# 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 shape-budget cost-mix loop-lint self-tests env-test task-done status facts-check facts-gen mutation-check size-metrics runtime-metrics build-time am6 am7 am8 edition-check replay-test loc play gate-review all

## fmt + clippy (deny warnings) + HashMap deny-lint
check:
	$(IN_REPO) $(CARGO) fmt --all --check
	$(IN_REPO) $(CARGO) clippy --workspace --all-targets -- -D warnings

## play GROUND from the terminal (INTENT stage 0's CLI player).
## `make play ARGS="--all-bots --bot random"` to watch one instead.
play:
	$(IN_REPO) $(CARGO) run -q -p cb-play -- $(ARGS)

## which control gates are due for a keep-or-kill argument (ADR-0006 D3)
gate-review:
	$(PY) $(TOOLS)/gate-review.py

## 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

# K10: a bundle must re-execute, and must be able to fail. Four controls
# from ADR-0005 §6, including truncate-by-one-byte and mutated-seed.
replay-test:
	$(PY) $(TOOLS)/replay-test.py

# AM-6 gate. Runs in RELEASE, where headroom is ~24x; the same assertion
# in debug has ~3.4x and flaked under load. The target is unchanged — only
# where it is measured.
am6:
	$(IN_REPO) $(CARGO) test --release -p games-ground --all-features \
	  am6_throughput -- --ignored --nocapture --test-threads=1

# ADR-0011 D2: is the vendored edition still what ground-game published?
# Reports "upstream not checked out" as its own outcome, never a pass.
edition-check:
	$(PY) $(TOOLS)/edition-check.py

# AM-8 N=10 determinism gate. One scenario, ten same-seed replays, all
# compared to the first. Not all 25: `make sim` already runs K8's double-
# run over every scenario, and repeating that eight more times costs 47 s
# per build to re-answer a question the second run already answered. The
# extra runs exist for the probabilistic class, and one workload gives
# that class its ten samples — see scenario::run_n.
am8:
	$(IN_REPO) $(CARGO) run -q -p cb-sim -- --runs 10 \
	  $(REPO)/scenarios/ground/gr-r06-round-resolve.yaml

# AM-7 scaling gate. Same release / single-thread reasoning as am6 and more
# so: a *ratio* of two timings taken under varying contention is worse than
# one reading, because the noise multiplies rather than cancels.
am7:
	$(IN_REPO) $(CARGO) test --release -p games-ground --all-features \
	  am7_cost_per_event -- --ignored --nocapture --test-threads=1

# AM-9 peak RSS (fast, gated). AM-5 needs a clean build — see build-time.
runtime-metrics:
	$(PY) $(TOOLS)/runtime-metrics.py --fast

# AM-5: clean release build, ~90s, into a throwaway CARGO_TARGET_DIR so the
# working cache survives. Reported not gated per GameKernel §5.
build-time:
	$(PY) $(TOOLS)/runtime-metrics.py

# AM-2 (M-D1-SPL, AM-1's anti-gaming pair) and AM-3.
size-metrics:
	$(PY) $(TOOLS)/size-metrics.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
	$(PY) $(TOOLS)/status.py --self-test
	$(PY) $(TOOLS)/facts.py --self-test
	$(PY) $(TOOLS)/mutation-check.py --self-test
	$(PY) $(TOOLS)/size-metrics.py --self-test
	$(PY) $(TOOLS)/runtime-metrics.py --self-test
	$(PY) $(TOOLS)/replay-test.py --self-test
	$(PY) $(TOOLS)/design.py --self-test
	cargo run --release -q -p games-ground --example difficulty -- --self-test
	$(PY) $(TOOLS)/edition-check.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"

# M-D1-MUT (CB-WP-0005 T02): invert each acceptance row's property and
# require the verifying command to go red. Deliberately NOT in `make all`:
# it rebuilds the workspace once per mutated row. Run it on demand and in
# CI, not in the inner loop.
mutation-check:
	$(PY) $(TOOLS)/mutation-check.py $(ARGS)

# T04: single source of fact (InnerLoop v1.2) — the DFD gate.
# facts.toml is GENERATED; facts-check fails if it disagrees with the
# instruments, or if a tagged artifact disagrees with it.
facts-check:
	$(PY) $(TOOLS)/facts.py --check

facts-gen:
	$(PY) $(TOOLS)/facts.py --gen

# CB-WP-0025 T06: the difficulty table (specs/RetrospectiveAnalysis.md §4).
# Winnable fraction from the solver plus a PLURAL policy panel -- a single
# policy's win rate may not be reported as a difficulty (§4.1).
difficulty:
	@cargo run --release -q -p games-ground --example difficulty

# CB-WP-0022 T05: the design-finding register, reported over
# specs/GroundRules.md. Shows the QUEUE by default; the log of closed
# findings is a line, not a listing, because a default view that mixes
# them loses the queue property (ADR-0012 D5).
design:
	@$(PY) $(TOOLS)/design.py

# T03: one-shot orientation — workplans, next task, spend, fast gates.
# Cheap by design: no build. Start a session with this instead of grepping.
status:
	@$(PY) $(TOOLS)/status.py

# 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-WP-0007 T03 / InnerLoop v1.5: session shape for the window since the
# last commit. Deliberately NOT in `make all` — failing the build on
# context would block committing, and committing is the natural point to
# compact. A gate that blocks the remedy is a trap.
shape-budget: cost-test
	$(PY) $(TOOLS)/cb-cost.py --shape-budget

# 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 size-metrics runtime-metrics am6 am7 am8 edition-check replay-test dep-weight self-tests env-test facts-check loop-lint bench-test