aleleba 959404823a Phase 6.4.25b: parametrize gate5 prompts path, add generalization probe ...

GATE5_PROMPTS_PATH env var lets the same 17-metric harness (veto system,
MCP retry/page handling) run against a different prompts file. Unset
behavior is unchanged -- the official gate 5 (data/gate5_prompts.jsonl,
10 frozen prompts) stays untouched.

data/gate5_generalization_probe.jsonl: 4 prompts in rubros confirmed
absent from the 138-seed corpus, the 10 gate5 prompts, and the 60-prompt
holdout -- ferreteria, gimnasio, tienda de mascotas, panaderia. Swapped
out "veterinaria" (originally planned) after finding seed 83 is a
substantial design-repair seed for a vet clinic; "tienda de mascotas"
verified clean instead. This is an additional check, separate from the
official gate 5, meant to test whether the correction generalizes across
business types rather than overfitting to the pizzeria case.

2026-08-03 22:53:07 +00:00

..

00_verify_hardware.py

Fase 0: scripts de verificacion de hardware e inspeccion de modulos

2026-07-28 03:52:10 +00:00

01_inspect_modules.py

Fase 0: scripts de verificacion de hardware e inspeccion de modulos

2026-07-28 03:52:10 +00:00

03_build_replay.py

Fix: OUTPUT_PATH de 03_build_replay.py apuntaba a /workspace/... (ruta de contenedor inexistente en el host)

2026-07-28 12:51:55 +00:00

04_sanitize.py

Fase 2: 04_sanitize.py - scrubbing de secretos de skills/agentes/plans (10 secretos unicos, gate en verde)

2026-07-29 00:35:59 +00:00

05_build_dataset.py

Phase 6.3: fix the augmentation, close the holdout leak, stop rewarding invented parameters

2026-07-30 17:16:05 +00:00

06_validate_dataset.py

Phase 6.3: fix the augmentation, close the holdout leak, stop rewarding invented parameters

2026-07-30 17:16:05 +00:00

07_build_lora2_mix.py

Phase 6.3: stop the gate depending on penpot.root, and stop blaming the plugin for its own bugs

2026-07-30 20:07:40 +00:00

07_lint_penpot_code.py

Phase 6.3: add the LoRA #2 mix builder and refine the linter

2026-07-30 17:11:36 +00:00

10_train.py

Phase 6.4.20: fix eval OOM by pinning per_device_eval_batch_size

2026-07-31 00:44:54 +00:00

20_merge_lora.py

Phase 6.4: make the gates fail when they cannot verify something

2026-07-30 17:37:46 +00:00

21_quantize_nvfp4.py

Phase 6.4: make the gates fail when they cannot verify something

2026-07-30 17:37:46 +00:00

30_eval_suite.py

Phase 6.4: make the gates fail when they cannot verify something

2026-07-30 17:37:46 +00:00

31_build_holdout_prompts.py

Phase 6.3: fix the augmentation, close the holdout leak, stop rewarding invented parameters

2026-07-30 17:16:05 +00:00

32_gate2_toolcalls.py

Phase 6.3: fix the augmentation, close the holdout leak, stop rewarding invented parameters

2026-07-30 17:16:05 +00:00

33_gate3_adherencia.py

Phase 6.3: fix the augmentation, close the holdout leak, stop rewarding invented parameters

2026-07-30 17:16:05 +00:00

34_gate4_e2e.py

Fase 5: puertas 2-4 - permitir results filename configurable via env var

2026-07-29 22:39:23 +00:00

35_build_penpot_design_holdout.py

Phase 6.3: fix the augmentation, close the holdout leak, stop rewarding invented parameters

2026-07-30 17:16:05 +00:00

35_gate5_penpot_design.py

Phase 6.4.25b: parametrize gate5 prompts path, add generalization probe

2026-08-03 22:53:07 +00:00