Merge main into item-104, keeping item 107 and dropping the finished item 104
This commit is contained in:
@@ -6,7 +6,7 @@
|
||||
|
||||
`Bar = 9`
|
||||
|
||||
`Next ID = 107`
|
||||
`Next ID = 108`
|
||||
|
||||
| Goal | W |
|
||||
|---|---|
|
||||
@@ -24,6 +24,7 @@
|
||||
|
||||
| ID | Release | Exempt | Item | R | S | A | G | Goals | Score |
|
||||
|---|---|---|---|---|---|---|---|---|---|
|
||||
| 107 | 0.1.0 | | **Have loop-claude put the README's Goals and Audience into every fresh worker prompt, under a line that the item sets the scope and the goals choose within it.** | 3 | 3 | 8 | 8 | 1.1, 1.2 | 28.1 |
|
||||
| 98 | 0.1.0 | | **Score R and S from a measurement wherever one exists, and calibrate each guessed score against the finished chunk's measured outcome.** | 2 | 5 | 6 | 7 | 1.1, 1.4 | 22.6 |
|
||||
| 99 | 0.1.0 | | **Drop the comprehension panel as a merge gate, and keep recording its scores and the places in the code its seats found hard, for later measurement and for other reviewers and agents to improve.** | 4 | 5 | 7 | 7 | 1.1, 1.4, 1.5 | 22.6 |
|
||||
| 87 | 0.1.0 | | **Score every `todo.md` item's complexity C from 1 to 10, and have `rank_todo.py` fail on an item without one.** | 3 | 4 | 6 | 7 | 1.1, 1.4 | 21.9 |
|
||||
@@ -33,7 +34,7 @@
|
||||
| 88 | 0.2.0 | | **Define one routing ladder of (model, effort) rungs ordered by a published ranking of their competence, and map a task's R + C to a rung relative to the project's model.** | 3 | 4 | 6 | 7 | 1.4 | 21.4 |
|
||||
| 90 | 0.2.0 | | **Route each reviewer by the chunk's R + C, once a replay of past chunks shows the routed reviewer finds the 🔴 and 🟡 findings on record.** | 4 | 5 | 6 | 7 | 1.4 | 20.2 |
|
||||
| 91 | 0.2.0 | | **Start each chunk's worker on the rung its item's R + C picks, never below the project's model, and step it one rung up after two unfinished verdicts on one chunk.** | 4 | 5 | 6 | 7 | 1.4 | 20.2 |
|
||||
| 105 | 0.2.0 | decision | **Compare review rounds per pass and reading cost for the five chunks before and after item 104 moved the principles out of the worker's context, and file an item if either rose.** | 1 | 2 | 5 | 6 | 1.4 | 20.0 |
|
||||
| 105 | 0.2.0 | decision | **Compare review rounds per pass and reading cost for the five chunks before and after the `worker:` decision moved the principles out of the worker's context, and file an item if either rose.** | 1 | 2 | 5 | 6 | 1.4 | 20.0 |
|
||||
| 92 | 0.2.0 | | **Have the worker route each subagent by its task's R + C, and delegate a task only when the worker needs just its conclusion.** | 2 | 2 | 5 | 6 | 1.4 | 19.0 |
|
||||
| 89 | 0.2.0 | | **Run the judge on the rung its chunk's R + C picks, once a replay of archived transcripts shows it returns the verdicts on record.** | 3 | 4 | 5 | 6 | 1.4 | 17.5 |
|
||||
| 1 | 0.3.0 | question | **Say in README → Install how the transcript archive is backed up, once bender-infra backs up ai-sandbox's data volume.** | 3 | 5 | 8 | 9 | 3, 4 | 27.0 |
|
||||
@@ -66,6 +67,14 @@
|
||||
|
||||
## Details
|
||||
|
||||
### 107. Have loop-claude put the README's Goals and Audience into every fresh worker prompt, under a line that the item sets the scope and the goals choose within it.
|
||||
|
||||
Today loop-claude hands the premises only to the judge (`bin/loop_claude/cycle/judge.py`), and a worker reads them only when the typed task says to read `README.md`. A worker that implements the simplest change (`docs/decisions.md` → the `worker:` decision) needs the goals to know what it must not give up, and "Ask, don't guess" checks the goals first. The premises are short: 113 words on this repo. The human chose this on 2026-10-13.
|
||||
|
||||
- Add the premises loop-claude already reads to `prompts.fresh`, with a test.
|
||||
- Above them, one line: the item sets the scope, and the goals choose between ways to meet it. A worker then extends no item towards a goal.
|
||||
- For a session outside the loop, add one line to `CLAUDE.md`'s working loop: read the README's Goals and Audience before starting a chunk.
|
||||
|
||||
### 98. Score R and S from a measurement wherever one exists, and calibrate each guessed score against the finished chunk's measured outcome.
|
||||
|
||||
A score that can be computed from the code it touches, such as the files an item names, comes from that computation. Otherwise size and risk are estimated from finished work, the way reference-class forecasting estimates a project from earlier projects like it. When a chunk merges, record its measured outcome beside the item's guessed R and S: lines and files changed, review rounds, 🔴 and 🟡 findings, and fixes the code needed later. Show the scorer, when it files an item, the finished items whose guessed scores sat nearest and what they measured. Once enough chunks are recorded, report how far each guess was from its outcome, so a scorer whose S runs high can be corrected. Item 87's C is scored and calibrated the same way.
|
||||
@@ -118,7 +127,7 @@ loop-claude reads the top item of the next release with `rank_todo.py` before st
|
||||
|
||||
Needs 88.
|
||||
|
||||
### 105. Compare review rounds per pass and reading cost for the five chunks before and after item 104 moved the principles out of the worker's context, and file an item if either rose.
|
||||
### 105. Compare review rounds per pass and reading cost for the five chunks before and after the `worker:` decision moved the principles out of the worker's context, and file an item if either rose.
|
||||
|
||||
The `worker:` decision is valid while review rounds per pass do not rise. Count the rounds from each PR's `Answer <pass> round <n>:` commits, and take reading cost from `docs/reading-cost.md`. Run it once five chunks have merged after the one that recorded the decision.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user