2026-10-19 14:47:59 -07:00
1 changed files with 11 additions and 0 deletions
@@ -69,6 +69,17 @@ happened. The adapter's own card table is **not** evidence here: it was measured
 packing. Rollback is `LORA_FILE=` (empty) in the env and one redeploy — no rebuild, no payload
 move; `LORA_SCALE=0` is the same result through the flag.
 **Measured on the cutover boot (2026-10-19, `02d04bc`).** Before: both probe prompts
 opened `I cannot provide…`. After: neither carries a refusal marker — one ran to its
 2 048-token cap, the other finished at 1 930 — so the direction is out. It still
 volunteers a `⚠️ Important Disclaimer` heading before answering, which is style, not the
 circuit: the marker sentence is gone, and a leading hedge is not an escape hatch. Chat,
 tools (`tool_calls` with valid JSON) and vision ("Red", 281 prompt tokens) answered from
 the same boot, and `DropInPaths` came back empty. Read the ledger, not this paragraph,
 for provenance: the fork prints the adapter's `prism.abliterate.*` keys — including the
 `base_gguf = Ternary-Bonsai-2-9B-PTQ1_0.gguf` line — at every start, so the packing
 mismatch is visible in the journal to anyone who boots it.
 **Harness contract** (`~/.omp/agent/models.yml`, provider `llamacpp (dankclaw-3090)`, id `frank-zealot`):
 `contextWindow: 200704` — **the per-slot window**, because llama.cpp divides `--ctx-size` across slots and answers a
 longer prompt with a 400, never a truncation — plus `maxTokens: 16384`, `input: [text, image]`