stage-3c: unsloth QLoRA training scaffold for Qwen3.5

Dockerfile.train builds a CUDA 12.4 + unsloth container that consumes the
Trainline JSONL datasets and emits a LoRA adapter at data/adapters/<run>/final.
Defaults target a 24 GB GPU (Qwen3.5-4B-Instruct-bnb-4bit, r=16, bf16, 3 epochs,
effective batch 8). README documents the build + run workflow.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

README.md

@@ -107,11 +107,49 @@ encrypted to authorized recipients via Sealine before any routing decision.
 
 ---
 
+## Training (Trainline + QLoRA)
+
+`psyc train-build-all` emits Alpaca-style JSONL datasets under
+`data/datasets/<task>-v<n>.jsonl` for four defensive tasks: `ioc_extraction`,
+`severity_classification`, `routing_decision`, `tlp_assignment`. QualityGate
+drops `TLP:RED`, restricted sources, empty/oversize, and credential-leak rows
+per the dossier's training-data policy.
+
+To fine-tune Qwen3.5-4B with QLoRA in an NVIDIA Docker container:
+
+```bash
+# 1. build datasets (one-off; re-run after ingestion changes)
+.venv/bin/psyc train-build-all
+
+# 2. build the training image (CUDA 12.4 + unsloth + Qwen3.5)
+docker build -t psyc-trainer -f Dockerfile.train .
+
+# 3. fine-tune (mount host data/ so adapters land there)
+docker run --gpus all --rm \
+    -v $(pwd)/data:/data \
+    psyc-trainer \
+    --dataset /data/datasets/ioc_extraction-v1.jsonl \
+    --dataset /data/datasets/severity_classification-v1.jsonl \
+    --dataset /data/datasets/routing_decision-v1.jsonl \
+    --dataset /data/datasets/tlp_assignment-v1.jsonl \
+    --output /data/adapters/psyc-v1
+```
+
+Defaults target a 24 GB consumer GPU (3090/4090): Qwen3.5-4B-Instruct at 4-bit,
+LoRA `r=16`/`alpha=16`, bf16, 3 epochs, effective batch size 8. For A100-40/80
+bump `--base-model unsloth/Qwen3.5-9B-Instruct-bnb-4bit` and raise
+`--batch-size` + `--max-seq-length`.
+
+Output: `data/adapters/psyc-v1/final/` (adapter weights) + `training_meta.json`
+(base model, hyperparameters, dataset list).
+
 ## Status
 
-Day 2 of a 48h build. Stage 1 shipped (Scoutline → DB → Cockpit list & detail).
-Stage 2 next: Classifyline → Sealine (PyNaCl sealed boxes) → Routeline →
-mock CERT destination → Ledgerline writes + `/ledger` cockpit page.
+Day 2 of a 48h build. Shipped: Scoutline (URLhaus) → Classifyline → Mapline
+(GeoResolver via ip-api.com) → Sealine (PyNaCl sealed boxes) → Routeline →
+Courier → mock CERT → Ledgerline. Cockpit has cases / case detail / ledger
+pages and a design-token CSS layer. Trainline emits LoRA-ready JSONL;
+`Dockerfile.train` builds an unsloth + Qwen3.5 QLoRA training container.
 
 ## License