Add nc_notes_semantic_search_answer tool that combines semantic search
with MCP sampling to generate natural language answers from retrieved
Nextcloud Notes. This enables Retrieval-Augmented Generation (RAG)
patterns without requiring a server-side LLM.
Key features:
- Client-side LLM generation via ctx.session.create_message()
- Graceful fallback when sampling unavailable
- Proper source citations in generated answers
- No results optimization (skips sampling when no docs found)
- Comprehensive unit and integration tests
Implementation details:
- SamplingSearchResponse model with generated_answer and sources
- Fixed prompt template with document context and citation instructions
- Model preferences hint Claude Sonnet for balanced performance
- Falls back to returning documents without answer on sampling failure
Updates:
- Add ADR-008 documenting sampling architecture decision
- Add MCP sampling pattern guidance to CLAUDE.md
- Update README.md and docs/notes.md (7 → 9 tools)
- Add 4 unit tests and 6 integration tests
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
This PR fixes multiple OAuth-related issues:
## Unified OAuth Callback
- Consolidated `/oauth/callback-nextcloud` and `/oauth/login-callback` into single `/oauth/callback` endpoint
- Flow type determined by session lookup via state parameter (no query params in redirect_uri)
- Fixes redirect_uri validation issues with IdPs requiring exact match
- Legacy endpoints kept as aliases for backwards compatibility
## PKCE Implementation
- Implemented PKCE (RFC 7636) for Flow 2 (resource provisioning)
- Generate code_verifier and code_challenge
- Store code_verifier in session storage
- Retrieve and use in token exchange
- Fixed PKCE for browser login (integrated mode)
- Previously only worked for external IdP (Keycloak)
- Now works for both Nextcloud OIDC and external IdP
## Login Elicitation Fixes (ADR-006)
- Fixed elicitation URL to route through MCP server endpoint
- Changed from direct Nextcloud URL to `/oauth/authorize-nextcloud`
- Ensures PKCE is properly handled by server
- Fixed login detection after OAuth flow completes
- Look up refresh token by state parameter instead of user_id
- Works even when Flow 1 token not present
- Added `get_refresh_token_by_provisioning_client_id()` method
## Session Authentication
- Fixed `/user/page` redirect loop
- Shared oauth_context with mounted browser_app
- SessionAuthBackend can now validate sessions correctly
## Tests
- Added comprehensive login elicitation test suite
- Updated scope authorization test expectations
- All 43 OAuth tests passing
## Files Changed
- `app.py`: Shared oauth_context, unified callback route
- `oauth_routes.py`: Unified callback, PKCE for Flow 2
- `browser_oauth_routes.py`: PKCE for integrated mode
- `oauth_tools.py`: Fixed elicitation URL generation
- `refresh_token_storage.py`: Added lookup by provisioning_client_id
- `test_login_elicitation.py`: New test suite
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Resolves the token exchange implementation gap where get_session_client()
was implemented but never used by tools. Unifies token acquisition into a
single async get_client() method that handles both pass-through and token
exchange modes transparently.
Core Changes:
- Make get_client() async and merge token exchange logic into it
- Remove scopes parameter from token exchange (Nextcloud doesn't support OAuth scopes)
- Update all 8 tool modules to use await get_client(ctx)
- Fix provisioning decorator to skip checks in BasicAuth mode
Token Acquisition Modes:
1. BasicAuth: Returns shared client (no token operations)
2. OAuth pass-through (default): Verifies and passes Flow 1 token to Nextcloud
3. OAuth token exchange (opt-in): Exchanges Flow 1 token for ephemeral token via RFC 8693
Key Architectural Clarifications:
- Progressive Consent (Flow 1/2) = Authorization architecture
- Token Exchange = Token acquisition pattern during tool execution
- Refresh tokens from Flow 2 are NEVER used for tool calls (only background jobs)
- Nextcloud scopes are "soft-scopes" enforced by MCP server, not IdP
Documentation Updates:
- ADR-004: Added comprehensive token acquisition patterns section
- CRITICAL-TOKEN-EXCHANGE-PATTERN.md: Updated to reflect implementation status
- CLAUDE.md: Updated architectural patterns with async get_client()
Testing:
- All 36 unit tests passing
- All 4 smoke tests passing (BasicAuth mode)
- Linting issues fixed (ruff)
Configuration:
ENABLE_TOKEN_EXCHANGE=false (default) - pass-through mode
ENABLE_TOKEN_EXCHANGE=true (opt-in) - token exchange mode
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Service account tokens (client_credentials grant) violate OAuth "act on-behalf-of"
principles and have been moved to ADR-002's "Will Not Implement" section.
## Problem Discovery
Testing revealed that service account tokens create Nextcloud user accounts
(e.g., `service-account-nextcloud-mcp-server`) due to user_oidc's bearer
provisioning feature. This violates core OAuth principles:
- ❌ Creates stateful server identity in Nextcloud
- ❌ All actions attributed to service account, not real user
- ❌ Breaks audit trail and user attribution
- ❌ Service account becomes "admin by another name"
## Changes
### Documentation (ADR-002)
- Moved service account (old Tier 1) to "Will Not Implement" section
- Added "OAuth Act On-Behalf-Of Principle" section
- Renumbered tiers:
- Tier 1: Impersonation (NOT IMPLEMENTED)
- Tier 2: Delegation via token exchange (IMPLEMENTED)
- Updated status to reflect rejection of service accounts
### Code Warnings
- Added comprehensive warning to KeycloakOAuthClient.get_service_account_token()
- Clarified VALID use: only as subject_token for RFC 8693 token exchange
- Clarified INVALID use: direct API access with service account token
### Supporting Documentation
- CLAUDE.md: Removed outdated "Tier 1" references, added rejection note
- oauth-impersonation-findings.md: Added prominent update banner
- audience-validation-setup.md: Updated tier numbers, added rejection note
- tests/manual/test_token_exchange.py: Added warning comment
## Valid Patterns (ADR-002)
✅ Foreground operations: User's access token from MCP request
✅ Background operations: Token exchange (impersonation/delegation)
✅ Offline access: Refresh tokens with user consent
❌ Service accounts: Creates independent server identity (REJECTED)
## Alternative
If service account pattern is truly needed, use BasicAuth mode instead of
OAuth mode. OAuth mode MUST maintain "act on-behalf-of" semantics.
Related: c12df98 (revert of service account test)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Remove file-based caching of OAuth client credentials and implement automatic
client lifecycle management for test fixtures.
Changes:
- Add RFC 7592 client deletion function in auth/client_registration.py
- Remove cache_file parameter from _create_oauth_client_with_scopes helper
- Update all OAuth credential fixtures to use yield/finalizer pattern
- Add automatic client cleanup at end of test session (best-effort)
- Remove persistent .nextcloud_oauth_*.json cache files
Benefits:
- No persistent cache files cluttering repository
- Fresh OAuth clients created for each test session via DCR
- Automatic cleanup attempts (RFC 7592 DELETE endpoint)
- Cleaner test environment with proper fixture lifecycle
Note: Client deletion may fail due to Nextcloud authentication middleware
(logged as warning). The key improvement is removing persistent cache files.
OAuth clients may accumulate in Nextcloud but can be cleaned manually.