Answer prose round 3: drop the claim that no later run deletes the reading-cost item
This commit is contained in:
@@ -25,7 +25,7 @@ Decisions live in `docs/decisions.md`:
|
||||
- the repo may name bender, bender-infra and ai-sandbox
|
||||
- todo.md: one table of items scored by the formula and goal weights it states, held to its bar, ranked by `bin/rank_todo.py`
|
||||
- reading cost: larv-review measures each finished chunk from loop-claude's archive and appends the figure to `docs/comprehension-history.md` in the next chunk's PR
|
||||
- reading cost: a rise is the last 5 chunks' median above the 5 before them, and files or refreshes one plan item that no later run deletes
|
||||
- reading cost: a rise is the last 5 chunks' median above the 5 before them, and files or refreshes one plan item
|
||||
|
||||
## Working rules
|
||||
|
||||
|
||||
+1
-1
@@ -2,7 +2,7 @@
|
||||
|
||||
## Unreleased
|
||||
|
||||
- larv-review runs the new `bin/reading_cost.py`, which measures each chunk `loop-claude` finished from its archive: the new input tokens the worker and its subagents took in before the worker's first commit, and the files git tracks that they read most. It appends each figure the project's `docs/comprehension-history.md` lacks. Once 10 chunks are measured, and the last 5 chunks' median is above the 5 before them, larv-review files one plan item naming the files read most, or refreshes it; a later run never deletes it. The chunk that ships it runs `reading_cost.py --reset`, so the trend counts only chunks that finished after it.
|
||||
- larv-review runs the new `bin/reading_cost.py`, which measures each chunk `loop-claude` finished from its archive: the new input tokens the worker and its subagents took in before the worker's first commit, and the files git tracks that they read most. It appends each figure the project's `docs/comprehension-history.md` lacks. Once 10 chunks are measured, and the last 5 chunks' median is above the 5 before them, larv-review files one plan item naming the files read most, or refreshes it. The chunk that ships it runs `reading_cost.py --reset`, so the trend counts only chunks that finished after it.
|
||||
- larv-review appends every scoring run to the project's `docs/comprehension-history.md`: the commit the seats read, each seat's five scores and the seats' mean, and the places each seat named. The ratchet compares a run with the history's last run on the default branch. The `comprehension floor:` entry in `docs/decisions.md` keeps only the decisions to ship under the floor; a project's next scoring run moves the last scores the entry still holds into the history. The seats do not read the history.
|
||||
- The README's goals put quality with the fewest interrupts first, as goal 1; sharing the setup, backups and leaking nothing follow as goals 2–4.
|
||||
- larv-review reruns the comprehension scoring run before merge when any commit since the last run changes more than `docs/decisions.md`, `docs/comprehension-history.md`, `todo.md` or `CHANGELOG.md`, so the recorded scores are the merged commit's. A score under the floor, or below the default branch's recorded scores, blocks the merge and is never filed in `todo.md`. A fix lifts either; your decision to ship under the floor lifts only a score under the floor. A rerun counts toward the three-round cap only when it reports a blocking score that no decision of yours covers.
|
||||
|
||||
+1
-1
@@ -114,6 +114,6 @@ lilleman decided to ship each of these under the floor on the day listed. Each l
|
||||
|
||||
2026-10-08, lilleman. Serves goal 1.1: comprehension measured from real work, at no model cost (goal 1.4). loop-claude archives from the main checkout, outside any PR, so a tracked file it wrote there would dirty that checkout. So `bin/reading_cost.py` measures each finished chunk the history lacks from the archive, in the next chunk's worktree. A PR that never merges then loses no figure, and loop-claude needs no change. Serves goal 4 by naming only files git tracks, and token counts. Rejected: loop-claude opening a PR of its own, one more PR per chunk and a tie to the forge; the worker measuring its own transcript before merging, which misses the chunk's tail. The figure counts new input tokens, uncached and cache-written, because workers read mostly through Bash and subagents, where parsed paths alone miss what they read. Valid while loop-claude archives every finished chunk with its subagents' transcripts.
|
||||
|
||||
## reading cost: a rise is the last 5 chunks' median above the 5 before them, and files or refreshes one plan item that no later run deletes
|
||||
## reading cost: a rise is the last 5 chunks' median above the 5 before them, and files or refreshes one plan item
|
||||
|
||||
2026-10-08, lilleman. Serves goal 1.1: comprehension never falls, so any rise counts. Per-chunk figures are noisy: a flat trend rises about every other chunk. So a rise refreshes the item and never refiles it, and a chunk that sees no rise leaves the item as it is. The chunk that ships the item resets the trend, so later figures do not refile it for work that chunk already did (goal 1.4). A median, because one chunk that ran a panel of readers before its first commit measured 2.99M tokens against a typical 80k–370k, and a mean let it decide the trend alone. No published standard sets this threshold. Valid while figures arrive once per chunk.
|
||||
|
||||
Reference in New Issue
Block a user