Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
19 commits
Select commit Hold shift + click to select a range
ba5a4a7
Replace draft/bench/improve loop with `acumen epoch` + knowledge wiki
PauBadiaM Sep 9, 2026
65bf462
Fix Claude transcript token footer: report billed usage, not per-mess…
PauBadiaM Sep 10, 2026
50e4e32
Add `acumen fit`: run many epochs with early stopping
PauBadiaM Sep 10, 2026
b5a1022
Remove the shipped acumen self-skill
PauBadiaM Sep 10, 2026
b35f5d5
Hide Codex's benign "Reading additional input from stdin" notice
PauBadiaM Sep 11, 2026
647e371
Render epoch/fit progress as tqdm-style bars
PauBadiaM Sep 11, 2026
bb0acf1
Fix build_training_rows() arity crash in acumen fit
PauBadiaM Sep 11, 2026
c6a5804
Suppress Codex internal tracing from the console
PauBadiaM Sep 11, 2026
e37c590
Label epoch/fit bar fields as mean success and total cost
PauBadiaM Sep 11, 2026
b25a4f8
Show elapsed time on the inferring-skill done line
PauBadiaM Sep 12, 2026
50b0ecd
Block benchmark agents from fetching the target's own source
PauBadiaM Sep 14, 2026
6e6c8dc
Stop `acumen fit` early when validation reaches 100%
PauBadiaM Sep 14, 2026
53ed127
Render agent tool calls and skill rationale as HTML
PauBadiaM Sep 15, 2026
744be02
Replace the loaded-only table with a dotplot, fix runs-table highlight
PauBadiaM Sep 15, 2026
892b9a9
Add a training-curve figure to the report overview
PauBadiaM Sep 15, 2026
d1a8288
Pair the loaded-only delta against the same task and model
PauBadiaM Sep 15, 2026
547e190
Add a held-out test split with a final evaluation and report section
PauBadiaM Sep 16, 2026
e15a08e
Build the report at the end of acumen fit; point tasks at fit
PauBadiaM Sep 17, 2026
cb50d37
Point acumen init's next step at acumen fit
PauBadiaM Sep 17, 2026
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
272 changes: 30 additions & 242 deletions README.md

Large diffs are not rendered by default.

1 change: 0 additions & 1 deletion pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,6 @@ urls.Documentation = "https://acumen.readthedocs.io/"
urls.Homepage = "https://github.com/scverse/acumen"
urls.Source = "https://github.com/scverse/acumen"
scripts.acumen = "acumen.cli:main"
scripts.acumen-install-skills = "acumen._skills.install:main"

[dependency-groups]
dev = [
Expand Down
47 changes: 35 additions & 12 deletions src/acumen/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,6 @@
summarize_checks,
)
from acumen.config import Config, ConfigError, load_config, parse_config
from acumen.draft import DraftError, DraftResult, draft_skill
from acumen.env import (
AuthMode,
EnvError,
Expand All @@ -41,15 +40,14 @@
scrubbed_env,
session_auth_available,
)
from acumen.epoch import EpochPlan, resolve_epoch
from acumen.grade import Grade, Reason, grade_answer, grade_run
from acumen.improve import (
ImproveError,
ImproveResult,
TrainRun,
collect_train_runs,
find_test_access,
find_valid_access,
improve_skill,
make_test_guard,
make_valid_guard,
)
from acumen.logs import LiveLog
from acumen.paths import RunKey, Split, arm_name, is_complete, parse_run_dir, run_dir, skill_from_arm
Expand Down Expand Up @@ -104,6 +102,14 @@
harvest_scripts,
)
from acumen.tasks import Task, TaskError, TaskSplit, load_tasks, parse_tasks
from acumen.training import (
EpochRow,
best_version,
build_training_rows,
epochs_since_best,
patience_exhausted,
write_training_csv,
)
from acumen.trajectory import Trajectory, render_trajectory
from acumen.transcript import (
build_trajectory,
Expand All @@ -112,8 +118,32 @@
render_codex_transcript,
render_transcript,
)
from acumen.wiki import (
RunRecord,
TaskWikiResult,
WikiError,
collect_arm_runs,
recorded_arms,
update_wiki,
)

__all__ = [
"EpochRow",
"build_training_rows",
"write_training_csv",
"patience_exhausted",
"best_version",
"epochs_since_best",
"EpochPlan",
"resolve_epoch",
"find_valid_access",
"make_valid_guard",
"RunRecord",
"TaskWikiResult",
"WikiError",
"collect_arm_runs",
"recorded_arms",
"update_wiki",
"AuthMode",
"AgentError",
"AgentOptions",
Expand All @@ -126,8 +156,6 @@
"CheckSummary",
"Config",
"ConfigError",
"DraftError",
"DraftResult",
"EnvError",
"Grade",
"Harvest",
Expand Down Expand Up @@ -160,7 +188,6 @@
"TaskGenResult",
"TaskSplit",
"Trajectory",
"TrainRun",
"__version__",
"api_auth_available",
"arm_metrics",
Expand All @@ -176,11 +203,8 @@
"build_report",
"check_task_split",
"check_tasks",
"collect_train_runs",
"draft_skill",
"dump_tasks",
"find_skill_access",
"find_test_access",
"generate_tasks",
"grade_answer",
"grade_run",
Expand All @@ -191,7 +215,6 @@
"installer_exists",
"is_complete",
"make_skill_guard",
"make_test_guard",
"latest_version",
"load_config",
"locate_transcript",
Expand Down
Empty file removed src/acumen/_skills/__init__.py
Empty file.
127 changes: 0 additions & 127 deletions src/acumen/_skills/data/SKILL.md

This file was deleted.

92 changes: 0 additions & 92 deletions src/acumen/_skills/data/references/authoring.md

This file was deleted.

Loading