feat(library-desk): add core API routers for wiki, vector, and ingestion

Ingestion Router: - POST /ingest/page - Index single page - POST /ingest/batch - Batch indexing - POST /ingest/all - Full knowledge base refresh - Support vector and graph ingestion Vector Router: - POST /vector/search - Semantic search via Qdrant - GET /vector/stats - Collection statistics - DELETE /vector/page - Remove page embeddings Wiki Router: - GET /wiki/pages - List wiki pages - GET /wiki/pages/{id} - Get page details - PUT /wiki/pages/{id} - Update page - POST /wiki/search - Search wiki content - Full Wiki.js GraphQL integration
2025-12-10 01:36:07 +01:00
parent 3ab44c2ab0
commit 9fe5faa3e7
3 changed files with 751 additions and 0 deletions
@@ -0,0 +1,169 @@
+"""
+Document Ingestion API Router
+
+Endpoints for ingesting wiki pages into the knowledge base (vectors + graph).
+"""
+from fastapi import APIRouter, Depends, HTTPException, Query
+from typing import Optional
+
+from src.services.ingestion_service import IngestionService
+from src.models.ingestion import (
+    IngestionRequest,
+    IngestionResult,
+    BatchIngestionRequest,
+    BatchIngestionResult
+)
+from src.core.dependencies import get_ingestion_service, verify_api_key
+
+router = APIRouter(prefix="/ingest", tags=["Document Ingestion"])
+
+
+@router.post("/page", response_model=IngestionResult)
+async def ingest_page(
+    request: IngestionRequest,
+    ingestion: IngestionService = Depends(get_ingestion_service),
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    Ingest a single wiki page into the knowledge base.
+
+    This endpoint:
+    1. Fetches page content from Wiki.js
+    2. Chunks content and generates embeddings (Qdrant)
+    3. Extracts entities and updates knowledge graph (Neo4j)
+
+    ## Use Cases
+
+    - **After page creation**: Automatically called by consolidation service
+    - **Manual re-indexing**: Force refresh a page after manual edits
+    - **Selective ingestion**: Skip vectors or graph if only one is needed
+
+    ## Performance
+
+    - Typical page: 1-3 seconds
+    - Large page (>5000 words): 5-10 seconds
+    - Vector and graph ingestion run in parallel
+
+    ## Example
+
+    ```bash
+    curl -X POST http://192.168.86.149:8089/ingest/page \
+      -H "Authorization: Bearer $API_KEY" \
+      -H "Content-Type: application/json" \
+      -d '{
+        "page_id": 19,
+        "user": "jpmschweitzer",
+        "force_refresh": false
+      }'
+    ```
+    """
+    result = await ingestion.ingest_page(
+        page_id=request.page_id,
+        user=request.user,
+        force_refresh=request.force_refresh,
+        skip_vectors=request.skip_vectors,
+        skip_graph=request.skip_graph
+    )
+
+    if not result.success:
+        raise HTTPException(
+            status_code=500,
+            detail=f"Ingestion failed: {result.error}"
+        )
+
+    return result
+
+
+@router.post("/batch", response_model=BatchIngestionResult)
+async def ingest_batch(
+    request: BatchIngestionRequest,
+    ingestion: IngestionService = Depends(get_ingestion_service),
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    Ingest multiple wiki pages concurrently.
+
+    ## Concurrency Control
+
+    The `max_concurrent` parameter controls how many pages are processed simultaneously:
+    - **Low (1-2)**: Safer for resource-constrained systems
+    - **Medium (3-5)**: Good balance of speed and stability
+    - **High (6-10)**: Maximum speed, requires good resources
+
+    ## Batch Size Recommendations
+
+    - **Small batches (<10 pages)**: Use max_concurrent=3-5
+    - **Medium batches (10-50 pages)**: Use max_concurrent=3
+    - **Large batches (>50 pages)**: Use max_concurrent=2, consider splitting
+
+    ## Example
+
+    ```bash
+    curl -X POST http://192.168.86.149:8089/ingest/batch \
+      -H "Authorization: Bearer $API_KEY" \
+      -H "Content-Type: application/json" \
+      -d '{
+        "page_ids": [19, 20, 21, 22],
+        "user": "jpmschweitzer",
+        "max_concurrent": 3
+      }'
+    ```
+    """
+    result = await ingestion.ingest_batch(
+        page_ids=request.page_ids,
+        user=request.user,
+        force_refresh=request.force_refresh,
+        skip_vectors=request.skip_vectors,
+        skip_graph=request.skip_graph,
+        max_concurrent=request.max_concurrent
+    )
+
+    return result
+
+
+@router.post("/all", response_model=BatchIngestionResult)
+async def ingest_all_pages(
+    user: str = Query(default="jpmschweitzer", description="User identifier"),
+    path_prefix: Optional[str] = Query(None, description="Path prefix filter (e.g., 'users/jpmschweitzer/tech')"),
+    force_refresh: bool = Query(False, description="Force re-ingestion of all pages"),
+    max_concurrent: int = Query(3, ge=1, le=10, description="Maximum concurrent ingestion tasks"),
+    ingestion: IngestionService = Depends(get_ingestion_service),
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    Ingest all wiki pages for a user (bulk re-indexing).
+
+    ## Use Cases
+
+    - **Initial setup**: Index all existing pages
+    - **Full re-index**: After major schema changes
+    - **Path-specific**: Re-index a specific section (e.g., all tech docs)
+
+    ## Performance
+
+    - **Small wiki (<50 pages)**: 2-5 minutes
+    - **Medium wiki (50-200 pages)**: 5-20 minutes
+    - **Large wiki (>200 pages)**: 20+ minutes
+
+    **Recommendation**: Run as background job for large wikis
+
+    ## Example
+
+    ```bash
+    # Ingest all pages for user
+    curl -X POST "http://192.168.86.149:8089/ingest/all?user=jpmschweitzer" \
+      -H "Authorization: Bearer $API_KEY"
+
+    # Ingest only tech docs
+    curl -X POST "http://192.168.86.149:8089/ingest/all?user=jpmschweitzer&path_prefix=users/jpmschweitzer/tech" \
+      -H "Authorization: Bearer $API_KEY"
+    ```
+    """
+    result = await ingestion.ingest_all_pages(
+        user=user,
+        path_prefix=path_prefix,
+        force_refresh=force_refresh,
+        max_concurrent=max_concurrent
+    )
+
+    return result
@@ -0,0 +1,173 @@
+"""
+Vector router for Library Desk API.
+
+Endpoints for semantic search and vector operations.
+"""
+
+from fastapi import APIRouter, HTTPException, Depends, Query
+from typing import Optional
+import logging
+
+from src.models.vector import (
+    SearchRequest, SearchResponse,
+    VectorUpdateRequest, VectorUpdateSummary,
+    CollectionListResponse,
+    DeletePageChunksRequest, DeletePageChunksResponse
+)
+from src.services.vector_service import VectorService
+from src.clients.qdrant_client import QdrantClientWrapper
+from src.clients.wikijs_client import WikiJSClient
+from src.clients.ollama_client import OllamaClient
+from src.core.dependencies import QdrantDep, WikiJSDep, OllamaDep, verify_api_key
+from src.core.multi_tenancy import DEFAULT_USER
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(prefix="/vector", tags=["Vector"])
+
+
+# Dependency to get vector service
+def get_vector_service(
+    qdrant_client: QdrantDep,
+    wiki_client: WikiJSDep,
+    ollama_client: OllamaDep
+) -> VectorService:
+    """Get vector service instance."""
+    return VectorService(qdrant_client, wiki_client, ollama_client)
+
+
+@router.post("/search", response_model=SearchResponse)
+async def semantic_search(
+    request: SearchRequest,
+    vector_service: VectorService = Depends(get_vector_service),
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    Perform semantic search across user's documents.
+
+    Uses Ollama to generate query embedding, then searches Qdrant
+    for similar document chunks.
+
+    **Example Request:**
+    ```json
+    {
+        "query": "how to configure docker",
+        "user": "jpmschweitzer",
+        "limit": 10,
+        "score_threshold": 0.5
+    }
+    ```
+
+    **Returns:** List of matching chunks with similarity scores
+    """
+    try:
+        return await vector_service.search(
+            query=request.query,
+            user=request.user,
+            limit=request.limit,
+            score_threshold=request.score_threshold
+        )
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    except Exception as e:
+        logger.error(f"Semantic search failed: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail="Search failed")
+
+
+@router.post("/update-from-page/{page_id}", response_model=VectorUpdateSummary)
+async def update_vectors_from_page(
+    page_id: int,
+    user: str = Query(default=DEFAULT_USER, description="User identifier"),
+    force_refresh: bool = Query(default=False, description="Force re-embedding"),
+    vector_service: VectorService = Depends(get_vector_service),
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    Update vector embeddings from a wiki page.
+
+    This endpoint:
+    1. Fetches the page from Wiki.js
+    2. Chunks the content (500 tokens with 50 token overlap)
+    3. Generates embeddings via Ollama
+    4. Upserts chunks to Qdrant with metadata
+
+    **Use Cases:**
+    - Called automatically after page creation/update (via BackgroundTasks)
+    - Called manually by user/Librarian to refresh vectors
+    - Called by Scheduler for batch processing
+
+    **Example:** `POST /vector/update-from-page/5?user=jpmschweitzer`
+
+    **Returns:** Summary with chunks created and processing time
+    """
+    try:
+        summary = await vector_service.update_from_page(
+            page_id=page_id,
+            user=user,
+            force_refresh=force_refresh
+        )
+
+        if not summary.success:
+            raise HTTPException(
+                status_code=500,
+                detail=f"Vector update failed: {summary.error_message}"
+            )
+
+        return summary
+
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"Failed to update vectors from page {page_id}: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail="Vector update failed")
+
+
+@router.delete("/pages/{page_id}", response_model=DeletePageChunksResponse)
+async def delete_page_chunks(
+    page_id: int,
+    user: str = Query(default=DEFAULT_USER, description="User identifier"),
+    vector_service: VectorService = Depends(get_vector_service),
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    Delete all vector chunks for a wiki page.
+
+    This is automatically called when a page is deleted from the wiki.
+
+    **Example:** `DELETE /vector/pages/5?user=jpmschweitzer`
+    """
+    try:
+        deleted_count = await vector_service.delete_page_chunks(
+            page_id=page_id,
+            user=user
+        )
+
+        return DeletePageChunksResponse(
+            page_id=page_id,
+            chunks_deleted=deleted_count,
+            success=deleted_count > 0,
+            message=f"Deleted {deleted_count} chunks for page {page_id}"
+        )
+
+    except Exception as e:
+        logger.error(f"Failed to delete chunks for page {page_id}: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail="Failed to delete chunks")
+
+
+@router.get("/collections", response_model=CollectionListResponse)
+async def list_collections(
+    vector_service: VectorService = Depends(get_vector_service),
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    List all Qdrant collections with statistics.
+
+    Returns collection names, vector counts, and point counts.
+
+    **Example:** `GET /vector/collections`
+    """
+    try:
+        return await vector_service.list_collections()
+    except Exception as e:
+        logger.error(f"Failed to list collections: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail="Failed to list collections")
@@ -0,0 +1,409 @@
+"""
+Wiki router for Library Desk API.
+
+Endpoints for wiki page and dossier management.
+All operations are scoped to user namespaces for multi-tenancy.
+"""
+
+from fastapi import APIRouter, HTTPException, Depends, Query, Security, BackgroundTasks
+from fastapi.security import HTTPAuthorizationCredentials
+from typing import Optional
+import logging
+
+from src.models.wiki import (
+    WikiPage, WikiPageList, WikiPageCreate, WikiPageUpdate, WikiPageMove,
+    WikiOperationResponse, WikiSearchResponse,
+    DossierList, WikiSearchResult
+)
+from src.services.wiki_service import WikiService
+from src.services.graph_service import GraphService
+from src.services.vector_service import VectorService
+from src.clients.wikijs_client import WikiJSClient
+from src.clients.neo4j_client import Neo4jClient
+from src.clients.qdrant_client import QdrantClientWrapper
+from src.clients.ollama_client import OllamaClient
+from src.core.dependencies import WikiJSDep, Neo4jDep, QdrantDep, OllamaDep, verify_api_key
+from src.core.multi_tenancy import DEFAULT_USER
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(prefix="/wiki", tags=["Wiki"])
+
+
+# Dependency to get wiki service
+def get_wiki_service(wiki_client: WikiJSDep) -> WikiService:
+    """Get wiki service instance."""
+    return WikiService(wiki_client)
+
+
+# Dependency to get graph service
+def get_graph_service(neo4j_client: Neo4jDep, wiki_client: WikiJSDep) -> GraphService:
+    """Get graph service instance."""
+    return GraphService(neo4j_client, wiki_client)
+
+
+# Dependency to get vector service
+def get_vector_service(
+    qdrant_client: QdrantDep,
+    wiki_client: WikiJSDep,
+    ollama_client: OllamaDep
+) -> VectorService:
+    """Get vector service instance."""
+    return VectorService(qdrant_client, wiki_client, ollama_client)
+
+
+# Page operations
+@router.get("/pages", response_model=WikiPageList)
+async def list_pages(
+    user: str = Query(default=DEFAULT_USER, description="User identifier"),
+    tag: Optional[str] = Query(default=None, description="Filter by tag (dossier)"),
+    limit: int = Query(default=50, ge=1, le=200, description="Maximum pages to return"),
+    wiki_service: WikiService = Depends(get_wiki_service),
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    List wiki pages for a user.
+
+    Optionally filter by tag (dossier). Pages are scoped to user's namespace.
+
+    **Example:** `/wiki/pages?user=jpmschweitzer&tag=projects&limit=20`
+    """
+    try:
+        return await wiki_service.list_pages(user=user, tag=tag, limit=limit)
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    except Exception as e:
+        logger.error(f"Failed to list pages: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail="Internal server error")
+
+
+@router.get("/pages/{page_id}", response_model=WikiPage)
+async def get_page(
+    page_id: int,
+    user: str = Query(default=DEFAULT_USER, description="User identifier"),
+    wiki_service: WikiService = Depends(get_wiki_service),
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    Get a single wiki page by ID.
+
+    Access is restricted to pages within the user's namespace.
+
+    **Example:** `/wiki/pages/123?user=jpmschweitzer`
+    """
+    try:
+        page = await wiki_service.get_page(page_id=page_id, user=user)
+        if not page:
+            raise HTTPException(status_code=404, detail=f"Page {page_id} not found or access denied")
+        return page
+    except HTTPException:
+        raise
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    except Exception as e:
+        logger.error(f"Failed to get page {page_id}: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail="Internal server error")
+
+
+@router.post("/pages", response_model=WikiPage, status_code=201)
+async def create_page(
+    page_data: WikiPageCreate,
+    background_tasks: BackgroundTasks,
+    wiki_service: WikiService = Depends(get_wiki_service),
+    graph_service: GraphService = Depends(get_graph_service),
+    vector_service: VectorService = Depends(get_vector_service),
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    Create a new wiki page.
+
+    The page will be created in the user's namespace. If path doesn't start
+    with namespace, it will be automatically prefixed.
+
+    **Auto-updates knowledge graph and vector embeddings**: After creating
+    the page, the graph and vectors are automatically updated in the
+    background to extract entities/relationships and generate semantic embeddings.
+
+    **Example Request:**
+    ```json
+    {
+        "title": "Library Desk Architecture",
+        "path": "/projects/library-desk/architecture",
+        "content": "# Architecture\\n\\nThis describes...",
+        "description": "Architecture documentation",
+        "tags": ["projects", "architecture"],
+        "user": "jpmschweitzer"
+    }
+    ```
+    """
+    try:
+        page = await wiki_service.create_page(page_data)
+
+        user = page_data.user or DEFAULT_USER
+
+        # Schedule BOTH graph and vector updates in background (non-blocking)
+        background_tasks.add_task(
+            graph_service.update_from_page,
+            page_id=page.id,
+            user=user
+        )
+        background_tasks.add_task(
+            vector_service.update_from_page,
+            page_id=page.id,
+            user=user
+        )
+
+        logger.info(f"Page {page.id} created, graph and vector updates scheduled")
+        return page
+
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    except Exception as e:
+        logger.error(f"Failed to create page: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail="Internal server error")
+
+
+@router.put("/pages/{page_id}", response_model=WikiPage)
+async def update_page(
+    page_id: int,
+    page_data: WikiPageUpdate,
+    background_tasks: BackgroundTasks,
+    user: str = Query(default=DEFAULT_USER, description="User identifier"),
+    wiki_service: WikiService = Depends(get_wiki_service),
+    graph_service: GraphService = Depends(get_graph_service),
+    vector_service: VectorService = Depends(get_vector_service),
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    Update an existing wiki page.
+
+    Only pages within the user's namespace can be updated.
+    Partial updates are supported - only provided fields will be updated.
+
+    **Auto-updates knowledge graph and vector embeddings**: After updating
+    the page, the graph and vectors are automatically refreshed in the
+    background to reflect the changes.
+
+    **Example Request:**
+    ```json
+    {
+        "title": "Updated Title",
+        "tags": ["projects", "updated"]
+    }
+    ```
+    """
+    try:
+        page = await wiki_service.update_page(
+            page_id=page_id,
+            page_data=page_data,
+            user=user
+        )
+
+        # Schedule BOTH graph and vector updates in background (non-blocking)
+        background_tasks.add_task(
+            graph_service.update_from_page,
+            page_id=page_id,
+            user=user,
+            force_refresh=True  # Force refresh on updates
+        )
+        background_tasks.add_task(
+            vector_service.update_from_page,
+            page_id=page_id,
+            user=user,
+            force_refresh=True  # Force refresh on updates
+        )
+
+        logger.info(f"Page {page_id} updated, graph and vector refresh scheduled")
+        return page
+
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    except Exception as e:
+        logger.error(f"Failed to update page {page_id}: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail="Internal server error")
+
+
+@router.delete("/pages/{page_id}", response_model=WikiOperationResponse)
+async def delete_page(
+    page_id: int,
+    background_tasks: BackgroundTasks,
+    user: str = Query(default=DEFAULT_USER, description="User identifier"),
+    wiki_service: WikiService = Depends(get_wiki_service),
+    vector_service: VectorService = Depends(get_vector_service),
+    graph_service: GraphService = Depends(get_graph_service),
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    Delete a wiki page.
+
+    Only pages within the user's namespace can be deleted.
+    This operation cannot be undone.
+
+    **Auto-cleanup**: Vector chunks and graph nodes for this page are
+    automatically deleted in the background.
+    """
+    try:
+        success = await wiki_service.delete_page(page_id=page_id, user=user)
+
+        # Schedule vector cleanup in background
+        background_tasks.add_task(
+            vector_service.delete_page_chunks,
+            page_id=page_id,
+            user=user
+        )
+
+        # Schedule graph cleanup in background
+        background_tasks.add_task(
+            graph_service.delete_page,
+            page_id=page_id,
+            user=user
+        )
+
+        logger.info(f"Page {page_id} deleted, vector and graph cleanup scheduled")
+        return WikiOperationResponse(
+            success=success,
+            message=f"Page {page_id} deleted successfully",
+            page_id=page_id
+        )
+    except ValueError as e:
+        raise HTTPException(status_code=404, detail=str(e))
+    except Exception as e:
+        logger.error(f"Failed to delete page {page_id}: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail="Internal server error")
+
+
+@router.post("/pages/{page_id}/move", response_model=WikiOperationResponse)
+async def move_page(
+    page_id: int,
+    move_data: WikiPageMove,
+    user: str = Query(default=DEFAULT_USER, description="User identifier"),
+    wiki_service: WikiService = Depends(get_wiki_service),
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    Move or rename a wiki page.
+
+    The new path must be within the user's namespace.
+
+    **Example Request:**
+    ```json
+    {
+        "new_path": "/projects/library-desk/docs/architecture"
+    }
+    ```
+    """
+    try:
+        success = await wiki_service.move_page(
+            page_id=page_id,
+            new_path=move_data.new_path,
+            user=user
+        )
+        if not success:
+            raise HTTPException(status_code=500, detail="Failed to move page")
+
+        return WikiOperationResponse(
+            success=True,
+            message=f"Page {page_id} moved successfully",
+            page_id=page_id,
+            page_path=move_data.new_path
+        )
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"Failed to move page {page_id}: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail="Internal server error")
+
+
+# Search operations
+@router.get("/search", response_model=WikiSearchResponse)
+async def search_pages(
+    q: str = Query(..., min_length=1, description="Search query"),
+    user: str = Query(default=DEFAULT_USER, description="User identifier"),
+    limit: int = Query(default=20, ge=1, le=100, description="Maximum results"),
+    wiki_service: WikiService = Depends(get_wiki_service),
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    Search wiki pages within user's namespace.
+
+    **Example:** `/wiki/search?q=architecture&user=jpmschweitzer&limit=10`
+    """
+    try:
+        results = await wiki_service.search_pages(
+            query=q,
+            user=user,
+            limit=limit
+        )
+
+        return WikiSearchResponse(
+            results=[
+                WikiSearchResult(
+                    id=r.id,
+                    path=r.path,
+                    title=r.title,
+                    description=r.description,
+                    relevance=None
+                )
+                for r in results
+            ],
+            query=q,
+            total=len(results)
+        )
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    except Exception as e:
+        logger.error(f"Search failed: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail="Internal server error")
+
+
+# Dossier operations
+@router.get("/dossiers", response_model=DossierList)
+async def list_dossiers(
+    user: str = Query(default=DEFAULT_USER, description="User identifier"),
+    wiki_service: WikiService = Depends(get_wiki_service),
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    List all dossiers (unique tags) for a user.
+
+    Dossiers are tag-based collections of pages.
+
+    **Example:** `/wiki/dossiers?user=jpmschweitzer`
+    """
+    try:
+        return await wiki_service.list_dossiers(user=user)
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    except Exception as e:
+        logger.error(f"Failed to list dossiers: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail="Internal server error")
+
+
+@router.get("/dossiers/{dossier_name}/pages", response_model=WikiPageList)
+async def get_dossier_pages(
+    dossier_name: str,
+    user: str = Query(default=DEFAULT_USER, description="User identifier"),
+    limit: int = Query(default=100, ge=1, le=500, description="Maximum pages"),
+    wiki_service: WikiService = Depends(get_wiki_service),
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    Get all pages in a dossier.
+
+    Returns pages tagged with the dossier name.
+
+    **Example:** `/wiki/dossiers/projects/pages?user=jpmschweitzer`
+    """
+    try:
+        return await wiki_service.get_dossier_pages(
+            dossier_name=dossier_name,
+            user=user,
+            limit=limit
+        )
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    except Exception as e:
+        logger.error(f"Failed to get dossier pages: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail="Internal server error")