lhumina_code/home
0
0
Fork 0
Code Issues 63 Pull requests Projects Releases Packages Wiki Activity Actions

slides + research app -> TFGrid VM ZOS #243

New issue
Open
opened 2026-06-03 12:57:05 +00:00 by despiegk · 1 comment
despiegk commented 2026-06-03 12:57:05 +00:00
Owner
Copy link

what

  • slides in 2 modes (web, picture generation, export to pptx for the web)
  • research app: light frontend on top of kimi agent for research purposes = background checks

tech

  • made with oschema and blueprint (for researcher)
  • use python runner for docx generation

deliverable < weekend

  • run on main in cloud TFGrid
  • voice integrated

info

  • skills/automation/background_check.md
  • see 'lab agent' run in proc
## what - [ ] slides in 2 modes (web, picture generation, export to pptx for the web) - [ ] research app: light frontend on top of kimi agent for research purposes = background checks tech - [ ] made with oschema and blueprint (for researcher) - [ ] use python runner for docx generation deliverable < weekend - [ ] run on main in cloud TFGrid - [ ] voice integrated info - skills/automation/background_check.md - see 'lab agent' run in proc
despiegk added this to the ACTIVE project 2026-06-03 12:57:14 +00:00
despiegk changed title from slides + research app, ready for future to slides + research app -> TFGrid VM ZOS 2026-06-03 12:57:30 +00:00
casper-stevens commented 2026-06-08 14:15:27 +00:00
Member
Copy link

Research-app status / audit — full technical breakdown filed as lhumina_code/hero_researcher#9.

hero_researcher today is a working TS→Rust port (multi-model research pipeline), mid-migration to Hero-canonical. Measured against this issue's checklist:

  • made with oschema and blueprint — NOT yet. _server ships a hand-written openrpc.json + dispatch_rpc(); schema/service.oschema exists but drives no codegen; no generated _sdk. This is the main gap — needs openrpc_server!-over-oschema migration + alignment to hero_blueprint/blueprints/service.
  • python runner for docx — NOT yet. Formatter emits markdown/json/html only (maps to md2docx).
  • light frontend on the kimi agent (= background checks) — partial. Current pipeline drives herolib_ai across many models, not a kimi-agent frontend; not wired to background_check / lab agent.
  • voice integrated — NOT yet.
  • run on main in cloud TFGrid (ZOS) — NOT yet (local UDS service only).

Already done: working pipeline (6 search providers, 8 platform scrapers, 3 tiers), JSON-RPC 2.0 server + HTML admin dashboard over rpc.sock/admin.sock, SQLite job persistence, canonical service.toml + service_base!() (passes lab infocheck), 13 runnable examples.

Detailed findings, deliberate-vs-drift breakdown (from commit history), and recommended sequencing are in lhumina_code/hero_researcher#9.

**Research-app status / audit** — full technical breakdown filed as `lhumina_code/hero_researcher#9`. `hero_researcher` today is a working TS→Rust port (multi-model research pipeline), mid-migration to Hero-canonical. Measured against this issue's checklist: - [ ] **made with oschema and blueprint** — NOT yet. `_server` ships a hand-written `openrpc.json` + `dispatch_rpc()`; `schema/service.oschema` exists but drives no codegen; no generated `_sdk`. This is the main gap — needs `openrpc_server!`-over-oschema migration + alignment to `hero_blueprint/blueprints/service`. - [ ] **python runner for docx** — NOT yet. Formatter emits markdown/json/html only (maps to `md2docx`). - [ ] **light frontend on the kimi agent (= background checks)** — partial. Current pipeline drives `herolib_ai` across many models, not a kimi-agent frontend; not wired to `background_check` / `lab agent`. - [ ] **voice integrated** — NOT yet. - [ ] **run on `main` in cloud TFGrid (ZOS)** — NOT yet (local UDS service only). **Already done:** working pipeline (6 search providers, 8 platform scrapers, 3 tiers), JSON-RPC 2.0 server + HTML admin dashboard over `rpc.sock`/`admin.sock`, SQLite job persistence, canonical `service.toml` + `service_base!()` (passes `lab infocheck`), 13 runnable examples. Detailed findings, deliberate-vs-drift breakdown (from commit history), and recommended sequencing are in `lhumina_code/hero_researcher#9`.
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
development
main
No results found.
Labels
Clear labels   
meeting-notes

Meeting notes and follow-ups

  
meeting-transcript

Raw meeting transcript; AI drafts the report

No labels
meeting-notes
meeting-transcript
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
ACTIVE
Assignees
Clear assignees
No assignees
casper-stevens
2 participants
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
lhumina_code/home#243
No description provided.