Scott Idem
750cde489d
feat: session_search tool + tool expansion docs update
...
session_search (tools/files.py):
- Full-text search across past session logs, exposed to the orchestrator
- Params: query (required), limit (default 5, max 20)
- Returns dated excerpts, newest first; own sessions only via ContextVars
- User-level — no TOOL_ROLES gating needed
- Registered in __init__.py callables + TOOL_CATEGORIES["Files"]
ARCH__FUTURE.md §2: updated tool count to 44, marked prior tools complete,
added Round 2 planned tools table (session_search now done, reminders due dates,
http_post, nc_talk_history, task_list priority filter, http_fetch max_chars),
noted datetime_now is not needed (already in system prompt via context_loader)
TODO__Agents.md: session_search checked off, Round 2 task list added
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-08 21:41:26 -04:00
Scott Idem
1603ad5124
docs: sync TODO and ARCH__FUTURE — local orchestrator status, new tools, fleet/mesh plans
...
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-04-29 19:05:11 -04:00
Scott Idem
1cc7988953
feat: add shell_exec tool and fix orchestrator model name resolution
...
- Add shell_exec to orchestrator tool suite (system.py + __init__.py)
Runs arbitrary shell commands on the Cortex host with timeout (1–120s),
combined stdout/stderr output, optional working_dir, and exit code reporting.
Enables system diagnostics (df, ls, ps, journalctl, etc.) from Agent mode.
- Fix orchestrator_engine.run() to use model_name from resolved registry entry
Previously used settings.orchestrator_model (.env hardcode) regardless of
what model was assigned to the orchestrator role. Now accepts model_name param
and falls back to settings value only when registry has no model_name.
- Update ARCH__FUTURE.md: date, running host, local orchestrator status,
model registry V2 progress, added Cortex Mesh concept (section 9)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-04-28 20:29:46 -04:00
Scott Idem
a4daebdc9b
feat: local LLM multi-model, session search, cron proactive types, notifications, docs overhaul
...
Local LLM:
- user_settings.py: per-user hosts/models config (local_llm.json)
- routers/local_llm.py + static/local_llm.html: dedicated settings page
- llm_client.py: local OpenAI-compatible backend via httpx
- config.py: LOCAL_API_URL/KEY/MODEL + per-backend timeouts
- Active model shown near backend toggle (amber hint text)
Memory distillation:
- memory_distiller.py: DISTILL_BACKEND_MID/LONG .env overrides
- scheduler.py + notification.py: notify NC Talk after mid/long distill
- notification.py: outbound channel abstraction (NC Talk, extensible)
Session search:
- routers/files.py: GET /sessions/search?q= with excerpts grouped by date
- static/index.html + app.js: search UI in file sidebar with highlight
- _esc() helper to prevent XSS in search results
Proactive cron:
- cron_runner.py: new job types — message (send directly) and brief (LLM + send)
- Both support optional per-job channel override
Channels:
- routers/nextcloud_talk.py: consolidated using notification._send_nct_message()
- routers/auth.py: local backend status in /auth/status
- routers/chat.py: /backend returns {primary, fallback, local_model} object
UI / UX:
- Copy button for user messages (matching assistant)
- Autocomplete disabled on sensitive form fields
- settings.html: local model section replaced with link to /settings/local
Docs overhaul:
- MASTER.md hub + ARCH__SYSTEM/BACKENDS/PERSONA/CHANNELS/FUTURE.md
- ARCH__Intelligence_Layer.md replaced with redirect table
- CORTEX.md trimmed to vision only; README updated
- OPEN_WEBUI_API.md added to docs/
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-04-05 20:53:06 -04:00
