tegwick
b52a9ec88a
Replaces the three hand-done steps of a task close (46 turns, $11.52 per CB-RES-0003): the heredoc flipping status in the workplan file, the hand-written hub call, and the hand-typed token counts. The third is the reason this task exists. Every update_task_status this repo produced carried estimated tokens_in/tokens_out — in a project whose central finding is that estimated token counts are worthless. task-done reads the measured figure from the transcripts, or refuses; there is no path through it that emits an estimate. cb-cost gains by_task_detail: cost, response count, model histogram and token components per task. task-done imports cb-cost rather than parsing its printed table, so the hub figure is not a copy that can drift from its source. The positive control found a real defect before the tool ran once. Attribution keyed on a bare T\d\d from the commit subject, so CB-WP-0002 T01, CB-WP-0003 T01 and CB-WP-0004 T01 shared a bucket: the self-test reported $12.10 for "T01" where the qualified figure is $2.33. That 5.2x overstatement would have been pushed to the hub as a *measured* number — the same fiction in a new form. task_label() now keys qualified subjects on the full id and leaves unqualified ones bare rather than retro-assigning them to a workplan. The pinned $93.15 benchmark is unchanged, so historical attribution was not disturbed. Fourth instance of trusted arithmetic: a number believed because a program produced it rather than a hand. Refusals, all exercised by --self-test: unknown id, typo'd id, already-done task, missing state_hub_task_id, no measured spend, and a status flip that produced no change. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
121 lines
4.7 KiB
Makefile
121 lines
4.7 KiB
Makefile
# One command surface (InnerLoop §agentic-efficiency #3). Deterministic,
|
|
# greppable output; precursor of the `cb` CLI.
|
|
#
|
|
# CB-WP-0004 T01: every target here runs from a clean shell, from any
|
|
# directory, with no prefix. Invoke as `make -C <repo> <target>` from
|
|
# elsewhere. No target requires `cd` or `export PATH` — CB-RES-0003
|
|
# measured 84 turns and $15.33 spent on exactly those two prefixes.
|
|
|
|
# Absolute path to this Makefile's directory, so recipes never depend on
|
|
# the caller's working directory.
|
|
REPO := $(patsubst %/,%,$(dir $(abspath $(lastword $(MAKEFILE_LIST)))))
|
|
|
|
# Locate cargo instead of requiring it on the inherited PATH. Mirrors
|
|
# tools/repo.py:cargo_bin() — kept in sync by `make env-test`.
|
|
CARGO := $(firstword $(shell command -v cargo 2>/dev/null) \
|
|
$(wildcard $(HOME)/.cargo/bin/cargo) \
|
|
$(wildcard /usr/local/cargo/bin/cargo) \
|
|
cargo)
|
|
export PATH := $(dir $(CARGO)):$(PATH)
|
|
|
|
PY := python3
|
|
TOOLS := $(REPO)/tools
|
|
|
|
# Every cargo recipe runs at the repo root; the shell does not persist cd.
|
|
IN_REPO := cd $(REPO) &&
|
|
|
|
.PHONY: check test sim bench bench-test coverage dep-weight cost cost-test cost-pin cost-budget cost-mix loop-lint self-tests env-test task-done loc all
|
|
|
|
## fmt + clippy (deny warnings) + HashMap deny-lint
|
|
check:
|
|
$(IN_REPO) $(CARGO) fmt --all --check
|
|
$(IN_REPO) $(CARGO) clippy --workspace --all-targets -- -D warnings
|
|
|
|
## unit + scenario-format tests
|
|
test:
|
|
$(IN_REPO) $(CARGO) test --workspace
|
|
|
|
## run all GROUND scenarios through cb-sim
|
|
dep-weight:
|
|
$(PY) $(TOOLS)/dep-weight.py
|
|
|
|
coverage:
|
|
$(PY) $(TOOLS)/rule-coverage.py
|
|
|
|
# M-D2-CST (specs/CostAccounting.md). cost-test is the positive control and
|
|
# runs first: a cost number from an unverified collector is void.
|
|
cost: cost-test
|
|
$(PY) $(TOOLS)/cb-cost.py --composition --by-task
|
|
|
|
cost-test:
|
|
$(PY) $(TOOLS)/cb-cost.py --self-test
|
|
|
|
# InnerLoop rules that are mechanically checkable (CB-WP-0003 T01).
|
|
loop-lint:
|
|
$(PY) $(TOOLS)/loop-lint.py
|
|
|
|
# Positive control for every reporting tool, per InnerLoop v1.1 Step 5.
|
|
self-tests:
|
|
$(PY) $(TOOLS)/cb-cost.py --self-test
|
|
$(PY) $(TOOLS)/loop-lint.py --self-test
|
|
$(PY) $(TOOLS)/rule-coverage.py --self-test
|
|
$(PY) $(TOOLS)/dep-weight.py --self-test
|
|
$(PY) $(TOOLS)/repo.py --self-test
|
|
$(PY) $(TOOLS)/task-done.py --self-test
|
|
|
|
# T01 positive control: prove the environment fix, do not assume it. Runs
|
|
# every tool from a foreign working directory with a PATH that has no
|
|
# cargo on it. Before T01 this failed; if it fails again, the friction is
|
|
# back and CB-EV-0003's measurement is invalid.
|
|
env-test:
|
|
@cd / && env PATH=/usr/bin:/bin $(PY) $(TOOLS)/repo.py --self-test
|
|
@cd / && env PATH=/usr/bin:/bin $(PY) $(TOOLS)/rule-coverage.py --self-test >/dev/null \
|
|
&& echo " [ok ] rule-coverage runs from / with no cargo on PATH"
|
|
@cd / && env PATH=/usr/bin:/bin $(PY) $(TOOLS)/dep-weight.py --self-test >/dev/null \
|
|
&& echo " [ok ] dep-weight runs from / with no cargo on PATH"
|
|
@cd / && env PATH=/usr/bin:/bin $(PY) $(TOOLS)/cb-cost.py --self-test >/dev/null \
|
|
&& echo " [ok ] cb-cost runs from / with no cargo on PATH"
|
|
@cd / && env PATH=/usr/bin:/bin $(PY) $(TOOLS)/loop-lint.py --self-test >/dev/null \
|
|
&& echo " [ok ] loop-lint runs from / with no cargo on PATH"
|
|
@$(MAKE) -C $(REPO) coverage >/dev/null \
|
|
&& echo " [ok ] make -C <repo> works from any directory"
|
|
|
|
# T02: close a task — flip the workplan file, read the *measured* cost
|
|
# from the transcripts, push the hub event with real numbers. Refuses on an
|
|
# unknown or already-done task, and refuses to report an estimate.
|
|
# make task-done T=CB-WP-0004-T02
|
|
task-done:
|
|
@test -n "$(T)" || { echo "usage: make task-done T=CB-WP-0004-T02" >&2; exit 2; }
|
|
$(PY) $(TOOLS)/task-done.py $(T) $(ARGS)
|
|
|
|
# CB-01/CB-02: live spend since the last commit.
|
|
cost-budget: cost-test
|
|
$(PY) $(TOOLS)/cb-cost.py --budget
|
|
|
|
# CB-RES-0003 baseline: mechanical vs judgment turns.
|
|
cost-mix: cost-test
|
|
$(PY) $(TOOLS)/cb-cost.py --composition
|
|
|
|
cost-pin: cost-test
|
|
$(PY) $(TOOLS)/cb-cost.py --pin fc76445 --composition --by-task
|
|
|
|
sim:
|
|
$(IN_REPO) $(CARGO) run -q -p cb-sim -- $(REPO)/scenarios/ground/*.yaml
|
|
|
|
## Criterion benches (AM-6/AM-7)
|
|
bench:
|
|
$(IN_REPO) $(CARGO) bench -p games-ground
|
|
|
|
## InnerLoop positive control: run every bench once, no measurement.
|
|
## Fails if a workload stalls or produces the wrong event count.
|
|
bench-test:
|
|
$(IN_REPO) $(CARGO) bench -p games-ground --bench synthetic -- --test
|
|
|
|
|
|
## AM-2/AM-3 input: source LOC per crate (excludes tests would need tokei)
|
|
loc:
|
|
@$(IN_REPO) for d in crates/cb-kernel crates/cb-events crates/cb-game-runtime games/ground tools/cb-sim; do \
|
|
printf '%-28s %s\n' $$d "$$(find $$d/src -name '*.rs' | xargs cat | grep -vcE '^\s*(//|$$)')"; \
|
|
done
|
|
|
|
all: check test sim coverage dep-weight self-tests env-test loop-lint bench-test
|