llm-ingestion-okf/docs
Kjell Tore Guttormsen c85347e8a5 docs(okf-v0.2): steps 1-3 are done, and step 3 was not behavior-neutral
The plan's own line said steps 1-3 change no behavior. V-A7's construction gate
made that untrue, and a stale premise in a plan is the class of thing this repo
has already paid for twice. Recorded where it was wrong, with the operator
decision that put the gate before D2 rather than at it, and with Door C's six
tolerance cases measured rather than expected.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01A2aKJxLejT9S8jYwoZ9fut
2026-07-26 20:10:37 +02:00
..
plan docs(okf-v0.2): steps 1-3 are done, and step 3 was not behavior-neutral 2026-07-26 20:10:37 +02:00
phase-3-split-table.md feat(phase-3): the index policy becomes configurable, with the reader that judges it 2026-07-25 20:30:54 +02:00
upstream-okf-upgrade-runbook.md docs: every upstream OKF release runs a runbook, and this repo is a black box 2026-07-26 19:18:43 +02:00