ceremony/test/forge-backends.test.sh
cluade-reviewer-andresmgsl ab23a3b1b6 feat(forge): two backends behind one call surface, and the shim owns paging
Term 1's foundation. lib/forge.sh gains forge_select, which sources exactly
one of lib/forge-github.sh or lib/forge-forgejo.sh; both define the same
verbs, so no branching reaches the 61 call sites. The github backend is the
current gh invocation extracted 1:1 — term 5 is kept by making that path
boring.

The page size moves OUT of the call sites and into the backend, because it
is not portable and fails silently. Measured 2026-08-02:

  ?per_page=100   GitHub 100 items   Forgejo 30 items  (ignored)
  ?limit=100      GitHub  30 items   Forgejo 50 items  (capped)

Both answer HTTP 200 with valid JSON. Every call site here is GitHub-shaped,
so a verbatim port would have swept 30 of rig's 137 issues and printed
"reconciled." — criterion 2 failing green, the same failure class as the
blind sweep. Both page_url helpers strip a stray page-size parameter in
either dialect, so a call site cannot reintroduce it by accident.

Forgejo caps a page at 50 whatever is asked, so pagination is mandatory, not
an optimisation. The gather is then PROVEN complete against x-total-count
rather than assumed complete because a loop ended.

@kimi-reviewer-andresmgsl's hardening (#4699): a missing x-total-count is
itself a loud refusal. Header exposure is a server setting, and an assert
that cannot run must not silently pass — that is the failure class
re-entering through the guard built to stop it.

Call sites are not ported yet; that is the next commit.

Refs #188
2026-08-02 19:00:58 +00:00

163 lines
6.9 KiB
Bash

#!/usr/bin/env bash
# Contract tests for lib/forge-github.sh and lib/forge-forgejo.sh
# (issue #188, term 1). set -u, not -e.
set -u
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
# shellcheck source=test/harness.sh
. "$ROOT/test/harness.sh"
# shellcheck source=lib/forge.sh
. "$ROOT/lib/forge.sh"
TMP="$(mktemp -d)"
trap 'rm -rf "$TMP"' EXIT
eq() {
local want="$1" got
shift
got="$("$@")" || return 1
[ "$got" = "$want" ]
}
# --- forge_select: exactly one backend, chosen deliberately -------------
check "select github loads the github backend" 0 "" \
bash -c '. '"$ROOT"'/lib/forge.sh; forge_select github; declare -f github_page_url >/dev/null'
check "select forgejo loads the forgejo backend" 0 "" \
bash -c '. '"$ROOT"'/lib/forge.sh; forge_select forgejo; declare -f forgejo_page_url >/dev/null'
check "select refuses an unknown forge" 1 "unknown forge" \
bash -c '. '"$ROOT"'/lib/forge.sh; forge_select gitlab'
check "select with no argument reads the environment" 0 "" \
bash -c 'CEREMONY_FORGE=forgejo; . '"$ROOT"'/lib/forge.sh; forge_select; [ "$FORGE" = forgejo ]'
# --- the page-size contract, both dialects ------------------------------
# The trap, measured 2026-08-02: each forge silently ignores the OTHER's
# page-size parameter and answers HTTP 200 with fewer items.
#
# ?per_page=100 GitHub 100 Forgejo 30 (ignored)
# ?limit=100 GitHub 30 Forgejo 50 (capped)
#
# So no call site names one, and these two functions are the only places
# that decide. Pure on purpose: the contract is testable without a network.
. "$ROOT/lib/forge-github.sh"
. "$ROOT/lib/forge-forgejo.sh"
check "github: a bare path gets a query" 0 "" \
eq 'repos/o/r/issues?per_page=100' github_page_url 'repos/o/r/issues'
check "github: an existing query is preserved" 0 "" \
eq 'repos/o/r/issues?state=open&per_page=100' github_page_url 'repos/o/r/issues?state=open'
check "forgejo: a bare path gets a query" 0 "" \
eq 'repos/o/r/issues?limit=50&page=1' forgejo_page_url 'repos/o/r/issues' 1
check "forgejo: an existing query is preserved" 0 "" \
eq 'repos/o/r/issues?state=open&limit=50&page=2' forgejo_page_url 'repos/o/r/issues?state=open' 2
# A caller that names a page size anyway must not be able to reintroduce the
# truncation — the parameter is stripped in BOTH dialects, on both backends,
# because the whole point is that the boundary decides and the call site
# cannot override it by accident.
check "github strips a stray per_page" 0 "" \
eq 'repos/o/r/issues?state=open&per_page=100' github_page_url 'repos/o/r/issues?state=open&per_page=30'
check "github strips a stray limit" 0 "" \
eq 'repos/o/r/issues?state=open&per_page=100' github_page_url 'repos/o/r/issues?state=open&limit=100'
check "forgejo strips a stray per_page" 0 "" \
eq 'repos/o/r/issues?state=open&limit=50&page=1' forgejo_page_url 'repos/o/r/issues?state=open&per_page=100' 1
check "forgejo strips a stray limit" 0 "" \
eq 'repos/o/r/issues?state=open&limit=50&page=1' forgejo_page_url 'repos/o/r/issues?state=open&limit=100' 1
check "stripping the only parameter leaves a clean query" 0 "" \
eq 'repos/o/r/issues?limit=50&page=1' forgejo_page_url 'repos/o/r/issues?per_page=100' 1
# --- the forgejo gather: complete, or loudly refused --------------------
# curl is stubbed as a function so these are hermetic. Each case writes the
# headers and body a real Forgejo would.
# fake_forge <total> <pages…> — install a curl stub serving <pages> as
# successive page bodies, declaring <total> in x-total-count. An empty
# string for <total> omits the header entirely (@kimi's #4699 case).
fake_forge() {
FAKE_TOTAL="$1"; shift
FAKE_PAGES=("$@")
FAKE_CALLS=0
curl() {
local hdr="" out="" url=""
while [ $# -gt 0 ]; do
case "$1" in
-D) hdr="$2"; shift ;;
-o) out="$2"; shift ;;
-H) shift ;;
-*) ;;
*) url="$1" ;;
esac
shift
done
local page=1
case "$url" in *page=*) page="${url##*page=}"; page="${page%%&*}" ;; esac
{
printf 'HTTP/1.1 200 OK\r\n'
[ -n "$FAKE_TOTAL" ] && printf 'X-Total-Count: %s\r\n' "$FAKE_TOTAL"
printf '\r\n'
} >"$hdr"
if [ "$page" -le "${#FAKE_PAGES[@]}" ]; then
printf '%s' "${FAKE_PAGES[$((page - 1))]}" >"$out"
else
printf '[]' >"$out"
fi
FAKE_CALLS=$((FAKE_CALLS + 1))
return 0
}
}
export CEREMONY_FORGE_API=https://forge.example/api/v1
# One page, and the count agrees with the declared total.
fake_forge 2 '[{"number":1},{"number":2}]'
check "a complete single-page gather returns its items" 0 "" \
eq $'1\n2' forge_api --paginate 'repos/o/r/issues' --jq '.[].number'
# Two pages that add up. The walk must not stop at the first page merely
# because it came back non-empty — rig has 137 issues across 3 pages, which
# is the case this models.
fake_forge 4 '[{"number":1},{"number":2}]' '[{"number":3},{"number":4}]'
check "a multi-page gather walks every page" 0 "" \
eq $'1\n2\n3\n4' forge_api --paginate 'repos/o/r/issues' --jq '.[].number'
# The whole reason the assert exists: a server that declares more than it
# hands over must not produce a "successful" partial sweep.
fake_forge 137 '[{"number":1},{"number":2}]'
check "a short gather is refused, not reconciled" 1 "incomplete gather" \
forge_api --paginate 'repos/o/r/issues' --jq '.[].number'
check "...and the refusal names both counts" 1 "collected 2 of 137" \
forge_api --paginate 'repos/o/r/issues' --jq '.[].number'
# @kimi-reviewer-andresmgsl's hardening (#4699): the guard must not be able
# to degrade silently either. A Forgejo that does not expose x-total-count
# leaves the assert with nothing to compare, and an assert that cannot run
# must refuse rather than pass.
fake_forge '' '[{"number":1},{"number":2}]'
check "a missing x-total-count refuses" 1 "did not send x-total-count" \
forge_api --paginate 'repos/o/r/issues' --jq '.[].number'
check "...and says why it cannot prove completeness" 1 "cannot prove the gather is complete" \
forge_api --paginate 'repos/o/r/issues' --jq '.[].number'
# --- HTTP failures are named, not swallowed -----------------------------
# gh exits non-zero on an HTTP error; curl does not without -f, and -f
# discards the body that explains why. So the status is read explicitly.
fake_forge 1 '[{"number":1}]'
curl() {
local hdr="" out=""
while [ $# -gt 0 ]; do
case "$1" in -D) hdr="$2"; shift ;; -o) out="$2"; shift ;; esac
shift
done
printf 'HTTP/1.1 404 Not Found\r\n\r\n' >"$hdr"
printf '{"message":"Not found"}' >"$out"
return 0
}
check "a 404 is a named failure" 1 "HTTP 404" forge_api 'repos/o/r/issues/9999'
check "a 404 names the endpoint" 1 "repos/o/r/issues/9999" forge_api 'repos/o/r/issues/9999'
# --- the api base must be known -----------------------------------------
check "no api base refuses" 1 "cannot reach the forge" \
bash -c 'unset CEREMONY_FORGE_API GITHUB_API_URL; . '"$ROOT"'/lib/forge-forgejo.sh; forgejo_api_base'
summary