#!/usr/bin/env bash
# release-agent.sh — THE way to release a felhom-agent version. One act: build → tag → publish →
# verify by independent download.
#
# WHY THIS EXISTS (R-115). Publishing used to be a step someone had to remember, and it was
# forgotten THREE TIMES IN FIVE DAYS:
#
#   * R-111  (2026-07-29) 17 releases v0.97.0-v0.113.0 built and never published, so a new customer
#            would have installed without the whole R-82 tiered-backup arc, F-CRIT-2 and F-REBOOT.
#   * 0.114.0 (same afternoon) built, deployed to felhom-pve, never published.
#   * 0.120.0 (2026-08-03) built, committed and deployed to BOTH demo hosts, never published. A
#            documented-path reinstall would have silently DOWNGRADED both boxes to the pre-merge
#            agent — and would have *succeeded* while doing it, because the current `step_grows`
#            sets SYSDATA_GROW=0 so the older agent's fatal mp1 resize never fires.
#
# R-111's own closing line said publishing should join the release train rather than stay a
# remembered step. It closed SHIPPED without that leg, and the leg recurred the same afternoon —
# which is the evidence that a note is not a mechanism. This file is the mechanism. The
# documentation now points here instead of at a raw `go build` line, so there is ONE documented way
# to release and it cannot complete without publishing.
#
# WHY IT TAGS (R-183). Since felhom-host-install.sh pins its sixteen agent-config fetches to
# `raw/tag/v<version>`, a released version without a git tag 404s a box mid-install, as root, on a
# virgin machine. The tag and the package are two halves of one release and are created together.
#
# WHY IT DOES NOT VOUCH. Vouching is what points machines at a version, and it stays the operator's
# deliberate act — the same prove-then-vouch principle that governed the golden two sessions ago.
# This script prints the version and sha to vouch; a human decides when.
#
# Usage:
#   GITEA_USER=admin GITEA_TOKEN=<token> ./scripts/release-agent.sh <version>
#
# Env: GITEA_USER/GITEA_TOKEN (package write) — same credentials publish-agent.sh already takes.
#      GITEA_BASE / GITEA_OWNER override the defaults.
#      RELEASE_ALLOW_DIRTY=1 skips the clean-tree gate (for a rehearsal; never for a real release).
set -euo pipefail

GITEA_BASE="${GITEA_BASE:-https://gitea.dooplex.hu}"
GITEA_OWNER="${GITEA_OWNER:-admin}"
REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"

die() { echo "[release-agent] ERROR: $*" >&2; exit 1; }
log() { echo "[release-agent] $*" >&2; }

VERSION="${1:-}"
[[ -n "$VERSION" ]] || die "version required (usage: GITEA_USER=.. GITEA_TOKEN=.. $0 <version>)"
[[ "$VERSION" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]] || die "version must be bare semver X.Y.Z (got '$VERSION')"
TAG="v$VERSION"

cd "$REPO_ROOT"

# ── 1. Clean-tree gate ──────────────────────────────────────────────────────────────────────────
# An unpushed change does not exist. Releasing a dirty tree publishes a binary whose source nobody
# else can obtain, and tags a commit that does not contain what was built.
if [[ "${RELEASE_ALLOW_DIRTY:-0}" != "1" ]]; then
    [[ -z "$(git status --porcelain)" ]] || die "working tree is dirty — commit and push first"
    local_head="$(git rev-parse HEAD)"
    git fetch -q origin main
    [[ "$local_head" == "$(git rev-parse origin/main)" ]] \
        || die "HEAD != origin/main — push first (an unpushed change does not exist)"
fi

# ── 2. Refuse to re-release a version that already exists ───────────────────────────────────────
# Silently overwriting a published artifact is how "the same version" comes to mean two different
# binaries on two different boxes.
if git rev-parse -q --verify "refs/tags/$TAG" >/dev/null; then
    die "tag $TAG already exists — releasing over it would make one version name two binaries"
fi
existing="$(curl -fsS -o /dev/null -w '%{http_code}' \
    "$GITEA_BASE/api/packages/$GITEA_OWNER/generic/felhom-agent/$VERSION/felhom-agent" 2>/dev/null || true)"
[[ "$existing" != "200" ]] || die "version $VERSION is ALREADY PUBLISHED — bump the version instead"

# ── 3. Build ────────────────────────────────────────────────────────────────────────────────────
BIN="$(mktemp -t felhom-agent-XXXXXX)"
trap 'rm -f "$BIN"' EXIT
log "building $VERSION …"
# REPRODUCIBLE BY CONSTRUCTION (R-186). The sha printed below is the one the operator vouches, and
# until now nobody could rebuild it to check: `go build` stamps a module version derived from VCS
# state, so a build made BEFORE the tag exists and a rebuild made after it are different binaries.
# Measured 2026-08-03 at this commit — same source, same toolchain, same ldflags:
#
#   default flags,  no tag yet .. 18f4a495…  14 085 464 B   (mod v0.121.2-0.2026…-3d0a1d61)
#   default flags,  tagged ...... 4a38f394…  14 085 440 B   (mod v0.121.99)
#   -trimpath -buildvcs=false ... 7ffcdf1d…  14 064 574 B   IDENTICAL both ways
#
# `-buildvcs=false` removes the stamp — nothing in this repo reads it (no `ReadBuildInfo` caller,
# verified) and the version comes from the explicit ldflag below, which is where it belongs.
# `-trimpath` removes absolute build paths, so a rebuild from a different checkout directory also
# matches. Neither is a sequencing trick: the property no longer depends on WHEN the build happens.
#
# CGO is deliberately left at its default. publish-agent.sh's fallback build used to force
# CGO_ENABLED=0 and therefore produced a DIFFERENT binary (13 990 236 B, 74 KB smaller) for the same
# version — one version name, two binaries, by whichever entry point was used. Both now build the
# same way; if that ever has to change, change it in BOTH or the guarantee is gone.
go build -trimpath -buildvcs=false -ldflags "-X main.version=$VERSION" -o "$BIN" ./cmd/felhom-agent \
    || die "go build failed"
built_ver="$("$BIN" --version 2>/dev/null | awk '{print $2}')"
[[ "$built_ver" == "$VERSION" ]] \
    || die "the built binary reports '$built_ver', not '$VERSION' — the ldflag did not take"
BUILT_SHA="$(sha256sum "$BIN" | awk '{print $1}')"
log "built ok: sha256 $BUILT_SHA"

# ── 4. Tag LOCALLY (the push comes after the publish — see step 6) ──────────────────────────────
#
# THE ORDER CHANGED, AND ONLY THE PUSH MOVED (R-188, 2026-08-03).
#
# It used to be tag → push tag → publish, and the reason written here was sound: a tag with no
# package is caught by scripts/check-published-versions.py, a package with no tag is invisible to it,
# because the Gitea package LISTING api needs a token the gate does not have.
#
# What that reasoning missed is that the tag PUSH is what wakes CI (`on: [push]`), so the gate ran in
# the seconds between the tag becoming visible and the package existing — and correctly failed. Every
# correct release had roughly a coin-flip chance of emailing the operator a failure for a release
# that worked. Measured across two releases in one session: runs 12/13 (v0.121.0) and 17/18
# (v0.121.1), same sha each time, opposite results. R-168 made that mail the thing that cannot be
# missed; a mail that is wrong half the time is one you stop reading, and then the real one goes too.
#
# So the tag is still created HERE, before anything is published — the build and the tag still
# describe the same commit, and a failed publish leaves a purely local tag that never misled anyone.
# It simply becomes VISIBLE (to CI, and to any installer fetching raw/tag/…) only once the package
# is downloadable. The invariant the old order protected is not traded away: it is asserted directly
# by the gate's new converse probe (a published version with no tag FAILS), so both directions are
# now checked rather than one being arranged for.
log "tagging $TAG at $(git rev-parse --short HEAD) …"
git tag -a "$TAG" -m "agent $TAG

Released by scripts/release-agent.sh.
sha256 of the published binary: $BUILT_SHA

felhom-host-install.sh fetches this version's config files from raw/tag/$TAG/configs/,
so this tag is part of the released artifact, not a bookmark (R-183)."

# ── 5. Publish (the existing script; deliberately not reimplemented) ────────────────────────────
log "publishing …"
# Invoked through `bash` DELIBERATELY, not as an executable. On 2026-08-03 the first real release
# through this script died here — `publish-agent.sh` has been mode 0644 since it was created on
# 2026-06-28, because every earlier caller ran it as `bash scripts/publish-agent.sh`. So the one leg
# R-115 exists to make unforgettable was, on its first use, unrunnable. The mode bit is restored in
# the same commit; this line makes the release independent of it, because a file mode is exactly the
# kind of thing that is lost again by a checkout, an archive, or a copy.
if ! bash "$REPO_ROOT/scripts/publish-agent.sh" "$VERSION" "$BIN"; then
    # The tag is LOCAL-ONLY at this point, so a failed publish must not leave one behind: the next
    # attempt would die at step 2's "tag $TAG already exists" and read as "this version is already
    # released", which would be exactly backwards. Only remove it if nothing was in fact published —
    # if a package DOES exist, the tag is wanted and must be pushed, not deleted.
    now_published="$(curl -fsS -o /dev/null -w '%{http_code}' \
        "$GITEA_BASE/api/packages/$GITEA_OWNER/generic/felhom-agent/$VERSION/felhom-agent" 2>/dev/null || true)"
    if [[ "$now_published" == "200" ]]; then
        log "publish reported failure but the package IS downloadable — keeping the local tag; push it with: git push origin $TAG"
    else
        git tag -d "$TAG" >/dev/null 2>&1 && log "removed the local-only tag $TAG so the release can be retried"
    fi
    die "publish failed"
fi

# ── 6. Push the tag, now that the package exists ────────────────────────────────────────────────
# This is the step that makes the release VISIBLE — to CI, and to every `raw/tag/v<version>/` fetch
# the installer makes. It runs last of the two so CI can never see a tag whose package is not there.
#
# If it fails, the release is HALF DONE and must be said so loudly: the package is published and the
# tag exists only in this clone, which is precisely the orphan the gate's converse probe now catches.
# The recovery is one line and it is printed rather than described.
log "pushing $TAG …"
if ! git push origin "$TAG"; then
    cat >&2 <<EOF

  RELEASE HALF DONE — the package is PUBLISHED and its tag is NOT pushed.

    version : $VERSION
    sha256  : $BUILT_SHA

  The tag exists in this clone only. Nothing installs from an untagged version (the installer
  fetches this version's configs from raw/tag/$TAG/), and scripts/check-published-versions.py will
  FAIL on it as a published version with no tag. Finish the release with:

      git push origin $TAG

EOF
    die "tag push failed after a successful publish — see above"
fi

# ── 7. Verify by an INDEPENDENT download ────────────────────────────────────────────────────────
# The publish step's own success is not proof: it reports on its own write. What matters is that a
# box can now GET the bytes and that they are the bytes that were built. This is the same
# presence-is-not-success rule the project earned twice — a step that says "done" and a fetch that
# returns the right sha are different claims.
log "verifying by independent download …"
DL="$(mktemp -t felhom-agent-dl-XXXXXX)"
trap 'rm -f "$BIN" "$DL"' EXIT
curl -fsS -o "$DL" "$GITEA_BASE/api/packages/$GITEA_OWNER/generic/felhom-agent/$VERSION/felhom-agent" \
    || die "round-trip GET failed — the version is NOT installable"
DL_SHA="$(sha256sum "$DL" | awk '{print $1}')"
[[ "$DL_SHA" == "$BUILT_SHA" ]] \
    || die "published sha $DL_SHA != built sha $BUILT_SHA — the artifact is not what was built"

# The tag must also serve the configs the installer will fetch from it.
cfg_code="$(curl -fsS -o /dev/null -w '%{http_code}' \
    "$GITEA_BASE/$GITEA_OWNER/felhom-agent/raw/tag/$TAG/configs/felhom-agent.service" 2>/dev/null || true)"
[[ "$cfg_code" == "200" ]] \
    || die "tag $TAG does not serve configs/felhom-agent.service (HTTP $cfg_code) — a box would 404 mid-install"

cat <<EOF

  RELEASED — and installable, verified by download, not by this script's own say-so.

    version : $VERSION
    tag     : $TAG
    sha256  : $BUILT_SHA

  NOT VOUCHED. Vouching is what points machines at this version and stays your deliberate act:
  hub operator UI → Configs → Day-0 artifacts. Until then boxes keep installing the previous one.
EOF