- Remove dead monkeypatch in test_stdio_calls_get_stdio_mcp
- Add _reload_config() teardown to single_user_env fixture
- Tighten AVAILABLE_APPS type to Callable[[FastMCP], None]
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Revert default transport to streamable-http (not a breaking change)
- Extract AVAILABLE_APPS constant to server/__init__.py (DRY)
- Wrap get_stdio_mcp ValueError in click.ClickException for clean errors
- Fix test_stdio.py: call _reload_config() so dynaconf sees env changes
- Use lazy %-style logging in stdio.py
- Add private API comments in test assertions
- Derive --enable-app CLI choices from AVAILABLE_APPS
- README: show explicit --transport stdio in uvx examples
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Many identity providers (AWS Cognito, Okta, Azure AD) reject or mishandle
colons in OAuth scope names. This migrates all custom scopes from
`resource:action` to `resource.action` format (e.g., `notes:read` →
`notes.read`), which is universally accepted and aligns with industry
conventions (Microsoft, Google).
Includes Alembic migration 004 for stored scope strings and ADR-024
documenting the rationale and RFC references.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
pythonvCard4 parses vCard BDAY fields into datetime.date objects, but
the Contact model expects Optional[str]. This caused a validation error
that crashed the entire contact list. Convert at the client layer
(consistent with the calendar client pattern) with a defensive check
at the server mapping layer.
Closes#672
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Fix emoji clearing bug: use _UNSET sentinel in update_collective so
emoji=None sends {"emoji": null} instead of raising ValueError
- Move collectives_get_trashed_collectives to Read Tools section
- Remove redundant is_trash field from ListTrashedPagesResponse
- Add page lifecycle note to collectives_trash_page docstring
- Add unit test for clearing collective emoji via update_collective
- Add integration test for clearing collective emoji via MCP tool
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Fix inconsistent error code in set_collective_emoji (400 → -32603)
- Allow clearing emoji via set_collective_emoji(emoji=None)
- Remove destructiveHint from trash operations (soft deletes are recoverable)
- Change delete_collective to idempotentHint=False (requires trash precondition)
- Add restore_collective and get_trashed_collectives tools
- Add unit tests for ValueError guard, clear-emoji path, and new tools
- Add integration test for full trash/restore/delete lifecycle
- Verify move_page returns new title in response message
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Rename collectives_update_collective to collectives_set_collective_emoji
(more precise since only emoji is settable)
- Use standard JSON-RPC error code -32603 (INTERNAL_ERROR) instead of -1
- Handle UnicodeDecodeError when reading page content via WebDAV
- Replace brittle 'Welcome' content assertion with length check
Fixes CI: test_update_operations_not_idempotent no longer matches the
renamed tool, which is correctly idempotent (no ETag involved).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Fix assign_tag sending Content-Type header with no body
- Mark collectives_update_collective as idempotent (no ETag involved)
- Raise OCSError when 'data' key missing instead of silent fallback
- Tighten color validator to 3 or 6 hex chars only
- Add comment explaining null emoji semantics in set_page_emoji
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Validate OCS envelope in trash_collective, delete_collective, trash_page
- Guard _unwrap_ocs against non-OCS responses with informative OCSError
- Remove _get_ocs_headers() indirection, use class constants directly
- Split headers: _OCS_HEADERS (GET) vs _OCS_HEADERS_JSON (with body)
- Fix docstring claiming emoji param is required when it is optional
- Rename misleading test, add test for non-OCS envelope handling
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add collectives_trash_collective and collectives_delete_collective MCP
tools with proper destructiveHint annotations. Refactor integration test
fixture to use MCP tools for cleanup instead of direct httpx/OCS calls.
Optimize _get_ocs_headers() to class-level constant.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Bugs:
- assign_tag/remove_tag now call _unwrap_ocs to surface OCS-level errors
- trash_page changed to idempotentHint=False (trashing twice errors)
- WebDAV path parts stripped of slashes to prevent double-slash paths
Robustness:
- _unwrap_ocs uses ocs.get("data", {}) instead of ocs["data"]
- Unit test added for missing data key in OCS envelope
Minor:
- MCP error codes use -1 (project convention) instead of HTTP status codes
- update_collective docstring notes that emoji is required
- CollectiveTag.color validated as hex format via field_validator
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Bug fixes:
- Catch OCSError/HTTPStatusError in all server tools, convert to McpError
- Guard update_collective against empty body (raise ValueError)
- Use restore_page response data in status message
ADR-017 annotation fix:
- Distinguish "remove" (reversible association) from "delete" (permanent):
remove_tag and deck_remove_label_from_card no longer set destructiveHint
- Update annotation test to exclude "remove" from destructive keywords
Data model improvements:
- Add trashTimestamp field to PageInfo
- Create ListTrashedPagesResponse with is_trash context flag
- Add collective_id to ListTagsResponse
Test robustness:
- Read NC credentials from environment variables (not hardcoded)
- Filter landing page by parentId == 0 instead of assuming pages[0]
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add destructiveHint=True to collectives_remove_tag (matches "remove"
keyword pattern in annotation tests)
- Change collectives_update_collective to idempotentHint=False (update
operations are non-idempotent per project convention)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Validate OCS envelope status before unwrapping data (raise OCSError on
statuscode >= 400)
- Fix test data: filePath should be "" for root-level pages, not filename
- Catch specific exceptions (HTTPStatusError, OSError) instead of bare
Exception in WebDAV content fetch, include error in log message
- Return updated resource data from update_collective, move_page, and
set_page_emoji instead of discarding API responses
- Fix create_page docstring to mention collectivePath/filePath/fileName
- Remove unused additional_headers parameter from _get_ocs_headers
- Add unit test for OCS error status validation
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implement MCP tools for the Collectives wiki/documentation app, enabling
agentic workflows for team knowledge base management.
16 tools covering collectives, pages, tags, search, and trash:
- Read: list collectives, list/get pages (with WebDAV content), search,
list tags, list trashed pages
- Write: create/update collective, create/move/trash/restore pages,
set emoji, create/assign/remove tags
Includes Docker hook for app installation, OCS API client with envelope
unwrapping, Pydantic models, unit tests (16), and integration tests (10).
Closes#621
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Fix three related contacts bugs:
- Parse dict-format vCard fields ({value, type}) that pythonvCard4 returns,
which previously crashed Pydantic validation expecting plain strings
- Include tel field in client output so phone numbers reach MCP tools
- Clarify addressbook parameter expects URI slug, not displayname
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace `assert entry.code_challenge` with a proper if-guard returning a
500 JSON error in the token endpoint, since Python's -O flag strips
asserts and would silently disable PKCE enforcement.
Invalidate the scope cache immediately after Login Flow v2 provisioning
completes, so users no longer hit ProvisioningRequiredError for up to
5 minutes after successfully authenticating.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add 429 retry with exponential backoff to register_client() (fixes CI
oauth matrix failures from parallel DCR requests)
- Make client_id, redirect_uri, and PKCE mandatory at token endpoint
- Add null-checks for discovery_url and OAuth credentials in proxy flows
- Add OIDC discovery document caching with 5-min TTL
- Add per-IP rate limiting on /oauth/register DCR proxy
- Discover DCR endpoint from OIDC discovery instead of hardcoding
- Extract extract_user_id_from_token to auth/token_utils.py (breaks
circular imports between server/ and auth/ layers)
- Add TTL scope cache in scope_authorization.py (avoids DB hit per tool)
- Add defense-in-depth scope validation in storage layer
- Broaden elicitation exception handling with graceful fallback
- Add idempotentHint to nc_auth_check_status, return "pending" status
after accepted elicitation, add polling interval to description
- Change ALL_SUPPORTED_SCOPES from tuple to frozenset for O(1) lookups
- Replace Optional[str] with str | None throughout config.py
- Use default_factory for ProxyCodeEntry/ASProxySession dataclasses
- Add proxy code/session cleanup to background loop
- Fix OIDC verification CI step to only run for oauth/login-flow modes
- Add unit tests for access.py REST endpoints (10 tests)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Consolidate MCP session + login flow cleanup into _mcp_session_with_login_flow() helper,
replacing 4 duplicated AsyncExitStack sites in app.py
- Fix get_shared_storage() race condition by using module-level anyio.Lock() init
(reverts regression from ba59763)
- Collapse cosmetic if/else branching in scope_authorization.py
- Consolidate dual password storage paths into single store_app_password_with_scopes() call
- Mark unused request param as _ in list_supported_scopes
- Make ALL_SUPPORTED_SCOPES an immutable tuple; use list() instead of .copy()
- Add hasattr(ctx, "elicit") guard in elicitation.py, narrow except to NotImplementedError
- Add YAML comment explaining --oauth flag for mcp-login-flow service
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix anyio.Lock() created at module import time; use lazy init in
get_shared_storage() to avoid instantiation before event loop exists
- Stop get_login_flow_session from silently swallowing DB exceptions;
re-raise and handle in caller with proper error response
- Update ProvisionAccessResponse and UpdateScopesResponse status field
docs to include all actual values (declined, cancelled, unchanged)
- Narrow except clause in present_login_url to (AttributeError,
NotImplementedError) instead of bare Exception
- Add KeyError handling in LoginFlowV2Client.initiate() and poll() for
clear errors on malformed Nextcloud responses
- Simplify redundant env-var bypass branches in scope_authorization.py
- Extract _maybe_login_flow_cleanup() context manager to replace 4
inline cleanup loop registrations in app.py; move sleep to end of
loop body so cleanup runs once at startup
- Replace fragile string replacement in _rewrite_login_flow_url with
proper urllib.parse URL handling
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix circular dependency in scope_authorization: auth tools requiring
only identity scopes (openid/profile/email) now bypass the login flow
provisioning check, so unprovisioned users can call provisioning tools
- Fix no-op detection in nc_auth_update_scopes: NULL scopes (legacy "all")
now correctly map to ALL_SUPPORTED_SCOPES instead of empty set
- Fix get_app_password_with_scopes swallowing exceptions: re-raise instead
of returning None, matching sibling methods
- Add missing audit logging to update_app_password_scopes,
delete_login_flow_session, and delete_expired_login_flow_sessions
- Pin setup-uv to v7.3.1 in CI unit-test job (was v7.3.0)
- Add FastMCP type annotation to register_auth_tools parameter
- Log warning when user accepts elicitation without checking acknowledged box
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Consolidate three independent RefreshTokenStorage lazy singletons into a
single lock-protected get_shared_storage() function, eliminating race
conditions on concurrent first-access. Remove blanket try/except in
_get_stored_scopes so storage errors propagate as proper MCP errors
instead of silently triggering "please provision" messages. Handle
declined/cancelled elicitation results in Login Flow tools by cleaning up
sessions and returning clear status. Add update_app_password_scopes() to
avoid unnecessary decrypt/re-encrypt when only scopes change. Add
unprovisioned-user early exit and no-op detection to nc_auth_update_scopes.
Remove four dead config fields and misleading NEXTCLOUD_PASSWORD deprecation
warning. Add periodic login flow session cleanup task. Generate separate
Fernet keys per service. Add board cleanup in deck integration test. Gate
CI unit tests on linting and skip Astrolabe build for single-user profile.
Fix test markers from oauth to multi_user_basic for astrolabe integration
tests. Update login_flow.py docstrings to document outbound HTTP calls.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix data loss in nc_auth_update_scopes: remove premature
delete_app_password call; old password stays valid until upsert
replaces it on successful re-provisioning
- Replace assert with proper error return in nc_auth_check_status
- Add lazy singleton for RefreshTokenStorage in auth_tools,
scope_authorization, and context to avoid per-call re-initialization
- Centralize _is_login_flow_mode() to get_settings().enable_login_flow
and remove duplicate definitions and per-call os.getenv reads
- Add dev-only comment to TOKEN_ENCRYPTION_KEY in docker-compose.yml
- Gate OIDC build steps in CI behind matrix.needs-playwright
- Add diagnostic step reporting Playwright skip count in CI
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Use lowercase generics (list[...]) in new deck response models
- Add clarifying comment on AddressBook.uri slug semantics
- Fall back calendar_display_name to calendar_name when absent
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Guard board.labels against None in deck_get_labels and resource
- Add TODO comments for calendar_display_name in single-calendar paths
- Document _raw_contact_to_model scope limitation (maps only what the
client returns; expanding requires changes to vCard parsing)
- Log debug warning when event has no start_datetime
- Verified Table model is safe with extra fields (Pydantic v2 ignores)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Enrich single-calendar event dicts with calendar_name before mapping
to CalendarEventSummary (list_events and upcoming_events paths)
- Extract _raw_contact_to_model() from inline mapping in contacts.py,
fix custom_fields type annotation to dict[str, Any]
- Add unit tests for _event_dict_to_summary covering categories parsing,
falsy coercion, and calendar name passthrough
- Replace duplicated test helper with import of production function
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Restore contact email/birthday/nickname data and per-event calendar
source that were silently dropped during response model wrapping.
Remove dead elif branches in OAuth deck tests, add regression tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
MCP tools returning raw lists caused FastMCP's _convert_to_content() to create
one TextContent block per element. Most MCP clients only read content[0], so
they saw a single result instead of the full list.
Wrapped 9 tool functions in proper response objects:
- deck: deck_get_boards, deck_get_stacks, deck_get_cards, deck_get_labels
- calendar: nc_calendar_list_events, nc_calendar_get_upcoming_events
- contacts: nc_contacts_list_addressbooks, nc_contacts_list_contacts
- tables: nc_tables_list_tables
Closes#568
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Enable ruff PLC0415 rule for all source files (tests excluded via
per-file-ignores). Move 136 inline imports to top-level across 33 files.
8 imports suppressed with noqa for legitimate reasons: circular
dependencies (client/__init__.py, context.py), optional dependency
guards (app.py document processors, auth/userinfo_routes.py), and
post-env-setup imports (smithery_main.py).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add NEXTCLOUD_VERIFY_SSL and NEXTCLOUD_CA_BUNDLE env vars to configure
TLS certificate verification for all outbound Nextcloud connections.
Centralizes SSL config via a new HTTP client factory (http.py) used by
all 27 Nextcloud-bound call sites, including API clients, OIDC endpoints,
OAuth flows, and health checks.
Closes#560
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace direct os.getenv() calls with get_settings().vector_sync_enabled
to ensure consistent behavior with both VECTOR_SYNC_ENABLED (deprecated)
and ENABLE_SEMANTIC_SEARCH environment variables.
Also add webhook management documentation guide.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add destructiveHint=True to deck_remove_label_from_card and
deck_unassign_user_from_card (ADR-017 compliance)
- Set idempotentHint=True since remove operations produce same end state
- Update test_annotations.py to exclude nc_webdav_create_directory from
non-idempotent check (MKCOL is idempotent by design - returns 405 if exists)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Migrate all direct ENABLE_OFFLINE_ACCESS environment variable checks to
use settings.enable_offline_access, which handles both the new
ENABLE_BACKGROUND_OPERATIONS and deprecated ENABLE_OFFLINE_ACCESS vars.
Also fixes JWT issuer validation in Docker by using NEXTCLOUD_PUBLIC_ISSUER_URL
when set, resolving 401 errors caused by internal/external URL mismatch.
Changes:
- app.py: Use settings for offline access checks in setup_oauth_config,
register_oauth_client, and tool registration
- oauth_tools.py: Use settings in provision_nextcloud_access and check_logged_in
- management.py: Use settings in get_user_session
- scope_authorization.py: Use settings in require_scopes decorator
- Remove unused os imports after migration
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement multi-user BasicAuth pass-through mode (ADR-020) where each
request includes BasicAuth credentials that are forwarded to Nextcloud
APIs without persistent storage.
Changes:
- Add _get_client_from_basic_auth() in context.py to extract credentials
from Authorization header (set by BasicAuthMiddleware)
- Add AstrolabeClient for app password provisioning via Astrolabe API
- Update oauth_sync.py with dual credential support (app passwords first,
then refresh tokens as fallback)
- Simplify oauth_tools.py provisioning logic
- Add integration tests for app password provisioning and multi-user BasicAuth
Features:
- Stateless multi-user mode: credentials passed per-request
- Optional background sync via app passwords (stored in Astrolabe)
- Falls back to refresh tokens if app password not available
- Test coverage for provisioning flow and pass-through mode
Related: ADR-019 (Multi-user BasicAuth), ADR-020 (Deployment Modes)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Add type casts for Starlette app state access
- Add assertions for cipher, card, board, stack after initialization
- Add None checks for XML element text attributes
- Handle __package__ being None in tracing setup
- Fix TokenBrokerService initialization to use storage credentials
Resolves 42 type warnings from ty-check, enabling CI linting to pass.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Adds comprehensive vector search support for Nextcloud Deck cards,
including semantic search indexing, chunk preview in the vector viz UI,
and proper deep linking to cards.
**Vector Search Indexing**
- Add deck_card scanning in scanner.py (scan_deck_cards function)
- Index cards from non-archived, non-deleted boards
- Store metadata: board_id, board_title, stack_id, stack_title, card_type, duedate, owner
- Content structure: title + "\n\n" + description (matches indexing format)
- Incremental sync based on lastModified timestamp
- Deletion tracking with grace period
**Vector Visualization Support**
- Add deck_card handler in context.py for chunk preview expansion
- Include board_id in search result metadata (bm25_hybrid.py, semantic.py)
- Expose metadata in viz_routes.py JSON responses
- Update vector-viz.js to construct proper Deck URLs: /apps/deck/board/{board_id}/card/{card_id}
- Update vector_viz.html filter label from "Deck" to "Deck Cards"
**Bug Fixes**
- Skip soft-deleted boards (deletedAt > 0) to prevent 403 Forbidden errors
- Applies to scanner, processor, and context expansion code paths
- Deck API returns deleted boards but rejects stack access with 403
**Testing**
- Add integration tests in test_deck_vector_search.py:
- test_deck_card_semantic_search: Filtered search with doc_type="deck_card"
- test_deck_card_appears_in_cross_app_search: Cross-app search includes deck cards
- test_deck_card_chunk_context: Chunk context fetching for viz preview
**Documentation**
- Update README.md: Add Deck cards to semantic search feature list
- Update semantic-search-architecture.md: Document deck_card support
- Update nc_semantic_search tool documentation
**Type Safety**
- Fix type narrowing for page_boundaries (could be None) using cast()
- Fix scanner.py payload None check for type safety
Resolves vector search for Deck cards across indexing, search, and visualization.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Address all reviewer comments from PR #387:
1. ✅ Add unit tests for annotations (tests/server/test_annotations.py)
- 10 comprehensive test functions validating all annotation patterns
- Tests for titles, read-only, destructive, idempotent operations
- Validates specific ADR-017 decisions (webdav write, semantic search)
- Cross-category consistency checks
2. ✅ Fix nc_webdav_write_file idempotency classification
- Changed from idempotentHint=False to idempotentHint=True
- Rationale: Uses HTTP PUT without version control
- Writing same content to same path = same end state (idempotent)
3. ✅ Fix semantic search openWorldHint inconsistency
- Changed from openWorldHint=False to openWorldHint=True
- Rationale: Consistent with other Nextcloud tools
- Nextcloud is external to MCP server (indexed data is implementation detail)
4. ✅ Update ADR-017 with resolved decisions
- Converted Open Questions to Resolved Questions
- Added detailed rationale for webdav write and semantic search
- Updated status from Proposed to Implemented
- Added decision timeline with dates
5. ✅ Add MCP Tool Annotations guidelines to CLAUDE.md
- Comprehensive section with code examples for all patterns
- Key principles documented (idempotency, destructive, open world)
- References ADR-017 for detailed rationale
All OAuth tools verified to have proper annotations (oauth_tools.py lines 686-751).
Add full integration for the Nextcloud News (RSS/Atom reader) app:
- Add NewsClient with complete CRUD operations for folders, feeds, and items
- Add 8 read-only MCP tools for listing/getting folders, feeds, items
- Add Pydantic models for News entities with camelCase alias support
- Add vector sync support for starred + unread items
- Add HTML to Markdown converter using markdownify for better embeddings
- Add Docker post-install hook to enable News app
- Add 25 unit tests for NewsClient API methods
Vector sync indexes starred and unread items, providing a balanced approach
that captures important (starred) and current (unread) content without
indexing the entire article history.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Increase sampling timeout from 30s to 300s in semantic.py to accommodate
slower local LLMs like Ollama
- Refactor RAG integration tests to support multiple providers (ollama,
openai, anthropic, bedrock)
- Remove unnecessary embedding_provider fixture since MCP server handles
embeddings internally
- Add --provider flag via tests/integration/conftest.py
- Add provider_fixtures.py with factory functions for generation providers
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
The Smithery scanner was reporting "0 tools" despite the server returning
valid tool definitions. Root cause: the server was returning SSE-formatted
responses (event: message\ndata: {...}) which the scanner couldn't parse.
Changes:
- Add json_response=True to FastMCP for Smithery stateless mode
- Clean up verbose docstring examples in semantic.py and webdav.py
The MCP spec allows both SSE and plain JSON responses for HTTP transport.
Setting json_response=True returns Content-Type: application/json with
plain JSON-RPC instead of text/event-stream with SSE format.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Implements optional context expansion for semantic search results that
fetches adjacent chunks (N-1 and N+1) from Qdrant to provide before/after
context. Removes configurable chunk overlap (default 200 chars) to avoid
duplicate text appearing in both context and excerpt.
Key changes:
- Add include_context and context_chars parameters to nc_semantic_search
and nc_semantic_search_answer tools
- Implement Qdrant cache fast path for chunk retrieval (avoids re-fetching
and re-parsing documents, especially important for PDFs)
- Add _get_chunk_by_index_from_qdrant() to fetch adjacent chunks
- Remove chunk overlap from before_context (last N chars) and after_context
(first N chars) to prevent duplicate text
- Fetch context in parallel with anyio.Semaphore (max 20 concurrent)
- Pass through page_number from SearchResult to SemanticSearchResult
- Remove document-level deduplication (keep chunk-level dedup from algorithm)
Context expansion is opt-in via include_context=true parameter. When enabled:
- Populates has_context_expansion, marked_text, before_context, after_context
- Adds truncation flags when context exceeds context_chars limit
- Falls back to document fetch for legacy data with truncated excerpts
Related: nextcloud_mcp_server/search/context.py:87-382,
nextcloud_mcp_server/server/semantic.py:161-255
Track character offsets (start_offset, end_offset) for each chunk in vector
database metadata, enabling precise chunk highlighting in visualization pane.
Changes:
- processor.py: Store chunk_start_offset and chunk_end_offset in Qdrant metadata
- processor.py: Added metadata_version=2 to indicate position tracking support
- search/semantic.py: Return chunk positions from search results
- server/semantic.py: Expose chunk positions in API responses (SemanticSearchResult)
Enables viz pane to:
1. Display exact matched chunk with surrounding context
2. Highlight the precise portion of text that matched the query
3. Build user trust by showing what the RAG system actually retrieved
Position tracking uses ChunkWithPosition dataclass from document_chunker.py
which provides character-accurate offsets in the original document.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Move access verification from individual search algorithms to final output
stage, eliminating redundant API calls and improving performance.
## Changes
**New:**
- `search/verification.py`: Centralized verification using anyio task groups
- Deduplicates results by (doc_id, doc_type) before verification
- Verifies all unique documents in parallel using structured concurrency
- Filters out inaccessible documents in single pass
**Modified Search Algorithms:**
- `search/semantic.py`: Removed _deduplicate_and_verify() and _verify_document_access()
- `search/keyword.py`: Removed _verify_access() and parallel verification
- `search/fuzzy.py`: Removed _verify_access() and parallel verification
- `search/hybrid.py`: Removed nextcloud_client parameter passing
All algorithms now return unverified results from Qdrant payload.
**Modified Output Stages:**
- `server/semantic.py`: Added verify_search_results() call after search
- `auth/viz_routes.py`: Added verify_search_results() call after search
Both endpoints now verify access once at final stage with deduplication.
## Performance Impact
**Before:**
- Hybrid mode (limit=10): 30 API calls (10 per algorithm × 3 algorithms)
- Single algorithm: 10-20 API calls (with verification buffer)
**After:**
- Hybrid mode (limit=10): 10 API calls (deduplicated verification)
- Single algorithm: 10 API calls (deduplicated verification)
**Performance Gain:** 3x reduction in API calls for hybrid search
## Architecture Benefits
- **Separation of concerns**: Algorithms handle scoring, output stage handles security
- **Deduplication**: Each document verified exactly once
- **Parallel execution**: All verifications run concurrently via anyio task groups
- **Consistency**: Same verification logic across MCP tools and viz endpoints
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
