Tool calls were invisible until the answer arrived: the only trace was the
sources list, and only for web searches. Surface them as they happen instead.
Add llm.stream_tool_calls(), an incremental version of resolve_tool_calls()
that yields a start and a completion event per tool call and ends with a
"resolved" event carrying the previous return value. resolve_tool_calls() is
kept as a thin wrapper that drops the progress events.
api/chat.py relays those events as a new SSE "tool" event, and wraps the
search-summary/knowledge-save step in one of the same shape, since it is a
noticeable pause of its own.
On the front end, ToolActivityList.vue renders one row per tool above the
assistant bubble (label, target, spinner while running, short result when
done). The store merges events by id and marks anything still running as
interrupted when the stream ends early. Display only - not persisted, so the
rows disappear when the session is reloaded, same as sources.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
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>
- 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>
- Split backend/app/core into weather/, discord/, memory_kb/, search/
subpackages by responsibility, keeping config.py and llm.py as the
shared foundation; updated all import sites accordingly.
- Add local Markdown knowledge base support (local_knowledge.py,
knowledge_base/fgo.md, LOCAL_KB_* settings) that embeds and injects
relevant docs into the system prompt by topic similarity.
- Add ruff and pyright as backend dev dependencies with basic config
in pyproject.toml for linting and type checking.
- Document local machine quirks in CLAUDE.md (Postgres on port 8080,
SSLKEYLOGFILE breaking litellm/pyright via OPENSSL_Uplink crashes).
- Add backend/run_dev.ps1 dev launcher and docs/discord-bot.md.
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.
colcaroliandClaude Opus 5