+3
-3
@@ -302,7 +302,7 @@ Valid while the later fixes per finished chunk, which `score-outcomes` and the r
|
||||
|
||||
## project config: a record may name a Confluence Cloud page as `confluence:` and its address, the loop reads and writes it as markdown, and a write never overwrites a save made since the loop's read
|
||||
|
||||
2026-11-15, larv-review, on lilleman's calls of 2026-11-12. Serves goal 1.6: a client's team keeps its records in its own wiki. Valid while one record fits one page, and while one session per project opens a record's copy, which todo.md's item 375 ends.
|
||||
2026-11-15, larv-review, on lilleman's calls of 2026-11-12. Serves goal 1.6: a client's team keeps its records in its own wiki. Valid while one record fits one page, and while each worktree opens its own copy of a record, as loop-claude's side-by-side chunks need.
|
||||
|
||||
- **A bench of readers picked the spelling.** Three fresh readers, seated as the person who writes a client's `config.toml`, each picked `decisions = "confluence:https://<site>/wiki/spaces/<space>/pages/<page ID>"`, pasted from the browser with or without the title at its end, over the bare address, a page ID beside a `confluence-site` key, and a table. Each named the match with `jira:`. Any of the five records may name a page; the goals file, the plan, the working rules and the principles may not.
|
||||
- **`decisions` and `comprehension-history` may name a page only where `plan` names a Jira epic.** rule-hook ranks a plan kept as a file before tool calls, inside its 30-second limit, and ranking reads those two records. A Confluence read and two adf-codec container runs would hold up every guarded tool call, and fail it while Confluence is down. `load` refuses goals in Jira beside a plan in a file for the same reason.
|
||||
@@ -711,12 +711,12 @@ Valid while the worker writes the tests that larv-review's reviewers hold to the
|
||||
- **The spelling.** A `Touches:` line, then one bullet per file: the path in backticks, then its parts, each a name in backticks or `lines <first>-<last>`, with `(small)` after a part the item changes only a little; a path or a name that holds a backtick takes a longer run of backticks with a space inside each end, as a Markdown code span does. A path alone is the whole file. Three readers seated as the README's audience picked the bulleted list over one line and over a table, since backticks hold a heading's commas, colons and parentheses. Two of the three put `(small)` after the part and outside the backticks, and two left line ranges unquoted. Each picked a different config key: `touch-predictions` was one reader's first choice and the second choice of the other two.
|
||||
- **A part's boundaries.** Python's `ast` module names the innermost function or class, a top-level assignment by the name it sets, and `(module)` for the rest. A Markdown file's parts are its headings outside fenced code. Any other file, and Python that doesn't parse, falls back to line ranges. A table row is no part of its own: the item named one, but the tables chunks collide on are the plan's and the changelog's, which don't count.
|
||||
- **What doesn't count.** The plan and every record the config names, the changelog among them, since every chunk writes them: `chunk-pr merge --finish` writes the plan and the changelog at merge time, and the other records are appended to. `touch-predictions record` leaves them out of what a chunk touched, and the rule keeps them out of predictions.
|
||||
- **The pick.** `chunk-preflight` takes the items of the next release that don't wait, in the plan's order, each where it overlaps neither the next item nor an item taken before it. The call asked for the set that keeps the most chunks running. The plan's order comes first all the same: the largest set could start a low-ranked item in place of one ranked above it, and with more ready items than the parallel limit, either set fills the limit. `todo.md` item 375 takes as many of the picked items as its limit allows.
|
||||
- **The pick.** `chunk-preflight` takes the items of the next release that don't wait, in the plan's order, each where it overlaps neither the next item nor an item taken before it. The call asked for the set that keeps the most chunks running. The plan's order comes first all the same: the largest set could start a low-ranked item in place of one ranked above it, and with more ready items than the parallel limit, either set fills the limit. loop-claude starts as many of the picked items as `parallel-chunks` allows.
|
||||
- **An overlap that is taken.** Two items may share a part where either marks it `(small)`. The call takes an overlap only for a small change to the same part, and a few lines re-apply onto whatever the other chunk did to it.
|
||||
- **Which items share a chunk** stays the worker's choice, by the review passes they fire, so the pick names items, and an item the next chunk takes starts no chunk of its own.
|
||||
- **The record is optional.** No path setting has a default, and a mandatory one would stop every project until its owner edits the config (goal 1.6). A project that leaves `touch-predictions` out is still picked for, and keeps no record. The worker runs `touch-predictions record` before it removes the chunk's items (`skills/larv-review/SKILL.md` §5), since the prediction leaves the plan with the item, and a plan in Jira keeps no history to read it back from.
|
||||
|
||||
Valid while `todo.md` item 375 runs chunks by this pick. Once the record holds enough chunks to show how often the predictions miss, an item, not filed yet, revisits the pick's order and the `(small)` rule.
|
||||
Valid while loop-claude starts a project's chunks side by side by this pick (`bin/loop_claude/loop/chunk_windows.py` `may_start`), which also checks each new chunk against the running chunks' items. Once the record holds enough chunks to show how often the predictions miss, an item, not filed yet, revisits the pick's order and the `(small)` rule.
|
||||
|
||||
## todo.md: one table of items, scored by the formula it states, held to its bar and ranked by `bin/rank_todo.py`, which ranks each blocker above the items it blocks; each achieve goal weighs by its position, code health first and four times as heavy while the comprehension panel's overall is under the project's readability floor or unmeasured, then the goals file's goals, and a maintain goal weighs 0.5 per point of the confidence an item's test, gate leg or probe adds to it; the table's order is the plan's only order
|
||||
|
||||
|
||||
@@ -12,7 +12,6 @@
|
||||
|
||||
| ID | Release | Blocked by | Exempt | Item | L | E | I | R | S | Moves | Score |
|
||||
|---|---|---|---|---|---|---|---|---|---|---|---|
|
||||
| 375 | 0.11.0 | | decision | **Run up to the project's configured number of chunks at once, each in its own window of one tmux session named for the project, mark a window whose chunk waits for the human, and refuse to start without tmux at the needed version.** | 4 | 2 | 3 | 7 | 7 | 1.5 by 7 | 0.6 |
|
||||
| 319 | 0.12.0 | | | **Start a fresh session with a brief of the chunk when a rung step changes the worker's model, in place of resuming the old session.** | 3 | 2 | 3 | 6 | 4 | 1.1 by 2, 1.4 by 2 | 1.2 |
|
||||
| 309 | 0.12.0 | | | **Run a scoring run's second pass on one head with two seats in place of four, once `larv-review agreement` shows the seats agree with each other more than a run agrees with its rerun.** | 2 | 2 | 2 | 4 | 2 | 1.4 by 3 | 1.2 |
|
||||
| 299 | 0.12.0 | | | **Replay the archived judge verdicts through code rules and a classifier trained locally on the archive, and file an item for each verdict kind one of them decides with no missed interrupt.** | 2 | 2 | 2 | 4 | 3 | 1.4 by 3 | 1.0 |
|
||||
@@ -75,14 +74,6 @@
|
||||
|
||||
## Details
|
||||
|
||||
### 375. Run up to the project's configured number of chunks at once, each in its own window of one tmux session named for the project, mark a window whose chunk waits for the human, and refuse to start without tmux at the needed version.
|
||||
|
||||
lilleman's call, 2026-11-13, splitting item 361. lilleman knows tmux and prefers it. loop-claude runs each chunk in its own window of one tmux session named for the project, such as session `loop-claude-config` with windows `item-372` and `item-373`. It runs up to the number of chunks the project's config allows at once, with 1 as the default, and starts the next chunk item 373's pass allows as each one merges. It uses tmux even at 1, so every project runs the same workflow (goal 1.3). Each window holds a loop-claude for its one chunk, so the interrupt and `/talk` work there as on any terminal. When a chunk waits for the human, loop-claude marks its window, renaming it to end in ` ?` and ringing the bell so tmux's status bar shows it, and clears the mark once it is answered. The DM each interrupt sends names the session and window to answer in, such as `loop-claude-config:item-372`, so the human goes straight to it.
|
||||
|
||||
Before starting anything — a worktree, a session, a window — loop-claude checks that tmux is installed at the needed version or later. Where it is missing or older, it stops and names the version it found and the one it needs. The needed version is the oldest that has every tmux command and option loop-claude uses, read from tmux's `CHANGES` file and cited in the decision that records it.
|
||||
|
||||
The config key for the parallel limit is a syntax users write, so a panel seated from the README's audience picks its spelling (`CLAUDE.md` → "Working loop" → "Bench a syntax"). run-heavy already sizes its slots from the machine, at one per 4 CPUs and with memory from `MemTotal`, so a larger VM runs more heavy commands at once without a change here.
|
||||
|
||||
### 319. Start a fresh session with a brief of the chunk when a rung step changes the worker's model, in place of resuming the old session.
|
||||
|
||||
On SWE-bench Verified with Haiku 4.5 and Opus 4.7, handing the strong model the weak model's transcript solved 69.2% at $1.61 a task; starting the strong model fresh solved 79.2% at $0.90 (arXiv 2608.24358, The Handoff Tax). A model switch also rereads the whole context uncached (Claude Code prompt caching docs). A worker that steps from Sonnet 5.5 to Opus 5.5 by `--resume` is the raw handoff; an effort-only step within one model keeps the cache and isn't. The escalated subagent, which starts fresh with the trigger's evidence, already follows the pattern that won.
|
||||
|
||||
Reference in New Issue
Block a user