final submission

fix(sft): move max_seq_length + dataset_text_field to SFTTrainer

fix(training): follow unsloth's Qwen3 guide exactly

feat(training): switch from LoRA to QLoRA per mentor recommendation

fix(training): upgrade to torch 2.5.1+cu124, restore unsloth for Qwen3

fix(training): drop unsloth, use bitsandbytes+PEFT for SFT

feat(training): A10G-optimised pipeline — auto train.py, Dockerfile.train, GH Action sync

perf(trajectory_gen): parallel workers + JSONL checkpoint for resume

fix(trajectory_gen): add --scenarios-dir flag for server-free generation

fix(submission): Dockerfile, wire-format fixes, scenario loading, real-scenario MockEnvClient

feat(training): Phase C6 — ablations, training curves, readme finalization

feat(training): Phase C5 — evaluation harness, baselines, plots, readme table

feat(training): Phase C4 — GRPO training, SFT warmstart, rollout, custom trainer

feat(training): Phase C3 — SFT trajectory generator, env clients, mock env

feat(phase-0): foundation — uv project, schemas, mocks, manifest, CI