Adds a note_pages table backing a tabbed notes panel where the user and
the model can both read and write. Only page titles (plus a short
preview) are injected into the system prompt on every turn; full page
content is kept out of context and fetched on demand via a read_note
tool, with write_note letting the model append to, replace, or create a
page.
Generalizes llm.resolve_web_search into resolve_tool_calls so the
tool-calling loop handles web_search and the new note tools through one
path. The chat stream emits a notes_updated SSE event when the model
edits a note so the frontend panel can refresh; local edits are tracked
as dirty and never clobbered by that refresh.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Sessions can now be downloaded as a JSON file containing the session
metadata and every message with its tags, and re-imported as a new
session from that same format.
GET /chat/sessions/{id}/export streams the session as a file download.
POST /chat/sessions/import validates the roles, then recreates the
session under a fresh UUID so importing never collides with an existing
session. The sidebar gets a per-row download button and an import button
that feeds a hidden file input.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Chat/memory/logs/models APIs were reachable without any auth even
though the app is deployed publicly behind Caddy HTTPS; only the
settings screen had a password. Add an optional SITE_PASSWORD-backed
session cookie gate in front of everything (settings included, on
top of its existing SETTINGS_PASSWORD), with a matching login screen
on the frontend. Stays fully backward compatible: with SITE_PASSWORD
unset the app behaves exactly as before.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
gpu_memory_percent is serialized as JSON null (not omitted) when no
GPU is present, but the template checked `!== undefined`, which is
true for null too. Calling .toFixed() on that null then threw during
render, blanking the whole widget instead of just hiding the GPU row.
Only showed up on GPU-less hosts like a Lightsail instance, not on
this dev machine which has a GPU.
- Add a password-protected /api/settings endpoint (HTTP Basic auth,
backend/app/core/auth.py) backed by a DB-stored allowlist of
connection settings (OPENAI_API_KEY, ANTHROPIC_API_KEY, AWS creds,
OLLAMA_API_BASE, TAVILY_API_KEY, LOCAL_KB_EMBEDDING_MODEL). Saved
values override .env and apply immediately via os.environ, so
Lightsail deployments no longer need SSH + `.env` edits to rotate
keys. Values are always returned masked to the frontend.
- Replace ModelSelector.vue's hardcoded model list with a DB-backed
/api/models CRUD API (read is public, writes reuse the settings
password) so the chat model dropdown can be edited from the GUI;
seed it once with the previous hardcoded presets on first boot.
- Fix local_knowledge.py reading LOCAL_KB_EMBEDDING_MODEL once at
import time instead of per-call, which would have silently ignored
GUI/DB overrides for the embedding model.
- Add SettingsPanel.vue (API keys + model management UI) and document
the new SETTINGS_PASSWORD env var in .env.example and the Lightsail
deploy guide.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
- Add backend/frontend Dockerfiles, nginx reverse proxy config, and
docker-compose.yml to run the app on AWS Lightsail; document the setup
in docs/deploy-lightsail.md. Fix a .gitignore path anchoring bug that
left backend/knowledge_base/web_search/ untracked instead of ignored.
- Summarize web search results into structured Markdown via LLM before
saving them to the local knowledge base, and support regenerating
existing entries from their source URLs (backend/app/core/memory_kb).
- Downgrade vite to ^6 to match @vitejs/plugin-vue's peer dependency
range, fixing a failing `npm ci` (found while testing the Docker build).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Introduces websearch.py (Tavily) + knowledge.py to ground chat responses
in search results, tagging.py to tag user and assistant messages via LLM
and pick related topics for the Discord useless-tips job, and
word_memory.py to track recent conversation nouns (surfaced in the new
WordPool.vue sidebar) used to pick tip topics close to a related tag.
- Cache the latest fetched tomorrow weather and expose it via /api/system/weather/latest
- Add a header Clock widget showing date/time plus the cached weather summary
- Redirect useless-talk mentions from the weather bot to the useless-tips webhook
- Switch Bedrock auth from bearer token to standard IAM access key/secret
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
colcaroliandClaude Opus 5