fix(docker): bake build-time git SHA into the image

`hermes dump` and the startup banner both call `git rev-parse HEAD` to
report the running commit, but `.dockerignore` line 2 excludes `.git` —
so inside the published image `hermes dump` shows
`version: ... [(unknown)]` and the banner drops its `· upstream <sha>`
suffix entirely.  That makes support triage from container bug reports
impossible: we can't tell which commit the user is actually running.

Fix: thread the build-time SHA through as a Docker build-arg, write it
to `/opt/hermes/.hermes_build_sha` in the image, and have a new
`hermes_cli/build_info.get_build_sha()` read it as a fallback after the
existing live-git lookup fails.  Output format is unchanged in both
callsites — same 8-char short SHA whether resolved live or baked.

Wiring:
  - Dockerfile: `ARG HERMES_GIT_SHA=` + write-file step after the source
    copy.  Empty/missing arg → no file written → callers fall through to
    live git (so local `docker build` without --build-arg is unchanged).
  - docker-publish.yml: passes `HERMES_GIT_SHA=${{ github.sha }}` on all
    four build-push-action steps (amd64/arm64, smoke-test + final push).
  - dump.py:_get_git_commit() / banner.py:get_git_banner_state(): try
    live git first, fall back to baked SHA, then to legacy `(unknown)`
    / None.  Banner returns `upstream == local, ahead=0` because a built
    image is by definition pinned to one commit.

Coverage:
  - Unit tests cover build_info (file present/absent/empty/error,
    truncation, whitespace), dump (live-git wins, both fallbacks,
    identical output-format regression guard), and banner (no-repo +
    baked, no-repo + no-sha, shallow-clone fallback).
  - tests/docker/test_dump_build_sha.py is an integration regression
    guard that runs against the real image, reads
    `/opt/hermes/.hermes_build_sha`, and asserts `hermes dump` surfaces
    its content (or stays at `(unknown)` if no file).
  - Verified end-to-end: `docker build --build-arg HERMES_GIT_SHA=abc...`
    → `docker run ... dump` reports `[abc12345]`; without the build-arg
    it reports `[(unknown)]` as before.
This commit is contained in:
Ben 2026-05-28 14:28:45 +10:00 committed by Ben Barclay
parent ebe04c66cd
commit 66489f38c7
9 changed files with 488 additions and 3 deletions

View file

@ -61,3 +61,56 @@ def test_get_git_banner_state_reads_origin_and_head(tmp_path):
state = banner.get_git_banner_state(repo_dir)
assert state == {"upstream": "b2f477a3", "local": "af8aad31", "ahead": 3}
def test_get_git_banner_state_falls_back_to_build_sha_when_no_repo():
"""Docker image case: no .git checkout — baked build SHA fills the gap.
``_resolve_repo_dir`` returns None when neither the running code's
parent nor ``$HERMES_HOME/hermes-agent/`` is a git repo (the canonical
case inside the published container, where .git is dockerignored).
The banner should still report the build SHA so support bug reports
can identify the running commit.
"""
from hermes_cli import banner
with patch.object(banner, "_resolve_repo_dir", return_value=None), \
patch("hermes_cli.build_info.get_build_sha", return_value="abcdef12"):
state = banner.get_git_banner_state()
assert state == {"upstream": "abcdef12", "local": "abcdef12", "ahead": 0}
def test_get_git_banner_state_returns_none_when_no_repo_and_no_build_sha():
"""Pip-installed wheel with neither git checkout nor baked SHA → None.
Banner correctly omits the upstream/local suffix in this case.
"""
from hermes_cli import banner
with patch.object(banner, "_resolve_repo_dir", return_value=None), \
patch("hermes_cli.build_info.get_build_sha", return_value=None):
state = banner.get_git_banner_state()
assert state is None
def test_get_git_banner_state_falls_back_when_live_git_returns_nothing(tmp_path):
"""Shallow clone without origin/main → still surface build SHA if baked.
Some install paths (e.g. ``git clone --depth 1`` without a remote) have
a ``.git`` directory but ``git rev-parse origin/main`` fails. When that
happens AND a baked SHA exists, return the baked one instead of None.
"""
from hermes_cli import banner
repo_dir = tmp_path / "repo"
(repo_dir / ".git").mkdir(parents=True)
# All git invocations fail (returncode=1, empty stdout).
failed = MagicMock(returncode=1, stdout="")
with patch("hermes_cli.banner.subprocess.run", return_value=failed), \
patch("hermes_cli.build_info.get_build_sha", return_value="cafef00d"):
state = banner.get_git_banner_state(repo_dir)
assert state == {"upstream": "cafef00d", "local": "cafef00d", "ahead": 0}

View file

@ -0,0 +1,78 @@
"""Tests for hermes_cli.build_info — baked-in build SHA resolution.
The build SHA is written by the Dockerfile's ``HERMES_GIT_SHA`` build-arg
into ``<project_root>/.hermes_build_sha``. These tests cover the read-side
helper: missing file, malformed file, truncation, and error tolerance.
"""
from pathlib import Path
from unittest.mock import patch
def test_get_build_sha_returns_none_when_file_absent(tmp_path):
"""Source installs: no file present → None, callers fall back to git."""
from hermes_cli import build_info
missing = tmp_path / ".hermes_build_sha" # never created
with patch.object(build_info, "_BUILD_SHA_FILE", missing):
assert build_info.get_build_sha() is None
def test_get_build_sha_reads_baked_file(tmp_path):
"""Docker image case: file exists with full 40-char SHA → truncated to 8."""
from hermes_cli import build_info
sha_file = tmp_path / ".hermes_build_sha"
sha_file.write_text("abcdef1234567890abcdef1234567890abcdef12\n")
with patch.object(build_info, "_BUILD_SHA_FILE", sha_file):
assert build_info.get_build_sha() == "abcdef12"
def test_get_build_sha_respects_short_argument(tmp_path):
"""``short=N`` truncates to N chars; ``short<=0`` returns full SHA."""
from hermes_cli import build_info
sha_file = tmp_path / ".hermes_build_sha"
full_sha = "abcdef1234567890abcdef1234567890abcdef12"
sha_file.write_text(full_sha + "\n")
with patch.object(build_info, "_BUILD_SHA_FILE", sha_file):
assert build_info.get_build_sha(short=12) == "abcdef123456"
assert build_info.get_build_sha(short=0) == full_sha
assert build_info.get_build_sha(short=-1) == full_sha
def test_get_build_sha_strips_whitespace(tmp_path):
"""The Dockerfile uses ``printf '%s\\n'`` — strip the trailing newline."""
from hermes_cli import build_info
sha_file = tmp_path / ".hermes_build_sha"
sha_file.write_text(" abcdef1234567890\n\n")
with patch.object(build_info, "_BUILD_SHA_FILE", sha_file):
assert build_info.get_build_sha() == "abcdef12"
def test_get_build_sha_returns_none_for_empty_file(tmp_path):
"""A whitespace-only file is treated as absent."""
from hermes_cli import build_info
sha_file = tmp_path / ".hermes_build_sha"
sha_file.write_text(" \n\n")
with patch.object(build_info, "_BUILD_SHA_FILE", sha_file):
assert build_info.get_build_sha() is None
def test_get_build_sha_swallows_read_errors(tmp_path):
"""Any IO exception from the read returns None — never raises."""
from hermes_cli import build_info
sha_file = tmp_path / ".hermes_build_sha"
sha_file.write_text("abcdef1234567890\n")
with patch.object(build_info, "_BUILD_SHA_FILE", sha_file), \
patch.object(Path, "read_text", side_effect=OSError("boom")):
assert build_info.get_build_sha() is None

View file

@ -0,0 +1,118 @@
"""Tests for hermes_cli.dump._get_git_commit — git SHA resolution for ``hermes dump``.
``hermes dump`` prints the running commit so support bug reports identify the
exact version. Source installs resolve it live via ``git rev-parse``; the
published Docker image excludes ``.git`` and falls back to the baked SHA
written by the Dockerfile's ``HERMES_GIT_SHA`` build-arg.
These tests cover both paths plus the failure modes (no git, no baked file).
"""
from unittest.mock import MagicMock, patch
def test_get_git_commit_uses_live_git_when_available(tmp_path):
"""Source install: ``git rev-parse --short=8 HEAD`` wins; no fallback."""
from hermes_cli import dump
repo_dir = tmp_path / "repo"
repo_dir.mkdir()
git_result = MagicMock(returncode=0, stdout="deadbeef\n")
# build_info should NOT be consulted when live git succeeds.
with patch("hermes_cli.dump.subprocess.run", return_value=git_result) as mock_run, \
patch("hermes_cli.build_info.get_build_sha") as mock_build:
commit = dump._get_git_commit(repo_dir)
assert commit == "deadbeef"
mock_run.assert_called_once()
mock_build.assert_not_called()
def test_get_git_commit_falls_back_to_build_sha_when_live_git_fails(tmp_path):
"""Docker image case: live git returns non-zero → use baked SHA."""
from hermes_cli import dump
repo_dir = tmp_path / "no-git-here"
repo_dir.mkdir()
failed = MagicMock(returncode=128, stdout="")
with patch("hermes_cli.dump.subprocess.run", return_value=failed), \
patch("hermes_cli.build_info.get_build_sha", return_value="cafef00d"):
commit = dump._get_git_commit(repo_dir)
assert commit == "cafef00d"
def test_get_git_commit_falls_back_when_git_returns_empty_stdout(tmp_path):
"""Edge case: git exits 0 but prints nothing — still try the baked SHA."""
from hermes_cli import dump
repo_dir = tmp_path / "repo"
repo_dir.mkdir()
empty = MagicMock(returncode=0, stdout="\n")
with patch("hermes_cli.dump.subprocess.run", return_value=empty), \
patch("hermes_cli.build_info.get_build_sha", return_value="abcdef12"):
commit = dump._get_git_commit(repo_dir)
assert commit == "abcdef12"
def test_get_git_commit_falls_back_when_git_raises(tmp_path):
"""git binary missing (e.g. minimal container w/o git) → baked SHA path."""
from hermes_cli import dump
repo_dir = tmp_path / "repo"
repo_dir.mkdir()
with patch("hermes_cli.dump.subprocess.run", side_effect=FileNotFoundError("git")), \
patch("hermes_cli.build_info.get_build_sha", return_value="feedface"):
commit = dump._get_git_commit(repo_dir)
assert commit == "feedface"
def test_get_git_commit_returns_unknown_when_neither_source_available(tmp_path):
"""Pip-installed wheel: no git, no baked SHA → '(unknown)' (legacy contract)."""
from hermes_cli import dump
repo_dir = tmp_path / "repo"
repo_dir.mkdir()
failed = MagicMock(returncode=128, stdout="")
with patch("hermes_cli.dump.subprocess.run", return_value=failed), \
patch("hermes_cli.build_info.get_build_sha", return_value=None):
commit = dump._get_git_commit(repo_dir)
assert commit == "(unknown)"
def test_get_git_commit_output_format_identical_between_sources(tmp_path):
"""Regression guard: live-git and baked-SHA outputs share the same shape.
Ben explicitly asked for identical output between Docker and source installs
so support tooling that parses ``hermes dump`` doesn't have to special-case
container builds. Both paths must return a bare 8-char SHA no prefix,
no suffix, no annotation.
"""
from hermes_cli import dump
repo_dir = tmp_path / "repo"
repo_dir.mkdir()
# Live-git path.
git_result = MagicMock(returncode=0, stdout="b2f477a3\n")
with patch("hermes_cli.dump.subprocess.run", return_value=git_result):
live = dump._get_git_commit(repo_dir)
# Baked-SHA path.
failed = MagicMock(returncode=128, stdout="")
with patch("hermes_cli.dump.subprocess.run", return_value=failed), \
patch("hermes_cli.build_info.get_build_sha", return_value="b2f477a3"):
baked = dump._get_git_commit(repo_dir)
assert live == baked == "b2f477a3"
# Same length, same charset — no decoration in either branch.
assert len(live) == 8
assert all(c in "0123456789abcdef" for c in live)