- #627: Set source.asset (URL/file_path) before save() in async creation
path so failed sources are identifiable and retry works
- #670: Only overwrite source title if it's a placeholder ("Processing...")
or empty, preserving user-set custom titles
- #651: Cascade-delete linked models when credential is deleted instead of
returning 409 Conflict; remove unused delete_models parameter
- Add tests for all three fixes (12 new tests)
- Add .harness and .mcp.json to .gitignore
* docs: update CLAUDE.md and user docs for error handling and podcast retry
Add missing documentation for features introduced in v1.7.2 (#590) and
v1.7.3 (#595): error classification system, global exception handlers,
ConfigurationError, podcast failure recovery, and retry endpoint.
* chore: update uv.lock
Resolve conflicts in ask.py and chat.py by merging the try/except error
handling from main with the extract_text_content helper from the PR.
Also apply the same fix to source_chat.py and transformation.py which
had the same vulnerable isinstance/str() pattern for structured LLM
response content (e.g. Gemini's envelope format).
Replace generic "An unexpected error occurred" messages with descriptive,
user-friendly error messages when LLM operations fail. Errors like invalid
API keys, wrong model names, and rate limits now surface clearly in the UI.
Adds error classification utility, global FastAPI exception handlers, and
frontend getApiErrorMessage() helper. Bumps version to 1.7.2.
Add empty-content validation in content_process() after extract_content()
returns. Sources with no extractable text (e.g. YouTube videos without
transcripts) now raise ValueError immediately instead of silently saving
an empty source. ValueError is already configured as a permanent failure
in the retry config, so no retries are wasted on unrecoverable situations.
Closes#527
Source.vectorize() wrapped its own ValueError in DatabaseOperationError,
bypassing the stop_on=[ValueError] retry guard in process_source_command.
This caused up to 15 retries when processing files with no extractable
text, blocking sync API requests indefinitely.
- Re-raise ValueError directly in Source.vectorize() instead of wrapping
- Add .strip() check to catch whitespace-only content
- Skip vectorization gracefully in save_source() when content is empty
- Add unit tests for vectorize error handling
Fixes#560
Some LLM providers (notably Gemini, DeepSeek via OpenAI-compatible
proxies) return ai_message.content as a list of content parts:
[{'type': 'text', 'text': '...', 'extras': {...}}]
The current code uses str() on non-string content, which produces the
Python repr of the entire list — not valid JSON. This breaks
PydanticOutputParser.parse() with OutputParserException.
This adds extract_text_content() to properly unwrap text from both
string and structured content formats, applied in ask.py, chat.py,
and prompt.py.
Fixes#329
* feat: content-type aware chunking and unified embedding
- Add chunking.py with HTML, Markdown, and plain text detection
- Add embedding.py with mean pooling for large content
- Create dedicated commands: embed_note, embed_insight, embed_source
- Use fire-and-forget pattern for embedding via submit_command()
- Refactor rebuild_embeddings_command to delegate to individual commands
- Remove legacy commands and needs_embedding() methods
- Reduce chunk size to 1500 chars for Ollama compatibility
- Update CLAUDE.md documentation for new architecture
Fixes#350, #142
* fix: address code review issues
- Note.save() now returns command_id for tracking embedding jobs
- Add length check after generate_embeddings() to fail fast on mismatch
- Add numpy as explicit dependency (was transitive)
- Remove hardcoded chunk sizes from docstrings
* docs: address code review comments
- Rename "SYNC PATH" to "DOMAIN MODEL PATH" in embedding router
- Add test_chunking.py and test_embedding.py to Testing Strategy
- Clarify auto-embedding behavior for each domain model
* fix: clean thinking tags from prompt graph output
Adds clean_thinking_content() to prompt.py to handle extended thinking
models that return <think>...</think> tags. This fixes empty titles
when saving notes from chat.
* chore: remove local docker-compose from git
* fix(frontend): handle null parent_id in search results
Add defensive check for null parent_id in search results to prevent
"Cannot read properties of null (reading 'split')" error. This can
happen with orphaned records in the database.
* fix: cascade delete embeddings and insights when source is deleted
When deleting a Source, now also deletes associated:
- source_embedding records
- source_insight records
This prevents orphaned records that cause null parent_id errors
in vector search results.
* fix: add cleanup for orphan embedding/insight records in migration 10
Deletes source_embedding and source_insight records where the
linked source no longer exists (source.id = NONE).
* chore: bump esperanto to 2.16
Increases ctx_num for Ollama models to accommodate larger notebook
context windows. See: https://github.com/lfnovo/esperanto/pull/69
Use model_copy() instead of creating new AIMessage to preserve
response_metadata, id, usage_metadata, etc. Also adds test coverage
for malformed thinking tags pattern.
Addresses PR #333 feedback from lfnovo and cubic-dev-ai.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add thinking content cleaning to notebook and source chat graphs.
Previously, models that output <think>...</think> tags (like DeepSeek)
or malformed variants without opening tags (like Nemotron) would leak
reasoning content into user-visible responses.
Changes:
- chat.py: Clean AI response content before returning messages
- source_chat.py: Same fix for source-specific chat
- text_utils.py: Handle malformed output where opening <think> tag
is missing but </think> is present
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* chore: improve podcast transcripts
* fix: remove date from insight - fixes#241
* fix: improve scrolling on source and insights - fixes#237
* chore: update esperanto to fix: #234
* chore: update esperanto to fix#226
* fix: process vectorization as subcommands to handle larger documents more gracefully - fix: #229
* feat: enable background job retry capabilities
* feat: reenable content types that were disabled during alpha version
* fix: remove unnecessary model caching causing many issues.
* feat: support multiple azure endpoints and keys just like openai compatible. Fixes#215
* docs: update azure variables
* chore: bump and update dependencies
New front-end
Launch Chat API
Manage Sources
Enable re-embedding of all contents
Sources can be added without a notebook now
Improved settings
Enable model selector on all chats
Background processing for better experience
Dark mode
Improved Notes
Improved Docs:
- Remove all Streamlit references from documentation
- Update deployment guides with React frontend setup
- Fix Docker environment variables format (SURREAL_URL, SURREAL_PASSWORD)
- Update docker image tag from :latest to :v1-latest
- Change navigation references (Settings → Models to just Models)
- Update development setup to include frontend npm commands
- Add MIGRATION.md guide for users upgrading from Streamlit
- Update quick-start guide with correct environment variables
- Add port 5055 documentation for API access
- Update project structure to reflect frontend/ directory
- Remove outdated source-chat documentation files
Creates the API layer for Open Notebook
Creates a services API gateway for the Streamlit front-end
Migrates the SurrealDB SDK to the official one
Change all database calls to async
New podcast framework supporting multiple speaker configurations
Implement the surreal-commands library for async processing
Improve docker image and docker-compose configurations
