4 Commits
Author SHA1 Message Date
Denton Social 440e49e76e Author runnable skill bodies via OpenAI-compatible codegen model
create_skill now writes a real predict/act body: the small decision model
still authors title + description (engine.generate), then a larger
OpenAI-compatible model (default qwen38-iq3s) writes the runnable code
against the SKILL.md contract. Bodies persist to data/skills/<cat>/<name>.py,
are hot-loaded via importlib, merged into the running tree, and the request
re-dispatches to the new leaf. The dashboard decision-flow view shows the
title/description with a writing badge while the body is being written.
Codegen failure degrades to a navigable stub.
2026-09-24 00:36:35 -05:00
Denton Social ea2e5b8045 Automate create_category via normal-mode generation of the decision model 2026-09-23 20:45:28 -05:00
Denton Social 0db41241be Add browser dashboard, run tracing, and logged navigation decisions
- dashboard.py: stdlib http.server + JSON API (tree/trace/dream/status,
  POST submit/relabel); static/ single-page Redux-DevTools-style inspector
- trace.py: runs.jsonl lifecycle events keyed by run_id
- scheduler/skills/skill: every decision carries run_id; navigation choices
  now logged (navigate:category/leaf); requeues stamp meta.parent_run
- cli: 'dashboard' subcommand; config.json untracked per-machine (see
  config.example.json)
2026-09-23 13:43:39 -05:00
semif-agent 4e0e0534c4 Add basic version: SemIf decision engine, urgency queue, skill tree, skill loop, decision log, dream pass, CLI 2026-09-23 03:01:45 -05:00