Commit Graph

6 Commits

Author SHA1 Message Date
Scott Idem
1fa5151d8a fix: correct V3 search filter key and response field names in ae_knowledge
- Filter key is "and" not "and_filters" (V3 API format)
- Entry IDs use journal_entry_id/id, not id_random (id_random is None)
- Dates use updated_on/created_on, not updated_at/created_at
- Total count lives in meta.data_list_count, not top-level total/count
- Inject query_string="%" when and filters present but no query, since
  the V3 search engine requires query_string for filters to apply
- Normalize tags from string to list in both entry_read and entries_list
- Fix order_by to use updated_on (not updated_at) in entries_list
- Correct ARCH__AE_INTEGRATION.md: and_filters → and, or_filters → or

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-30 21:12:44 -04:00
Scott Idem
71e472bebe feat: improved ae_journal_search + AE integration docs
Search improvements:
- Switched from LIKE on default_qry_str to query_string path (fulltext
  MATCH/AGAINST IN BOOLEAN MODE — uses the index, supports +/- boolean ops)
- Added tag filter (icontains on tags field)
- Added date_from / date_to filters (created_on gte/lte)
- Added type_code / topic_code exact-match filters
- Added sort_by / sort_order control (updated, created, name, priority)
- Added status / priority filters
- Added page parameter for pagination
- Richer output: updated date, tags, pagination hint
- Updated Gemini tool declaration with all new params

Docs:
- documentation/ARCH__AE_INTEGRATION.md — journal_entry full schema,
  search operator reference, current tool inventory, planned phases
  (broader AE integration: tasks, people, calendar, knowledge import)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-30 20:10:04 -04:00
Scott Idem
77327d97ad feat: improve AE Journal read toolset
- ae_journal_entry_read: expose full entry content by id_random (title,
  journal, tags, summary, full content with configurable truncation)
- ae_journal_entries_list: browse all entries in a journal newest-first,
  numbered with id/title/tags/summary/date and pagination support
- ae_journal_search: richer output — tags, updated date, 400-char preview
  (was 200), show summary OR preview (not both when summary exists)

_get_entry() was already implemented; read tool just exposes it properly.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-30 19:47:59 -04:00
Scott Idem
ed191cf0b4 feat: add journal entry update, disable, append, prepend tools
Four new tools for full journal entry lifecycle management:

- ae_journal_entry_update  — PATCH any combination of fields (title,
  content, summary, tags, enable); only provided fields are changed
- ae_journal_entry_disable — soft-delete via enable=false
- ae_journal_entry_append  — fetch entry, append timestamped section
  to the bottom (ideal for running logs / data logs)
- ae_journal_entry_prepend — fetch entry, prepend timestamped section
  to the top (most-recent-first pattern)

Shared _get_entry / _patch_entry helpers keep the read-modify-write
logic DRY. Also fixed journal_entry_create to prefer the canonical
journal_entry_id field over the legacy id_random alias.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-28 22:02:22 -04:00
Scott Idem
44f215c764 feat: add ae_journal_list tool
Lists all Aether Journals for the configured account via
POST /v3/crud/journal/search with no filters (account scoped by header).
Returns name + id_random for each journal so the agent can discover
available journals before searching or writing entries.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-28 21:50:02 -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