diff options
Diffstat (limited to '.ai/scripts/tests')
25 files changed, 3398 insertions, 1130 deletions
diff --git a/.ai/scripts/tests/agent-lock.bats b/.ai/scripts/tests/agent-lock.bats new file mode 100644 index 0000000..dbcffe1 --- /dev/null +++ b/.ai/scripts/tests/agent-lock.bats @@ -0,0 +1,214 @@ +#!/usr/bin/env bats +# +# Tests for claude-templates/.ai/scripts/agent-lock — a mkdir-atomic advisory +# lock helper for agent workflows (sentry's single-runner and roam-write +# locks). flock can't span an agent's tool calls: every Bash call is its own +# short-lived shell, so a flock dies with the call that took it. This helper +# persists the lock on disk between calls and self-clears after a crash via +# age-based staleness reclaim. +# +# Contract under test: +# agent-lock acquire <name> [--ttl=SECONDS] [--wait[=SECONDS]] +# exit 0 → acquired (fresh, or reclaimed from a stale prior holder). +# exit 1 → busy: a live lock holds <name>; deferred (note on stderr). +# exit 2 → usage error (bad/absent name, unknown subcommand). +# agent-lock refresh <name> → re-touch a held lock (heartbeat); exit 1 if absent. +# agent-lock release <name> → remove the lock; idempotent (exit 0 if already free). +# agent-lock status <name> → print free|held|stale + metadata; exit 0 (query). +# agent-lock path <name> → print the resolved lock dir path; does not create it. +# +# Staleness is age-based on the metadata file's mtime versus the lock's own +# recorded TTL, so a crashed holder's lock expires instead of wedging every +# later acquire. Heartbeat (refresh) re-touches the mtime, keeping a live +# holder's lock young. Every reclaim surfaces a note (never silent). +# +# Lock home: /run/user/<uid>/agent-locks/<name>/ (tmpfs: host-local, out of +# every repo, cleared on reboot), with ~/.cache/agent-locks/ as the fallback +# where no runtime dir exists. AGENT_LOCK_DIR overrides the base for tests and +# advanced callers; the helper otherwise owns the path scheme and callers pass +# only names. +# +# Strategy: AGENT_LOCK_DIR points every lock at a temp base, so tests never +# touch a real runtime dir. Staleness is exercised by aging the metadata +# file's mtime with `touch` rather than sleeping. + +SCRIPT="$(cd "$(dirname "$BATS_TEST_FILENAME")/.." && pwd)/agent-lock" +BASH_BIN="$(command -v bash)" + +setup() { + TEST_DIR="$(mktemp -d -t agent-lock-bats.XXXXXX)" + LOCK_BASE="$TEST_DIR/locks" +} + +teardown() { + rm -rf "$TEST_DIR" +} + +lock() { + run env AGENT_LOCK_DIR="$LOCK_BASE" "$BASH_BIN" "$SCRIPT" "$@" +} + +# meta-file path for a lock name, for direct inspection / aging. +meta_of() { + printf '%s/%s/meta\n' "$LOCK_BASE" "$1" +} + +# ---- acquire: fresh win + metadata -------------------------------------- + +@test "acquire: fresh name wins (exit 0) and writes pid/host/timestamp/ttl" { + lock acquire job + [ "$status" -eq 0 ] + local meta; meta="$(meta_of job)" + [ -f "$meta" ] + grep -q "^pid=$$\|^pid=[0-9][0-9]*$" "$meta" + grep -q "^host=$(uname -n)$" "$meta" + grep -qE "^acquired=[0-9]{4}-[0-9]{2}-[0-9]{2}T" "$meta" + grep -qE "^ttl=[0-9]+$" "$meta" +} + +@test "acquire: honors an explicit --ttl in the metadata" { + lock acquire job --ttl=45 + [ "$status" -eq 0 ] + grep -q "^ttl=45$" "$(meta_of job)" +} + +# ---- acquire: contention (one winner) ----------------------------------- + +@test "acquire: a second acquire of a live lock defers (exit 1, note)" { + lock acquire job + [ "$status" -eq 0 ] + lock acquire job + [ "$status" -eq 1 ] + [[ "$output" == *job* ]] +} + +@test "acquire: two racing acquires yield exactly one winner" { + # Fire both without releasing; exactly one mkdir wins. + env AGENT_LOCK_DIR="$LOCK_BASE" "$BASH_BIN" "$SCRIPT" acquire race & p1=$! + env AGENT_LOCK_DIR="$LOCK_BASE" "$BASH_BIN" "$SCRIPT" acquire race & p2=$! + local r1=0 r2=0 + wait $p1 || r1=$? + wait $p2 || r2=$? + # One exits 0 (won), one exits 1 (deferred). + [ "$((r1 + r2))" -eq 1 ] +} + +# ---- release: frees the lock -------------------------------------------- + +@test "release: frees a held lock so the next acquire wins" { + lock acquire job + [ "$status" -eq 0 ] + lock release job + [ "$status" -eq 0 ] + [ ! -d "$LOCK_BASE/job" ] + lock acquire job + [ "$status" -eq 0 ] +} + +@test "release: is idempotent on an already-free lock (exit 0)" { + lock release never-held + [ "$status" -eq 0 ] +} + +# ---- staleness reclaim (surfaced, never silent) ------------------------- + +@test "acquire: reclaims a stale lock and surfaces the reclaim note" { + lock acquire job --ttl=1 + [ "$status" -eq 0 ] + # Age the metadata mtime well past the 1s TTL. + touch -d '1 hour ago' "$(meta_of job)" + lock acquire job --ttl=1 + [ "$status" -eq 0 ] + [[ "$output" == *reclaim* ]] + [[ "$output" == *job* ]] + # The reclaim installed fresh metadata (young again), not the aged holder's. + lock status job + [[ "$output" == *held* ]] + [[ "$output" != *stale* ]] +} + +@test "acquire: a lock inside its TTL is not stale (stays deferred)" { + lock acquire job --ttl=3600 + [ "$status" -eq 0 ] + lock acquire job --ttl=3600 + [ "$status" -eq 1 ] +} + +# ---- heartbeat (refresh keeps a live lock young) ------------------------ + +@test "refresh: re-touches a held lock so it is no longer stale" { + lock acquire job --ttl=1 + [ "$status" -eq 0 ] + touch -d '1 hour ago' "$(meta_of job)" + lock status job + [[ "$output" == *stale* ]] + lock refresh job + [ "$status" -eq 0 ] + lock status job + [[ "$output" == *held* ]] + [[ "$output" != *stale* ]] +} + +@test "refresh: an absent lock cannot be refreshed (exit 1)" { + lock refresh nothing + [ "$status" -eq 1 ] +} + +# ---- status query ------------------------------------------------------- + +@test "status: reports free for an unheld lock (exit 0)" { + lock status job + [ "$status" -eq 0 ] + [[ "$output" == *free* ]] +} + +@test "status: reports held with metadata for a live lock" { + lock acquire job --ttl=3600 + lock status job + [ "$status" -eq 0 ] + [[ "$output" == *held* ]] + [[ "$output" == *"host=$(uname -n)"* ]] +} + +# ---- path resolution: runtime dir home with cache fallback -------------- + +@test "path: resolves under AGENT_LOCK_DIR when set" { + lock path job + [ "$status" -eq 0 ] + [ "$output" = "$LOCK_BASE/job" ] + [ ! -d "$LOCK_BASE/job" ] # path does not create the lock +} + +@test "path: prefers the runtime dir home when no override is set" { + local rt="$TEST_DIR/run" + mkdir -p "$rt" + run env -u AGENT_LOCK_DIR XDG_RUNTIME_DIR="$rt" "$BASH_BIN" "$SCRIPT" path job + [ "$status" -eq 0 ] + [ "$output" = "$rt/agent-locks/job" ] +} + +@test "path: falls back to the cache home when no runtime dir exists" { + local home="$TEST_DIR/home" + mkdir -p "$home" + run env -u AGENT_LOCK_DIR -u XDG_RUNTIME_DIR -u XDG_CACHE_HOME \ + HOME="$home" "$BASH_BIN" "$SCRIPT" path job + [ "$status" -eq 0 ] + [ "$output" = "$home/.cache/agent-locks/job" ] +} + +# ---- usage errors ------------------------------------------------------- + +@test "usage: a missing name is a usage error (exit 2)" { + lock acquire + [ "$status" -eq 2 ] +} + +@test "usage: a name with a slash is rejected (exit 2)" { + lock acquire bad/name + [ "$status" -eq 2 ] +} + +@test "usage: an unknown subcommand is a usage error (exit 2)" { + lock frobnicate job + [ "$status" -eq 2 ] +} diff --git a/.ai/scripts/tests/capture-guard.bats b/.ai/scripts/tests/capture-guard.bats new file mode 100644 index 0000000..31632a4 --- /dev/null +++ b/.ai/scripts/tests/capture-guard.bats @@ -0,0 +1,130 @@ +#!/usr/bin/env bats +# +# Tests for claude-templates/.ai/scripts/capture-guard — detects live +# org-capture buffers visiting a target file before a workflow edits that +# file on disk (the roam inbox, in inbox.org roam mode Phase D). Editing the file +# underneath an indirect org-capture buffer wedges the capture (see emacs.md). +# +# Contract under test: +# capture-guard [TARGET_FILE] (default TARGET_FILE = ~/org/roam/inbox.org) +# exit 0 → safe to edit: emacsclient absent, daemon unreachable, or no +# capture buffer visits TARGET_FILE. +# exit 1 → a live capture buffer visits TARGET_FILE; its name(s) printed. +# +# Strategy: the emacsclient boundary is mocked with a PATH stub. The stub +# answers the reachability probe (`-e t`) per STUB_REACHABLE and returns a +# canned, real-emacsclient-shaped result (quoted string) for the buffer query +# per STUB_BUFS. The script's own quote-stripping and exit logic is the code +# under test; the file-equal-p precision is real-Emacs behavior we trust. + +SCRIPT="$(cd "$(dirname "$BATS_TEST_FILENAME")/.." && pwd)/capture-guard" +BASH_BIN="$(command -v bash)" + +setup() { + TEST_DIR="$(mktemp -d -t capture-guard-bats.XXXXXX)" + STUB_DIR="$TEST_DIR/bin" + mkdir -p "$STUB_DIR" + + cat > "$STUB_DIR/emacsclient" <<'STUB' +#!/usr/bin/env bash +# Mock emacsclient. `-e t` is the reachability probe; anything else is the +# buffer query, answered with the real-emacsclient-shaped quoted string. +expr="$2" +if [ "$expr" = "t" ]; then + [ "${STUB_REACHABLE:-1}" = "1" ] && { echo t; exit 0; } + exit 1 +fi +printf '%s\n' "${STUB_BUFS:-\"\"}" +exit 0 +STUB + chmod +x "$STUB_DIR/emacsclient" + + EMPTY_DIR="$TEST_DIR/empty" + mkdir -p "$EMPTY_DIR" +} + +teardown() { + rm -rf "$TEST_DIR" +} + +# ---- Safe-to-edit (exit 0) cases ------------------------------------ + +@test "capture-guard: emacsclient absent is safe (exit 0, no output)" { + run env PATH="$EMPTY_DIR" "$BASH_BIN" "$SCRIPT" + [ "$status" -eq 0 ] + [ -z "$output" ] +} + +@test "capture-guard: daemon unreachable is safe (exit 0)" { + run env PATH="$STUB_DIR:$PATH" STUB_REACHABLE=0 "$BASH_BIN" "$SCRIPT" + [ "$status" -eq 0 ] + [ -z "$output" ] +} + +@test "capture-guard: reachable with no capture buffers is safe (exit 0)" { + run env PATH="$STUB_DIR:$PATH" STUB_REACHABLE=1 STUB_BUFS='""' "$BASH_BIN" "$SCRIPT" + [ "$status" -eq 0 ] + [ -z "$output" ] +} + +# ---- Blocked (exit 1) cases ----------------------------------------- + +@test "capture-guard: one live capture buffer blocks (exit 1, name printed)" { + run env PATH="$STUB_DIR:$PATH" STUB_REACHABLE=1 STUB_BUFS='"CAPTURE-inbox.org"' \ + "$BASH_BIN" "$SCRIPT" + [ "$status" -eq 1 ] + [[ "$output" == *"CAPTURE-inbox.org"* ]] +} + +@test "capture-guard: multiple live capture buffers all reported (exit 1)" { + run env PATH="$STUB_DIR:$PATH" STUB_REACHABLE=1 \ + STUB_BUFS='"CAPTURE-inbox.org,CAPTURE-2-inbox.org"' \ + "$BASH_BIN" "$SCRIPT" + [ "$status" -eq 1 ] + [[ "$output" == *"CAPTURE-inbox.org"* ]] + [[ "$output" == *"CAPTURE-2-inbox.org"* ]] +} + +@test "capture-guard: blocked output does not contain stray surrounding quotes" { + run env PATH="$STUB_DIR:$PATH" STUB_REACHABLE=1 STUB_BUFS='"CAPTURE-inbox.org"' \ + "$BASH_BIN" "$SCRIPT" + [ "$status" -eq 1 ] + [[ "$output" != \"* ]] + [[ "$output" != *\" ]] +} + +# ---- Argument handling ---------------------------------------------- + +@test "capture-guard: accepts an explicit target-file argument" { + run env PATH="$STUB_DIR:$PATH" STUB_REACHABLE=1 STUB_BUFS='""' \ + "$BASH_BIN" "$SCRIPT" "$TEST_DIR/some-other-inbox.org" + [ "$status" -eq 0 ] + [ -z "$output" ] +} + +# ---- --wait poll mode ----------------------------------------------- + +@test "capture-guard --wait: returns 0 instantly when already safe (no sleep)" { + SECONDS=0 + run env PATH="$STUB_DIR:$PATH" STUB_REACHABLE=1 STUB_BUFS='""' \ + "$BASH_BIN" "$SCRIPT" --wait + [ "$status" -eq 0 ] + [ -z "$output" ] + [ "$SECONDS" -lt 2 ] # didn't poll-sleep +} + +@test "capture-guard --wait=1: times out to exit 1 when persistently blocked" { + # Stub always reports the buffer, so it never clears — the short budget + # forces a timeout. Capped sleep keeps this near 1s. + run env PATH="$STUB_DIR:$PATH" STUB_REACHABLE=1 STUB_BUFS='"CAPTURE-inbox.org"' \ + "$BASH_BIN" "$SCRIPT" --wait=1 + [ "$status" -eq 1 ] + [[ "$output" == *"CAPTURE-inbox.org"* ]] +} + +@test "capture-guard --wait=N accepts a target after the flag" { + run env PATH="$STUB_DIR:$PATH" STUB_REACHABLE=1 STUB_BUFS='""' \ + "$BASH_BIN" "$SCRIPT" --wait=1 "$TEST_DIR/some-other-inbox.org" + [ "$status" -eq 0 ] + [ -z "$output" ] +} diff --git a/.ai/scripts/tests/flashcard-sync.bats b/.ai/scripts/tests/flashcard-sync.bats index 608a280..e6ffc21 100644 --- a/.ai/scripts/tests/flashcard-sync.bats +++ b/.ai/scripts/tests/flashcard-sync.bats @@ -6,6 +6,7 @@ setup() { SCRIPT_DIR="$(cd "$(dirname "$BATS_TEST_FILENAME")/.." && pwd)" SYNC="$SCRIPT_DIR/flashcard-sync" + STATS="$SCRIPT_DIR/flashcard-stats.py" TMP="$(mktemp -d)" } @@ -36,3 +37,27 @@ EOF [ "$status" -eq 1 ] [ ! -f "$HOME/sync/phone/anki/dirty.apkg" ] } + +@test "flashcard-stats: a multi-tagged :fundamental:drill: card still counts" { + # Regression guard: a curated card carrying a second org tag must not drop + # from the count. A :drill:$ anchor would have counted only one card here. + cat > "$TMP/multitag.org" <<'EOF' +#+TITLE: Multitag Test + +* Orbital Regimes +** What is LEO? :fundamental:drill: +:PROPERTIES: +:ID: c1 +:END: +Low Earth Orbit is the region below about 2000 kilometers. +** What is GEO? :drill: +:PROPERTIES: +:ID: c2 +:END: +Geostationary orbit sits at roughly 35786 kilometers of altitude. +EOF + run python3 "$STATS" "$TMP/multitag.org" + [ "$status" -eq 0 ] + [[ "$output" == *"Cards: 2"* ]] + [[ "$output" == *clean* ]] +} diff --git a/.ai/scripts/tests/inbox-status.bats b/.ai/scripts/tests/inbox-status.bats index bc8a734..27a497e 100644 --- a/.ai/scripts/tests/inbox-status.bats +++ b/.ai/scripts/tests/inbox-status.bats @@ -45,6 +45,18 @@ teardown() { [[ "$output" == *"0 pending"* ]] } +@test "inbox-status: ignores an in-flight .inbox-send-* temp file" { + mkdir "$TMP/inbox" + # inbox-send writes to a .inbox-send-* temp then renames it into place; + # during that window the temp must not read as a pending handoff, or a + # concurrent boundary check blocks on a file that's about to become real. + touch "$TMP/inbox/.inbox-send-abc123.org" + cd "$TMP" + run "$SCRIPT" + [ "$status" -eq 0 ] + [[ "$output" == *"0 pending"* ]] +} + @test "inbox-status: -q suppresses the per-item lines" { mkdir "$TMP/inbox" echo body > "$TMP/inbox/handoff.org" diff --git a/.ai/scripts/tests/lint-org-cli.bats b/.ai/scripts/tests/lint-org-cli.bats index d457696..b9faef6 100644 --- a/.ai/scripts/tests/lint-org-cli.bats +++ b/.ai/scripts/tests/lint-org-cli.bats @@ -20,6 +20,24 @@ teardown() { [[ "$output" == *"lint-org: file="* ]] } +@test "lint-org.el default invocation is report-only — file untouched" { + # bare #+begin_src is a mechanical fix (→ #+begin_example) that the old + # default applied on disk; a linter reports, it doesn't write + printf '* H\n\n#+begin_src\nx\n#+end_src\n' > "$TMPFILE" + before="$(cat "$TMPFILE")" + run emacs --batch -q -l "$SCRIPTS_DIR/lint-org.el" "$TMPFILE" + [ "$status" -eq 0 ] + [[ "$output" == *"would-fix"* ]] + [ "$(cat "$TMPFILE")" = "$before" ] +} + +@test "lint-org.el --fix applies mechanical fixes on disk" { + printf '* H\n\n#+begin_src\nx\n#+end_src\n' > "$TMPFILE" + run emacs --batch -q -l "$SCRIPTS_DIR/lint-org.el" --fix "$TMPFILE" + [ "$status" -eq 0 ] + grep -q '#+begin_example' "$TMPFILE" +} + @test "wrap-org-table.el loads and runs without -L on the load path" { run emacs --batch -q -l "$SCRIPTS_DIR/wrap-org-table.el" --width=120 "$TMPFILE" [ "$status" -eq 0 ] diff --git a/.ai/scripts/tests/route-batch.bats b/.ai/scripts/tests/route-batch.bats new file mode 100644 index 0000000..84ded5f --- /dev/null +++ b/.ai/scripts/tests/route-batch.bats @@ -0,0 +1,202 @@ +#!/usr/bin/env bats +# +# Tests for claude-templates/.ai/scripts/route-batch — the wrap-up router's +# mechanical go path (wrapup-routing spec, Phase 4 / D7 / D9). +# +# Contract under test: +# route-batch --list one "<destination>\t<heading>" line per task +# carrying :ROUTE_CANDIDATE:; silent when none; +# never modifies anything +# route-batch --go per candidate: write the subtree (minus the +# :ROUTE_CANDIDATE: line) as a one-task handoff, +# deliver via inbox-send to the destination's +# inbox/, then remove the subtree from the local +# todo.org. Send failure leaves the task in +# place and exits non-zero. Empty set: no-op. +# +# Strategy: fixture roots under $TEST_DIR hold a source project and two +# destination projects; INBOX_SEND_ROOTS sandboxes inbox-send's discovery to +# them (the same hook inbox-send's own tests use). + +SCRIPT="$(cd "$(dirname "$BATS_TEST_FILENAME")/.." && pwd)/route-batch" + +setup() { + TEST_DIR="$(mktemp -d -t route-batch-bats.XXXXXX)" + ROOTS="$TEST_DIR/roots" + SRC="$ROOTS/srcproj" + mkdir -p "$SRC/.ai" "$SRC/inbox" \ + "$ROOTS/alpha/.ai" "$ROOTS/alpha/inbox" \ + "$ROOTS/beta/.ai" "$ROOTS/beta/inbox" + touch "$ROOTS/alpha/todo.org" # alpha has a todo.org; beta deliberately not + + cat > "$SRC/todo.org" <<'EOF' +* Srcproj Open Work +** TODO [#B] Alpha-bound task :feature: +:PROPERTIES: +:ROUTE_CANDIDATE: alpha +:END: +Body line about the alpha work. +*** TODO Sub-task that rides along +** TODO [#C] Purely local task +Local body stays put. +** TODO [#C] Beta-bound task :quick: +:PROPERTIES: +:CREATED: [2026-07-01 Tue] +:ROUTE_CANDIDATE: beta +:END: +Beta body. +EOF + + export INBOX_SEND_ROOTS="$ROOTS" + cd "$SRC" +} + +teardown() { + rm -rf "$TEST_DIR" +} + +# ---- --list ------------------------------------------------------------ + +@test "route-batch --list: one destination+heading line per candidate, backlog excluded" { + run "$SCRIPT" --list + [ "$status" -eq 0 ] + [[ "$output" == *"alpha"*"Alpha-bound task"* ]] + [[ "$output" == *"beta"*"Beta-bound task"* ]] + [[ "$output" != *"Purely local task"* ]] +} + +@test "route-batch --list: empty candidate set is silent (exit 0)" { + sed -i '/:ROUTE_CANDIDATE:/d' todo.org + run "$SCRIPT" --list + [ "$status" -eq 0 ] + [ -z "$output" ] +} + +@test "route-batch --list: modifies nothing (skip leaves all in place)" { + before="$(cat todo.org)" + run "$SCRIPT" --list + [ "$status" -eq 0 ] + [ "$(cat todo.org)" = "$before" ] + [ -z "$(ls "$ROOTS/alpha/inbox" "$ROOTS/beta/inbox" 2>/dev/null | grep -v ':')" ] +} + +# ---- --go -------------------------------------------------------------- + +@test "route-batch --go: delivers each candidate to its destination inbox with provenance" { + run "$SCRIPT" --go + [ "$status" -eq 0 ] + alpha_file=$(find "$ROOTS/alpha/inbox" -name '*from-srcproj*' -type f) + beta_file=$(find "$ROOTS/beta/inbox" -name '*from-srcproj*' -type f) + [ -n "$alpha_file" ] + [ -n "$beta_file" ] + grep -q 'Alpha-bound task' "$alpha_file" + grep -q 'Sub-task that rides along' "$alpha_file" # children ride along + grep -q 'Beta-bound task' "$beta_file" + ! grep -q ':ROUTE_CANDIDATE:' "$alpha_file" + ! grep -q ':ROUTE_CANDIDATE:' "$beta_file" +} + +@test "route-batch --go: removes routed subtrees from todo.org, leaves local tasks" { + run "$SCRIPT" --go + [ "$status" -eq 0 ] + ! grep -q 'Alpha-bound task' todo.org + ! grep -q 'Sub-task that rides along' todo.org + ! grep -q 'Beta-bound task' todo.org + grep -q 'Purely local task' todo.org + grep -q 'Local body stays put' todo.org +} + +@test "route-batch --go: a kept property drawer survives minus the marker" { + run "$SCRIPT" --go + [ "$status" -eq 0 ] + beta_file=$(find "$ROOTS/beta/inbox" -name '*from-srcproj*' -type f) + grep -q ':CREATED: \[2026-07-01 Tue\]' "$beta_file" +} + +@test "route-batch --go: destination with inbox/ but no todo.org still delivers" { + run "$SCRIPT" --go + [ "$status" -eq 0 ] + [ ! -f "$ROOTS/beta/todo.org" ] + [ -n "$(find "$ROOTS/beta/inbox" -name '*from-srcproj*' -type f)" ] +} + +@test "route-batch --go: empty candidate set is a silent no-op (exit 0)" { + sed -i '/:ROUTE_CANDIDATE:/d' todo.org + before="$(cat todo.org)" + run "$SCRIPT" --go + [ "$status" -eq 0 ] + [ -z "$output" ] + [ "$(cat todo.org)" = "$before" ] +} + +@test "route-batch --go: a failed send leaves that task in place, marker intact, and exits non-zero" { + sed -i 's/:ROUTE_CANDIDATE: beta/:ROUTE_CANDIDATE: ghost/' todo.org + run "$SCRIPT" --go + [ "$status" -ne 0 ] + grep -q 'Beta-bound task' todo.org # failed route stays local + grep -q ':ROUTE_CANDIDATE: ghost' todo.org # marker survives so it resurfaces next wrap + ! grep -q 'Alpha-bound task' todo.org # the good route still landed + [ -n "$(find "$ROOTS/alpha/inbox" -name '*from-srcproj*' -type f)" ] +} + +@test "route-batch --go: handoff headings are promoted to top level" { + run "$SCRIPT" --go + [ "$status" -eq 0 ] + alpha_file=$(find "$ROOTS/alpha/inbox" -name '*from-srcproj*' -type f) + grep -q '^\* TODO \[#B\] Alpha-bound task' "$alpha_file" + grep -q '^\*\* TODO Sub-task that rides along' "$alpha_file" +} + +@test "route-batch --go: a drawer emptied by the marker strip is pruned from the handoff" { + run "$SCRIPT" --go + [ "$status" -eq 0 ] + alpha_file=$(find "$ROOTS/alpha/inbox" -name '*from-srcproj*' -type f) + ! grep -q ':PROPERTIES:' "$alpha_file" +} + +# ---- Overlapping candidates (nested marker data-loss regression) -------- + +@test "route-batch --go: nested candidates conflict — both stay, bystander survives, exit non-zero" { + cat > todo.org <<'EOF' +* Srcproj Open Work +** TODO [#B] Parent bound for alpha +:PROPERTIES: +:ROUTE_CANDIDATE: alpha +:END: +Parent body. +*** TODO Child bound for beta +:PROPERTIES: +:ROUTE_CANDIDATE: beta +:END: +Child body. +** TODO [#C] Innocent bystander task +Bystander body. +EOF + run "$SCRIPT" --go + [ "$status" -ne 0 ] + [[ "$output" == *"CONFLICT"* ]] + grep -q 'Parent bound for alpha' todo.org + grep -q 'Child bound for beta' todo.org + grep -q 'Innocent bystander task' todo.org + grep -q 'Bystander body' todo.org + [ -z "$(find "$ROOTS/alpha/inbox" "$ROOTS/beta/inbox" -name '*from-srcproj*' -type f)" ] +} + +@test "route-batch: duplicate identical markers in one drawer dedupe to a single route" { + cat > todo.org <<'EOF' +* Srcproj Open Work +** TODO [#B] Double-tagged for alpha +:PROPERTIES: +:ROUTE_CANDIDATE: alpha +:ROUTE_CANDIDATE: alpha +:END: +Body. +EOF + run "$SCRIPT" --list + [ "$status" -eq 0 ] + [ "$(echo "$output" | grep -c 'Double-tagged')" -eq 1 ] + [[ "$output" != *"CONFLICT"* ]] + run "$SCRIPT" --go + [ "$status" -eq 0 ] + [ "$(find "$ROOTS/alpha/inbox" -name '*from-srcproj*' -type f | wc -l)" -eq 1 ] +} diff --git a/.ai/scripts/tests/self-inject.bats b/.ai/scripts/tests/self-inject.bats new file mode 100644 index 0000000..482f61d --- /dev/null +++ b/.ai/scripts/tests/self-inject.bats @@ -0,0 +1,78 @@ +#!/usr/bin/env bats +# Tests for self-inject.sh — tmux is the external boundary, stubbed with a +# recording fake so no real server is needed. + +setup() { + SCRIPT="$BATS_TEST_DIRNAME/../self-inject.sh" + STUB_DIR="$BATS_TEST_TMPDIR/bin" + LOG="$BATS_TEST_TMPDIR/tmux.log" + mkdir -p "$STUB_DIR" +} + +# A tmux stub that records every invocation and answers list-panes from +# $STUB_PANES (empty by default, so pane derivation fails unless a test +# provides ancestry-matching output). +make_stub() { + cat > "$STUB_DIR/tmux" <<'EOF' +#!/bin/sh +echo "$@" >> "$LOG" +case "$1" in + list-panes) printf '%s\n' "$STUB_PANES" ;; +esac +EOF + chmod +x "$STUB_DIR/tmux" +} + +@test "self-inject: -t pane with no pairs echoes the pane and exits 0" { + make_stub + run env PATH="$STUB_DIR:$PATH" LOG="$LOG" STUB_PANES="" sh "$SCRIPT" -t %42 + [ "$status" -eq 0 ] + [ "$output" = "%42" ] + # Pane was supplied, nothing sent: tmux must not have been called. + [ ! -e "$LOG" ] +} + +@test "self-inject: no pane derivable and no -t exits 1 with an error" { + make_stub + run env PATH="$STUB_DIR:$PATH" LOG="$LOG" STUB_PANES="" sh "$SCRIPT" 0 "hello" + [ "$status" -eq 1 ] + case "$output" in *"no owning pane"*) : ;; *) false ;; esac +} + +@test "self-inject: derives the pane from process ancestry via list-panes" { + make_stub + # The stub reports the bats test process itself as a pane's pane_pid; + # the script runs as our child, so that pid is in its ancestry. + run env PATH="$STUB_DIR:$PATH" LOG="$LOG" STUB_PANES="$$ %7" sh "$SCRIPT" + [ "$status" -eq 0 ] + [ "$output" = "%7" ] +} + +@test "self-inject: one delay/text pair sends literal text then Enter" { + make_stub + run env PATH="$STUB_DIR:$PATH" LOG="$LOG" STUB_PANES="" sh "$SCRIPT" -t %3 0 "/clear" + [ "$status" -eq 0 ] + run cat "$LOG" + [ "${lines[0]}" = "send-keys -t %3 -l /clear" ] + [ "${lines[1]}" = "send-keys -t %3 Enter" ] +} + +@test "self-inject: multiple pairs send in order" { + make_stub + run env PATH="$STUB_DIR:$PATH" LOG="$LOG" STUB_PANES="" \ + sh "$SCRIPT" -t %3 0 "/clear" 0 "go — resume" + [ "$status" -eq 0 ] + run cat "$LOG" + [ "${lines[0]}" = "send-keys -t %3 -l /clear" ] + [ "${lines[1]}" = "send-keys -t %3 Enter" ] + [ "${lines[2]}" = "send-keys -t %3 -l go — resume" ] + [ "${lines[3]}" = "send-keys -t %3 Enter" ] +} + +@test "self-inject: dangling odd argument after pairs is ignored" { + make_stub + run env PATH="$STUB_DIR:$PATH" LOG="$LOG" STUB_PANES="" sh "$SCRIPT" -t %3 0 "one" 99 + [ "$status" -eq 0 ] + run cat "$LOG" + [ "${#lines[@]}" -eq 2 ] +} diff --git a/.ai/scripts/tests/spec-sort.bats b/.ai/scripts/tests/spec-sort.bats new file mode 100644 index 0000000..583e458 --- /dev/null +++ b/.ai/scripts/tests/spec-sort.bats @@ -0,0 +1,453 @@ +#!/usr/bin/env bats +# +# Tests for claude-templates/.ai/scripts/spec-sort — the one-time docs-pile +# retrofit from the docs-lifecycle spec: classify docs/**/*.org outside +# docs/specs/ (spec candidate iff it carries BOTH a Decisions heading AND an +# Implementation phases heading), show an evidence panel, and on --apply +# move + rename confirmed candidates to docs/specs/*-spec.org, prepend the +# status heading (:ID:, dated history line), rewrite the keyword header to +# the two-sequence form, relink file: links across the rewritten roots, +# stamp :LAST_SPEC_SORT: in .ai/notes.org. +# +# Contract under test (docs/specs/2026-07-01-docs-lifecycle-spec.org, +# "The retrofit"): +# - dry-run report is the default; --apply writes +# - --apply refuses on a dirty worktree (exit 2) unless --allow-dirty +# - every candidate needs --confirm REL=KEYWORD or --skip REL (exit 1 +# otherwise); terminal keywords need --reason REL=TEXT +# - plan validated before the first write; destination collisions block +# - bare-path mentions in rewritten roots block --apply until +# --acknowledge-bare waives them (reported, never rewritten) +# - mid-apply failure names applied/not-applied + git restore recovery +# - idempotent: a sorted project yields no candidates, no changes +# +# Strategy: each test builds a throwaway git project fixture and runs the +# real script against it. Mid-apply failure is forced via the test-only +# SPEC_SORT_INJECT_FAIL_AFTER env hook. + +SCRIPT="$(cd "$(dirname "$BATS_TEST_FILENAME")/.." && pwd)/spec-sort" + +setup() { + TEST_DIR="$(mktemp -d -t spec-sort-bats.XXXXXX)" + PROJ="$TEST_DIR/proj" + mkdir -p "$PROJ" +} + +teardown() { + rm -rf "$TEST_DIR" +} + +# Standard fixture: one spec candidate, one note, a stray root spec with a +# spine, an anomaly (-spec.org name, no spine), inbound links from todo.org, +# a sibling note, a session archive (report-only surface), and .ai/notes.org +# with a Workflow State section. +make_project() { + cd "$PROJ" + git init -q + git config user.email test@test + git config user.name test + mkdir -p docs/design .ai/sessions + + cat > docs/design/widget.org <<'EOF' +#+TITLE: Widget Feature +#+DATE: 2026-05-01 +#+TODO: DRAFT REVIEW | SHIPPED + +* Metadata +| Status | draft | +| Owner | Craig | + +* Summary +The widget feature. See [[file:scratch-note.org][the note]]. + +* Decisions [1/2] +** DONE Pick the widget shape +** TODO Pick the color + +* Implementation phases +** Phase 1 — build =src/widget.py= +EOF + + cat > docs/design/scratch-note.org <<'EOF' +#+TITLE: Scratch Note + +* Metadata +| Status | n/a | + +* Thoughts +See [[file:widget.org][the widget spec]]. +EOF + + cat > docs/rooty-spec.org <<'EOF' +#+TITLE: Rooty + +* Decisions +** DONE Only decision + +* Implementation phases +** Phase 1 — nothing +EOF + + cat > docs/lonely-spec.org <<'EOF' +#+TITLE: Lonely +Just prose, no spine. +EOF + + cat > todo.org <<'EOF' +* Open Work +** DOING [#B] Widget feature +Spec: [[file:docs/design/widget.org][widget spec]]. +Summary anchor: [[file:docs/design/widget.org::*Summary][the summary]]. +EOF + + cat > .ai/notes.org <<'EOF' +* Active Reminders + +* Workflow State +:LAST_AUDIT: 2026-06-28 +EOF + + cat > .ai/sessions/2026-06-01-old.org <<'EOF' +Old log: [[file:../../docs/design/widget.org][widget]] +EOF + + git add -A + git commit -qm init +} + +# Confirm flags that satisfy the gate for the standard fixture's candidates. +CONFIRM_ALL=(--confirm docs/design/widget.org=DRAFT --confirm docs/rooty-spec.org=DRAFT) + +# ---- Classification (dry-run) ---------------------------------------- + +@test "spec-sort: dry-run classifies the spine-carrying doc as a candidate" { + make_project + run "$SCRIPT" + [ "$status" -eq 0 ] + [[ "$output" == *"CANDIDATE docs/design/widget.org -> docs/specs/widget-spec.org"* ]] +} + +@test "spec-sort: a Metadata table alone does not qualify — note stays a note" { + make_project + run "$SCRIPT" + [ "$status" -eq 0 ] + [[ "$output" == *"NOTE docs/design/scratch-note.org"* ]] + [[ "$output" != *"CANDIDATE docs/design/scratch-note.org"* ]] +} + +@test "spec-sort: stray root spec with a spine is a candidate, suffix not doubled" { + make_project + run "$SCRIPT" + [ "$status" -eq 0 ] + [[ "$output" == *"CANDIDATE docs/rooty-spec.org -> docs/specs/rooty-spec.org"* ]] + [[ "$output" != *"rooty-spec-spec.org"* ]] +} + +@test "spec-sort: -spec.org name without a spine is an anomaly, never auto-moved" { + make_project + run "$SCRIPT" + [ "$status" -eq 0 ] + [[ "$output" == *"ANOMALY docs/lonely-spec.org"* ]] + [[ "$output" != *"CANDIDATE docs/lonely-spec.org"* ]] +} + +@test "spec-sort: docs/specs/ contents are excluded from classification" { + make_project + mkdir -p docs/specs + cp docs/design/widget.org docs/specs/sorted-spec.org + git add -A && git commit -qm more + run "$SCRIPT" + [ "$status" -eq 0 ] + [[ "$output" != *"CANDIDATE docs/specs/sorted-spec.org"* ]] +} + +@test "spec-sort: no docs/ directory is a silent no-op" { + cd "$PROJ" + git init -q + git config user.email test@test + git config user.name test + echo x > README.md + git add -A && git commit -qm init + run "$SCRIPT" + [ "$status" -eq 0 ] + [ -z "$output" ] +} + +# ---- Evidence panel --------------------------------------------------- + +@test "spec-sort: evidence panel shows status field, cookies, and todo.org task" { + make_project + run "$SCRIPT" + [ "$status" -eq 0 ] + [[ "$output" == *"status field: draft"* ]] + [[ "$output" == *"Decisions [1/2]"* ]] + [[ "$output" == *"todo.org:"*"DOING"*"Widget feature"* ]] +} + +@test "spec-sort: keyword proposal follows the evidence — DOING from the linked DOING task" { + make_project + run "$SCRIPT" + [ "$status" -eq 0 ] + # status field says draft, but the linking todo.org task is DOING — the + # panel proposes the state the strongest evidence supports + [[ "$output" == *"proposed keyword: DOING"* ]] +} + +@test "spec-sort: an 'incomplete' status field never proposes the terminal IMPLEMENTED" { + make_project + sed -i 's/| Status | draft |/| Status | incomplete |/' docs/design/widget.org + git add -A && git commit -qm status + run "$SCRIPT" + [ "$status" -eq 0 ] + [[ "$output" != *"proposed keyword: IMPLEMENTED"* ]] +} + +# ---- Confirm gate ----------------------------------------------------- + +@test "spec-sort --apply: refuses when a candidate is neither confirmed nor skipped" { + make_project + run "$SCRIPT" --apply --confirm docs/design/widget.org=DRAFT + [ "$status" -eq 1 ] + [[ "$output" == *"unconfirmed"* ]] + [[ "$output" == *"docs/rooty-spec.org"* ]] + [ -f docs/design/widget.org ] # nothing moved +} + +@test "spec-sort --apply: a terminal keyword without --reason refuses" { + make_project + run "$SCRIPT" --apply --confirm docs/design/widget.org=IMPLEMENTED --skip docs/rooty-spec.org + [ "$status" -eq 1 ] + [[ "$output" == *"--reason"* ]] + [ -f docs/design/widget.org ] +} + +@test "spec-sort --apply: a terminal keyword with --reason records it in the history line" { + make_project + run "$SCRIPT" --apply --confirm docs/design/widget.org=IMPLEMENTED \ + --reason "docs/design/widget.org=shipped in v2, confirmed against src" \ + --skip docs/rooty-spec.org + [ "$status" -eq 0 ] + grep -q '^\* IMPLEMENTED Widget Feature' docs/specs/widget-spec.org + grep -q 'shipped in v2, confirmed against src' docs/specs/widget-spec.org +} + +@test "spec-sort --apply: --skip leaves the candidate in place and still stamps the marker" { + make_project + run "$SCRIPT" --apply --skip docs/design/widget.org --skip docs/rooty-spec.org + [ "$status" -eq 0 ] + [ -f docs/design/widget.org ] + grep -q ':LAST_SPEC_SORT:' .ai/notes.org +} + +# ---- Preflight -------------------------------------------------------- + +@test "spec-sort --apply: refuses on a dirty worktree (exit 2)" { + make_project + echo "drift" >> todo.org + run "$SCRIPT" --apply "${CONFIRM_ALL[@]}" + [ "$status" -eq 2 ] + [[ "$output" == *"dirty"* ]] + [ -f docs/design/widget.org ] +} + +@test "spec-sort --apply --allow-dirty: proceeds and names what recovery loses" { + make_project + echo "drift" >> todo.org + git add todo.org && git commit -qm drift # keep the link intact; dirty a different file + echo "scratch" > untracked-note.txt + echo "local edit" >> .ai/notes.org + run "$SCRIPT" --apply --allow-dirty "${CONFIRM_ALL[@]}" + [ "$status" -eq 0 ] + [[ "$output" == *"pre-existing"* ]] + [[ "$output" == *".ai/notes.org"* ]] + [ -f docs/specs/widget-spec.org ] +} + +# ---- Move + rename + rewrite ------------------------------------------ + +@test "spec-sort --apply: moves, renames to -spec.org, prepends status heading with :ID: and history" { + make_project + run "$SCRIPT" --apply "${CONFIRM_ALL[@]}" + [ "$status" -eq 0 ] + [ -f docs/specs/widget-spec.org ] + [ ! -f docs/design/widget.org ] + grep -q '^\* DRAFT Widget Feature' docs/specs/widget-spec.org + grep -q ':ID:' docs/specs/widget-spec.org + grep -q 'retrofitted by spec-sort' docs/specs/widget-spec.org +} + +@test "spec-sort --apply: keyword header rewritten to the two-sequence form" { + make_project + run "$SCRIPT" --apply "${CONFIRM_ALL[@]}" + [ "$status" -eq 0 ] + grep -q '^#+TODO: TODO | DONE$' docs/specs/widget-spec.org + grep -q '^#+TODO: DRAFT READY DOING | IMPLEMENTED SUPERSEDED CANCELLED$' docs/specs/widget-spec.org + ! grep -q 'DRAFT REVIEW | SHIPPED' docs/specs/widget-spec.org +} + +@test "spec-sort --apply: Metadata Status field mirrors the confirmed keyword in lowercase" { + make_project + run "$SCRIPT" --apply --confirm docs/design/widget.org=READY --skip docs/rooty-spec.org + [ "$status" -eq 0 ] + grep -q '^\* READY Widget Feature' docs/specs/widget-spec.org + grep -Eq '^\| Status[[:space:]]*\|[[:space:]]*ready' docs/specs/widget-spec.org +} + +# ---- Relink ----------------------------------------------------------- + +@test "spec-sort --apply: rewrites the todo.org link, preserving the description" { + make_project + run "$SCRIPT" --apply "${CONFIRM_ALL[@]}" + [ "$status" -eq 0 ] + grep -q '\[\[file:docs/specs/widget-spec.org\]\[widget spec\]\]' todo.org + ! grep -q 'docs/design/widget.org' todo.org +} + +@test "spec-sort --apply: preserves a ::anchor suffix through the rewrite" { + make_project + run "$SCRIPT" --apply "${CONFIRM_ALL[@]}" + [ "$status" -eq 0 ] + grep -q '\[\[file:docs/specs/widget-spec.org::\*Summary\]\[the summary\]\]' todo.org +} + +@test "spec-sort --apply: recomputes a sibling note's relative link to the moved spec" { + make_project + run "$SCRIPT" --apply "${CONFIRM_ALL[@]}" + [ "$status" -eq 0 ] + grep -q '\[\[file:../specs/widget-spec.org\]\[the widget spec\]\]' docs/design/scratch-note.org +} + +@test "spec-sort --apply: recomputes the moved spec's own outbound link to an unmoved note" { + make_project + run "$SCRIPT" --apply "${CONFIRM_ALL[@]}" + [ "$status" -eq 0 ] + grep -q '\[\[file:../design/scratch-note.org\]\[the note\]\]' docs/specs/widget-spec.org +} + +@test "spec-sort: session archives are reported, never rewritten" { + make_project + run "$SCRIPT" + [ "$status" -eq 0 ] + [[ "$output" == *"REPORT .ai/sessions/2026-06-01-old.org"* ]] + run "$SCRIPT" --apply "${CONFIRM_ALL[@]}" + [ "$status" -eq 0 ] + grep -q 'docs/design/widget.org' .ai/sessions/2026-06-01-old.org +} + +@test "spec-sort: a synced template path report names the canonical rulesets file" { + make_project + mkdir -p .ai/workflows + echo 'See [[file:../../docs/design/widget.org][widget]]' > .ai/workflows/startup.org + git add -A && git commit -qm wf + run "$SCRIPT" + [ "$status" -eq 0 ] + [[ "$output" == *"REPORT .ai/workflows/startup.org"* ]] + [[ "$output" == *"claude-templates/.ai/workflows/startup.org"* ]] +} + +# ---- Bare-path mentions ----------------------------------------------- + +@test "spec-sort --apply: a bare-path mention in a rewritten root blocks until acknowledged" { + make_project + echo "raw mention: docs/design/widget.org needs review" >> todo.org + git add -A && git commit -qm bare + run "$SCRIPT" --apply "${CONFIRM_ALL[@]}" + [ "$status" -eq 1 ] + [[ "$output" == *"BARE"* ]] + [ -f docs/design/widget.org ] # nothing moved + run "$SCRIPT" --apply --acknowledge-bare "${CONFIRM_ALL[@]}" + [ "$status" -eq 0 ] + grep -q 'raw mention: docs/design/widget.org' todo.org # reported, never rewritten +} + +@test "spec-sort --apply: a moving doc's bare mention of its own old path is acknowledgeable, not post-apply residue" { + make_project + echo "History: docs/design/widget.org was drafted in May." >> docs/design/widget.org + git add -A && git commit -qm selfmention + run "$SCRIPT" --apply "${CONFIRM_ALL[@]}" + [ "$status" -eq 1 ] + [[ "$output" == *"BARE"* ]] + run "$SCRIPT" --apply --acknowledge-bare "${CONFIRM_ALL[@]}" + [ "$status" -eq 0 ] # the acknowledged mention rides along to docs/specs/; not residue + grep -q ':LAST_SPEC_SORT:' .ai/notes.org +} + +# ---- Plan validation --------------------------------------------------- + +@test "spec-sort --apply: a destination collision blocks validation, nothing moved" { + make_project + mkdir -p docs/specs + echo "occupied" > docs/specs/widget-spec.org + git add -A && git commit -qm occupy + run "$SCRIPT" --apply "${CONFIRM_ALL[@]}" + [ "$status" -eq 1 ] + [[ "$output" == *"destination exists"* ]] + [ -f docs/design/widget.org ] + [ "$(cat docs/specs/widget-spec.org)" = "occupied" ] +} + +@test "spec-sort --apply: writes the plan file before executing" { + make_project + run "$SCRIPT" --apply --plan-file "$TEST_DIR/plan.json" "${CONFIRM_ALL[@]}" + [ "$status" -eq 0 ] + [ -f "$TEST_DIR/plan.json" ] + grep -q 'widget-spec.org' "$TEST_DIR/plan.json" +} + +# ---- Mid-apply failure recovery ---------------------------------------- + +@test "spec-sort --apply: forced mid-apply failure yields named recovery, not a half-migrated shrug" { + make_project + run env SPEC_SORT_INJECT_FAIL_AFTER=1 "$SCRIPT" --apply "${CONFIRM_ALL[@]}" + [ "$status" -eq 1 ] + [[ "$output" == *"RECOVERY"* ]] + [[ "$output" == *"git restore"* ]] + [[ "$output" == *"applied"* ]] + [[ "$output" == *"not applied"* ]] + ! grep -q ':LAST_SPEC_SORT:' .ai/notes.org # no stamp on a failed apply +} + +# ---- Idempotence + marker ---------------------------------------------- + +@test "spec-sort --apply: stamps :LAST_SPEC_SORT: in the Workflow State section" { + make_project + run "$SCRIPT" --apply "${CONFIRM_ALL[@]}" + [ "$status" -eq 0 ] + grep -q ':LAST_SPEC_SORT: ' .ai/notes.org + # lands inside the Workflow State section, alongside the existing marker + awk '/^\* Workflow State/{ws=1} ws && /:LAST_SPEC_SORT:/{found=1} END{exit !found}' .ai/notes.org +} + +@test "spec-sort --apply: creates the Workflow State section when notes.org lacks it" { + make_project + printf '* Active Reminders\n' > .ai/notes.org + git add -A && git commit -qm notes + run "$SCRIPT" --apply "${CONFIRM_ALL[@]}" + [ "$status" -eq 0 ] + grep -q '^\* Workflow State' .ai/notes.org + grep -q ':LAST_SPEC_SORT: ' .ai/notes.org +} + +@test "spec-sort --apply: zero candidates still stamps the marker (clears the nudge)" { + make_project + rm docs/design/widget.org docs/rooty-spec.org docs/lonely-spec.org + git add -A && git commit -qm notes-only + run "$SCRIPT" --apply + [ "$status" -eq 0 ] + grep -q ':LAST_SPEC_SORT:' .ai/notes.org +} + +@test "spec-sort: a second run after a successful apply finds nothing to do" { + make_project + run "$SCRIPT" --apply "${CONFIRM_ALL[@]}" + [ "$status" -eq 0 ] + git add -A && git commit -qm sorted + run "$SCRIPT" + [ "$status" -eq 0 ] + [[ "$output" != *"CANDIDATE"* ]] + run "$SCRIPT" --apply + [ "$status" -eq 0 ] + run git status --porcelain + # only the re-stamped marker (same date) may differ — tree stays clean + [ -z "$(git status --porcelain -- docs todo.org)" ] +} diff --git a/.ai/scripts/tests/task-review-staleness.bats b/.ai/scripts/tests/task-review-staleness.bats index 488b023..79aad79 100644 --- a/.ai/scripts/tests/task-review-staleness.bats +++ b/.ai/scripts/tests/task-review-staleness.bats @@ -49,6 +49,16 @@ task_unreviewed() { printf '** %s [#%s] %s\nBody.\n\n' "$keyword" "$prio" "$title" >> "$TODO" } +# Emit a qualifying task whose LAST_REVIEWED is an org-native inactive +# timestamp — [YYYY-MM-DD Day] — matching the CREATED:/CLOSED: cookies that +# sit in the same drawer. The date is derived from an ISO date via `date`. +task_reviewed_org() { + local keyword="$1" prio="$2" title="$3" isodate="$4" + local org="[$(date -d "$isodate" '+%F %a')]" + printf '** %s [#%s] %s\n:PROPERTIES:\n:LAST_REVIEWED: %s\n:END:\nBody.\n\n' \ + "$keyword" "$prio" "$title" "$org" >> "$TODO" +} + # ---- Normal cases ---------------------------------------------------- @test "staleness: empty file reports zero" { @@ -85,6 +95,20 @@ task_unreviewed() { [ "$output" = "2" ] } +@test "staleness: org-native bracketed LAST_REVIEWED parses — recent is fresh" { + task_reviewed_org TODO A "Reviewed five days ago, org stamp" "$D5" + run bash "$SCRIPT" "$TODO" 30 + [ "$status" -eq 0 ] + [ "$output" = "0" ] +} + +@test "staleness: org-native bracketed LAST_REVIEWED parses — old is stale" { + task_reviewed_org TODO A "Reviewed forty days ago, org stamp" "$D40" + run bash "$SCRIPT" "$TODO" 30 + [ "$status" -eq 0 ] + [ "$output" = "1" ] +} + # ---- Boundary cases -------------------------------------------------- @test "staleness: age exactly equal to threshold is fresh" { @@ -136,9 +160,23 @@ task_unreviewed() { [ "$output" = "0" ] } -@test "staleness: malformed LAST_REVIEWED is treated as stale" { +@test "staleness: malformed LAST_REVIEWED warns to stderr and is not counted" { task_reviewed TODO A "Bad date" "not-a-date" - run bash "$SCRIPT" "$TODO" 30 + # stdout carries only the count — the malformed stamp is not folded in. + run bash -c "bash '$SCRIPT' '$TODO' 30 2>/dev/null" + [ "$status" -eq 0 ] + [ "$output" = "0" ] + # stderr carries the loud warning naming the offending value. + run bash -c "bash '$SCRIPT' '$TODO' 30 2>&1 1>/dev/null" + [ "$status" -eq 0 ] + [[ "$output" == *"not-a-date"* ]] + [[ "$output" == *"LAST_REVIEWED"* ]] +} + +@test "staleness: malformed stamp is excluded while real stale tasks still count" { + task_reviewed TODO A "Real stale" "$D40" + task_reviewed TODO B "Broken stamp" "garbage" + run bash -c "bash '$SCRIPT' '$TODO' 30 2>/dev/null" [ "$status" -eq 0 ] [ "$output" = "1" ] } @@ -161,6 +199,17 @@ task_unreviewed() { [[ "${lines[2]}" == *"Reviewed recently"* ]] } +@test "staleness --list: org-native bracketed stamp sorts by its real date" { + task_reviewed TODO A "Bare recent" "$D5" + task_reviewed_org TODO B "Org-stamped old" "$D40" + run bash "$SCRIPT" --list "$TODO" 10 + [ "$status" -eq 0 ] + # The org-bracketed old stamp must sort ahead of the bare recent one — + # proof it parsed to a real date rather than falling to 0000-00-00. + [[ "${lines[0]}" == *"Org-stamped old"* ]] + [[ "${lines[1]}" == *"Bare recent"* ]] +} + @test "staleness --list: takes only the requested count" { task_unreviewed TODO A "First" task_reviewed TODO B "Second" "$D40" diff --git a/.ai/scripts/tests/test-lint-org.el b/.ai/scripts/tests/test-lint-org.el index 3a83602..ceee209 100644 --- a/.ai/scripts/tests/test-lint-org.el +++ b/.ai/scripts/tests/test-lint-org.el @@ -193,6 +193,65 @@ real suspicious-language warning here #+end_src ") +;; invalid-block, false-positive case — a correctly paired example block whose +;; body holds a heading-shaped line. org's parser reads the `** ' inside the +;; verbatim body as a structural break, loses the open block, and flags BOTH +;; delimiters as "Possible incomplete block". +(defconst lo-test--verbatim-heading-block "\ +* Heading + +#+begin_example +** Feature Name or Topic +Body line. +#+end_example + +Trailing prose. +") + +;; invalid-block, literal-delimiter case — a paired src block whose body holds +;; a literal `#+end_example' plus a heading-shaped line. Only `#+end_src' +;; closes a src block, so all three findings here are false. +(defconst lo-test--literal-end-in-src "\ +* Heading + +#+begin_src text +#+end_example +** heading shaped +#+end_src +") + +;; invalid-block, uppercase-delimiter case — org accepts #+BEGIN_/#+END_ in +;; either case, and the pre-fix script flagged both delimiters here too. +(defconst lo-test--uppercase-verbatim-block "\ +* Heading + +#+BEGIN_EXAMPLE +** heading shaped +#+END_EXAMPLE +") + +;; invalid-block, genuine case — a block that really is never closed. The +;; suppression must not reach this one. +(defconst lo-test--unterminated-block "\ +* Heading + +#+begin_example +truly unterminated block body +") + +;; A genuinely unterminated block *after* a correctly paired one — verifies the +;; suppression is scoped per block rather than per file. +(defconst lo-test--paired-then-unterminated "\ +* Heading + +#+begin_example +** heading shaped +#+end_example + +#+begin_example +never closed +") + ;; Mixed fixture — each category once. (defconst lo-test--mixed "\ * Mixed @@ -392,6 +451,55 @@ suspicious-language judgment." (should (= 1 suspicious)))) ;;; --------------------------------------------------------------------------- +;;; invalid-block — false positives on correctly paired verbatim blocks + +(ert-deftest lo-verbatim-heading-block-emits-no-invalid-block () + "Normal: a paired example block containing a heading-shaped body line emits +no invalid-block judgment. Both delimiters are flagged by org-lint because the +parser treats the `** ' inside the verbatim body as a structural break." + (let* ((out (lo-test--run lo-test--verbatim-heading-block)) + (res (plist-get out :result)) + (judgments (lo-test--judgments (plist-get out :issues)))) + ;; File untouched, no fixes applied — suppression only, never a rewrite. + (should (equal lo-test--verbatim-heading-block res)) + (should (= 0 (plist-get out :fixes))) + (should-not (member 'invalid-block (lo-test--checkers judgments))))) + +(ert-deftest lo-literal-end-delimiter-in-src-emits-no-invalid-block () + "Boundary: a paired src block whose body holds a literal `#+end_example' and +a heading-shaped line emits no invalid-block judgment. Only `#+end_src' closes +a src block, so the interior delimiter is body text." + (let* ((out (lo-test--run lo-test--literal-end-in-src)) + (judgments (lo-test--judgments (plist-get out :issues)))) + (should-not (member 'invalid-block (lo-test--checkers judgments))))) + +(ert-deftest lo-uppercase-verbatim-block-emits-no-invalid-block () + "Boundary: block delimiters are case-insensitive in org, so an uppercase +`#+BEGIN_EXAMPLE' pair is suppressed the same as a lowercase one." + (let* ((out (lo-test--run lo-test--uppercase-verbatim-block)) + (judgments (lo-test--judgments (plist-get out :issues)))) + (should-not (member 'invalid-block (lo-test--checkers judgments))))) + +(ert-deftest lo-unterminated-block-still-emits-invalid-block () + "Error: a block that is never closed still emits its invalid-block judgment. +This is the finding the checker exists for — the suppression must not mask it." + (let* ((out (lo-test--run lo-test--unterminated-block)) + (judgments (lo-test--judgments (plist-get out :issues)))) + (should (member 'invalid-block (lo-test--checkers judgments))))) + +(ert-deftest lo-invalid-block-suppression-is-scoped-per-block () + "Boundary: a paired block and an unterminated block in the same file — the +paired one is suppressed and the unterminated one still reports. Exactly one +invalid-block judgment, and it points at the unterminated opener (line 7)." + (let* ((out (lo-test--run lo-test--paired-then-unterminated)) + (judgments (lo-test--judgments (plist-get out :issues))) + (invalid (cl-remove-if-not + (lambda (i) (eq (plist-get i :checker) 'invalid-block)) + judgments))) + (should (= 1 (length invalid))) + (should (= 7 (plist-get (car invalid) :line))))) + +;;; --------------------------------------------------------------------------- ;;; --check mode (ert-deftest lo-check-mode-does-not-modify-file () @@ -620,6 +728,29 @@ followups file on the next run." ;;; --------------------------------------------------------------------------- ;;; org-table-standard check (width budget + rules between rows) +(ert-deftest lo-table-inside-example-block-not-flagged () + "Pipe-led ASCII art inside an example block is not a table; no judgment." + (let* ((run (lo-test--run + "* H\n\n#+begin_example\n| client |----->| server |\n| box | | box |\n#+end_example\n" + 1 t)) + (judgments (lo-test--judgments (plist-get run :issues)))) + (should-not (memq 'org-table-standard (lo-test--checkers judgments))))) + +(ert-deftest lo-table-inside-src-block-not-flagged () + "Shell pipes inside a src block are not a table; no judgment." + (let* ((run (lo-test--run + "* H\n\n#+begin_src sh\n| sort\n| uniq -c\n#+end_src\n" 1 t)) + (judgments (lo-test--judgments (plist-get run :issues)))) + (should-not (memq 'org-table-standard (lo-test--checkers judgments))))) + +(ert-deftest lo-real-table-after-block-still-flagged () + "Block safety must not mask a genuine violation later in the file." + (let* ((run (lo-test--run + "* H\n\n#+begin_example\n| art |\n#+end_example\n\n| a | b |\n| 1 | 2 |\n" + 1 t)) + (judgments (lo-test--judgments (plist-get run :issues)))) + (should (memq 'org-table-standard (lo-test--checkers judgments))))) + (ert-deftest lo-table-over-budget-emits-judgment () "A table line rendering wider than 120 surfaces as an org-table-standard judgment." (let* ((wide (make-string 130 ?x)) @@ -659,5 +790,311 @@ missing-rules violation." (judgments (lo-test--judgments (plist-get run :issues)))) (should-not (memq 'org-table-standard (lo-test--checkers judgments))))) +;;; --------------------------------------------------------------------------- +;;; level-2 dated-header check (claude-rules/todo-format.md) + +(ert-deftest lo-level2-dated-header-is-judgment () + "A level-2 heading beginning with a YYYY-MM-DD date is flagged." + (let* ((out (lo-test--run + "* Open Work\n\n** 2026-06-20 Sat @ 10:00:00 -0500 Something resolved\nBody.\n")) + (res (plist-get out :result)) + (judgments (lo-test--judgments (plist-get out :issues)))) + (should (= 0 (plist-get out :fixes))) ; judgment-only, never auto-fixed + (should (member 'level-2-dated-header (lo-test--checkers judgments))))) + +(ert-deftest lo-level2-done-task-not-flagged () + "A level-2 task closed with a terminal keyword + CLOSED: is fine." + (let* ((out (lo-test--run + "* Open Work\n\n** DONE [#B] Something resolved\nCLOSED: [2026-06-20 Sat]\nBody.\n")) + (judgments (lo-test--judgments (plist-get out :issues)))) + (should-not (member 'level-2-dated-header (lo-test--checkers judgments))))) + +(ert-deftest lo-level3-dated-entry-not-flagged () + "A dated event-log entry at level 3 is the correct sub-task shape, not a defect." + (let* ((out (lo-test--run + "* Open Work\n\n** TODO [#B] Parent task\n*** 2026-06-20 Sat @ 10:00:00 -0500 sub-entry landed\nBody.\n")) + (judgments (lo-test--judgments (plist-get out :issues)))) + (should-not (member 'level-2-dated-header (lo-test--checkers judgments))))) + +;;; subtask-done-not-dated check (the inverse: level-3+ done keyword) + +(ert-deftest lo-subtask-done-not-dated-flags-level3 () + "A level-3 DONE sub-task still carrying the keyword is flagged for conversion." + (let* ((out (lo-test--run + "* Open Work\n\n** TODO [#B] Parent\n*** DONE [#C] Sub-task done\nCLOSED: [2026-06-20 Sat 10:00]\nBody.\n")) + (judgments (lo-test--judgments (plist-get out :issues)))) + (should (= 0 (plist-get out :fixes))) ; judgment-only, never auto-fixed + (should (member 'subtask-done-not-dated (lo-test--checkers judgments))))) + +(ert-deftest lo-subtask-done-not-dated-flags-level4-cancelled () + "A level-4 CANCELLED sub-task is flagged too." + (let* ((out (lo-test--run + "* Open Work\n\n** PROJECT [#B] Parent\n*** TODO Mid\n**** CANCELLED Deep abandoned\nCLOSED: [2026-06-20 Sat]\n")) + (judgments (lo-test--judgments (plist-get out :issues)))) + (should (member 'subtask-done-not-dated (lo-test--checkers judgments))))) + +(ert-deftest lo-subtask-done-not-dated-ignores-level2 () + "A level-2 DONE task is a top-level task, not a sub-task — this checker skips it." + (let* ((out (lo-test--run + "* Open Work\n\n** DONE [#B] Top-level\nCLOSED: [2026-06-20 Sat]\nBody.\n")) + (judgments (lo-test--judgments (plist-get out :issues)))) + (should-not (member 'subtask-done-not-dated (lo-test--checkers judgments))))) + +(ert-deftest lo-subtask-done-not-dated-ignores-dated-and-lowercase () + "An already-dated level-3 entry, and the word done in a title, are not flagged." + (let* ((out (lo-test--run + "* Open Work\n\n** TODO [#B] Parent\n*** 2026-06-20 Sat @ 10:00:00 -0400 landed\n*** TODO wrap the done cleanup\n")) + (judgments (lo-test--judgments (plist-get out :issues)))) + (should-not (member 'subtask-done-not-dated (lo-test--checkers judgments))))) + +;;; dated-log-heading-active-timestamp check (stale SCHEDULED/DEADLINE on a +;;; completed dated-log entry — the home 2026-07-17 agenda-pollution bug) + +(ert-deftest lo-dated-log-active-scheduled-is-flagged () + "A dated-log entry still carrying an active SCHEDULED is flagged: org renders +it on the agenda forever despite the missing keyword." + (let* ((out (lo-test--run + "* Open Work\n\n** TODO [#B] Parent\n*** 2026-06-20 Sat @ 10:00:00 -0500 trip booked\nSCHEDULED: <2026-06-18 Thu>\nBody.\n")) + (judgments (lo-test--judgments (plist-get out :issues)))) + (should (= 0 (plist-get out :fixes))) ; judgment-only, never auto-fixed + (should (member 'dated-log-heading-active-timestamp (lo-test--checkers judgments))))) + +(ert-deftest lo-dated-log-active-deadline-is-flagged () + "An active DEADLINE on a dated-log entry is flagged too." + (let* ((out (lo-test--run + "* Open Work\n\n** TODO [#B] Parent\n*** 2026-06-20 Sat @ 10:00:00 -0500 shipped\nDEADLINE: <2026-06-25 Thu>\n")) + (judgments (lo-test--judgments (plist-get out :issues)))) + (should (member 'dated-log-heading-active-timestamp (lo-test--checkers judgments))))) + +(ert-deftest lo-dated-log-clean-entry-not-flagged () + "A dated-log entry with no active planning timestamp is correct — not flagged." + (let* ((out (lo-test--run + "* Open Work\n\n** TODO [#B] Parent\n*** 2026-06-20 Sat @ 10:00:00 -0500 done cleanly\nBody only.\n")) + (judgments (lo-test--judgments (plist-get out :issues)))) + (should-not (member 'dated-log-heading-active-timestamp (lo-test--checkers judgments))))) + +(ert-deftest lo-dated-log-inactive-timestamp-not-flagged () + "An inactive [..] timestamp doesn't render on the agenda, so it isn't flagged — +only active <..> planning timestamps are the defect." + (let* ((out (lo-test--run + "* Open Work\n\n** TODO [#B] Parent\n*** 2026-06-20 Sat @ 10:00:00 -0500 recorded\nSCHEDULED: [2026-06-18 Thu]\n")) + (judgments (lo-test--judgments (plist-get out :issues)))) + (should-not (member 'dated-log-heading-active-timestamp (lo-test--checkers judgments))))) + +(ert-deftest lo-dated-log-active-scheduled-on-live-todo-not-flagged () + "A live TODO (keyword present) that legitimately carries an active SCHEDULED is +not a dated-log heading, so this checker leaves it alone." + (let* ((out (lo-test--run + "* Open Work\n\n** TODO [#B] Parent\n*** TODO [#C] real upcoming task\nSCHEDULED: <2026-06-18 Thu>\n")) + (judgments (lo-test--judgments (plist-get out :issues)))) + (should-not (member 'dated-log-heading-active-timestamp (lo-test--checkers judgments))))) + +;;; --------------------------------------------------------------------------- +;;; structural heading checks (org-lint gaps) + +(defun lo-test--checker-lines (issues checker) + "Lines of judgment ISSUES whose :checker is CHECKER, document order." + (mapcar (lambda (i) (plist-get i :line)) + (cl-remove-if-not + (lambda (i) (and (eq (plist-get i :kind) 'judgment) + (eq (plist-get i :checker) checker))) + (reverse issues)))) + +(ert-deftest lo-indented-heading-flags-leading-whitespace () + "Error: a heading indented off column 0 is flagged (org demotes it to body)." + (let* ((out (lo-test--run "* Open\n ** TODO indented and lost\n** TODO fine\n")) + (j (lo-test--judgments (plist-get out :issues)))) + (should (member 'indented-heading (lo-test--checkers j))) + (should (= 1 (length (lo-test--checker-lines (plist-get out :issues) + 'indented-heading)))))) + +(ert-deftest lo-indented-heading-skips-stars-inside-blocks () + "Boundary: indented stars inside a #+begin_/#+end_ block are legitimate content." + (let* ((out (lo-test--run "* Open\n#+begin_example\n ** not a heading\n#+end_example\n")) + (j (lo-test--judgments (plist-get out :issues)))) + (should-not (member 'indented-heading (lo-test--checkers j))))) + +(ert-deftest lo-indented-heading-skips-single-star-list-bullets () + "Normal: an indented single `*' is a valid plain-list bullet, not a demoted +heading, so it is not flagged — only two-or-more indented stars are." + (let* ((out (lo-test--run "* Open\nintro line\n * first bullet\n * second bullet\n * nested bullet\n")) + (j (lo-test--judgments (plist-get out :issues)))) + (should-not (member 'indented-heading (lo-test--checkers j))))) + +(ert-deftest lo-empty-heading-flags-bare-stars () + "Error: a line of bare stars with no title is flagged." + (let* ((out (lo-test--run "* Open\n** \n** TODO real\n")) + (j (lo-test--judgments (plist-get out :issues)))) + (should (member 'empty-heading (lo-test--checkers j))))) + +(ert-deftest lo-malformed-priority-flags-lowercase-and-skips-valid () + "Error + Normal: a lowercase/oversized cookie flags; a valid [#B] stays silent." + (let* ((bad (lo-test--run "* Open\n** TODO [#a] lowercase cookie\n** TODO [#BB] oversized\n")) + (ok (lo-test--run "* Open\n** TODO [#B] valid cookie\n")) + (jo (lo-test--judgments (plist-get ok :issues)))) + (should (= 2 (length (lo-test--checker-lines (plist-get bad :issues) + 'malformed-priority-cookie)))) + (should-not (member 'malformed-priority-cookie (lo-test--checkers jo))))) + +(ert-deftest lo-malformed-priority-skips-verbatim-cookie-in-title () + "Boundary: a dated-log title quoting =[#D]= verbatim is not a real cookie." + (let* ((out (lo-test--run "* Open\n** TODO [#B] parent\n*** 2026-05-14 reprioritized =[#D]= -> =[#B]=\n")) + (j (lo-test--judgments (plist-get out :issues)))) + (should-not (member 'malformed-priority-cookie (lo-test--checkers j))))) + +(ert-deftest lo-done-without-closed-flags-undated-level2 () + "Error: a level-2 DONE with no CLOSED line is flagged; a dated one is not." + (let* ((bad (lo-test--run "* Resolved\n** DONE undated finished\nbody\n")) + (jb (lo-test--judgments (plist-get bad :issues))) + (ok (lo-test--run "* Resolved\n** DONE dated\nCLOSED: [2026-06-29 Mon]\n")) + (jo (lo-test--judgments (plist-get ok :issues)))) + (should (member 'level2-done-without-closed (lo-test--checkers jb))) + (should-not (member 'level2-done-without-closed (lo-test--checkers jo))))) + +(ert-deftest lo-done-without-closed-ignores-deeper-levels () + "Boundary: a level-3 DONE (a dated-log sub-entry) need not carry CLOSED." + (let* ((out (lo-test--run "* Resolved\n** DONE parent\nCLOSED: [2026-06-29 Mon]\n*** DONE nested no-closed\n")) + (j (lo-test--judgments (plist-get out :issues)))) + (should-not (member 'level2-done-without-closed (lo-test--checkers j))))) + +(ert-deftest lo-structural-checks-silent-on-clean-file () + "Normal: a well-formed file trips none of the four structural checkers." + (let* ((out (lo-test--run "* Open Work\n** TODO [#A] a task :tag:\n** DOING [#B] another\n* Resolved\n** DONE [#C] done\nCLOSED: [2026-06-29 Mon]\n")) + (checkers (lo-test--checkers (lo-test--judgments (plist-get out :issues))))) + (dolist (c '(indented-heading empty-heading malformed-priority-cookie + level2-done-without-closed)) + (should-not (member c checkers))))) + (provide 'test-lint-org) ;;; test-lint-org.el ends here + +;;; --------------------------------------------------------------------------- +;;; task-missing-last-reviewed (claude-rules/todo-format.md) + +(ert-deftest lo-task-without-last-reviewed-is-judgment () + "An open level-2 task with no :LAST_REVIEWED: is flagged." + (let* ((out (lo-test--run "* Open Work\n** TODO [#B] A task :feature:\nBody.\n")) + (js (lo-test--judgments (plist-get out :issues)))) + (should (memq 'task-missing-last-reviewed (lo-test--checkers js))))) + +(ert-deftest lo-task-with-last-reviewed-is-clean () + "A task carrying the property is not flagged." + (let* ((out (lo-test--run (concat "* Open Work\n** TODO [#B] A task :feature:\n" + ":PROPERTIES:\n:LAST_REVIEWED: 2026-07-23\n:END:\n" + "Body.\n"))) + (js (lo-test--judgments (plist-get out :issues)))) + (should-not (memq 'task-missing-last-reviewed (lo-test--checkers js))))) + +(ert-deftest lo-task-last-reviewed-accepts-org-timestamp () + "The org-native [YYYY-MM-DD Day] form counts, matching the staleness script." + (let* ((out (lo-test--run (concat "* Open Work\n** TODO [#B] A task :feature:\n" + ":PROPERTIES:\n:LAST_REVIEWED: [2026-07-23 Thu]\n:END:\n"))) + (js (lo-test--judgments (plist-get out :issues)))) + (should-not (memq 'task-missing-last-reviewed (lo-test--checkers js))))) + +(ert-deftest lo-done-task-without-last-reviewed-is-clean () + "Completed tasks leave the review pool, so they are never flagged." + (let* ((out (lo-test--run (concat "* Open Work\n** DONE [#B] A task :feature:\n" + "CLOSED: [2026-07-23 Thu]\n"))) + (js (lo-test--judgments (plist-get out :issues)))) + (should-not (memq 'task-missing-last-reviewed (lo-test--checkers js))))) + +(ert-deftest lo-subtask-without-last-reviewed-is-clean () + "Only level-2 tasks are in the review pool; deeper headings are not." + (let* ((out (lo-test--run (concat "* Open Work\n** TODO [#B] Parent :feature:\n" + ":PROPERTIES:\n:LAST_REVIEWED: 2026-07-23\n:END:\n" + "*** TODO A sub-task\n"))) + (js (lo-test--judgments (plist-get out :issues)))) + (should-not (memq 'task-missing-last-reviewed (lo-test--checkers js))))) + +(ert-deftest lo-cookieless-task-without-last-reviewed-is-clean () + "The staleness script selects on a priority cookie, so match that scope." + (let* ((out (lo-test--run "* Open Work\n** TODO Manual testing and validation\n")) + (js (lo-test--judgments (plist-get out :issues)))) + (should-not (memq 'task-missing-last-reviewed (lo-test--checkers js))))) + +(ert-deftest lo-verify-task-without-last-reviewed-is-judgment () + "VERIFY is in the review pool too." + (let* ((out (lo-test--run "* Open Work\n** VERIFY [#B] Waiting on Craig\n")) + (js (lo-test--judgments (plist-get out :issues)))) + (should (memq 'task-missing-last-reviewed (lo-test--checkers js))))) + +;;; --------------------------------------------------------------------------- +;;; todo-format checkers skip docs/specs/ files (claude-rules/todo-format.md) +;; +;; The four todo-format-family checkers encode todo.org completion conventions. +;; A spec legitimately uses ** DONE <decision> with no CLOSED cookie and +;; ** <dated> — <who> review-history headings, so those checkers misfire on +;; every spec. They must skip any file under a docs/specs/ path segment. + +(defun lo-test--run-at (relpath content) + "Write CONTENT to <tmpdir>/RELPATH, run lint on it, return :issues. +RELPATH is a relative path (may contain slashes) so a docs/specs/ segment +can be exercised — the checkers key on the file's path, not just its name." + (let* ((root (make-temp-file "lo-test-root-" t)) + (file (expand-file-name relpath root))) + (make-directory (file-name-directory file) t) + (unwind-protect + (progn + (with-temp-file file (insert content)) + (lo-test--reset) + (lo-process-file file) + (prog1 (list :issues lo-issues) + (lo-test--drop-buffer file))) + (delete-directory root t)))) + +(defconst lo-test--spec-decisions + "* Decisions [1/1]\n** DONE Some decision\n- Context: x\n" + "A spec Decisions section: a level-2 DONE with no CLOSED cookie.") + +(defconst lo-test--spec-history + "* Review history\n** 2026-07-14 Tue @ 02:03:28 -0500 — Claude — responder\n- What: x\n" + "A spec review-history section: a level-2 dated header.") + +(ert-deftest lo-todo-checkers-fire-on-a-normal-org-file () + "Baseline: the checkers DO fire on a non-spec path (the bug is scope, not silence)." + (let* ((out (lo-test--run-at "todo.org" lo-test--spec-decisions)) + (cs (lo-test--checkers (lo-test--judgments (plist-get out :issues))))) + (should (memq 'level2-done-without-closed cs)))) + +(ert-deftest lo-level2-done-without-closed-skips-specs () + (let* ((out (lo-test--run-at "docs/specs/2026-07-14-x-spec.org" lo-test--spec-decisions)) + (cs (lo-test--checkers (lo-test--judgments (plist-get out :issues))))) + (should-not (memq 'level2-done-without-closed cs)))) + +(ert-deftest lo-level2-dated-header-skips-specs () + (let* ((out (lo-test--run-at "docs/specs/2026-07-14-x-spec.org" lo-test--spec-history)) + (cs (lo-test--checkers (lo-test--judgments (plist-get out :issues))))) + (should-not (memq 'level-2-dated-header cs)))) + +(ert-deftest lo-dated-log-active-timestamp-skips-specs () + (let* ((c "* History\n** 2026-07-14 Tue @ 02:03:28 -0500 — did a thing\nSCHEDULED: <2026-07-20 Mon>\n") + (out (lo-test--run-at "docs/specs/2026-07-14-x-spec.org" c)) + (cs (lo-test--checkers (lo-test--judgments (plist-get out :issues))))) + (should-not (memq 'dated-log-heading-active-timestamp cs)))) + +(ert-deftest lo-subtask-done-not-dated-skips-specs () + (let* ((c "* Work\n** TODO Parent\n*** DONE A sub-decision\n") + (out (lo-test--run-at "docs/specs/2026-07-14-x-spec.org" c)) + (cs (lo-test--checkers (lo-test--judgments (plist-get out :issues))))) + (should-not (memq 'subtask-done-not-dated cs)))) + +(ert-deftest lo-link-checks-still-fire-on-specs () + "Only the todo-format family is scoped out; a broken link in a spec still flags." + (let* ((c "* X\n[[file:does-not-exist-xyz.org][link]]\n") + (out (lo-test--run-at "docs/specs/2026-07-14-x-spec.org" c)) + (cs (lo-test--checkers (lo-test--judgments (plist-get out :issues))))) + (should (memq 'link-to-local-file cs)))) + +(ert-deftest lo-task-missing-last-reviewed-skips-specs () + "The fifth todo-format checker (added 2026-07-23) skips specs too — a spec's +phases section may carry ** TODO [#x] items that aren't backlog tasks." + (let* ((c "* Implementation phases\n** TODO [#B] Phase one\nBody.\n") + (out (lo-test--run-at "docs/specs/2026-07-14-x-spec.org" c)) + (cs (lo-test--checkers (lo-test--judgments (plist-get out :issues))))) + (should-not (memq 'task-missing-last-reviewed cs))) + ;; And still fires on a normal file. + (let* ((c "* Work\n** TODO [#B] Real backlog task\nBody.\n") + (out (lo-test--run-at "todo.org" c)) + (cs (lo-test--checkers (lo-test--judgments (plist-get out :issues))))) + (should (memq 'task-missing-last-reviewed cs)))) diff --git a/.ai/scripts/tests/test-todo-cleanup.el b/.ai/scripts/tests/test-todo-cleanup.el index ad9260b..1e964b3 100644 --- a/.ai/scripts/tests/test-todo-cleanup.el +++ b/.ai/scripts/tests/test-todo-cleanup.el @@ -30,16 +30,22 @@ ;;; Harness (defun tc-test--reset (&optional check) - (setq tc-fixes 0 tc-archived 0 tc-bumped 0 tc-issues nil + (setq tc-fixes 0 tc-archived 0 tc-bumped 0 tc-archived-to-file 0 tc-issues nil + tc-sealed 0 tc-seal nil tc-convert-subtasks nil tc-check-only (and check t) tc-archive-done t tc-sync-child-priority nil - tc-current-file nil)) + tc-current-file nil + ;; Aging step OFF by default so the in-file-move tests are unaffected by + ;; the wall clock; the aging harness re-enables it with fixed params. + tc-archive-retain-days nil tc-archive-reference-date nil tc-archive-file nil)) (defun tc-test--reset-sync (&optional check) - (setq tc-fixes 0 tc-archived 0 tc-bumped 0 tc-issues nil + (setq tc-fixes 0 tc-archived 0 tc-bumped 0 tc-archived-to-file 0 tc-issues nil + tc-sealed 0 tc-seal nil tc-check-only (and check t) tc-archive-done nil tc-sync-child-priority t - tc-current-file nil)) + tc-current-file nil + tc-archive-retain-days nil tc-archive-reference-date nil tc-archive-file nil)) (defun tc-test--drop-buffer (file) (let ((buf (find-buffer-visiting file))) @@ -355,6 +361,207 @@ from the heading line through (not including) the next level-1 heading or EOF." (should (tc-test--has (plist-get out :report) "skipped")))) ;;; --------------------------------------------------------------------------- +;;; --archive-done file-aging: keep last week in-file, move older to task-archive + +(defun tc-test--age (content &optional opts) + "Run `--archive-done' with the file-aging step enabled. +OPTS is a plist: :retain (days; default 7, may be nil to disable), :ref +\(YEAR MONTH DAY reference date), :runs (default 1), :check. Writes CONTENT to a +temp todo file and points `tc-archive-file' at a not-yet-existing temp archive. +Returns a plist: :result (todo contents), :archive (archive-file contents or +nil), :archived (in-file move count), :to-file (aged count), :issues — all from +the last run." + (let* ((retain (if (plist-member opts :retain) (plist-get opts :retain) 7)) + (ref (plist-get opts :ref)) + (runs (or (plist-get opts :runs) 1)) + (check (plist-get opts :check)) + (todo (make-temp-file "tc-age-todo-" nil ".org")) + (adir (make-temp-file "tc-age-arch-" t)) + (afile (expand-file-name "task-archive.org" adir)) + last) + (unwind-protect + (progn + (with-temp-file todo (insert content)) + (dotimes (_ runs) + (tc-test--reset check) + (setq tc-archive-retain-days retain + tc-archive-reference-date ref + tc-archive-file afile) + (tc-process-file todo) + (setq last (list :archived tc-archived :to-file tc-archived-to-file + :issues tc-issues)) + (tc-test--drop-buffer todo)) + (append + last + (list :result (with-temp-buffer (insert-file-contents todo) (buffer-string)) + :archive (and (file-readable-p afile) + (with-temp-buffer (insert-file-contents afile) + (buffer-string)))))) + (tc-test--drop-buffer todo) + (delete-file todo) + (delete-directory adir t)))) + +;; Reference "today" for these fixtures is 2026-06-29; with retain 7 the cutoff +;; is 2026-06-22, so a task closed on or after 2026-06-22 stays in-file. +(defconst tc-test--age-resolved "\ +* Age Open Work +** TODO [#A] still open +* Age Resolved +** DONE [#B] recent within window +CLOSED: [2026-06-25 Thu] +recent body +** DONE [#C] old beyond window +CLOSED: [2026-05-01 Fri] +old body line +** CANCELLED [#C] old cancelled too +CLOSED: [2026-04-15 Wed] +** DONE [#B] exactly at cutoff stays +CLOSED: [2026-06-22 Sun] +** DONE [#C] undated no-date archived +no closed date in this body +") + +(defconst tc-test--age-straggler "\ +* Age Open Work +** TODO [#A] still open +** DONE [#C] old straggler +CLOSED: [2026-03-01 Sun] +straggler body +* Age Resolved +** DONE [#B] recent stays +CLOSED: [2026-06-26 Fri] +") + +(ert-deftest tc-age-moves-old-and-undated-resolved () + "Normal: closed-beyond-window AND undated subtrees leave the file; only those +closed within the window (cutoff inclusive) stay." + (let* ((out (tc-test--age tc-test--age-resolved '(:ref (2026 6 29)))) + (resolved (tc-test--section (plist-get out :result) "Age Resolved")) + (arch (plist-get out :archive))) + (should (= 3 (plist-get out :to-file))) + (should-not (tc-test--has resolved "old beyond window")) + (should-not (tc-test--has resolved "old cancelled too")) + (should-not (tc-test--has resolved "undated no-date archived")) + (should (tc-test--has resolved "recent within window")) + (should (tc-test--has resolved "exactly at cutoff stays")) + (should arch) + (should (tc-test--has arch "Resolved (archived)")) + (should (tc-test--has arch "old beyond window")) + (should (tc-test--has arch "old body line")) + (should (tc-test--has arch "old cancelled too")) + (should (tc-test--has arch "undated no-date archived")) + (should-not (tc-test--has arch "recent within window")))) + +(ert-deftest tc-age-disabled-when-retain-nil () + "Boundary: nil retain disables the aging step entirely (legacy behavior)." + (let ((out (tc-test--age tc-test--age-resolved '(:retain nil :ref (2026 6 29))))) + (should (= 0 (plist-get out :to-file))) + (should (equal tc-test--age-resolved (plist-get out :result))) + (should-not (plist-get out :archive)))) + +(ert-deftest tc-age-is-idempotent () + "Boundary: a second run finds nothing new to age; the todo file is stable." + (let ((once (tc-test--age tc-test--age-resolved '(:ref (2026 6 29) :runs 1))) + (twice (tc-test--age tc-test--age-resolved '(:ref (2026 6 29) :runs 2)))) + (should (equal (plist-get once :result) (plist-get twice :result))) + (should (= 0 (plist-get twice :to-file))))) + +(ert-deftest tc-age-check-mode-previews-without-writing () + "Boundary: --check reports the aged count but writes neither file." + (let ((out (tc-test--age tc-test--age-resolved '(:ref (2026 6 29) :check t)))) + (should (= 3 (plist-get out :to-file))) + (should (equal tc-test--age-resolved (plist-get out :result))) + (should-not (plist-get out :archive)))) + +(ert-deftest tc-age-straggler-moves-through-to-archive () + "Normal: an old-dated DONE in Open Work moves to Resolved then ages out in one run." + (let* ((out (tc-test--age tc-test--age-straggler '(:ref (2026 6 29)))) + (open (tc-test--section (plist-get out :result) "Age Open Work")) + (resolved (tc-test--section (plist-get out :result) "Age Resolved")) + (arch (plist-get out :archive))) + (should-not (tc-test--has open "old straggler")) + (should-not (tc-test--has resolved "old straggler")) + (should (tc-test--has arch "old straggler")) + (should (tc-test--has arch "straggler body")) + (should (tc-test--has resolved "recent stays")) + (should (= 1 (plist-get out :archived))) + (should (= 1 (plist-get out :to-file))))) + +(ert-deftest tc-age-append-preserves-existing-archive () + "Error/edge: appending to a populated archive keeps prior entries and one scaffold." + (let* ((adir (make-temp-file "tc-arch-" t)) + (afile (expand-file-name "task-archive.org" adir))) + (unwind-protect + (progn + (tc--append-subtrees-to-archive-file afile (list "** DONE one\n")) + (tc--append-subtrees-to-archive-file afile (list "** DONE two\n")) + (let ((content (with-temp-buffer (insert-file-contents afile) + (buffer-string))) + (n 0) (start 0)) + (should (tc-test--has content "** DONE one")) + (should (tc-test--has content "** DONE two")) + (should (tc-test--before-p content "** DONE one" "** DONE two")) + (while (string-match "\\* Resolved (archived)" content start) + (setq n (1+ n) start (match-end 0))) + (should (= 1 n)))) + (delete-directory adir t)))) + +;;; --------------------------------------------------------------------------- +;;; --archive-done aging: the archive follows the todo file's gitignore status + +(defun tc-test--age-in-git-repo (gitignore-todo) + "Init a temp git repo, write todo.org with an old Resolved entry, optionally +gitignore todo.org, then run `--archive-done' aging with the DEFAULT archive path +(archive/task-archive.org beside the todo file). Return a plist: :gitignore (final +.gitignore contents or nil), :archive-ignored (whether git ignores the archive), +:archive-exists." + (let* ((root (make-temp-file "tc-git-" t)) + ;; Private backup dir: this helper writes a file literally named + ;; todo.org and runs a real (non-check) pass, so without this its + ;; backup lands in the shared temp dir under the exact production + ;; name and is indistinguishable from a real one. + (temporary-file-directory + (file-name-as-directory (make-temp-file "tc-git-bk-" t))) + (todo (expand-file-name "todo.org" root)) + (archive (expand-file-name "archive/task-archive.org" root)) + (gi (expand-file-name ".gitignore" root))) + (unwind-protect + (let ((default-directory root)) + (call-process "git" nil nil nil "init" "-q") + (with-temp-file todo (insert tc-test--age-resolved)) + (when gitignore-todo (with-temp-file gi (insert "/todo.org\n"))) + (tc-test--reset nil) + (setq tc-archive-retain-days 7 + tc-archive-reference-date '(2026 6 29) + tc-archive-file nil) ; default path, beside the todo file + (tc-process-file todo) + (tc-test--drop-buffer todo) + (list :gitignore (and (file-readable-p gi) + (with-temp-buffer (insert-file-contents gi) + (buffer-string))) + :archive-ignored + (eq 0 (call-process "git" nil nil nil "check-ignore" "-q" archive)) + :archive-exists (file-readable-p archive))) + (delete-directory root t) + (delete-directory temporary-file-directory t)))) + +(ert-deftest tc-age-self-protect-gitignores-archive-when-todo-ignored () + "When the todo file is gitignored, the aged-out archive is added to .gitignore +so it inherits the same privacy." + (let ((out (tc-test--age-in-git-repo t))) + (should (plist-get out :archive-exists)) + (should (string-match-p "task-archive" (or (plist-get out :gitignore) ""))) + (should (plist-get out :archive-ignored)))) + +(ert-deftest tc-age-self-protect-leaves-tracked-todo-archive-tracked () + "When the todo file is tracked, the archive is not gitignored — no .gitignore +entry is added for it." + (let ((out (tc-test--age-in-git-repo nil))) + (should (plist-get out :archive-exists)) + (should-not (plist-get out :archive-ignored)) + (should-not (string-match-p "task-archive" (or (plist-get out :gitignore) ""))))) + +;;; --------------------------------------------------------------------------- ;;; Realistic synthetic sample (committed under fixtures/) (defun tc-test--sample-file () @@ -380,6 +587,95 @@ from the heading line through (not including) the next level-1 heading or EOF." (should (> (plist-get out :archived) 0))))) ;;; --------------------------------------------------------------------------- +;;; --archive-done retention default + +(ert-deftest tc-archive-retain-default-is-one-month () + "The shipped retention default is one month (31 days), not the legacy 7. +The defvar initializes from this defconst; the live var itself is mutated by +other tests, so the immutable defconst is the stable contract to pin." + (should (= 31 tc-archive-retain-days-default))) + +;;; --------------------------------------------------------------------------- +;;; --seal: rename the working archive to resolved-YYYY-MM-DD.org + +(defun tc-test--seal (&optional opts) + "Run `--seal' against a temp todo file with a temp archive dir. +OPTS is a plist: :archive-content (seed task-archive.org with this; nil = no +working archive), :ref (YEAR MONTH DAY seal date; default (2026 7 18)), +:check, :presealed (also create resolved-<ref>.org first, to test collision). +Returns a plist: :sealed count, :issues, :working-exists, :sealed-exists, +:sealed-name, :report." + (let* ((ref (or (plist-get opts :ref) '(2026 7 18))) + (check (plist-get opts :check)) + (archive-content (plist-get opts :archive-content)) + (todo (make-temp-file "tc-seal-todo-" nil ".org")) + (adir (make-temp-file "tc-seal-arch-" t)) + (afile (expand-file-name "task-archive.org" adir)) + (sealed-name (format "resolved-%04d-%02d-%02d.org" + (nth 0 ref) (nth 1 ref) (nth 2 ref))) + (sealed (expand-file-name sealed-name adir))) + (unwind-protect + (progn + (with-temp-file todo (insert "* Open Work\n** TODO [#A] live\n")) + (when archive-content (with-temp-file afile (insert archive-content))) + (when (plist-get opts :presealed) + (with-temp-file sealed (insert "pre-existing seal\n"))) + (tc-test--reset check) + ;; Set every mode flag explicitly: tc-test--reset leaves + ;; tc-convert-subtasks untouched, so a convert test running earlier in + ;; the suite would otherwise still own the dispatch and run convert. + (setq tc-archive-done nil tc-sync-child-priority nil + tc-convert-subtasks nil tc-seal t tc-sealed 0 + tc-archive-reference-date ref + tc-archive-file afile) + (let ((report (with-output-to-string (tc-process-file todo) (tc-emit-report)))) + (tc-test--drop-buffer todo) + (list :sealed tc-sealed + :issues tc-issues + :working-exists (file-readable-p afile) + :sealed-exists (file-readable-p sealed) + :sealed-name sealed-name + :report report))) + (tc-test--drop-buffer todo) + (delete-file todo) + (delete-directory adir t)))) + +(ert-deftest tc-seal-renames-working-archive-to-dated-file () + "Normal: --seal renames task-archive.org to resolved-<seal-date>.org." + (let ((out (tc-test--seal '(:archive-content "* Resolved (archived)\n** DONE old\n" + :ref (2026 7 18))))) + (should (= 1 (plist-get out :sealed))) + (should-not (plist-get out :working-exists)) + (should (plist-get out :sealed-exists)) + (should (equal "resolved-2026-07-18.org" (plist-get out :sealed-name))) + (should (tc-test--has (plist-get out :report) "sealed task-archive.org → resolved-2026-07-18.org")))) + +(ert-deftest tc-seal-nothing-to-seal-is-a-reported-noop () + "Boundary: no working archive present — reported no-op, nothing created." + (let ((out (tc-test--seal '(:ref (2026 7 18))))) + (should (= 0 (plist-get out :sealed))) + (should-not (plist-get out :sealed-exists)) + (should (tc-test--has (plist-get out :report) "no working archive to seal")))) + +(ert-deftest tc-seal-check-mode-previews-without-renaming () + "Boundary: --check reports the seal but leaves the working archive in place." + (let ((out (tc-test--seal '(:archive-content "* Resolved (archived)\n" + :ref (2026 7 18) :check t)))) + (should (= 1 (plist-get out :sealed))) + (should (plist-get out :working-exists)) + (should-not (plist-get out :sealed-exists)) + (should (tc-test--has (plist-get out :report) "would seal")))) + +(ert-deftest tc-seal-refuses-to-clobber-existing-sealed-file () + "Error: resolved-<today>.org already exists — refuse, leave both files intact." + (let ((out (tc-test--seal '(:archive-content "* Resolved (archived)\n" + :ref (2026 7 18) :presealed t)))) + (should (= 0 (plist-get out :sealed))) + (should (plist-get out :working-exists)) + (should (plist-get out :sealed-exists)) + (should (tc-test--has (plist-get out :report) "already exists")))) + +;;; --------------------------------------------------------------------------- ;;; Sync-child-priority harness + fixtures (defun tc-test--sync (content &optional runs check) @@ -570,5 +866,311 @@ in ISSUES, in document order." (should (= 2 (plist-get once :bumped))) (should (= 2 (plist-get twice :bumped))))) +;;; --------------------------------------------------------------------------- +;;; --convert-subtasks harness + tests + +(defun tc-test--reset-convert (&optional check) + (setq tc-fixes 0 tc-archived 0 tc-bumped 0 tc-converted 0 tc-archived-to-file 0 + tc-issues nil tc-sealed 0 tc-seal nil + tc-check-only (and check t) + tc-archive-done nil tc-sync-child-priority nil tc-convert-subtasks t + tc-current-file nil + tc-archive-retain-days nil tc-archive-reference-date nil tc-archive-file nil)) + +(defun tc-test--convert (content &optional runs check) + "Write CONTENT to a temp .org file, run `--convert-subtasks' RUNS times (default 1). +Return a plist: :result final file contents, :converted count from the last run, +:issues from the last run. CHECK non-nil ⇒ --check (preview, no writes)." + (let ((file (make-temp-file "tc-test-" nil ".org")) + last-converted last-issues) + (unwind-protect + (progn + (with-temp-file file (insert content)) + (dotimes (_ (or runs 1)) + (tc-test--reset-convert check) + (tc-process-file file) + (setq last-converted tc-converted last-issues tc-issues) + (tc-test--drop-buffer file)) + (list :result (with-temp-buffer (insert-file-contents file) + (buffer-string)) + :converted last-converted + :issues last-issues)) + (tc-test--drop-buffer file) + (delete-file file)))) + +;; The UTC offset in a converted header is the test machine's local offset for +;; that date, so assertions match it as `[-+]NNNN' rather than a fixed value — +;; the mode's job is to emit a well-formed offset, not to run in one timezone. + +(defconst tc-test--convert-timed + "* Project Open Work +** TODO [#B] Parent task +*** DONE [#C] F12 opens the terminal :feature:quick: +CLOSED: [2026-06-27 Sat 12:50] +Verified live: docks, toggles, colors clean. +") + +(ert-deftest tc-convert-timed-subtask-normal () + "Normal: a timed CLOSED close becomes a dated header, keyword/priority/tags/CLOSED gone." + (let* ((out (tc-test--convert tc-test--convert-timed)) + (res (plist-get out :result))) + (should (= 1 (plist-get out :converted))) + (should (string-match-p + "^\\*\\*\\* 2026-06-27 Sat @ 12:50:00 [-+][0-9]\\{4\\} F12 opens the terminal$" + res)) + (should-not (string-match-p "CLOSED:" res)) + (should-not (string-match-p "DONE" res)) + (should (string-match-p "Verified live: docks, toggles, colors clean\\." res)) + (should (string-match-p "^\\*\\* TODO \\[#B\\] Parent task$" res)))) + +(defconst tc-test--convert-dateonly + "* Project Open Work +** PROJECT [#B] Parent +**** DONE [#B] Write full spec :refactor: +CLOSED: [2026-05-04 Mon] +Body. +") + +(ert-deftest tc-convert-dateonly-boundary-midnight () + "Boundary: a date-only CLOSED (no time) yields 00:00:00, at level 4." + (let ((res (plist-get (tc-test--convert tc-test--convert-dateonly) :result))) + (should (string-match-p + "^\\*\\*\\*\\* 2026-05-04 Mon @ 00:00:00 [-+][0-9]\\{4\\} Write full spec$" + res)) + (should-not (string-match-p "CLOSED:" res)))) + +(defconst tc-test--convert-level2 + "* Project Open Work +** DONE [#B] Top-level task +CLOSED: [2026-06-01 Mon 09:00] +Body. +") + +(ert-deftest tc-convert-leaves-level-2-alone-boundary () + "Boundary: a level-2 DONE task is a top-level task, not a sub-task — untouched." + (let ((out (tc-test--convert tc-test--convert-level2))) + (should (= 0 (plist-get out :converted))) + (should (equal tc-test--convert-level2 (plist-get out :result))))) + +(ert-deftest tc-convert-idempotent-boundary () + "Boundary: a second run over an already-dated entry converts nothing new." + (let ((once (tc-test--convert tc-test--convert-timed 1)) + (twice (tc-test--convert tc-test--convert-timed 2))) + (should (equal (plist-get once :result) (plist-get twice :result))) + (should (= 0 (plist-get twice :converted))))) + +(defconst tc-test--convert-nested + "* Project Open Work +** TODO [#B] Parent +*** DONE Outer sub :feature: +CLOSED: [2026-06-10 Wed 08:15] +**** DONE Inner sub +CLOSED: [2026-06-09 Tue 07:00] +Inner body. +") + +(ert-deftest tc-convert-nested-done-subtasks-boundary () + "Boundary: a done sub-task nested under a done sub-task — both convert." + (let* ((out (tc-test--convert tc-test--convert-nested)) + (res (plist-get out :result))) + (should (= 2 (plist-get out :converted))) + (should (string-match-p + "^\\*\\*\\* 2026-06-10 Wed @ 08:15:00 [-+][0-9]\\{4\\} Outer sub$" res)) + (should (string-match-p + "^\\*\\*\\*\\* 2026-06-09 Tue @ 07:00:00 [-+][0-9]\\{4\\} Inner sub$" res)) + (should-not (string-match-p "CLOSED:" res)))) + +(defconst tc-test--convert-cancelled + "* Project Open Work +** TODO [#B] Parent +*** CANCELLED [#C] Abandoned idea :feature: +CLOSED: [2026-06-15 Mon 10:00] +") + +(ert-deftest tc-convert-cancelled-subtask-boundary () + "Boundary: a CANCELLED sub-task converts too (terminal state)." + (let ((res (plist-get (tc-test--convert tc-test--convert-cancelled) :result))) + (should (string-match-p + "^\\*\\*\\* 2026-06-15 Mon @ 10:00:00 [-+][0-9]\\{4\\} Abandoned idea$" res)) + (should-not (string-match-p "CANCELLED" res)))) + +(defconst tc-test--convert-noclosed + "* Project Open Work +** TODO [#B] Parent +*** DONE Orphan with no closed date +Body only. +") + +(ert-deftest tc-convert-skips-subtask-without-closed-error () + "Error: a done sub-task with no parseable CLOSED is flagged and left unchanged." + (let ((out (tc-test--convert tc-test--convert-noclosed))) + (should (= 0 (plist-get out :converted))) + (should (equal tc-test--convert-noclosed (plist-get out :result))) + (should (cl-some (lambda (i) (eq (plist-get i :kind) 'convert-skip)) + (plist-get out :issues))))) + +(ert-deftest tc-convert-check-mode-previews-without-writing () + "Check mode reports the conversion but writes nothing." + (let ((out (tc-test--convert tc-test--convert-timed 1 t))) + (should (= 1 (plist-get out :converted))) + (should (equal tc-test--convert-timed (plist-get out :result))) + (should (cl-some (lambda (i) (eq (plist-get i :kind) 'convert-would)) + (plist-get out :issues))))) + +(defconst tc-test--convert-closed-with-deadline + "* Project Open Work +** TODO [#B] Parent task +*** DONE [#C] Ship the panel :feature: +CLOSED: [2026-06-27 Sat 12:50] DEADLINE: <2026-06-30 Tue> +Body line. +") + +(ert-deftest tc-convert-strips-deadline-sharing-the-planning-line-boundary () + "Boundary: a DEADLINE sharing the CLOSED planning line goes too — a dated-log +entry carries no active planning timestamp (todo-format.md). Body survives." + (let* ((out (tc-test--convert tc-test--convert-closed-with-deadline)) + (res (plist-get out :result))) + (should (= 1 (plist-get out :converted))) + (should (string-match-p + "^\\*\\*\\* 2026-06-27 Sat @ 12:50:00 [-+][0-9]\\{4\\} Ship the panel$" + res)) + (should-not (string-match-p "CLOSED:" res)) + (should-not (string-match-p "DEADLINE:" res)) + (should (string-match-p "^Body line\\.$" res)))) + +(defconst tc-test--convert-closed-and-scheduled-separate-lines + "* Project Open Work +** TODO [#B] Parent task +*** DONE [#C] Book the venue :feature: +CLOSED: [2026-06-27 Sat 12:50] +SCHEDULED: <2026-06-20 Sat> +Body line. +") + +(ert-deftest tc-convert-strips-scheduled-on-its-own-line () + "Normal (the home bug): a SCHEDULED planning line on its own — the completion +rewrite dropped keyword/priority/tags but left the SCHEDULED, pinning the dated +entry to the agenda as weeks-overdue. Both planning lines go; body survives." + (let* ((out (tc-test--convert tc-test--convert-closed-and-scheduled-separate-lines)) + (res (plist-get out :result))) + (should (= 1 (plist-get out :converted))) + (should (string-match-p + "^\\*\\*\\* 2026-06-27 Sat @ 12:50:00 [-+][0-9]\\{4\\} Book the venue$" + res)) + (should-not (string-match-p "CLOSED:" res)) + (should-not (string-match-p "SCHEDULED:" res)) + (should (string-match-p "^Body line\\.$" res)))) + +(defconst tc-test--convert-scheduled-in-body-prose + "* Project Open Work +** TODO [#B] Parent task +*** DONE [#C] Note the mechanism :feature: +CLOSED: [2026-06-27 Sat 12:50] +An active SCHEDULED: <2026-06-20 Sat> in prose must survive. +") + +(ert-deftest tc-convert-leaves-planning-shaped-body-prose-alone () + "Boundary: a planning-shaped token inside body prose (not a canonical planning +line) is left untouched — the strip stops at the first non-planning line." + (let* ((out (tc-test--convert tc-test--convert-scheduled-in-body-prose)) + (res (plist-get out :result))) + (should (= 1 (plist-get out :converted))) + (should-not (string-match-p "CLOSED:" res)) + (should (string-match-p "An active SCHEDULED: <2026-06-20 Sat> in prose must survive\\." res)))) + (provide 'test-todo-cleanup) ;;; test-todo-cleanup.el ends here + +;;; --------------------------------------------------------------------------- +;;; Backup before mutating (parity with lint-org.el / wrap-org-table.el) +;; +;; todo-cleanup rewrites todo.org in place and left no copy behind, while both +;; sibling org-mutators back up to /tmp first. It is also the one that runs most +;; often (every wrap, every sentry cycle). Emacs's own backup does not fire under +;; --batch -q, so there was genuinely no undo short of git. + +(ert-deftest tc-backup-written-before-a-real-mutation () + "A real (non-check) run leaves a copy holding the pre-edit content. + +`temporary-file-directory' is rebound to a private dir for the duration: the +backup name derives from the *file's* basename, and the real todo.org shares +that basename, so a live sentry run writing /tmp/todo.org.before-todo-cleanup.* +would otherwise be indistinguishable from this test's own artifact. The first +version of this test globbed the shared /tmp and passed only until a real run +created one (2026-07-24)." + (let* ((dir (make-temp-file "tc-backup-" t)) + (bdir (file-name-as-directory (make-temp-file "tc-bk-" t))) + (file (expand-file-name "todo.org" dir)) + (before "* P Open Work\n** TODO [#B] parent\n*** DONE a subtask\nCLOSED: [2026-07-01 Tue]\n")) + (unwind-protect + (progn + (with-temp-file file (insert before)) + (let ((tc-check-only nil) + (tc-convert-subtasks t) + (temporary-file-directory bdir)) + (tc-process-file file)) + (let ((backups (file-expand-wildcards + (concat bdir "todo.org.before-todo-cleanup.*")))) + (should backups) + (should (string-match-p + "a subtask" + (with-temp-buffer (insert-file-contents (car backups)) + (buffer-string)))))) + (delete-directory dir t) + (delete-directory bdir t)))) + +(ert-deftest tc-no-backup-in-check-mode () + "--check writes nothing, so it must not leave a backup either. +Uses a private `temporary-file-directory' for the same isolation reason." + (let* ((dir (make-temp-file "tc-backup-" t)) + (bdir (file-name-as-directory (make-temp-file "tc-bk-" t))) + (file (expand-file-name "todo.org" dir))) + (unwind-protect + (progn + (with-temp-file file + (insert "* P Open Work\n** TODO [#B] parent\n*** DONE sub\nCLOSED: [2026-07-01 Tue]\n")) + (let ((tc-check-only t) + (tc-convert-subtasks t) + (temporary-file-directory bdir)) + (tc-process-file file)) + (should-not (file-expand-wildcards + (concat bdir "todo.org.before-todo-cleanup.*")))) + (delete-directory dir t) + (delete-directory bdir t)))) + +(ert-deftest tc-backup-never-overwrites-an-earlier-one () + "Two invocations in the same second must not collapse to one backup. + +open-tasks.org runs --convert-subtasks then --archive-done back to back, each +a sub-second batch run. With a second-resolution stamp and copy-file's +OK-IF-ALREADY-EXISTS, the second invocation overwrote the first's backup with +already-mutated content, so the true pre-session original was unrecoverable — +the exact state the backup exists to preserve (found 2026-07-24 in review)." + (let* ((dir (make-temp-file "tc-collide-" t)) + (bdir (file-name-as-directory (make-temp-file "tc-cbk-" t))) + (file (expand-file-name "todo.org" dir)) + (original (concat "* P Open Work\n** TODO [#B] parent\n*** DONE sub\n" + "CLOSED: [2026-07-01 Tue]\n" + "* P Resolved\n** DONE [#C] old\nCLOSED: [2025-01-01 Wed]\n"))) + (unwind-protect + (progn + (with-temp-file file (insert original)) + ;; Two back-to-back invocations, as the shipped workflow does. + (let ((temporary-file-directory bdir)) + (let ((tc-check-only nil) (tc-convert-subtasks t)) + (tc-process-file file)) + (let ((tc-check-only nil) (tc-convert-subtasks nil) (tc-archive-done t) + (tc-archive-retain-days nil)) + (tc-process-file file))) + (let ((backups (file-expand-wildcards + (concat bdir "todo.org.before-todo-cleanup.*")))) + ;; Both invocations kept their own backup. + (should (= (length backups) 2)) + ;; And one of them still holds the true original. + (should (cl-some (lambda (b) + (string= original + (with-temp-buffer (insert-file-contents b) + (buffer-string)))) + backups)))) + (delete-directory dir t) + (delete-directory bdir t)))) diff --git a/.ai/scripts/tests/test-wrap-org-table.el b/.ai/scripts/tests/test-wrap-org-table.el index 8d1ecb6..0b3b375 100644 --- a/.ai/scripts/tests/test-wrap-org-table.el +++ b/.ai/scripts/tests/test-wrap-org-table.el @@ -186,3 +186,45 @@ (should (string-match-p "Prose before\\." content)) (should (string-match-p "Prose after\\." content)))) (delete-file file)))) + +;;; --------------------------------------------------------------------------- +;;; block safety — pipe lines inside #+begin_/#+end_ blocks are never tables + +(defconst wot-test--block-content + "#+begin_example +| client |----->| server | +| box | | box | +#+end_example +" + "An example block whose ASCII-art lines start with pipes.") + +(defun wot-test--process-content (content budget) + "Write CONTENT to a temp file, run `wot-process-file' at BUDGET, return result." + (let ((file (make-temp-file "wot-test" nil ".org"))) + (unwind-protect + (progn + (with-temp-file file (insert content)) + (wot-process-file file budget) + (with-temp-buffer (insert-file-contents file) (buffer-string))) + (delete-file file)))) + +(ert-deftest wot-process-file-leaves-example-block-byte-identical () + (let ((content (concat "* Diagram\n\n" wot-test--block-content))) + (should (equal (wot-test--process-content content 120) content)))) + +(ert-deftest wot-process-file-reformats-table-but-not-block () + (let* ((content (concat "* Doc\n\n" wot-test--block-content "\n" + wot-test--wide-input)) + (result (wot-test--process-content content 40))) + (should (string-match-p (regexp-quote wot-test--block-content) result)) + (should (string-match-p (regexp-quote wot-test--wide-expected) result)))) + +(ert-deftest wot-process-file-skips-pipes-in-src-block () + (let ((content "* Pipeline\n\n#+begin_src sh\n| sort\n| uniq -c\n#+end_src\n")) + (should (equal (wot-test--process-content content 120) content)))) + +(ert-deftest wot-process-file-literal-inner-end-marker-stays-in-block () + "A literal #+end_src quoted inside an example block must not close it." + (let ((content (concat "* Doc\n\n#+begin_example\n#+begin_src sh\nx\n" + "#+end_src\n| art |----| art |\n#+end_example\n"))) + (should (equal (wot-test--process-content content 120) content)))) diff --git a/.ai/scripts/tests/test_apkg_to_orgdrill.py b/.ai/scripts/tests/test_apkg_to_orgdrill.py new file mode 100644 index 0000000..6a95ea4 --- /dev/null +++ b/.ai/scripts/tests/test_apkg_to_orgdrill.py @@ -0,0 +1,301 @@ +"""Tests for apkg-to-orgdrill.py — the inverse of flashcard-to-anki.py. + +The converter reads an Anki .apkg (a zip holding collection.anki2 / .anki21 +sqlite) and emits an org-drill .org in the house canonical shape. It is +stdlib-only (zipfile + sqlite3), so it imports directly — no genanki stub. + +The apkg schema these tests build by hand mirrors what genanki actually +writes, confirmed against a real apkg generated from flashcard-to-anki.py: + - col.decks : JSON {did: {"name": ...}}, always including id-1 "Default" + - col.models : JSON {mid: {"name": ..., "flds": [{"name": "Front"}, ...]}} + - notes.flds : fields joined by \x1f; tags space-padded (" tag ") + - cards : nid -> did (the Default deck carries no cards) + +The round-trip test closes the loop through flashcard-to-anki.py's own +parse(): original org -> forward parse tuples -> apkg fixture -> converter +-> recovered org -> forward parse -> assert the (front, back, tag) tuples +match. Only the apkg materialization is hand-built (the genanki boundary); +everything else is the real code on both sides. +""" +from __future__ import annotations + +import importlib.util +import json +import sqlite3 +import sys +import types +import zipfile +from pathlib import Path + +import pytest + +SCRIPTS = Path(__file__).resolve().parents[1] +CONVERTER = SCRIPTS / "apkg-to-orgdrill.py" +FORWARD = SCRIPTS / "flashcard-to-anki.py" + + +def _load(path: Path, name: str, stub_genanki: bool = False): + if stub_genanki: + sys.modules.setdefault("genanki", types.ModuleType("genanki")) + spec = importlib.util.spec_from_file_location(name, path) + assert spec and spec.loader + module = importlib.util.module_from_spec(spec) + # Register before exec: @dataclass resolves cls.__module__ via sys.modules + # (Python 3.14), which is None for an unregistered importlib module. + sys.modules[name] = module + spec.loader.exec_module(module) + return module + + +@pytest.fixture(scope="module") +def conv(): + return _load(CONVERTER, "apkg_to_orgdrill") + + +@pytest.fixture(scope="module") +def forward(): + return _load(FORWARD, "flashcard_to_anki", stub_genanki=True) + + +# --- fixture builder: write a genanki-shaped apkg by hand ------------------ + +def _make_apkg( + path: Path, + decks: dict[int, str], + models: dict[int, list[str]], + notes: list[tuple[int, int, list[str], str]], # (nid, mid, fields, tag) + cards: list[tuple[int, int]], # (nid, did) + *, + media: str = "{}", +) -> None: + """Materialize a minimal apkg matching genanki's collection.anki2 shape.""" + col_dir = path.parent / f"{path.stem}-build" + col_dir.mkdir(parents=True, exist_ok=True) + db = col_dir / "collection.anki2" + if db.exists(): + db.unlink() + con = sqlite3.connect(db) + con.execute("CREATE TABLE col (id INTEGER, decks TEXT, models TEXT)") + decks_json = {"1": {"name": "Default"}} + decks_json.update({str(did): {"name": name} for did, name in decks.items()}) + models_json = { + str(mid): {"name": f"{decks.get(list(decks)[0], 'M')} model", + "flds": [{"name": n, "ord": i} for i, n in enumerate(flds)]} + for mid, flds in models.items() + } + con.execute("INSERT INTO col (id, decks, models) VALUES (1, ?, ?)", + (json.dumps(decks_json), json.dumps(models_json))) + con.execute("CREATE TABLE notes (id INTEGER, mid INTEGER, flds TEXT, tags TEXT)") + for nid, mid, fields, tag in notes: + con.execute("INSERT INTO notes (id, mid, flds, tags) VALUES (?, ?, ?, ?)", + (nid, mid, "\x1f".join(fields), f" {tag} " if tag else " ")) + con.execute("CREATE TABLE cards (id INTEGER, nid INTEGER, did INTEGER)") + for i, (nid, did) in enumerate(cards): + con.execute("INSERT INTO cards (id, nid, did) VALUES (?, ?, ?)", (1000 + i, nid, did)) + con.commit() + con.close() + with zipfile.ZipFile(path, "w") as z: + z.write(db, "collection.anki2") + z.writestr("media", media) + + +# --- html_to_org_body ------------------------------------------------------ + +def test_html_to_org_splits_br_into_lines(conv): + assert conv.html_to_org_body("one<br>two<br>three") == ["one", "two", "three"] + + +def test_html_to_org_handles_br_variants(conv): + assert conv.html_to_org_body("a<br/>b<br />c<BR>d") == ["a", "b", "c", "d"] + + +def test_html_to_org_unescapes_entities_amp_last(conv): + # Inverts escape_html (which escapes & first): < > & -> < > &. + assert conv.html_to_org_body("x <tag> & y") == ["x <tag> & y"] + + +def test_html_to_org_preserves_a_literal_escaped_entity(conv): + # Forward-escaping the literal "<" yields "&lt;"; the inverse must + # recover "<", not "<". + assert conv.html_to_org_body("&lt;") == ["<"] + + +def test_html_to_org_strips_answer_hr(conv): + assert conv.html_to_org_body('front<hr id="answer">back') == ["front", "back"] + + +def test_html_to_org_empty_back_is_empty(conv): + assert conv.html_to_org_body("") == [] + + +# --- read_apkg ------------------------------------------------------------- + +def test_read_apkg_single_deck_recovers_front_back_tag_deck(conv, tmp_path): + apkg = tmp_path / "d.apkg" + _make_apkg( + apkg, + decks={20: "My Deck"}, + models={9: ["Front", "Back"]}, + notes=[(100, 9, ["Q1?", "A1.<br>line2"], "sec-one")], + cards=[(100, 20)], + ) + recovered = conv.read_apkg(apkg) + assert len(recovered) == 1 + note = recovered[0] + assert note.deck == "My Deck" + assert note.front == "Q1?" + assert note.back_html == "A1.<br>line2" + assert note.tag == "sec-one" + + +def test_read_apkg_multiple_decks_grouped(conv, tmp_path): + apkg = tmp_path / "multi.apkg" + _make_apkg( + apkg, + decks={20: "Deck A", 21: "Deck B"}, + models={9: ["Front", "Back"]}, + notes=[(100, 9, ["QA?", "AA"], "ta"), (101, 9, ["QB?", "AB"], "tb")], + cards=[(100, 20), (101, 21)], + ) + decks = {n.deck for n in conv.read_apkg(apkg)} + assert decks == {"Deck A", "Deck B"} + + +def test_read_apkg_skips_default_deck_without_cards(conv, tmp_path): + apkg = tmp_path / "def.apkg" + _make_apkg( + apkg, + decks={20: "Real Deck"}, + models={9: ["Front", "Back"]}, + notes=[(100, 9, ["Q?", "A"], "t")], + cards=[(100, 20)], + ) + assert {n.deck for n in conv.read_apkg(apkg)} == {"Real Deck"} + + +def test_read_apkg_warns_and_skips_non_basic_model(conv, tmp_path, capsys): + apkg = tmp_path / "cloze.apkg" + _make_apkg( + apkg, + decks={20: "Cloze Deck"}, + models={9: ["Text", "Extra"]}, # not Front/Back + notes=[(100, 9, ["some {{c1::text}}", "extra"], "t")], + cards=[(100, 20)], + ) + recovered = conv.read_apkg(apkg) + assert recovered == [] + assert "skip" in capsys.readouterr().err.lower() + + +def test_read_apkg_reads_anki21_collection_name(conv, tmp_path): + # A .anki21 collection filename must be read the same as .anki2. + apkg = tmp_path / "new.apkg" + _make_apkg( + apkg, + decks={20: "Deck"}, + models={9: ["Front", "Back"]}, + notes=[(100, 9, ["Q?", "A"], "t")], + cards=[(100, 20)], + ) + # Rewrite the zip renaming the collection member to .anki21. + with zipfile.ZipFile(apkg) as z: + data = z.read("collection.anki2") + media = z.read("media") + with zipfile.ZipFile(apkg, "w") as z: + z.writestr("collection.anki21", data) + z.writestr("media", media) + assert conv.read_apkg(apkg)[0].front == "Q?" + + +def test_read_apkg_flags_media_reference(conv, tmp_path, capsys): + apkg = tmp_path / "media.apkg" + _make_apkg( + apkg, + decks={20: "Deck"}, + models={9: ["Front", "Back"]}, + notes=[(100, 9, ["Q?", 'see <img src="x.png">'], "t")], + cards=[(100, 20)], + ) + conv.read_apkg(apkg) + assert "media" in capsys.readouterr().err.lower() + + +# --- notes_to_org ---------------------------------------------------------- + +def test_notes_to_org_emits_canonical_shape(conv): + Note = conv.Note + notes = [ + Note(deck="My Deck", front="Q1?", back_html="A1.", tag="alpha"), + Note(deck="My Deck", front="Q2?", back_html="A2.", tag="alpha"), + ] + ids = iter(["id-1", "id-2"]) + org = conv.notes_to_org(notes, "My Deck", new_id=lambda: next(ids)) + assert "#+TITLE: My Deck" in org + assert "* alpha" in org + assert "** Q1? :drill:" in org + assert ":ID: id-1" in org + assert ":ID: id-2" in org + assert org.count("* alpha") == 1 # both cards share one section + + +def test_notes_to_org_distinct_tags_get_distinct_sections(conv): + Note = conv.Note + notes = [ + Note(deck="D", front="Qa?", back_html="a", tag="alpha"), + Note(deck="D", front="Qb?", back_html="b", tag="beta"), + ] + org = conv.notes_to_org(notes, "D", new_id=lambda: "x") + assert "* alpha" in org and "* beta" in org + + +# --- round-trip through the real forward parse() --------------------------- + +def test_round_trip_matches_forward_parse_tuples(conv, forward, tmp_path): + original = ( + "#+TITLE: RT Deck\n" + "\n" + "* First Section\n" + "** What is 2+2? :drill:\n" + ":PROPERTIES:\n:ID: aaaa\n:END:\n" + "Four.\n" + "Second line with <angle> & amp.\n" + "\n" + "* Second Section\n" + "** Capital of France? :drill:\n" + "Paris.\n" + ) + tuples = forward.parse(original) # [(front, back_html, anki_tags), ...] + assert len(tuples) == 2 + + apkg = tmp_path / "rt.apkg" + _make_apkg( + apkg, + decks={20: "RT Deck"}, + models={9: ["Front", "Back"]}, + # anki_tags is a list; the apkg tags field is space-joined. + notes=[(100 + i, 9, [f, b], " ".join(tags)) + for i, (f, b, tags) in enumerate(tuples)], + cards=[(100 + i, 20) for i in range(len(tuples))], + ) + + by_deck = conv.convert(apkg) + assert set(by_deck) == {"RT Deck"} + recovered_tuples = forward.parse(by_deck["RT Deck"]) + assert recovered_tuples == tuples + + +# --- errors ---------------------------------------------------------------- + +def test_read_apkg_missing_collection_errors(conv, tmp_path): + bad = tmp_path / "bad.apkg" + with zipfile.ZipFile(bad, "w") as z: + z.writestr("media", "{}") + with pytest.raises(Exception): + conv.read_apkg(bad) + + +def test_read_apkg_not_a_zip_errors(conv, tmp_path): + notzip = tmp_path / "plain.apkg" + notzip.write_text("not a zip") + with pytest.raises(Exception): + conv.read_apkg(notzip) diff --git a/.ai/scripts/tests/test_cj_remove_block.py b/.ai/scripts/tests/test_cj_remove_block.py index 2c8dade..3cdee46 100644 --- a/.ai/scripts/tests/test_cj_remove_block.py +++ b/.ai/scripts/tests/test_cj_remove_block.py @@ -14,6 +14,34 @@ import pytest SCRIPT = Path(__file__).parent.parent / "cj-remove-block.py" +@pytest.fixture(autouse=True) +def isolated_tmpdir(tmp_path, monkeypatch): + """Give every test in this module a private TMPDIR. + + The script backs up to the system temp dir under a name derived from the + edited file's BASENAME. The real todo.org shares that basename, so any test + operating on a fixture named todo.org writes something indistinguishable + from a production backup — and an earlier version of this file globbed the + shared /tmp and unlinked every match, so a routine `make test` destroyed + Craig's real backups (found in review, 2026-07-24). + + Isolating at module scope rather than per-test is deliberate: the same bug + was fixed once in the elisp sibling and left here, so relying on each new + test to remember is exactly how it recurred. Autouse makes it structural. + """ + d = tmp_path / "_tmpdir" + d.mkdir() + # TMPDIR covers subprocess invocations of the script. + monkeypatch.setenv("TMPDIR", str(d)) + # tempfile.gettempdir() caches its answer on first call, so a test that + # loads the module in-process would keep writing to the real /tmp no matter + # what TMPDIR says. Override the cache too — this is the gap that made the + # env-var-only version still leak one backup per suite run. + import tempfile as _tempfile + monkeypatch.setattr(_tempfile, "tempdir", str(d)) + return d + + @pytest.fixture def run_remove(tmp_path): """Write content to a temp org file, run cj-remove-block, return new contents.""" @@ -155,3 +183,142 @@ class TestCjRemoveBlockSafety: err, post_content = run_remove_expecting_failure(original, start=4, end=2) assert err.returncode != 0 assert post_content == original + + +class TestMultiBlockRangeRefused: + """The validation exists to catch a drifted range, but it only checked the + first and last lines of that range. A span from one block's opening fence to + a LATER block's closing fence passed, and the removal silently deleted every + line between — real prose, headings, whole tasks — with a zero exit. Drift is + the skill's normal operating mode (respond-to-cj-comments edits the file as it + processes, and a file under cj review usually holds several blocks), so this + is the exact scenario the check was written for. Reproduced 2026-07-24.""" + + TWO_BLOCKS = ( + "* Alpha\n" + "#+begin_src cj:\n" + "note A\n" + "#+end_src\n" + "KEEP THIS LINE\n" + "* Beta\n" + "#+begin_src cj:\n" + "note B\n" + "#+end_src\n" + ) + + def test_range_spanning_two_blocks_is_refused(self, run_remove_expecting_failure): + # Lines 2..9: block one's opener through block two's closer. + err, content = run_remove_expecting_failure(self.TWO_BLOCKS, 2, 9) + assert err.returncode == 1 + assert "KEEP THIS LINE" in content, "content between the blocks was destroyed" + assert "* Beta" in content, "a heading between the blocks was destroyed" + + def test_refusal_names_the_reason(self, run_remove_expecting_failure): + err, _ = run_remove_expecting_failure(self.TWO_BLOCKS, 2, 9) + assert "more than one" in err.stderr.decode().lower() + + def test_a_correct_single_block_range_still_removes(self, run_remove): + # The fix must not over-tighten: the legitimate range still works. + out = run_remove(self.TWO_BLOCKS, 2, 4) + assert "note A" not in out + assert "KEEP THIS LINE" in out + assert "note B" in out, "the second block must be untouched" + + def test_a_nested_end_src_inside_the_range_is_refused(self, run_remove_expecting_failure): + # Any #+end_src before the final line means the range covers >1 block. + content = ( + "#+begin_src cj:\n" + "a\n" + "#+end_src\n" + "middle\n" + "#+begin_src cj:\n" + "b\n" + "#+end_src\n" + ) + err, after = run_remove_expecting_failure(content, 1, 7) + assert err.returncode == 1 + assert "middle" in after + + +class TestSafeMutation: + """The script rewrites Craig's org files (todo.org, notes.org). It wrote with + a bare write_text, which truncates the target on open, and took no backup — + so a mid-write failure left the file truncated with no copy to recover from. + lint-org.el, the other tool that mutates these files, backs up to a temp dir + first. Match that, and make the write atomic. + + Every test here redirects TMPDIR to a private directory. The backup name + derives from the file's basename, and the real todo.org shares it, so a test + globbing the shared temp dir cannot tell its own artifact from a genuine + backup — and an earlier version of this class globbed /tmp and unlinked every + match, so a routine `make test` destroyed real backups (found in review, + 2026-07-24). Never glob or delete across the shared temp dir.""" + + ONE_BLOCK = "* T\n#+begin_src cj:\nnote\n#+end_src\nkeep\n" + + def test_a_backup_is_written_before_mutating(self, tmp_path): + import subprocess, glob, os + bdir = tmp_path / "bk" + bdir.mkdir() + f = tmp_path / "todo.org" + f.write_text(self.ONE_BLOCK) + subprocess.run( + ["python3", str(SCRIPT), "--file", str(f), "--start", "2", "--end", "4"], + check=True, capture_output=True, + env={**os.environ, "TMPDIR": str(bdir)}, + ) + backups = glob.glob(str(bdir / "todo.org.before-cj-remove.*")) + assert backups, "no backup was written before mutating the org file" + assert "note" in Path(max(backups)).read_text() + + def test_no_partial_file_when_the_write_fails(self, tmp_path, monkeypatch): + import importlib.util + spec = importlib.util.spec_from_file_location("crb", SCRIPT) + mod = importlib.util.module_from_spec(spec) + spec.loader.exec_module(mod) + bdir = tmp_path / "bk" + bdir.mkdir() + monkeypatch.setenv("TMPDIR", str(bdir)) + f = tmp_path / "todo.org" + f.write_text(self.ONE_BLOCK) + def boom(*a, **k): + raise OSError("disk full") + monkeypatch.setattr(mod.os, "replace", boom) + with pytest.raises(OSError): + mod.remove_range(f, 2, 4) + # The original survives intact — no truncation, no partial. + assert f.read_text() == self.ONE_BLOCK + + +class TestBackupNeverOverwrites: + """Same defect class as todo-cleanup's, and more reachable here: the + respond-to-cj-comments skill removes several annotations in quick + succession, so a second-resolution stamp collides and the later backup + overwrote the earlier one with already-mutated content.""" + + TWO_BLOCKS = ( + "* A\n#+begin_src cj:\nfirst\n#+end_src\n" + "* B\n#+begin_src cj:\nsecond\n#+end_src\n" + ) + + def test_consecutive_removals_each_keep_a_backup(self, tmp_path, monkeypatch): + import subprocess, glob + bdir = tmp_path / "bk" + bdir.mkdir() + monkeypatch.setenv("TMPDIR", str(bdir)) + f = tmp_path / "todo.org" + f.write_text(self.TWO_BLOCKS) + original = f.read_text() + # Remove the second block, then the first — back to back, same second. + subprocess.run(["python3", str(SCRIPT), "--file", str(f), + "--start", "6", "--end", "8"], + check=True, capture_output=True, + env={**__import__("os").environ, "TMPDIR": str(bdir)}) + subprocess.run(["python3", str(SCRIPT), "--file", str(f), + "--start", "2", "--end", "4"], + check=True, capture_output=True, + env={**__import__("os").environ, "TMPDIR": str(bdir)}) + backups = glob.glob(str(bdir / "todo.org.before-cj-remove.*")) + assert len(backups) == 2, f"expected 2 backups, got {len(backups)}" + contents = [Path(b).read_text() for b in backups] + assert original in contents, "no backup holds the true original" diff --git a/.ai/scripts/tests/test_cross_agent_discover.py b/.ai/scripts/tests/test_cross_agent_discover.py deleted file mode 100644 index f0d2bb7..0000000 --- a/.ai/scripts/tests/test_cross_agent_discover.py +++ /dev/null @@ -1,204 +0,0 @@ -"""Tests for cross-agent-discover (TDD: tests written before implementation).""" - -from __future__ import annotations - -import json -import os -import subprocess -import textwrap -from pathlib import Path - -import pytest - -SCRIPT = Path(__file__).resolve().parent.parent / "cross-agent-comms" / "cross-agent-discover" - - -def _run(args: list[str], env: dict | None = None) -> subprocess.CompletedProcess: - return subprocess.run([str(SCRIPT), *args], capture_output=True, text=True, env=env) - - -@pytest.fixture -def fake_home(tmp_path, monkeypatch): - home = tmp_path / "home" - home.mkdir() - monkeypatch.setenv("HOME", str(home)) - return home - - -def _make_project(home: Path, name: str) -> Path: - proj = home / "projects" / name - (proj / ".ai").mkdir(parents=True) - return proj - - -def _write_peers_toml(home: Path, content: str) -> Path: - cfg = home / ".config" / "cross-agent-comms" - cfg.mkdir(parents=True, exist_ok=True) - peers = cfg / "peers.toml" - peers.write_text(content) - return peers - - -def test_discover_help(fake_home): - result = _run(["--help"], env={**os.environ, "HOME": str(fake_home)}) - assert result.returncode == 0 - assert "discover" in result.stdout.lower() or "enumerate" in result.stdout.lower() - - -def test_discover_local_only_no_projects(fake_home): - """Empty home → reports zero local projects, zero peers.""" - result = _run(["--no-cache"], env={**os.environ, "HOME": str(fake_home)}) - assert result.returncode == 0 - # No crash; mentions local somehow. - assert "local" in result.stdout.lower() or "0 project" in result.stdout.lower() - - -def test_discover_lists_local_projects(fake_home): - _make_project(fake_home, "homelab") - _make_project(fake_home, "career") - _make_project(fake_home, "claude-templates") - result = _run(["--no-cache"], env={**os.environ, "HOME": str(fake_home)}) - assert result.returncode == 0 - assert "homelab" in result.stdout - assert "career" in result.stdout - assert "claude-templates" in result.stdout - - -def test_discover_excludes_dirs_without_ai_subdir(fake_home): - """Directories under ~/projects/ that lack .ai/ are NOT projects.""" - _make_project(fake_home, "real-project") - (fake_home / "projects" / "not-a-project").mkdir(parents=True) - result = _run(["--no-cache"], env={**os.environ, "HOME": str(fake_home)}) - assert result.returncode == 0 - assert "real-project" in result.stdout - assert "not-a-project" not in result.stdout - - -def test_discover_no_peers_toml_just_local(fake_home): - _make_project(fake_home, "homelab") - result = _run(["--no-cache"], env={**os.environ, "HOME": str(fake_home)}) - assert result.returncode == 0 - # No peers section since no toml. - assert "homelab" in result.stdout - - -def test_discover_lists_peers_from_toml(fake_home): - _write_peers_toml(fake_home, textwrap.dedent("""\ - [peers.velox] - host = "velox" - ssh_user = "cjennings" - - [peers.bastion] - host = "bastion.local" - ssh_user = "cjennings" - """)) - _make_project(fake_home, "homelab") - result = _run(["--no-cache"], env={**os.environ, "HOME": str(fake_home)}) - assert result.returncode == 0 - assert "velox" in result.stdout - assert "bastion" in result.stdout - - -def test_discover_malformed_peers_toml_errors_clearly(fake_home): - _write_peers_toml(fake_home, "not valid toml at all = = =") - result = _run(["--no-cache"], env={**os.environ, "HOME": str(fake_home)}) - assert result.returncode != 0 - assert "peers.toml" in result.stderr or "TOML" in result.stderr or "parse" in result.stderr.lower() - - -def test_discover_json_output_schema(fake_home): - _make_project(fake_home, "homelab") - _make_project(fake_home, "career") - _write_peers_toml(fake_home, textwrap.dedent("""\ - [peers.velox] - host = "velox" - """)) - result = _run(["--json", "--no-cache"], env={**os.environ, "HOME": str(fake_home)}) - assert result.returncode == 0 - payload = json.loads(result.stdout) - assert "local" in payload - assert "peers" in payload - assert isinstance(payload["local"], list) - assert isinstance(payload["peers"], list) - assert "homelab" in payload["local"] - assert "career" in payload["local"] - velox = next((p for p in payload["peers"] if p["name"] == "velox"), None) - assert velox is not None - # Reachability is a key — value depends on actual SSH state. - assert "reachable" in velox - - -def test_discover_peer_scope(fake_home): - _write_peers_toml(fake_home, textwrap.dedent("""\ - [peers.velox] - host = "velox" - - [peers.bastion] - host = "bastion.local" - """)) - result = _run(["--peer", "velox", "--no-cache", "--json"], env={**os.environ, "HOME": str(fake_home)}) - assert result.returncode == 0 - payload = json.loads(result.stdout) - peer_names = [p["name"] for p in payload["peers"]] - assert "velox" in peer_names - assert "bastion" not in peer_names - - -def test_discover_unreachable_peer_marked(fake_home): - """A peer with a definitely-unreachable host gets reachable=False.""" - _write_peers_toml(fake_home, textwrap.dedent("""\ - [peers.bogus] - host = "definitely-not-a-real-host.invalid" - ssh_user = "nobody" - """)) - result = _run(["--no-cache", "--json"], env={**os.environ, "HOME": str(fake_home)}, ) - assert result.returncode == 0 - payload = json.loads(result.stdout) - bogus = next((p for p in payload["peers"] if p["name"] == "bogus"), None) - assert bogus is not None - assert bogus["reachable"] is False - - -def test_discover_cache_hit_within_window(fake_home): - """Second invocation within 5 min reads cache (skip the SSH probe).""" - _make_project(fake_home, "homelab") - # First call populates cache. - result1 = _run(["--json"], env={**os.environ, "HOME": str(fake_home)}) - assert result1.returncode == 0 - cache = fake_home / ".cache" / "cross-agent-comms" / "discovery.json" - assert cache.exists() - # Tamper with the cache to a marker only the cache path can produce. - payload = json.loads(cache.read_text()) - payload["_test_marker"] = True - cache.write_text(json.dumps(payload)) - # Second call (no --no-cache) should return the tampered payload. - result2 = _run(["--json"], env={**os.environ, "HOME": str(fake_home)}) - assert result2.returncode == 0 - payload2 = json.loads(result2.stdout) - assert payload2.get("_test_marker") is True - - -def test_discover_no_cache_flag_bypasses(fake_home): - """--no-cache ignores even a fresh cache.""" - _make_project(fake_home, "homelab") - cache_dir = fake_home / ".cache" / "cross-agent-comms" - cache_dir.mkdir(parents=True) - cache_dir.joinpath("discovery.json").write_text(json.dumps({ - "_test_marker": True, "local": [], "peers": [] - })) - result = _run(["--no-cache", "--json"], env={**os.environ, "HOME": str(fake_home)}) - assert result.returncode == 0 - payload = json.loads(result.stdout) - # Cache marker should NOT appear in fresh result. - assert payload.get("_test_marker") is None or payload.get("_test_marker") is False - assert "homelab" in payload["local"] - - -def test_discover_halt_shows_banner(fake_home): - halt = fake_home / ".config" / "cross-agent-comms" / "HALT" - halt.parent.mkdir(parents=True) - halt.write_text("halted") - _make_project(fake_home, "homelab") - result = _run(["--no-cache"], env={**os.environ, "HOME": str(fake_home)}) - assert result.returncode == 0 # discover continues to print under HALT - assert "HALT" in result.stdout diff --git a/.ai/scripts/tests/test_cross_agent_halt.py b/.ai/scripts/tests/test_cross_agent_halt.py deleted file mode 100644 index f8bf0b3..0000000 --- a/.ai/scripts/tests/test_cross_agent_halt.py +++ /dev/null @@ -1,204 +0,0 @@ -"""Tests for cross-agent-halt and cross-agent-resume (TDD).""" - -from __future__ import annotations - -import os -import subprocess -import textwrap -from pathlib import Path - -import pytest - -HALT_SCRIPT = Path(__file__).resolve().parent.parent / "cross-agent-comms" / "cross-agent-halt" -RESUME_SCRIPT = Path(__file__).resolve().parent.parent / "cross-agent-comms" / "cross-agent-resume" - - -def _run(script: Path, args: list[str], env: dict | None = None) -> subprocess.CompletedProcess: - return subprocess.run([str(script), *args], capture_output=True, text=True, env=env) - - -@pytest.fixture -def isolated_env(tmp_path, monkeypatch): - """Isolated HOME + a fake systemctl that records calls without acting.""" - fake_home = tmp_path / "home" - fake_home.mkdir() - fake_bin = tmp_path / "bin" - fake_bin.mkdir() - # Fake systemctl: no-op, exit 0. - fake_systemctl = fake_bin / "systemctl" - fake_systemctl.write_text("#!/usr/bin/env bash\nexit 0\n") - fake_systemctl.chmod(0o755) - # Fake ssh: succeed only for known-good host. - fake_ssh = fake_bin / "ssh" - fake_ssh.write_text(textwrap.dedent("""\ - #!/usr/bin/env bash - # Find the destination arg (skip flags). - target="" - for arg in "$@"; do - case "$arg" in - -*|*=*) ;; - *@*|localhost|*.local|*.invalid) target="$arg"; break ;; - *) target="$arg"; break ;; - esac - done - case "$target" in - *invalid*|*unreachable*) exit 255 ;; - *) exit 0 ;; - esac - """)) - fake_ssh.chmod(0o755) - - monkeypatch.setenv("HOME", str(fake_home)) - # Prepend our fake bin so systemctl + ssh are intercepted, but keep real /bin etc. - monkeypatch.setenv("PATH", f"{fake_bin}:{os.environ.get('PATH', '')}") - return fake_home - - -# ---- cross-agent-halt ---- - - -def test_halt_help(isolated_env): - result = _run(HALT_SCRIPT, ["--help"], env={**os.environ, "HOME": str(isolated_env), - "PATH": os.environ["PATH"]}) - assert result.returncode == 0 - assert "halt" in result.stdout.lower() - - -def test_halt_creates_halt_file(isolated_env): - halt_file = isolated_env / ".config" / "cross-agent-comms" / "HALT" - assert not halt_file.exists() - result = _run(HALT_SCRIPT, [], env={**os.environ, "HOME": str(isolated_env), - "PATH": os.environ["PATH"]}) - assert result.returncode == 0 - assert halt_file.exists() - - -def test_halt_with_reason_writes_body(isolated_env): - result = _run(HALT_SCRIPT, ["pausing for incident review"], - env={**os.environ, "HOME": str(isolated_env), "PATH": os.environ["PATH"]}) - assert result.returncode == 0 - halt_file = isolated_env / ".config" / "cross-agent-comms" / "HALT" - assert halt_file.exists() - assert "pausing for incident review" in halt_file.read_text() - - -def test_halt_idempotent(isolated_env): - """Running halt twice doesn't error.""" - halt_file = isolated_env / ".config" / "cross-agent-comms" / "HALT" - r1 = _run(HALT_SCRIPT, [], env={**os.environ, "HOME": str(isolated_env), "PATH": os.environ["PATH"]}) - assert r1.returncode == 0 - assert halt_file.exists() - r2 = _run(HALT_SCRIPT, [], env={**os.environ, "HOME": str(isolated_env), "PATH": os.environ["PATH"]}) - assert r2.returncode == 0 - assert halt_file.exists() - - -def test_halt_does_not_pkill(isolated_env): - """Per design: halt does NOT call pkill. Verify by checking no pkill process gets launched.""" - # Replace pkill in PATH with something that fails loudly so we'd see if halt invoked it. - fake_bin = isolated_env.parent / "bin" - pkill = fake_bin / "pkill" - pkill.write_text("#!/usr/bin/env bash\necho 'PKILL CALLED' >&2\nexit 99\n") - pkill.chmod(0o755) - result = _run(HALT_SCRIPT, [], env={**os.environ, "HOME": str(isolated_env), "PATH": os.environ["PATH"]}) - assert result.returncode == 0 - assert "PKILL CALLED" not in result.stderr - - -def test_halt_tailnet_reports_per_peer(isolated_env): - """--tailnet iterates peers.toml and reports per-peer status.""" - cfg = isolated_env / ".config" / "cross-agent-comms" - cfg.mkdir(parents=True) - (cfg / "peers.toml").write_text(textwrap.dedent("""\ - [peers.velox] - host = "velox" - ssh_user = "cjennings" - - [peers.bogus] - host = "definitely-unreachable.invalid" - ssh_user = "cjennings" - """)) - result = _run(HALT_SCRIPT, ["--tailnet"], - env={**os.environ, "HOME": str(isolated_env), "PATH": os.environ["PATH"]}) - # Partial halt → exit 1. - assert result.returncode == 1 - assert "velox" in result.stdout - assert "bogus" in result.stdout - # ✓ marker for velox, ✗ for bogus. - assert "✓" in result.stdout - assert "✗" in result.stdout - assert "PARTIAL" in result.stdout or "partial" in result.stdout.lower() - - -def test_halt_tailnet_all_reachable_exits_zero(isolated_env): - cfg = isolated_env / ".config" / "cross-agent-comms" - cfg.mkdir(parents=True) - (cfg / "peers.toml").write_text(textwrap.dedent("""\ - [peers.velox] - host = "velox" - ssh_user = "cjennings" - """)) - result = _run(HALT_SCRIPT, ["--tailnet"], - env={**os.environ, "HOME": str(isolated_env), "PATH": os.environ["PATH"]}) - assert result.returncode == 0 - assert "velox" in result.stdout - - -# ---- cross-agent-resume ---- - - -def test_resume_help(isolated_env): - result = _run(RESUME_SCRIPT, ["--help"], - env={**os.environ, "HOME": str(isolated_env), "PATH": os.environ["PATH"]}) - assert result.returncode == 0 - assert "resume" in result.stdout.lower() - - -def test_resume_removes_halt_file(isolated_env): - halt_file = isolated_env / ".config" / "cross-agent-comms" / "HALT" - halt_file.parent.mkdir(parents=True) - halt_file.write_text("halted") - assert halt_file.exists() - result = _run(RESUME_SCRIPT, [], - env={**os.environ, "HOME": str(isolated_env), "PATH": os.environ["PATH"]}) - assert result.returncode == 0 - assert not halt_file.exists() - - -def test_resume_when_no_halt_active_succeeds(isolated_env): - """No HALT to clear is not an error.""" - result = _run(RESUME_SCRIPT, [], - env={**os.environ, "HOME": str(isolated_env), "PATH": os.environ["PATH"]}) - assert result.returncode == 0 - - -def test_resume_prints_per_session_instructions(isolated_env): - """Resume must surface that polling does NOT auto-resume.""" - halt_file = isolated_env / ".config" / "cross-agent-comms" / "HALT" - halt_file.parent.mkdir(parents=True) - halt_file.write_text("halted") - result = _run(RESUME_SCRIPT, [], - env={**os.environ, "HOME": str(isolated_env), "PATH": os.environ["PATH"]}) - assert result.returncode == 0 - out = result.stdout.lower() - assert "polling" in out - assert "auto" in out or "explicit" in out or "session" in out - - -def test_resume_tailnet_partial_failure_exit_1(isolated_env): - cfg = isolated_env / ".config" / "cross-agent-comms" - cfg.mkdir(parents=True) - (cfg / "peers.toml").write_text(textwrap.dedent("""\ - [peers.velox] - host = "velox" - - [peers.bogus] - host = "unreachable-host.invalid" - """)) - halt_file = cfg / "HALT" - halt_file.write_text("halted") - result = _run(RESUME_SCRIPT, ["--tailnet"], - env={**os.environ, "HOME": str(isolated_env), "PATH": os.environ["PATH"]}) - assert result.returncode == 1 - assert "velox" in result.stdout - assert "bogus" in result.stdout diff --git a/.ai/scripts/tests/test_cross_agent_recv.py b/.ai/scripts/tests/test_cross_agent_recv.py deleted file mode 100644 index 27c53a5..0000000 --- a/.ai/scripts/tests/test_cross_agent_recv.py +++ /dev/null @@ -1,176 +0,0 @@ -"""Tests for cross-agent-recv.""" - -from __future__ import annotations - -import json -import os -import subprocess -from pathlib import Path - -import pytest - -SCRIPT = Path(__file__).resolve().parent.parent / "cross-agent-comms" / "cross-agent-recv" - - -def _make_message(path: Path, *, conv_id: str = "test-conv", seq: int = 1, msg_type: str = "request", - proto_version: str = "5", title: str = "Test", requires_tools: str | None = None, - body: str = "Body.\n") -> Path: - fm_lines = [ - f"#+TITLE: {title}", - f"#+CONVERSATION_ID: {conv_id}", - f"#+MESSAGE_TYPE: {msg_type}", - f"#+SEQUENCE: {seq}", - "#+TIMESTAMP: 2026-04-27T05:00:00-05:00", - f"#+PROTOCOL_VERSION: {proto_version}", - ] - if requires_tools: - fm_lines.append(f"#+REQUIRES_TOOLS: {requires_tools}") - path.write_text("\n".join(fm_lines) + "\n\n" + body) - return path - - -def _run(args: list[str], env: dict | None = None) -> subprocess.CompletedProcess: - return subprocess.run([str(SCRIPT), *args], capture_output=True, text=True, env=env) - - -@pytest.fixture -def isolated_env(tmp_path, monkeypatch): - fake_home = tmp_path / "home" - fake_home.mkdir() - monkeypatch.setenv("HOME", str(fake_home)) - return fake_home - - -def test_recv_help(isolated_env): - result = _run(["--help"], env={**os.environ, "HOME": str(isolated_env)}) - assert result.returncode == 0 - assert "Receive and decide" in result.stdout - - -def test_recv_missing_file_rejects(isolated_env, tmp_path): - result = _run([str(tmp_path / "nope.org")], env={**os.environ, "HOME": str(isolated_env)}) - assert result.returncode == 3 # reject - - -def test_recv_malformed_frontmatter_rejects(isolated_env, tmp_path): - bad = tmp_path / "bad.org" - bad.write_text("not org-mode at all\n") - result = _run([str(bad), "--no-verify"], env={**os.environ, "HOME": str(isolated_env)}) - assert result.returncode == 3 - assert "decision: reject" in result.stdout - - -def test_recv_missing_required_field_rejects(isolated_env, tmp_path): - msg = tmp_path / "msg.org" - # Missing PROTOCOL_VERSION among others. - msg.write_text("#+TITLE: x\n#+CONVERSATION_ID: c\n\nBody.\n") - result = _run([str(msg), "--no-verify"], env={**os.environ, "HOME": str(isolated_env)}) - assert result.returncode == 3 - assert "missing required" in result.stdout - - -def test_recv_protocol_version_mismatch_query(isolated_env, tmp_path): - msg = _make_message(tmp_path / "msg.org", proto_version="4") - result = _run([str(msg), "--no-verify"], env={**os.environ, "HOME": str(isolated_env)}) - assert result.returncode == 2 # query - assert "PROTOCOL_VERSION mismatch" in result.stdout - - -def test_recv_invalid_message_type_rejects(isolated_env, tmp_path): - msg = _make_message(tmp_path / "msg.org", msg_type="banana") - result = _run([str(msg), "--no-verify"], env={**os.environ, "HOME": str(isolated_env)}) - assert result.returncode == 3 - assert "invalid MESSAGE_TYPE" in result.stdout - - -def test_recv_missing_signature_rejects(isolated_env, tmp_path): - """When verify is on, a missing .asc sibling rejects.""" - msg = _make_message(tmp_path / "msg.org") - # No .asc sidecar. - result = _run([str(msg)], env={**os.environ, "HOME": str(isolated_env)}) - assert result.returncode == 3 - assert "signature file missing" in result.stdout - - -def test_recv_valid_processes(isolated_env, tmp_path): - """A valid message with --no-verify and no dedup match → process.""" - msg = _make_message(tmp_path / "msg.org") - result = _run([str(msg), "--no-verify"], env={**os.environ, "HOME": str(isolated_env)}) - assert result.returncode == 0 # process - assert "decision: process" in result.stdout - assert "sha256:" in result.stdout - - -def test_recv_dedup_against_identical_existing(isolated_env, tmp_path): - """Same content + same SEQUENCE in same dir → dedup.""" - inbox = tmp_path / "inbox" - inbox.mkdir() - first = _make_message(inbox / "20260427T100000Z-from-x-c.org", conv_id="c", seq=5) - # Second message with same content — name differs (canonical-style would have different timestamp). - second = _make_message(inbox / "20260427T100100Z-from-x-c.org", conv_id="c", seq=5) - # Bodies must be byte-identical for hash equality. - second.write_bytes(first.read_bytes()) - result = _run([str(second), "--no-verify"], env={**os.environ, "HOME": str(isolated_env)}) - assert result.returncode == 1 # dedup - assert "decision: dedup" in result.stdout - - -def test_recv_collision_with_different_content_processes(isolated_env, tmp_path): - """Same SEQUENCE + same CONVERSATION_ID but different content → process both.""" - inbox = tmp_path / "inbox" - inbox.mkdir() - _make_message(inbox / "20260427T100000Z-from-x-c.org", conv_id="c", seq=5, body="First body.\n") - second = _make_message(inbox / "20260427T100100Z-from-x-c.org", conv_id="c", seq=5, body="Different body.\n") - result = _run([str(second), "--no-verify"], env={**os.environ, "HOME": str(isolated_env)}) - assert result.returncode == 0 # process - assert "decision: process" in result.stdout - - -def test_recv_requires_tools_missing_query(isolated_env, tmp_path): - """REQUIRES_TOOLS naming a definitely-missing binary → query.""" - msg = _make_message(tmp_path / "msg.org", requires_tools="definitely-not-installed-xyzzy-9000") - result = _run([str(msg), "--no-verify"], env={**os.environ, "HOME": str(isolated_env)}) - assert result.returncode == 2 # query - assert "required tools unavailable" in result.stdout - - -def test_recv_requires_tools_present_processes(isolated_env, tmp_path): - """REQUIRES_TOOLS naming a real binary → process.""" - msg = _make_message(tmp_path / "msg.org", requires_tools="ls,cat") - result = _run([str(msg), "--no-verify"], env={**os.environ, "HOME": str(isolated_env)}) - assert result.returncode == 0 - assert "decision: process" in result.stdout - - -def test_recv_json_output(isolated_env, tmp_path): - msg = _make_message(tmp_path / "msg.org") - result = _run([str(msg), "--no-verify", "--json"], env={**os.environ, "HOME": str(isolated_env)}) - assert result.returncode == 0 - payload = json.loads(result.stdout) - assert payload["decision"] == "process" - assert payload["message_type"] == "request" - assert payload["conversation_id"] == "test-conv" - - -def test_recv_halt_blocks(isolated_env, tmp_path): - halt = isolated_env / ".config" / "cross-agent-comms" / "HALT" - halt.parent.mkdir(parents=True) - halt.write_text("halted\n") - msg = _make_message(tmp_path / "msg.org") - result = _run([str(msg), "--no-verify"], env={**os.environ, "HOME": str(isolated_env)}) - assert result.returncode == 5 - assert "halt active" in result.stderr.lower() - - -def test_recv_halt_leaves_message_in_place(isolated_env, tmp_path): - """Per spec: under HALT, recv must NOT move/dedup/reject — leave file in place.""" - halt = isolated_env / ".config" / "cross-agent-comms" / "HALT" - halt.parent.mkdir(parents=True) - halt.write_text("halted\n") - msg = _make_message(tmp_path / "msg.org") - pre_content = msg.read_text() - result = _run([str(msg), "--no-verify"], env={**os.environ, "HOME": str(isolated_env)}) - assert result.returncode == 5 - # File still exists with same content. - assert msg.exists() - assert msg.read_text() == pre_content diff --git a/.ai/scripts/tests/test_cross_agent_send.py b/.ai/scripts/tests/test_cross_agent_send.py deleted file mode 100644 index f716e95..0000000 --- a/.ai/scripts/tests/test_cross_agent_send.py +++ /dev/null @@ -1,210 +0,0 @@ -"""Tests for cross-agent-send. - -Subprocess-based: treat the script as a black-box CLI and assert on its -exit codes, stdout, and the files it produces. -""" - -from __future__ import annotations - -import os -import subprocess -import textwrap -from pathlib import Path - -import pytest - -SCRIPT = Path(__file__).resolve().parent.parent / "cross-agent-comms" / "cross-agent-send" - - -def _make_message(tmp_path: Path, conv_id: str = "test-conv", seq: int = 1, msg_type: str = "request", - proto_version: str = "5") -> Path: - msg = tmp_path / "msg.org" - msg.write_text(textwrap.dedent(f"""\ - #+TITLE: Test message - #+CONVERSATION_ID: {conv_id} - #+MESSAGE_TYPE: {msg_type} - #+SEQUENCE: {seq} - #+TIMESTAMP: 2026-04-27T05:00:00-05:00 - #+PROTOCOL_VERSION: {proto_version} - - Body. - """)) - return msg - - -def _run(args: list[str], env: dict | None = None, cwd: Path | None = None) -> subprocess.CompletedProcess: - return subprocess.run( - [str(SCRIPT), *args], - capture_output=True, - text=True, - env=env, - cwd=cwd, - ) - - -@pytest.fixture -def isolated_env(tmp_path, monkeypatch): - """Redirect HOME so peers.toml, HALT, marker files are scoped to the test.""" - fake_home = tmp_path / "home" - fake_home.mkdir() - monkeypatch.setenv("HOME", str(fake_home)) - # Pre-create projects/ so derive_sender_project has somewhere to look. - (fake_home / "projects" / "homelab").mkdir(parents=True) - return fake_home - - -def test_send_help(isolated_env): - """--help works without side effects.""" - result = _run(["--help"], env={**os.environ, "HOME": str(isolated_env)}) - assert result.returncode == 0 - assert "Send a cross-agent message" in result.stdout - - -def test_send_missing_message_file(isolated_env): - """Nonexistent message file returns general error.""" - import socket - machine = socket.gethostname().split(".")[0] - result = _run( - [f"{machine}.homelab", str(isolated_env / "nonexistent.org")], - env={**os.environ, "HOME": str(isolated_env)}, - ) - assert result.returncode == 1 - assert "not found" in result.stderr.lower() - - -def test_send_invalid_destination_format(isolated_env, tmp_path): - """Destination without . returns dest-not-found exit code.""" - msg = _make_message(tmp_path) - result = _run( - ["bogus", str(msg)], - env={**os.environ, "HOME": str(isolated_env)}, - ) - assert result.returncode == 2 - assert "<machine>.<project>" in result.stderr or "destination" in result.stderr.lower() - - -def test_send_dest_not_in_peers(isolated_env, tmp_path): - """Cross-machine destination with no peers.toml entry exits 2.""" - msg = _make_message(tmp_path) - result = _run( - ["unknownmachine.homelab", str(msg)], - env={**os.environ, "HOME": str(isolated_env)}, - ) - assert result.returncode == 2 - assert "not found in peers" in result.stderr - - -def test_send_frontmatter_missing_required(isolated_env, tmp_path): - """Message missing required fields exits 4.""" - bad = tmp_path / "bad.org" - bad.write_text("#+TITLE: nope\n\nBody.\n") - import socket - machine = socket.gethostname().split(".")[0] - result = _run( - [f"{machine}.homelab", str(bad)], - env={**os.environ, "HOME": str(isolated_env)}, - ) - assert result.returncode == 4 - assert "missing required fields" in result.stderr - - -def test_send_invalid_message_type(isolated_env, tmp_path): - """Unknown MESSAGE_TYPE exits 4.""" - msg = _make_message(tmp_path, msg_type="frobnicate") - import socket - machine = socket.gethostname().split(".")[0] - result = _run( - [f"{machine}.homelab", str(msg)], - env={**os.environ, "HOME": str(isolated_env)}, - ) - assert result.returncode == 4 - assert "MESSAGE_TYPE" in result.stderr - - -def test_send_halt_blocks(isolated_env, tmp_path): - """When HALT exists, send refuses with exit 5.""" - halt = isolated_env / ".config" / "cross-agent-comms" / "HALT" - halt.parent.mkdir(parents=True) - halt.write_text("test halt\n") - msg = _make_message(tmp_path) - import socket - machine = socket.gethostname().split(".")[0] - result = _run( - [f"{machine}.homelab", str(msg)], - env={**os.environ, "HOME": str(isolated_env)}, - ) - assert result.returncode == 5 - assert "halt active" in result.stderr.lower() - - -def test_send_same_machine_no_sign_delivers(isolated_env, tmp_path): - """Same-machine delivery with --no-sign produces a canonically named file.""" - msg = _make_message(tmp_path, conv_id="my-conv") - import socket - machine = socket.gethostname().split(".")[0] - # Sender is derived from CWD walking up to ~/projects/<name>/ - cwd = isolated_env / "projects" / "homelab" - result = _run( - [f"{machine}.homelab", str(msg), "--no-sign"], - env={**os.environ, "HOME": str(isolated_env)}, - cwd=cwd, - ) - assert result.returncode == 0, f"stderr={result.stderr}" - inbox = isolated_env / "projects" / "homelab" / "inbox" / "from-agents" - files = list(inbox.glob("*-from-homelab-my-conv.org")) - assert len(files) == 1 - # No sig file with --no-sign. - assert not list(inbox.glob("*.asc")) - # Canonical filename pattern. - assert files[0].name.startswith("2026") and files[0].name.endswith("-from-homelab-my-conv.org") - - -def test_send_same_machine_signed_writes_asc(isolated_env, tmp_path): - """Signed delivery writes both .org and .asc.""" - msg = _make_message(tmp_path, conv_id="signed-conv") - import socket - machine = socket.gethostname().split(".")[0] - cwd = isolated_env / "projects" / "homelab" - # Use the real GPG keyring (not isolating GPG — Craig's existing keys are fine for tests). - real_env = {**os.environ, "HOME": str(isolated_env), "GNUPGHOME": str(Path.home() / ".gnupg")} - result = _run( - [f"{machine}.homelab", str(msg)], - env=real_env, - cwd=cwd, - ) - if result.returncode != 0: - pytest.skip(f"GPG signing unavailable in this environment: {result.stderr}") - inbox = isolated_env / "projects" / "homelab" / "inbox" / "from-agents" - org_files = list(inbox.glob("*-from-homelab-signed-conv.org")) - asc_files = list(inbox.glob("*-from-homelab-signed-conv.org.asc")) - assert len(org_files) == 1 - assert len(asc_files) == 1 - - -def test_send_filename_ignores_input_basename(isolated_env, tmp_path): - """User's input filename is ignored; canonical filename is generated.""" - weird = tmp_path / "weird-user-name.org" - weird.write_text(textwrap.dedent("""\ - #+TITLE: Title - #+CONVERSATION_ID: ignored-input - #+MESSAGE_TYPE: request - #+SEQUENCE: 1 - #+TIMESTAMP: 2026-04-27T05:00:00-05:00 - #+PROTOCOL_VERSION: 5 - - Body. - """)) - import socket - machine = socket.gethostname().split(".")[0] - cwd = isolated_env / "projects" / "homelab" - result = _run( - [f"{machine}.homelab", str(weird), "--no-sign"], - env={**os.environ, "HOME": str(isolated_env)}, - cwd=cwd, - ) - assert result.returncode == 0 - inbox = isolated_env / "projects" / "homelab" / "inbox" / "from-agents" - # No file named after the user's input. - assert not (inbox / "weird-user-name.org").exists() - # Canonical naming used. - assert list(inbox.glob("*-from-homelab-ignored-input.org")) diff --git a/.ai/scripts/tests/test_cross_agent_status.py b/.ai/scripts/tests/test_cross_agent_status.py deleted file mode 100644 index bb5b8ba..0000000 --- a/.ai/scripts/tests/test_cross_agent_status.py +++ /dev/null @@ -1,165 +0,0 @@ -"""Tests for cross-agent-status (TDD: tests written before implementation).""" - -from __future__ import annotations - -import json -import os -import subprocess -import textwrap -from pathlib import Path - -import pytest - -SCRIPT = Path(__file__).resolve().parent.parent / "cross-agent-comms" / "cross-agent-status" - - -def _make_msg(path: Path, *, conv_id: str, seq: int, msg_type: str = "request", - proto_version: str = "5", timestamp: str = "2026-04-27T05:00:00-05:00") -> Path: - path.parent.mkdir(parents=True, exist_ok=True) - path.write_text(textwrap.dedent(f"""\ - #+TITLE: T - #+CONVERSATION_ID: {conv_id} - #+MESSAGE_TYPE: {msg_type} - #+SEQUENCE: {seq} - #+TIMESTAMP: {timestamp} - #+PROTOCOL_VERSION: {proto_version} - - Body. - """)) - return path - - -def _run(args: list[str], env: dict | None = None) -> subprocess.CompletedProcess: - return subprocess.run([str(SCRIPT), *args], capture_output=True, text=True, env=env) - - -@pytest.fixture -def fake_projects(tmp_path, monkeypatch): - """Create a fake ~/projects/<name>/inbox/from-agents/ tree under tmp_path.""" - home = tmp_path / "home" - home.mkdir() - monkeypatch.setenv("HOME", str(home)) - return home - - -def test_status_help(fake_projects): - result = _run(["--help"], env={**os.environ, "HOME": str(fake_projects)}) - assert result.returncode == 0 - assert "snapshot" in result.stdout.lower() or "pending" in result.stdout.lower() - - -def test_status_no_projects_clean_output(fake_projects): - result = _run([], env={**os.environ, "HOME": str(fake_projects)}) - assert result.returncode == 0 - # Empty machine prints either header-only table or "no projects" — accept either. - # No crash, no pending claims. - assert "pending" in result.stdout.lower() or result.stdout.strip() == "" - - -def test_status_one_pending_shows_up(fake_projects): - inbox = fake_projects / "projects" / "homelab" / "inbox" / "from-agents" - _make_msg(inbox / "20260427T100000Z-from-career-fixup.org", conv_id="fixup", seq=1) - result = _run([], env={**os.environ, "HOME": str(fake_projects)}) - assert result.returncode == 0 - assert "homelab" in result.stdout - assert "1" in result.stdout # pending count - assert "20260427T100000Z-from-career-fixup.org" in result.stdout - - -def test_status_released_conversation_zero_pending(fake_projects): - """A conversation with a release message in it counts as 0 pending.""" - inbox = fake_projects / "projects" / "homelab" / "inbox" / "from-agents" - _make_msg(inbox / "20260427T100000Z-from-career-done.org", conv_id="done", seq=1) - _make_msg(inbox / "20260427T100100Z-from-homelab-done.org", conv_id="done", seq=2, msg_type="release") - result = _run([], env={**os.environ, "HOME": str(fake_projects)}) - assert result.returncode == 0 - # Check the homelab row shows 0 pending. - lines = [ln for ln in result.stdout.splitlines() if "homelab" in ln] - # At least one homelab line should show 0 pending or "—". - assert any("0" in ln or "—" in ln for ln in lines) - - -def test_status_partial_release(fake_projects): - """Conversation with release + a later message → that later message counts as pending.""" - inbox = fake_projects / "projects" / "homelab" / "inbox" / "from-agents" - _make_msg(inbox / "20260427T100000Z-from-career-x.org", conv_id="x", seq=1, - timestamp="2026-04-27T05:00:00-05:00") - _make_msg(inbox / "20260427T100100Z-from-homelab-x.org", conv_id="x", seq=2, msg_type="release", - timestamp="2026-04-27T05:01:00-05:00") - # New message AFTER release: starts a fresh thread that's pending. - _make_msg(inbox / "20260427T200000Z-from-career-x.org", conv_id="x", seq=3, - timestamp="2026-04-27T15:00:00-05:00") - result = _run([], env={**os.environ, "HOME": str(fake_projects)}) - assert result.returncode == 0 - homelab_line = next(ln for ln in result.stdout.splitlines() if "homelab" in ln) - assert "1" in homelab_line # the post-release message is pending - - -def test_status_multiple_projects(fake_projects): - inbox_a = fake_projects / "projects" / "homelab" / "inbox" / "from-agents" - inbox_b = fake_projects / "projects" / "career" / "inbox" / "from-agents" - _make_msg(inbox_a / "20260427T100000Z-from-x-a.org", conv_id="a", seq=1) - _make_msg(inbox_b / "20260427T100100Z-from-x-b.org", conv_id="b", seq=1) - _make_msg(inbox_b / "20260427T100200Z-from-x-c.org", conv_id="c", seq=1) - result = _run([], env={**os.environ, "HOME": str(fake_projects)}) - assert result.returncode == 0 - # career has 2 pending, homelab has 1. - career_line = next(ln for ln in result.stdout.splitlines() if "career" in ln) - homelab_line = next(ln for ln in result.stdout.splitlines() if "homelab" in ln) - assert "2" in career_line - assert "1" in homelab_line - - -def test_status_json_output(fake_projects): - inbox = fake_projects / "projects" / "homelab" / "inbox" / "from-agents" - _make_msg(inbox / "20260427T100000Z-from-career-test.org", conv_id="test", seq=1) - result = _run(["--json"], env={**os.environ, "HOME": str(fake_projects)}) - assert result.returncode == 0 - payload = json.loads(result.stdout) - assert "projects" in payload - assert isinstance(payload["projects"], list) - homelab = next((p for p in payload["projects"] if p["name"] == "homelab"), None) - assert homelab is not None - assert homelab["pending_count"] == 1 - - -def test_status_sort_pending_first(fake_projects): - """Projects with pending messages sort before projects with 0.""" - (fake_projects / "projects" / "alpha" / "inbox" / "from-agents").mkdir(parents=True) - inbox_zeta = fake_projects / "projects" / "zeta" / "inbox" / "from-agents" - _make_msg(inbox_zeta / "20260427T100000Z-from-x-z.org", conv_id="z", seq=1) - result = _run([], env={**os.environ, "HOME": str(fake_projects)}) - assert result.returncode == 0 - lines = result.stdout.splitlines() - zeta_idx = next(i for i, ln in enumerate(lines) if "zeta" in ln) - alpha_idx = next(i for i, ln in enumerate(lines) if "alpha" in ln) - assert zeta_idx < alpha_idx, "pending project should sort before zero-pending project" - - -def test_status_halt_shows_banner(fake_projects): - halt = fake_projects / ".config" / "cross-agent-comms" / "HALT" - halt.parent.mkdir(parents=True) - halt.write_text("halted for test") - inbox = fake_projects / "projects" / "homelab" / "inbox" / "from-agents" - _make_msg(inbox / "20260427T100000Z-from-x-x.org", conv_id="x", seq=1) - result = _run([], env={**os.environ, "HOME": str(fake_projects)}) - assert result.returncode == 0 # status continues to print under HALT - assert "HALT" in result.stdout - # Banner should mention the reason. - assert "halted for test" in result.stdout - - -def test_status_projects_glob_override(fake_projects): - inbox = fake_projects / "projects" / "homelab" / "inbox" / "from-agents" - _make_msg(inbox / "20260427T100000Z-from-x-a.org", conv_id="a", seq=1) - other_inbox = fake_projects / "projects" / "career" / "inbox" / "from-agents" - _make_msg(other_inbox / "20260427T100100Z-from-x-b.org", conv_id="b", seq=1) - # Glob limits to homelab only. - result = _run( - ["--projects-glob", str(fake_projects / "projects" / "homelab" / "inbox" / "from-agents") + "/"], - env={**os.environ, "HOME": str(fake_projects)}, - ) - assert result.returncode == 0 - assert "homelab" in result.stdout - # career not in scope. - assert "career" not in result.stdout diff --git a/.ai/scripts/tests/test_cross_agent_watch.py b/.ai/scripts/tests/test_cross_agent_watch.py deleted file mode 100644 index 417cc19..0000000 --- a/.ai/scripts/tests/test_cross_agent_watch.py +++ /dev/null @@ -1,155 +0,0 @@ -"""Tests for cross-agent-watch. - -Black-box: spawn the script, drop files into a watched dir, read the log. -Tests use --no-notify to avoid firing real desktop notifications. -""" - -from __future__ import annotations - -import os -import subprocess -import time -from pathlib import Path - -import pytest - -SCRIPT = Path(__file__).resolve().parent.parent / "cross-agent-comms" / "cross-agent-watch" - - -def _spawn(watched_dir: Path, log_path: Path, env: dict) -> subprocess.Popen: - return subprocess.Popen( - [ - str(SCRIPT), - "--projects-glob", str(watched_dir) + "/", - "--log", str(log_path), - "--no-notify", - "--quiet", - ], - stdout=subprocess.DEVNULL, - stderr=subprocess.PIPE, - env=env, - ) - - -def _wait_for_log_lines(log_path: Path, expected: int, timeout: float = 5.0) -> list[str]: - deadline = time.time() + timeout - while time.time() < deadline: - if log_path.exists(): - lines = [ln for ln in log_path.read_text().splitlines() if ln] - if len(lines) >= expected: - return lines - time.sleep(0.1) - if log_path.exists(): - return [ln for ln in log_path.read_text().splitlines() if ln] - return [] - - -@pytest.fixture -def isolated_env(tmp_path, monkeypatch): - fake_home = tmp_path / "home" - fake_home.mkdir() - monkeypatch.setenv("HOME", str(fake_home)) - return fake_home - - -def test_watch_help(isolated_env): - result = subprocess.run( - [str(SCRIPT), "--help"], - capture_output=True, text=True, - env={**os.environ, "HOME": str(isolated_env)}, - ) - assert result.returncode == 0 - assert "Usage:" in result.stdout - - -def test_watch_empty_glob_exits_nonzero(isolated_env): - """Glob resolving to zero dirs should exit non-zero with a clear message.""" - result = subprocess.run( - [str(SCRIPT), "--projects-glob", "/nonexistent/path/*/foo/", "--no-notify", "--quiet"], - capture_output=True, text=True, - env={**os.environ, "HOME": str(isolated_env)}, - timeout=3, - ) - assert result.returncode != 0 - assert "0 directories" in result.stderr - - -def test_watch_logs_org_file_create(isolated_env, tmp_path): - watched = tmp_path / "watched" - watched.mkdir() - log = tmp_path / "watch.log" - proc = _spawn(watched, log, {**os.environ, "HOME": str(isolated_env)}) - try: - # Give inotifywait a moment to attach. - time.sleep(0.3) - (watched / "test-msg.org").write_text("hello") - lines = _wait_for_log_lines(log, expected=1, timeout=3.0) - assert len(lines) >= 1 - assert "test-msg.org" in lines[-1] - finally: - proc.terminate() - proc.wait(timeout=2) - - -def test_watch_filters_tmp_files(isolated_env, tmp_path): - """Files starting with .tmp. must NOT trigger log entries.""" - watched = tmp_path / "watched" - watched.mkdir() - log = tmp_path / "watch.log" - proc = _spawn(watched, log, {**os.environ, "HOME": str(isolated_env)}) - try: - time.sleep(0.3) - (watched / ".tmp.staging-file.org").write_text("hello") - # Wait briefly to confirm nothing logs. - time.sleep(0.5) - if log.exists(): - content = log.read_text() - assert ".tmp.staging-file" not in content - # Then drop a real file to confirm watcher is alive. - (watched / "real.org").write_text("real") - lines = _wait_for_log_lines(log, expected=1, timeout=3.0) - assert any("real.org" in ln for ln in lines) - finally: - proc.terminate() - proc.wait(timeout=2) - - -def test_watch_filters_asc_sidecars(isolated_env, tmp_path): - """Only .org events fire; .asc sidecars are silent.""" - watched = tmp_path / "watched" - watched.mkdir() - log = tmp_path / "watch.log" - proc = _spawn(watched, log, {**os.environ, "HOME": str(isolated_env)}) - try: - time.sleep(0.3) - (watched / "msg.org.asc").write_text("sig") - time.sleep(0.5) - if log.exists(): - assert "msg.org.asc" not in log.read_text() - # .org event still works. - (watched / "msg.org").write_text("body") - lines = _wait_for_log_lines(log, expected=1, timeout=3.0) - assert any(ln.endswith("msg.org") for ln in lines) - finally: - proc.terminate() - proc.wait(timeout=2) - - -def test_watch_halt_suppresses_but_logs(isolated_env, tmp_path): - """When HALT is set, watcher logs the event with (suppressed by HALT) marker.""" - halt = isolated_env / ".config" / "cross-agent-comms" / "HALT" - halt.parent.mkdir(parents=True) - halt.write_text("halted") - watched = tmp_path / "watched" - watched.mkdir() - log = tmp_path / "watch.log" - proc = _spawn(watched, log, {**os.environ, "HOME": str(isolated_env)}) - try: - time.sleep(0.3) - (watched / "halted-event.org").write_text("body") - lines = _wait_for_log_lines(log, expected=1, timeout=3.0) - assert len(lines) >= 1 - assert "suppressed by HALT" in lines[-1] - finally: - proc.terminate() - proc.wait(timeout=2) diff --git a/.ai/scripts/tests/test_flashcard_stats.py b/.ai/scripts/tests/test_flashcard_stats.py index 606f7c1..46deccc 100644 --- a/.ai/scripts/tests/test_flashcard_stats.py +++ b/.ai/scripts/tests/test_flashcard_stats.py @@ -217,6 +217,31 @@ def test_parse_cards_captures_body_without_drawer_planning_or_answer_header(stat assert c["body"] == "the real answer" +def test_parse_cards_counts_a_multitag_heading_as_a_card(stats): + """A card multi-tagged :fundamental:drill: still counts; the front is clean.""" + text = "* Sec\n** Q multi? :fundamental:drill:\nthe answer\n" + cards, _ = stats.parse_cards(text.splitlines()) + assert len(cards) == 1 + assert cards[0]["heading"] == "Q multi?" + assert cards[0]["body"] == "the answer" + + +def test_parse_cards_ignores_a_tagged_heading_without_drill(stats): + """A tagged heading missing :drill: is not a drill card.""" + text = "* Sec\n** Just a note :note:\nbody\n" + cards, _ = stats.parse_cards(text.splitlines()) + assert cards == [] + + +def test_parse_cards_body_stops_at_next_multitag_card(stats): + """The body scan ends at the next L2 card even when it is multi-tagged.""" + text = "** Q1? :a:drill:\nbody1\n** Q2? :drill:\nbody2\n" + cards, _ = stats.parse_cards(text.splitlines()) + assert len(cards) == 2 + assert cards[0]["body"] == "body1" + assert cards[1]["body"] == "body2" + + def test_find_duplicate_fronts_matches_normalized_headings(stats): cards = [ {"heading": "What is LEO?"}, diff --git a/.ai/scripts/tests/test_flashcard_to_anki.py b/.ai/scripts/tests/test_flashcard_to_anki.py index 058b0cd..fa38b64 100644 --- a/.ai/scripts/tests/test_flashcard_to_anki.py +++ b/.ai/scripts/tests/test_flashcard_to_anki.py @@ -34,14 +34,33 @@ def test_default_output_path_targets_phone_anki_dir(drill): assert result == Path.home() / "sync" / "phone" / "anki" / "health-drill.apkg" -def test_default_deck_name_is_raw_basename(drill): - """Deck name is the input basename with case preserved; #+TITLE is ignored.""" - assert drill.default_deck_name(Path("/x/deepsat.org")) == "deepsat" +def test_default_deck_name_uses_org_title(drill): + """The #+TITLE drives the Anki deck name, not the filename slug.""" + org = "#+TITLE: Refutations\n* Section\n** Q? :drill:\na\n" + assert drill.default_deck_name(Path("/x/refutation-drill.org"), org) == "Refutations" -def test_default_deck_name_keeps_hyphens(drill): - """A hyphenated basename is kept verbatim rather than title-cased.""" - assert drill.default_deck_name(Path("/x/health-drill.org")) == "health-drill" +def test_default_deck_name_title_is_trimmed(drill): + """Surrounding whitespace on the #+TITLE value is stripped.""" + org = "#+TITLE: DeepSat Flashcards \n" + assert drill.default_deck_name(Path("/x/deepsat.org"), org) == "DeepSat Flashcards" + + +def test_default_deck_name_title_match_is_case_insensitive(drill): + """A lowercase #+title: keyword is still recognized.""" + org = "#+title: Health Flashcards\n" + assert drill.default_deck_name(Path("/x/health-drill.org"), org) == "Health Flashcards" + + +def test_default_deck_name_falls_back_to_basename_without_title(drill): + """No #+TITLE line falls back to the input basename, case preserved.""" + org = "* Section\n** Q? :drill:\na\n" + assert drill.default_deck_name(Path("/x/deepsat.org"), org) == "deepsat" + + +def test_default_deck_name_blank_title_falls_back_to_basename(drill): + """An empty #+TITLE value is ignored in favour of the basename.""" + assert drill.default_deck_name(Path("/x/health-drill.org"), "#+TITLE: \n") == "health-drill" # --- section_to_tag (pure) --- @@ -139,17 +158,18 @@ Geostationary Earth Orbit. def test_parse_returns_front_back_tag_per_card(drill): cards = drill.parse(SECTIONED) assert len(cards) == 2 - assert cards[0] == ("What is LEO?", "Low Earth Orbit.", "orbital-regimes") + # The section becomes the sole Anki tag (as a one-element list). + assert cards[0] == ("What is LEO?", "Low Earth Orbit.", ["orbital-regimes"]) assert cards[1][0] == "What is GEO?" def test_parse_card_without_a_section_gets_the_drill_tag(drill): - assert drill.parse("** Lone card? :drill:\nbody\n") == [("Lone card?", "body", "drill")] + assert drill.parse("** Lone card? :drill:\nbody\n") == [("Lone card?", "body", ["drill"])] def test_parse_strips_properties_drawer_from_back(drill): text = "** Q? :drill:\n:PROPERTIES:\n:ID: abc\n:END:\nThe answer.\n" - assert drill.parse(text) == [("Q?", "The answer.", "drill")] + assert drill.parse(text) == [("Q?", "The answer.", ["drill"])] def test_parse_trims_leading_and_trailing_blank_body_lines(drill): @@ -159,7 +179,59 @@ def test_parse_trims_leading_and_trailing_blank_body_lines(drill): def test_parse_card_with_only_a_drawer_has_empty_back(drill): text = "** Q? :drill:\n:PROPERTIES:\n:ID: x\n:END:\n" - assert drill.parse(text) == [("Q?", "", "drill")] + assert drill.parse(text) == [("Q?", "", ["drill"])] + + +# --- multi-tag headings, --tag-filter, --guid-salt ------------------------- + +MULTITAG = """* Fundamentals +** What is LEO? :fundamental:drill: +Low Earth Orbit. +** What is GEO? :drill: +Geostationary Earth Orbit. +""" + + +def test_parse_multitag_heading_is_a_card_when_drill_is_present(drill): + """A heading with a second org tag still parses when drill is among them.""" + cards = drill.parse(MULTITAG) + assert len(cards) == 2 + assert cards[0][0] == "What is LEO?" + + +def test_parse_multitag_tags_ride_along_next_to_the_section_tag(drill): + """Non-drill org tags become Anki tags alongside the section tag.""" + cards = drill.parse(MULTITAG) + assert cards[0][2] == ["fundamentals", "fundamental"] # section slug + org tag + assert cards[1][2] == ["fundamentals"] # drill-only -> section only + + +def test_parse_heading_without_drill_tag_is_not_a_card(drill): + """A tagged heading missing :drill: is not a card (e.g. :note:).""" + assert drill.parse("* S\n** Just a note :note:\nbody\n") == [] + + +def test_parse_tag_filter_returns_only_cards_with_that_org_tag(drill): + """--tag-filter narrows to cards carrying the given org tag.""" + cards = drill.parse(MULTITAG, tag_filter="fundamental") + assert len(cards) == 1 + assert cards[0][0] == "What is LEO?" + + +def test_parse_body_bounded_by_any_l1_or_l2_heading(drill): + """A card body stops at the next L1/L2 heading, multi-tagged or not.""" + text = "** Q1? :a:drill:\nbody1\n** Q2? :drill:\nbody2\n" + cards = drill.parse(text) + assert cards[0][1] == "body1" + assert cards[1][1] == "body2" + + +def test_card_guid_salt_changes_the_guid(drill, monkeypatch): + """--guid-salt gives a subset deck its own GUID space; no salt is unchanged.""" + monkeypatch.setattr(drill.genanki, "guid_for", lambda *a: ":".join(a), raising=False) + assert drill.card_guid("front", None) == "front" + assert drill.card_guid("front", "fundamentals") == "fundamentals:front" + assert drill.card_guid("front", None) != drill.card_guid("front", "fundamentals") def test_parse_joins_multiline_body_with_br(drill): diff --git a/.ai/scripts/tests/test_inbox_send.py b/.ai/scripts/tests/test_inbox_send.py index a0094dc..9b0a8c6 100644 --- a/.ai/scripts/tests/test_inbox_send.py +++ b/.ai/scripts/tests/test_inbox_send.py @@ -97,6 +97,52 @@ class TestInboxSendDiscovery: result = run_script(["--list"], roots=[tmp_path / "does-not-exist"]) assert result.returncode == 0 + def test_inbox_send_list_displays_dot_stripped_name(self, project_root, run_script, tmp_path): + """Dotted project basenames display dot-stripped (.emacs.d → emacsd).""" + project_root(".emacs.d") + result = run_script(["--list"], roots=[tmp_path / "projects"]) + assert "emacsd" in result.stdout + + +class TestInboxSendDotAlias: + """A dotted project basename resolves both verbatim and dot-stripped.""" + + def test_resolves_by_dot_stripped_alias(self, project_root, run_script, tmp_path): + """'emacsd' delivers to the .emacs.d project.""" + project_root(".emacs.d") + cwd = project_root("source") + run_script( + ["emacsd", "--text", "hi"], + cwd=cwd, roots=[tmp_path / "projects"], + ) + files = list((tmp_path / "projects" / ".emacs.d" / "inbox").iterdir()) + assert len(files) == 1 + + def test_resolves_by_exact_dotted_name_still(self, project_root, run_script, tmp_path): + """Backward-compat: the verbatim '.emacs.d' target still resolves.""" + project_root(".emacs.d") + cwd = project_root("source") + run_script( + [".emacs.d", "--text", "hi"], + cwd=cwd, roots=[tmp_path / "projects"], + ) + files = list((tmp_path / "projects" / ".emacs.d" / "inbox").iterdir()) + assert len(files) == 1 + + def test_exact_match_wins_over_alias(self, project_root, run_script, tmp_path): + """An exact basename match is preferred over a dot-stripped collision.""" + project_root("emacsd") # exact + project_root(".emacs.d") # would also normalize to 'emacsd' + cwd = project_root("source") + run_script( + ["emacsd", "--text", "hi"], + cwd=cwd, roots=[tmp_path / "projects"], + ) + exact = list((tmp_path / "projects" / "emacsd" / "inbox").iterdir()) + dotted = list((tmp_path / "projects" / ".emacs.d" / "inbox").iterdir()) + assert len(exact) == 1 + assert dotted == [] + # ---------------------------------------------------------------------- # Slug derivation from text and from filenames @@ -355,3 +401,192 @@ class TestInboxSendErrors: assert result.returncode != 0 files = list((tmp_path / "projects" / "target" / "inbox").iterdir()) assert files == [] + + +# ---------------------------------------------------------------------- +# Filename collisions (two sends deriving the same name must not overwrite) +# ---------------------------------------------------------------------- + +def _load_module(): + import importlib.util + spec = importlib.util.spec_from_file_location("inbox_send", SCRIPT) + mod = importlib.util.module_from_spec(spec) + spec.loader.exec_module(mod) + return mod + + +class TestFilenameCollisions: + """Two sends in the same minute with the same leading phrase derived + identical filenames and the second silently overwrote the first + (a message was lost this way, 2026-07-02).""" + + def test_send_text_same_minute_same_phrase_keeps_both(self, tmp_path): + from datetime import datetime + mod = _load_module() + inbox = tmp_path / "inbox" + inbox.mkdir() + now = datetime(2026, 7, 2, 5, 42, 0) + prefix = "identical leading phrase long enough to fill the whole slug budget entirely" + first = mod.send_text(inbox, prefix + " tail one", "archsetup", None, now) + second = mod.send_text(inbox, prefix + " tail two", "archsetup", None, now) + assert first != second + assert first.exists() and second.exists() + assert first.name != second.name + assert "tail one" in first.read_text() + assert "tail two" in second.read_text() + + def test_send_text_collision_suffix_increments(self, tmp_path): + from datetime import datetime + mod = _load_module() + inbox = tmp_path / "inbox" + inbox.mkdir() + now = datetime(2026, 7, 2, 5, 42, 0) + paths = [mod.send_text(inbox, "same lead phrase differs later A", "src", "fixed-slug", now) + for _ in range(3)] + names = [p.name for p in paths] + assert names[0].endswith("fixed-slug.org") + assert names[1].endswith("fixed-slug-2.org") + assert names[2].endswith("fixed-slug-3.org") + + def test_send_file_collision_preserves_extension(self, tmp_path): + from datetime import datetime + mod = _load_module() + inbox = tmp_path / "inbox" + inbox.mkdir() + src = tmp_path / "note.org" + src.write_text("body one") + now = datetime(2026, 7, 2, 5, 42, 0) + first = mod.send_file(inbox, src, "src", None, now) + src.write_text("body two") + second = mod.send_file(inbox, src, "src", None, now) + assert second.name.endswith("note-2.org") + assert first.read_text() == "body one" + assert second.read_text() == "body two" + + def test_cli_two_rapid_sends_lose_nothing(self, project_root, run_script, tmp_path): + project_root("sender") + target = project_root("receiver") + roots = [tmp_path / "projects"] + prefix = "identical leading phrase long enough to fill the whole slug budget entirely" + run_script(["receiver", "--text", prefix + " message one"], + cwd=tmp_path / "projects" / "sender", roots=roots) + run_script(["receiver", "--text", prefix + " message two"], + cwd=tmp_path / "projects" / "sender", roots=roots) + files = list((target / "inbox").iterdir()) + assert len(files) == 2 + bodies = "".join(f.read_text() for f in files) + assert "message one" in bodies and "message two" in bodies + + +class TestAtomicWrite: + """A send wrote straight to the destination path in another project's + inbox/, and write_text truncates on open, so any mid-write failure left a + zero-byte .org there. inbox-status counts that phantom as a pending + handoff, blocking a turn in the receiving project over a file with no + content (2026-07-23). The write must be atomic: the inbox sees a complete + file or nothing.""" + + def test_send_text_writes_utf8(self, tmp_path): + from datetime import datetime + mod = _load_module() + inbox = tmp_path / "inbox" + inbox.mkdir() + now = datetime(2026, 7, 23, 4, 36, 0) + # An em dash and an accented char — both non-ASCII. + dest = mod.send_text(inbox, "accent café and dash — here", "src", None, now) + # Reading as utf-8 must round-trip; a locale-encoded write would raise + # under a C locale, and reading back proves the bytes are utf-8. + assert "—" in dest.read_text(encoding="utf-8") + + def test_send_text_no_partial_on_write_failure(self, tmp_path, monkeypatch): + from datetime import datetime + mod = _load_module() + inbox = tmp_path / "inbox" + inbox.mkdir() + now = datetime(2026, 7, 23, 4, 36, 0) + # Force the atomic finalize to fail after the temp file is written. + def boom(*a, **k): + raise OSError("disk full") + monkeypatch.setattr(mod.os, "replace", boom) + with pytest.raises(OSError): + mod.send_text(inbox, "a message that should never half-land", "src", None, now) + # No phantom, no leftover temp: the inbox is empty. + assert list(inbox.iterdir()) == [] + + def test_send_text_leaves_no_temp_on_success(self, tmp_path): + from datetime import datetime + mod = _load_module() + inbox = tmp_path / "inbox" + inbox.mkdir() + now = datetime(2026, 7, 23, 4, 36, 0) + dest = mod.send_text(inbox, "clean send", "src", None, now) + assert list(inbox.iterdir()) == [dest] + + def test_send_file_no_partial_on_write_failure(self, tmp_path, monkeypatch): + from datetime import datetime + mod = _load_module() + inbox = tmp_path / "inbox" + inbox.mkdir() + src = tmp_path / "note.org" + src.write_text("body") + now = datetime(2026, 7, 23, 4, 36, 0) + def boom(*a, **k): + raise OSError("disk full") + monkeypatch.setattr(mod.os, "replace", boom) + with pytest.raises(OSError): + mod.send_file(inbox, src, "src", None, now) + assert list(inbox.iterdir()) == [] + + def test_send_file_leaves_no_temp_on_success(self, tmp_path): + from datetime import datetime + mod = _load_module() + inbox = tmp_path / "inbox" + inbox.mkdir() + src = tmp_path / "note.org" + src.write_text("payload") + now = datetime(2026, 7, 23, 4, 36, 0) + dest = mod.send_file(inbox, src, "src", None, now) + assert list(inbox.iterdir()) == [dest] + assert dest.read_text() == "payload" + + +class TestSmallerDefects: + """Two low-severity defects found reading inbox-send during the 2026-07-23 + sweep: an unreadable source raised an uncaught traceback instead of the + clean error every other failure path produces, and a roots config naming + both a parent and one of its children listed the same project twice.""" + + def test_unreadable_source_gives_clean_error_not_traceback( + self, project_root, run_script, tmp_path + ): + project_root("sender") + project_root("receiver") + roots = [tmp_path / "projects"] + src = tmp_path / "secret.bin" + src.write_text("x") + src.chmod(0o000) + try: + result = run_script( + ["receiver", "--file", str(src)], + cwd=tmp_path / "projects" / "sender", + roots=roots, + expect_failure=True, + ) + finally: + src.chmod(0o644) + assert result.returncode == 1 + # The clean "inbox-send: <message>" shape, not a Python traceback. + assert result.stderr.startswith("inbox-send:") + assert "Traceback" not in result.stderr + + def test_discover_projects_dedupes_parent_and_child_root(self, tmp_path): + mod = _load_module() + # A project directory, reachable both as a child of its parent root and + # as a root in its own right. + parent = tmp_path / "projects" + proj = parent / "app" + (proj / ".ai").mkdir(parents=True) + (proj / "inbox").mkdir() + found = mod.discover_projects([parent, proj]) + resolved = [p.resolve() for p in found] + assert resolved.count(proj.resolve()) == 1 diff --git a/.ai/scripts/tests/test_route_recommend.py b/.ai/scripts/tests/test_route_recommend.py new file mode 100644 index 0000000..2ec900a --- /dev/null +++ b/.ai/scripts/tests/test_route_recommend.py @@ -0,0 +1,152 @@ +"""Tests for route_recommend.py — the wrap-up routing recommendation engine. + +The core is a pure function recommend(item, projects) -> (destination, confidence): +- strong: a project's name (or its dot-stripped form) appears literally in the item +- weak: a distinctive name token overlaps, but the full name doesn't +- none: no overlap; the item stays put (destination is None) + +A multi-way tie at the top tier downgrades to weak with a deterministic pick. +An empty project list yields none. + +The CLI wires this to inbox-send.py's discover_projects (sandboxed here via the +INBOX_SEND_ROOTS env var, the same hook inbox-send's own tests use). +""" + +import subprocess +import sys +from pathlib import Path + +SCRIPTS = Path(__file__).parent.parent +SCRIPT = SCRIPTS / "route_recommend.py" +sys.path.insert(0, str(SCRIPTS)) + +import route_recommend as rr # noqa: E402 + + +# --- pure function: the five spec'd cases ----------------------------------- + +def test_strong_match_named_literally(): + dest, conf = rr.recommend("fix the rulesets refactor command", ["rulesets", "home", "work"]) + assert (dest, conf) == ("rulesets", "strong") + + +def test_strong_match_via_dot_stripped_name(): + # ".emacs.d" addressed as "emacsd" in the item is still a literal hit. + dest, conf = rr.recommend("update the emacsd ai-term module", [".emacs.d", "rulesets"]) + assert (dest, conf) == (".emacs.d", "strong") + + +def test_strong_match_dotted_name_verbatim(): + dest, conf = rr.recommend("patch .emacs.d startup", [".emacs.d", "rulesets"]) + assert (dest, conf) == (".emacs.d", "strong") + + +def test_weak_match_topic_token_only(): + # "wttrin" is a token of "emacs-wttrin" but the full name isn't present. + dest, conf = rr.recommend("the wttrin weather bug", ["emacs-wttrin", "rulesets"]) + assert (dest, conf) == ("emacs-wttrin", "weak") + + +def test_no_match_stays_put(): + dest, conf = rr.recommend("calibrate the telescope mount", ["rulesets", "deepsat"]) + assert dest is None + assert conf == "none" + + +def test_two_project_strong_tie_downgrades_to_weak(): + # Both named literally → ambiguous → weak, deterministic tie-break (alphabetical). + dest, conf = rr.recommend("sync rulesets and home configs", ["rulesets", "home", "work"]) + assert conf == "weak" + assert dest == "home" # tie-break: most-overlap then alphabetical + + +def test_empty_project_list_is_none(): + assert rr.recommend("anything at all", []) == (None, "none") + + +# --- boundary / robustness -------------------------------------------------- + +def test_literal_name_requires_word_boundary(): + # "home" must not match inside "homeowner". + dest, conf = rr.recommend("the homeowner association meeting", ["home", "rulesets"]) + assert dest is None and conf == "none" + + +def test_path_mention_counts_as_literal(): + dest, conf = rr.recommend("edit ~/code/rulesets/Makefile", ["rulesets", "home"]) + assert (dest, conf) == ("rulesets", "strong") + + +def test_strong_beats_weak_when_both_present(): + # "rulesets" named literally (strong) outranks an emacs-wttrin token hit (weak). + dest, conf = rr.recommend("the wttrin fix belongs in rulesets", ["rulesets", "emacs-wttrin"]) + assert (dest, conf) == ("rulesets", "strong") + + +# --- CLI + discovery reuse (sandboxed roots) -------------------------------- + +def _run(args, roots, item): + import os + env = {"PATH": os.environ.get("PATH", ""), "HOME": os.environ.get("HOME", "/tmp"), + "INBOX_SEND_ROOTS": ":".join(str(r) for r in roots)} + return subprocess.run([sys.executable, str(SCRIPT), "--item", item, *args], + capture_output=True, text=True, env=env) + + +def _mk_project(tmp_path, name): + proj = tmp_path / "projects" / name + (proj / ".ai").mkdir(parents=True, exist_ok=True) + (proj / "inbox").mkdir(exist_ok=True) + return proj + + +def test_cli_discovers_and_recommends(tmp_path): + _mk_project(tmp_path, "foo") + _mk_project(tmp_path, "bar") + r = _run([], roots=[tmp_path / "projects"], item="fix the foo widget") + assert r.returncode == 0 + assert r.stdout.strip() == "foo\tstrong" + + +def test_cli_no_match_prints_none(tmp_path): + _mk_project(tmp_path, "foo") + r = _run([], roots=[tmp_path / "projects"], item="unrelated grocery list") + assert r.returncode == 0 + assert r.stdout.strip() == "none" + + +def test_cli_exclude_drops_current_project(tmp_path): + _mk_project(tmp_path, "foo") + _mk_project(tmp_path, "bar") + # Item names foo, but foo is excluded as the current project → no other match. + r = _run(["--exclude", "foo"], roots=[tmp_path / "projects"], item="fix the foo widget") + assert r.returncode == 0 + assert r.stdout.strip() == "none" + + +# ---------------------------------------------------------------------- +# Duplicate candidate names +# +# Projects are collapsed to bare basenames, so two projects sharing a basename +# across roots (~/code/notes and ~/projects/notes) appear twice in the candidate +# list. Both literal-match, recommend read len(strong) > 1 as an ambiguous tie, +# and a correct strong match was downgraded to weak. Latent when discovered +# 2026-07-24 (27 projects, 27 distinct basenames) but real. +# ---------------------------------------------------------------------- + +def test_duplicate_candidate_name_keeps_strong_confidence(): + assert rr.recommend("fix the notes thing", ["notes", "other"]) == ("notes", "strong") + # The same name twice must not read as a tie. + assert rr.recommend("fix the notes thing", ["notes", "notes", "other"]) == ("notes", "strong") + + +def test_genuine_ambiguity_still_downgrades(): + # Two DIFFERENT projects both matching is a real tie and stays weak — the + # dedupe must collapse identical names only, never real ambiguity. + dest, conf = rr.recommend("notes and other both", ["notes", "other"]) + assert conf == "weak" + + +def test_duplicates_do_not_change_the_chosen_destination(): + dest, _ = rr.recommend("fix the notes thing", ["notes", "notes"]) + assert dest == "notes" diff --git a/.ai/scripts/tests/test_upcoming_birthdays.py b/.ai/scripts/tests/test_upcoming_birthdays.py new file mode 100644 index 0000000..1e15183 --- /dev/null +++ b/.ai/scripts/tests/test_upcoming_birthdays.py @@ -0,0 +1,168 @@ +"""Tests for upcoming_birthdays.py — the daily-prep upcoming-birthdays block. + +Pure core: + parse_birthdays(text) -> [Birthday(name, month, day, year|None), ...] + upcoming(birthdays, today, window=30) -> [Upcoming(name, date, days_away, age|None), ...] + format_block(items, window, callout_days=7) -> str + +Birth year 1900 is the placeholder org-contacts uses when the real year is +unknown; those entries carry year=None and render date-only (no age). +""" + +import datetime as dt +import subprocess +import sys +from pathlib import Path + +SCRIPTS = Path(__file__).parent.parent +SCRIPT = SCRIPTS / "upcoming_birthdays.py" +sys.path.insert(0, str(SCRIPTS)) + +import upcoming_birthdays as ub # noqa: E402 + + +# --- parse_birthdays -------------------------------------------------------- + +def test_parse_reads_name_month_day_year(): + text = "** Jane Doe\n:PROPERTIES:\n:BIRTHDAY: 1970-08-05\n:END:\n" + bdays = ub.parse_birthdays(text) + assert bdays == [ub.Birthday("Jane Doe", 8, 5, 1970)] + + +def test_parse_placeholder_year_1900_becomes_none(): + text = "** John Smith\n:PROPERTIES:\n:BIRTHDAY: 1900-07-14\n:END:\n" + bdays = ub.parse_birthdays(text) + assert bdays == [ub.Birthday("John Smith", 7, 14, None)] + + +def test_parse_skips_contacts_without_birthday(): + text = ( + "** No Birthday\n:PROPERTIES:\n:PHONE: 555\n:END:\n" + "** Has Birthday\n:PROPERTIES:\n:BIRTHDAY: 1990-03-02\n:END:\n" + ) + bdays = ub.parse_birthdays(text) + assert [b.name for b in bdays] == ["Has Birthday"] + + +def test_parse_strips_heading_stars_and_tags(): + text = "*** Bob Jones :friend:\n:PROPERTIES:\n:BIRTHDAY: 1980-01-01\n:END:\n" + bdays = ub.parse_birthdays(text) + assert bdays[0].name == "Bob Jones" + + +def test_parse_ignores_malformed_birthday_lines(): + text = "** Bad Date\n:PROPERTIES:\n:BIRTHDAY: not-a-date\n:END:\n" + assert ub.parse_birthdays(text) == [] + + +# --- upcoming --------------------------------------------------------------- + +TODAY = dt.date(2026, 7, 18) + + +def test_upcoming_birthday_today_is_zero_days(): + bdays = [ub.Birthday("Today Person", 7, 18, 1990)] + got = ub.upcoming(bdays, TODAY) + assert got[0].days_away == 0 + assert got[0].date == dt.date(2026, 7, 18) + + +def test_upcoming_includes_within_window(): + bdays = [ub.Birthday("Soon", 7, 23, 1990)] + got = ub.upcoming(bdays, TODAY, window=30) + assert got[0].days_away == 5 + + +def test_upcoming_excludes_beyond_window(): + bdays = [ub.Birthday("Far", 9, 1, 1990)] # 45 days out + assert ub.upcoming(bdays, TODAY, window=30) == [] + + +def test_upcoming_boundary_day_30_included_day_31_excluded(): + on = [ub.Birthday("On", 8, 17, 1990)] # exactly 30 days + off = [ub.Birthday("Off", 8, 18, 1990)] # 31 days + assert ub.upcoming(on, TODAY, window=30)[0].days_away == 30 + assert ub.upcoming(off, TODAY, window=30) == [] + + +def test_upcoming_uses_next_year_when_this_years_passed(): + # today is 2026-07-18; a Jan 5 birthday recurs on 2027-01-05 + today = dt.date(2026, 12, 27) + bdays = [ub.Birthday("New Year", 1, 5, 1990)] + got = ub.upcoming(bdays, today, window=30) + assert got[0].date == dt.date(2027, 1, 5) + assert got[0].days_away == 9 + + +def test_upcoming_age_is_occurrence_year_minus_birth_year(): + bdays = [ub.Birthday("Ager", 7, 23, 1970)] + got = ub.upcoming(bdays, TODAY) + assert got[0].age == 56 # 2026 - 1970 + + +def test_upcoming_age_none_for_placeholder(): + bdays = [ub.Birthday("Placeholder", 7, 23, None)] + got = ub.upcoming(bdays, TODAY) + assert got[0].age is None + + +def test_upcoming_sorted_by_days_away(): + bdays = [ + ub.Birthday("Later", 8, 10, 1990), + ub.Birthday("Sooner", 7, 20, 1990), + ] + got = ub.upcoming(bdays, TODAY) + assert [u.name for u in got] == ["Sooner", "Later"] + + +def test_upcoming_leap_day_maps_to_feb_28_in_non_leap_year(): + today = dt.date(2027, 2, 1) # 2027 is not a leap year + bdays = [ub.Birthday("Leapling", 2, 29, 2000)] + got = ub.upcoming(bdays, today, window=30) + assert got[0].date == dt.date(2027, 2, 28) + + +# --- format_block ----------------------------------------------------------- + +def test_format_block_empty_reports_none(): + out = ub.format_block([], window=30) + assert "No birthdays" in out + + +def test_format_block_callout_marks_within_seven_days(): + items = [ub.Upcoming("Soon", dt.date(2026, 7, 22), 4, 40)] + out = ub.format_block(items, window=30, callout_days=7) + assert "⚠" in out + assert "Soon" in out + assert "40" in out # age shown + + +def test_format_block_beyond_callout_is_not_flagged(): + items = [ub.Upcoming("Later", dt.date(2026, 8, 10), 23, 30)] + out = ub.format_block(items, window=30, callout_days=7) + assert "⚠" not in out + + +def test_format_block_placeholder_shows_date_only_no_age(): + items = [ub.Upcoming("NoYear", dt.date(2026, 7, 25), 7, None)] + out = ub.format_block(items, window=30) + assert "NoYear" in out + assert "turns" not in out + + +# --- CLI -------------------------------------------------------------------- + +def test_cli_runs_against_a_fixture_file(tmp_path): + contacts = tmp_path / "contacts.org" + contacts.write_text( + "** Alice\n:PROPERTIES:\n:BIRTHDAY: 1990-07-20\n:END:\n" + "** Bob\n:PROPERTIES:\n:BIRTHDAY: 1900-12-01\n:END:\n" + ) + res = subprocess.run( + [sys.executable, str(SCRIPT), "--file", str(contacts), + "--today", "2026-07-18", "--window", "30"], + capture_output=True, text=True, + ) + assert res.returncode == 0 + assert "Alice" in res.stdout + assert "Bob" not in res.stdout # Dec 1 is outside the 30-day window |