Kral d83a39a8d8 MLX server: prompt cache limit (memory); restart after the T01 test ...

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014aUaQeLnwbb1zTpN7kHeat

2026-10-03 18:47:03 +02:00

docs

MLX server: prompt cache limit (memory); restart after the T01 test

2026-10-03 18:47:03 +02:00

harness

G0181: restore ALV output in K spec; K prompt keeps output form

2026-10-03 18:26:24 +02:00

tasks

Runner: G2 finds the FUNCTION statement after local classes; budget floor applied to all tasks

2026-10-03 18:25:30 +02:00

tasks_gen/eval

Handover notes, train/STATE.md, detached night chain for DeepSeek reruns and the stage 1 baseline

2026-10-03 18:34:07 +02:00

train

MLX server: prompt cache limit (memory); restart after the T01 test

2026-10-03 18:47:03 +02:00

.env.example

Harness: runner, generator, tasks T01 T13 T14 T15, CLAUDE.md

2026-10-02 21:42:51 +02:00

.gitignore

Ignore train/.venv

2026-10-03 17:34:02 +02:00

CLAUDE.md

Empirical filter runner (DeepSeek); real cost ratio in docs

2026-10-03 09:29:20 +02:00

package-lock.json

Harness: runner, generator, tasks T01 T13 T14 T15, CLAUDE.md

2026-10-02 21:42:51 +02:00

package.json

Harness: runner, generator, tasks T01 T13 T14 T15, CLAUDE.md

2026-10-02 21:42:51 +02:00

Description

ABAP LLM Training

2.4 MiB

Languages

ABAP 90.6%

Python 6.3%

ABAP CDS 3%

Shell 0.1%