kyle/sift
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

P5b README: changes during the run (KV overflow on run 1; my fixture-size bug in task 02's given test)

Browse Source 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
kyle
2026-09-26 17:58:12 -07:00
co-authored by Claude Opus 5.5
parent d52a4fa1e6
commit 7b7eb4e19b
1 changed files with 9 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/plans/p5b/README.md
+9 -1
View File
@@ -24,4 +24,12 @@ compiled against a panic-only skeleton on master `1311cf3` and failed for the in
## Changes during the run ## 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.