Skip to content

chore(skills): gen3 measurement lands as HOLD — verifier invalidated the promotion #726

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
drewstone merged 5 commits into from
Aug 3, 2026
Merged

chore(skills): gen3 measurement lands as HOLD — verifier invalidated the promotion #726

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
76b8d4c
refactor(skills): pin agent-graphs generation records under generations/
drewstone Aug 3, 2026
7513e2e
feat(skills): add two train cases for the mission-in-deliverable cluster
drewstone Aug 3, 2026
59c92ba
feat(skills): promote agent-graphs SKILL.md v3 through the gen3 gated…
drewstone Aug 3, 2026
b0a4905
revert(skills): hold gen3 — adversarial verification invalidated the …
drewstone Aug 3, 2026
343e1af
docs(skills): record gen3 as HOLD in the version history
drewstone Aug 3, 2026
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
2 changes: 2 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,3 +18,5 @@ corpus/
test_repo/
.sic-run-*/
.swe-run-*/
.gen2-runs/
.gen3-runs/
4 changes: 2 additions & 2 deletions bench/src/agent-graphs-gen2.mts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@
* Smoke: GEN2_SMOKE=1 pnpm tsx src/agent-graphs-gen2.mts — stubs both LLM calls,
* exercises the full loop wiring + gate + report at zero cost.
*
* Writes skills/agent-graphs/gen2.json; on ship, replaces SKILL.md with v2.
* Writes skills/agent-graphs/generations/gen2.json; on ship, replaces SKILL.md with v2.
*/

import { createHash } from 'node:crypto'
Expand Down Expand Up @@ -56,7 +56,7 @@ import {
const HERE = dirname(fileURLToPath(import.meta.url))
const REPO = join(HERE, '..', '..')
const SKILL_PATH = join(REPO, 'skills', 'agent-graphs', 'SKILL.md')
const OUT_PATH = join(REPO, 'skills', 'agent-graphs', 'gen2.json')
const OUT_PATH = join(REPO, 'skills', 'agent-graphs', 'generations', 'gen2.json')
const RUNS_ROOT = join(REPO, '.gen2-runs')
const SMOKE = process.env.GEN2_SMOKE === '1'

Expand Down
Loading