Scott.Idem/Cortex-Inara
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
31 Commits 1 Branch 0 Tags
6316ffa1d4ffaba2a3a83eea8823a277eecc8b5d
Commit Graph

5 Commits

Author SHA1 Message Date
Scott Idem
6316ffa1d4 feat: cron job system for Inara (remind + note types) 
- cron_runner.py: job storage (CRONS.json), schedule parsing, execution
- tools/cron.py: cron_list/add/remove/toggle + reminders_clear tools
- scheduler.py: load user crons at startup, expose get_scheduler() for
  live add/remove without restarts
- context_loader.py: auto-include REMINDERS.md in system prompt (tier 2+)
  so cron reminders surface automatically without Inara having to poll
- inara/CRONS.json + REMINDERS.md: backing files (initially empty)

Schedule formats: hourly | daily | daily:HH:MM | weekly:DOW | weekly:DOW:HH:MM
Job types: remind (→ REMINDERS.md) | note (→ SCRATCH.md)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-20 21:17:49 -04:00
Scott Idem
1b32667872 feat: scratchpad tool + fix Claude auth token expiry warning 
- Add cortex/tools/scratch.py with scratch_read/write/append/clear tools
- Register all four scratch tools in the orchestrator tool registry
- Create inara/SCRATCH.md as the backing file (never distilled/archived)
- Fix auth.py: expiresAt reflects short-lived access token (~8h) not the
  1-year refresh token — suppress expiry warning when refreshToken is present

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-20 21:10:03 -04:00
Scott Idem
24d16734a5 feat: personal task management tools for Inara 
Adds task_list, task_create, task_update, task_complete orchestrator tools
backed by inara/TASKS.json — private to each agent instance.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-18 23:17:38 -04:00
Scott Idem
9b818aa5c7 feat: orchestrator Agent mode UI + claude_allow_dir tool + fix DDG search 
- Add Agent mode toggle to web UI input row — routes through POST /orchestrate
  instead of /chat; polls for result with live tool-call count in thinking bubble
- Add cortex/tools/system.py with claude_allow_dir tool; registers in tool registry
- Fix web search: duckduckgo_search renamed to ddgs, update import + requirements.txt
- Allow WebSearch and WebFetch in ~/.claude/settings.json for Claude CLI fallback
- Add claude-allow-dir script docs and security note to CLAUDE.md

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-18 22:42:44 -04:00
Scott Idem
ed472ce9a0 feat: Intelligence Layer Phase 1 — orchestrator service 
Adds the Gemini API orchestrator (ReAct tool loop → Claude responder):

Orchestrator engine + router:
- orchestrator_engine.py: Gemini API tool loop, Claude CLI handoff
- routers/orchestrator.py: POST /orchestrate (async job queue), GET /orchestrate/{job_id}

Tools (cortex/tools/):
- web.py: DuckDuckGo web search (no key required)
- ae_knowledge.py: ae_journal_search + ae_journal_entry_create (AE V3 API)
- ae_tasks.py: ae_task_list (reads agents_sync Kanban filesystem)
- files.py: file_read (path-allowlisted to safe dirs)

Config + deps:
- config.py: orchestrator, DuckDuckGo, and AE API settings
- requirements.txt: google-genai, duckduckgo-search
- .env.default: reference config with all new keys documented

Docs:
- CLAUDE.md, README.md, documentation/ added to repo
- Port references updated 7331 → 8000 throughout
- Default model updated to gemini-2.5-flash

Tested: ae_task_list, ae_journal_search, web_search all working end-to-end.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-18 19:37:49 -04:00