation: `src/lib/guardrails/`.
+- Documentation: [docs/security/GUARDRAILS.md](../security/GUARDRAILS.md).
+
+When debugging an MCP call that appears blocked, check both the MCP audit log
+(`scope_denied:*` entries) and the guardrails audit trail — a request may be rejected by
+a guardrail **before** it ever reaches the MCP scope enforcement layer.
+
 ---
 
 ## REST API Endpoints