Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,12 @@ All notable changes to this project are documented here, following
parallel. Stress-verified 12/12 green (previously intermittent).

### Added
- **`factcli` is now a `live_verified` hub card** — the self-contained reference
proof target (PR #21) gained a demo manifest (`demos/factcli.yaml`) and a real
recorded run: the loop refactored it **F → A** (Gemini refiner, real cli-judge,
no Anthropic), recorded via `demo record` (KTD2). The hub now shows **two**
verified-run cards (15 demos / 6 recipes); `factcli` joins the graduated cohort
in `tests/test_starter_demos.py`.
- **`automate-your-job` graduated from recipe → live `live_verified` demo** — the
first recipe to become a real, recorded run. A team-lead's repetitive task
(turn a captured day of activity into a standup digest) was handed to the loop:
Expand Down
10 changes: 10 additions & 0 deletions demos/factcli.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
id: factcli
title: factcli — self-contained agent-native CLI
domain: Self-contained proof
target: a tiny CLI graded on the D2 non-interactive contract (version / project new / fs ls)
lane: codebase
goal: refactor a deliberately-buggy CLI until it passes the cli-judge D2 contract — the
self-contained reference loop that needs no external catalog tool or Go toolchain
kind: demo
contributor: wjlgatech
result_ref: factcli.json
12 changes: 12 additions & 0 deletions demos/results/factcli.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
{
"demo_id": "factcli",
"source": "live_verified",
"grade_trajectory": [
"F",
"A"
],
"final_grade": "A",
"convergence_status": "converged",
"report_ref": "factcli.report.md",
"engine_version": "0.1.0"
}
10 changes: 10 additions & 0 deletions demos/results/factcli.report.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
# Research report — run #2

- Target: factcli (D2 contract) (codebase lane)
- Goal: make factcli agent-native
- Status: **converged** | Final grade: **A**
- Iterations: 2
- Grade trajectory: F -> A

## Learnings compounded
- (none)
2 changes: 1 addition & 1 deletion tests/test_starter_demos.py
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@
# Graduated self-contained demos: recipes that became real, `live_verified` demos
# via an actual F->A loop run + `demo record` (a third cohort, distinct from the 10
# article starters and the catalog proof-targets). These legitimately ship verified.
GRADUATED_DEMO_IDS = {"automate-your-job"}
GRADUATED_DEMO_IDS = {"automate-your-job", "factcli"}


def _reg():
Expand Down
Loading