From 7b7eb4e19b5bb136e15fb9443113e03b88ce0e6e Mon Sep 17 00:00:00 2001 From: Kyle Isom Date: Sat, 26 Sep 2026 17:58:12 -0700 Subject: [PATCH] P5b README: changes during the run (KV overflow on run 1; my fixture-size bug in task 02's given test) Co-Authored-By: Claude Opus 5.5 --- docs/plans/p5b/README.md | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/docs/plans/p5b/README.md b/docs/plans/p5b/README.md index b0ff988..ae6c111 100644 --- a/docs/plans/p5b/README.md +++ b/docs/plans/p5b/README.md @@ -24,4 +24,12 @@ compiled against a panic-only skeleton on master `1311cf3` and failed for the in ## Changes during the run -(none yet) +- **Run 1, task 01 (2026-09-26 11:01–12:24): infrastructure, not the model.** straylight's + llama-server ran out of shared KV (4 slots over one 262,144-token pool). The session got + `Context size has been exceeded` with no commit. Hermes's ornith context was capped at 131072 + (Kyle: "b is acceptable"); the task was re-run clean and passed (`dca0004`, rebased to `7595ad8`). +- **Task 02, first attempt: my test, not the model or the task.** `TestEmbeddingsAreCachedAcrossQuestions` + used `longDoc(12)`, which is 4,617 tokens. That is under `SmallDoc` (6000), so rule 2 answers + it `"whole"`, while the test expected `"hybrid"`. Ornith measured the document and was working + it out when I stopped the session (22 min). Fix `d52a4fa`: `longDoc(30)` (11,677 tokens, 10 + chunks) plus a `t.Fatalf` precondition. Relaunched from task 02 on a clean tree.