Move the Touches: reader into plan, so plan_store's check imports no package that imports it back
CI / tests (pull_request) Has been cancelled

This commit is contained in:
2026-11-18 16:21:43 +01:00
parent 6b20685f8c
commit 2d30339d25
11 changed files with 14 additions and 10 deletions
+1 -1
View File
@@ -14,7 +14,7 @@ from failure import Failure
from project_config.main import located
from loop_claude.loop.reload import LoopRun
from release_plan.next_chunk import NextChunk, NoItem, planned
from touch_predictions.prediction import overlaps, predicted, Touches
from plan.touches import overlaps, predicted, Touches
from loop_state.paths import Paths
from transcript_archive.project_key import project_key
from release_plan.release_standing import project_plan
@@ -1,5 +1,7 @@
"""An item's prediction of the files and parts it will touch, as its detail spells it, and where two predictions overlap.
It sits in plan, beside the items whose details it reads, so that plan_store's `rank_todo.py --check` and todo-item can refuse a list it cannot read: touch_predictions imports plan_store, so plan_store cannot import from touch_predictions.
The spelling, which the decision `todo.md: an item of the next release predicts the files and parts it will touch …` gives the reasons for:
Touches:
+1 -1
View File
@@ -7,11 +7,11 @@ from plan_store.plans import cells, Plan, Written
from failure import Failure
from plan.todo_table import item_details, items, NoItemsTable, renames
from plan_store import markdown_edits
from plan.touches import predicted
from plan import ranking
from record_store.stores import RecordStore
from text_files.file_writes import replace_file
from plan_store.scoring import weighing_texts
from touch_predictions.prediction import predicted
# What the reader of a missing todo.md is told.
MISSING = "every project keeps a todo.md, and rank_todo.py --help shows one"
+1 -1
View File
@@ -11,8 +11,8 @@ from project_config.test_project_config import configured
from plan.test_ranking import DECISIONS, OLD_SHAPE, README, TODO
from project_config.settings import DEFAULT_FLOOR
from plan import goals_file, ranking
from todo_item.test_todo_item import READABLE_TOUCHES, UNREADABLE_BULLETS
import rank_todo
from todo_item.test_todo_item import READABLE_TOUCHES, UNREADABLE_BULLETS
class Main(unittest.TestCase):
+1 -1
View File
@@ -91,10 +91,10 @@ from project_config.main import located
from plan_store.plans import no_item, PlanStore, TAGLINE, Written
from plan.release import parsed, Release, version as release_version
from plan_store.stores import store as plan_store
from plan.touches import predicted
from record_store.stores import RecordStore, store
from todo_item.table import shown, table
from todo_item.edits import with_bullet
from touch_predictions.prediction import predicted
# Each score flag, as --l or --L, and the field it sets.
LETTERS = ("L", "E", "I", "S")
+1 -1
View File
@@ -3,7 +3,7 @@ import dataclasses
from failure import Failure
from plan.todo_table import Item, waiting
from touch_predictions.prediction import LABEL, overlaps, predicted, Touches
from plan.touches import LABEL, overlaps, predicted, Touches
@dataclasses.dataclass(frozen=True)
+1 -1
View File
@@ -3,7 +3,7 @@ import re
from failure import Failure
from git_cli.git_repo import git, Git
from touch_predictions.prediction import Part, Touches
from plan.touches import Part, Touches
from touch_predictions.file_parts import part_names
HUNK = re.compile(r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@", re.M)
+1 -1
View File
@@ -49,7 +49,7 @@ import typing
from git_cli.git_repo import default_ref, git, Git
from failure import Failure
from plan_store.stores import store as plan_store
from touch_predictions.prediction import predicted, together, Touches
from plan.touches import predicted, together, Touches
from project_config.main import project
from project_config.settings import ProjectConfig, TOUCH_PREDICTIONS
from touch_predictions import record
+1 -1
View File
@@ -3,7 +3,7 @@ import re
from failure import Failure
from record_store.stores import RecordStore
from touch_predictions.prediction import rendered, Touches
from plan.touches import rendered, Touches
from text_files.utc_stamp import STAMPED
TITLE = "# Touch predictions"
@@ -16,7 +16,7 @@ from failure import Failure
from test_env import isolated_env
from project_config.main import located
from record_store.fakes import MemoryStore
from touch_predictions.prediction import overlaps, Part, predicted, rendered, together
from plan.touches import overlaps, Part, predicted, rendered, together
from plan_store.todo_md import plan_of
from project_config.settings import ProjectConfig
from project_config.test_project_config import write_config
+3 -1
View File
@@ -272,7 +272,7 @@ Touches:
On 2026-11-18 six items (400, 401, 416, 420, 421 and 422) held `Touches:` lists that touch-predictions cannot read, such as ``- `bin/judge_replay/main.py` (small)`` and ``- `README.md`: loop-claude's section (small)``. chunk-preflight reads the lists first, so loop-claude silently started nothing beside item 401, and slots sat idle for over an hour; the same mistake had been fixed by hand on 2026-11-16 (commit 4b508615). Nothing checked a list when it was written.
Both checks call `predicted` from `bin/touch_predictions/prediction.py`, so they cannot drift from the reader; its spelling stays as it is. `todo-item add` and `edit --detail` refuse such a detail, writing nothing, in main.py before the plan's backend gets it, so a plan in Jira is held to it too. `rank_todo.py --check` fails on any item in todo.md whose list it cannot read, naming the item and the reason. Moves 1.5 (delivery speed): idle chunk slots are what the mistake cost.
Both checks call `predicted`, so they cannot drift from the reader; its spelling stays as it is. The reader moves from `bin/touch_predictions/prediction.py` to `bin/plan/touches.py`, since touch_predictions imports plan_store and plan_store's check needs the reader. `todo-item add` and `edit --detail` refuse such a detail, writing nothing, in main.py before the plan's backend gets it, so a plan in Jira is held to it too. `rank_todo.py --check` fails on any item in todo.md whose list it cannot read, naming the item and the reason. Moves 1.5 (delivery speed): idle chunk slots are what the mistake cost.
Touches:
@@ -281,6 +281,8 @@ Touches:
- `bin/plan_store/todo_md.py`: `FilePlan.check`
- `bin/test_rank_todo.py`
- `bin/rank_todo.py`: `(module)` (small)
- `bin/plan/touches.py`
- `bin/touch_predictions/prediction.py`
- `rules/todo-items.md`: `` # Todo items (`todo.md`) `` (small)
### 316. Launch comprehension seats as an agent type of their own under `agents/`, without `CLAUDE.md` and the skill and agent listings a general-purpose subagent carries.