docs: add 'versions' to catalog descriptions in AGENTS.md and mcp-author.md (#1479)

The catalog command/tool exposes a 'versions' category that emits the
compiler's pinned semver versions (copilot_cli, awf, mcpg). This was
accurately documented in docs/cli.md but omitted from:

- AGENTS.md: catalog.rs module description listed "(tools, runtimes,
  models, etc.)" — now lists all six categories explicitly.
- docs/mcp-author.md: catalog tool row said "engines, and models" —
  now says "engines, models, and pinned versions" matching the source
  tool description in src/mcp_author/mod.rs.

Verified against src/inspect/catalog.rs models() / engines() functions
and the CatalogParams comment in src/mcp_author/mod.rs.

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: github-actions[bot]

AGENTS.md

@@ -167,7 +167,7 @@ fail-closed and only pauses when the agent actually proposed a reviewed output.
 │   │   ├── trace.rs      # `ado-aw trace`: correlate audit telemetry with the local IR graph
 │   │   ├── whatif.rs     # `ado-aw whatif`: static downstream skip classification for failures
 │   │   ├── lint.rs       # `ado-aw lint`: structural workflow lint checks
-│   │   └── catalog.rs    # `ado-aw catalog`: list in-tree registries (tools, runtimes, models, etc.)
+│   │   └── catalog.rs    # `ado-aw catalog`: list in-tree registries (safe-outputs, runtimes, tools, engines, models, pinned versions)
 │   ├── detect.rs         # Agentic workflow detection — discovers compiled pipelines; used by all lifecycle commands
 │   ├── update_check.rs   # Version update check — queries GitHub Releases and prints advisory when newer version is available
 │   ├── ndjson.rs         # NDJSON parsing utilities

docs/mcp-author.md

@@ -23,7 +23,7 @@ workflows.
 | `trace_failure` | Trace a build's failed-job chain using audit data plus any local IR graph. | `{ "build_id_or_url": "123", "step": null, "org": null, "project": null, "pat": null }` |
 | `whatif` | Classify downstream jobs if a step or job fails. | `{ "source_path": "...", "failing_id": "Agent" }` |
 | `lint_workflow` | Run structural lint checks. | `{ "source_path": "agents/example.md" }` |
-| `catalog` | List safe-outputs, runtimes, tools, engines, and models. | `{ "kind": "safe-outputs" }` |
+| `catalog` | List safe-outputs, runtimes, tools, engines, models, and pinned versions. | `{ "kind": "safe-outputs" }` |
 | `audit_build` | Download and analyze a build; same shape as `ado-aw audit --json`. | `{ "build_id_or_url": "123", "org": null, "project": null, "pat": null, "artifacts": null, "no_cache": false }` |
 
 ## Trust model