feat(ai): add workspace process command for manual embedding generation

tdoc-crawler ai workspace create my-project

```

### 2. Query Your Knowledge Base

### 2. Process Documents (Generate Embeddings)

After adding TDocs to your workspace, process them to generate RAG/GraphRAG embeddings:

```bash

# Process all TDocs in workspace (only new ones)

tdoc-crawler ai workspace process -w my-project

# Force reprocess all TDocs

tdoc-crawler ai workspace process -w my-project --force

```

Note: If you created the workspace with `--auto-build`, documents are processed automatically when added.

### 3. Query Your Knowledge Base

Once you have a workspace with documents, query using semantic search and knowledge graph (RAG + GraphRAG):

    summarize_tdoc,

)

from tdoc_crawler.ai.models import SourceKind

from tdoc_crawler.ai.operations.pipeline import process_all

from tdoc_crawler.config import CacheManager

HELP_PANEL = "AI Commands"

        console.print(table)

@_workspace_app.command("process")

def workspace_process(

    workspace: Annotated[str, typer.Option("--workspace", "-w", help="Workspace name")],

    new_only: Annotated[bool, typer.Option("--new-only", help="Process only TDocs not already completed")] = True,

    force_rerun: Annotated[bool, typer.Option("--force", help="Force reprocessing of all TDocs")] = False,

    json_output: Annotated[bool, typer.Option("--json", help="Output as JSON")] = False,

) -> None:

    """Process all TDoc members in a workspace through the AI pipeline."""

    manager = CacheManager().register()

    storage = AiStorage(manager.root / ".ai" / "lancedb")

    # Get workspace members

    members = storage.list_workspace_members(workspace, include_inactive=False)

    tdoc_ids = [m.source_item_id for m in members if m.is_active and m.source_kind.value == "tdoc"]

    if not tdoc_ids:

        if json_output:

            typer.echo(json.dumps({"workspace": normalize_workspace_name(workspace), "processed": 0, "message": "No TDoc members found"}))

        else:

            console.print(f"[yellow]No TDoc members found in workspace '{normalize_workspace_name(workspace)}'[/yellow]")

        return

    # Process TDocs

    results = process_all(

        tdoc_ids=tdoc_ids,

        checkout_base=manager.root,

        new_only=new_only,

        force_rerun=force_rerun,

        workspace=workspace,

    )

    if json_output:

        typer.echo(json.dumps({

            "workspace": normalize_workspace_name(workspace),

            "processed": len(results),

            "total_members": len(tdoc_ids),

            "tdoc_ids": list(results.keys()),

        }))

    else:

        console.print(f"[green]Processed {len(results)}/{len(tdoc_ids)} TDoc(s) in workspace '{normalize_workspace_name(workspace)}'[/green]")

@_workspace_app.command("delete")

def workspace_delete(

    name: Annotated[str, typer.Argument(..., help="Workspace name")],