fix(issue-26): review - an unreadable env file is an error, NUL lines are skipped, integers are ASCII in every locale, empty flags are refused

Merge-workspace review of PR #43 (codex R1-R4, claude R1/R2).

- R1: envfile.parse raises EnvFileError when the file exists but cannot be
  read or decoded as a whole; `--shell` prints the cause and exits 1, so the
  wrapper stops (rc 1, as before #26) instead of running on defaults, and
  mqtt_common's entry points stop on the same error. A bad single line is
  still a warning. The wrapper's message no longer claims a read failure
  when the cause is elsewhere ("cannot load ... see the line above").
- R2: lib.sh mam_int spells out the ASCII blanks and digits instead of
  [[:space:]]/[0-9], which follow the locale: U+2003 30 U+2003 was 30 in the
  wrapper and invalid in the runner under en_US.UTF-8. The test oracle
  _expected uses the same ASCII rule.
- R3: an integer flag given explicitly with an empty value is refused like
  any other invalid value; only an absent flag keeps its default.
- R4: a line holding a NUL byte is skipped with a warning by both loaders;
  before, the wrapper read "leftright" and the Python loader died.
- .mam.env.example states the format: no expansion, `export` and bash's own
  variables skipped, a trailing `# ...` is part of the value, the environment
  wins, an unreadable file is an error.

Tests: unreadable (0000) and invalid-UTF-8 files stop the wrapper and the
Python loader; a NUL line is skipped by both; Unicode blanks/digits are
invalid for mam_int, _positive_int, the wrapper and the runner under C and
en_US.UTF-8; explicit empty values for the five integer flags are refused.
All of them fail on b58edac.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff

tests/test_issue26_envfile.py

@@ -143,7 +143,54 @@ def test_a1_an_unreadable_parser_fails_loudly(tmp_path):
                          env=_env(tmp_path, f, {"DELEGATE_JOB_PYTHON": str(tmp_path / "no-python")}),
                          cwd=str(tmp_path), timeout=60)
     assert res.returncode == 1
-    assert f"ERROR: cannot read {f}" in res.stderr
+    assert f"ERROR: cannot load {f}" in res.stderr
+
+
+def _python_load(env: dict) -> subprocess.CompletedProcess:
+    code = "from lib_py.delegation import mqtt_common; mqtt_common.ensure_env_loaded(); print('LOADED')"
+    return subprocess.run([sys.executable, "-c", code], capture_output=True, text=True, env=env, timeout=60)
+
+
+@pytest.mark.parametrize("kind", ["permission", "utf8"])
+def test_a1_a_file_that_cannot_be_read_stops_both_loaders(tmp_path, kind):
+    """Review R1: a file that exists but cannot be read or decoded as a whole
+    is an error in the wrapper (rc 1, as before #26) and in the Python entry
+    points - never an empty configuration that runs on defaults."""
+    f = tmp_path / "broken.env"
+    if kind == "permission":
+        if os.geteuid() == 0:
+            pytest.skip("root reads a 000 file")
+        f.write_text("PROBE_A=one\n")
+        f.chmod(0)
+        cause = "PermissionError"
+    else:
+        f.write_bytes(b"PROBE_A=one\nPROBE_B=\xff\xfe\n")
+        cause = "UnicodeDecodeError"
+    try:
+        res = subprocess.run(["bash", str(WRAPPER), "--help"], capture_output=True, text=True,
+                             env=_env(tmp_path, f), cwd=str(tmp_path), timeout=60)
+        assert res.returncode == 1, res.stdout + res.stderr
+        assert f"ERROR: {f}: cannot read ({cause})" in res.stderr, res.stderr
+        assert f"ERROR: cannot load {f}" in res.stderr, res.stderr
+        assert "one" not in res.stderr  # no value in any message
+        py = _python_load(_env(tmp_path, f))
+        assert py.returncode != 0 and "LOADED" not in py.stdout, py.stdout + py.stderr
+        assert f"{f}: cannot read ({cause})" in py.stderr and "EnvFileError" in py.stderr, py.stderr[-500:]
+    finally:
+        f.chmod(0o600)
+
+
+def test_a1_a_nul_line_is_skipped_by_both_loaders(tmp_path):
+    """Review R4: no environment can carry a NUL byte. Both loaders skip that
+    line with a warning naming it (not its value) and keep the lines around it."""
+    f = tmp_path / "nul.env"
+    f.write_bytes(b"GOOD=ok\nVALUE=left\x00right\nAFTER=yes\n")
+    env = _env(tmp_path, f)
+    got = _wrapper_values(env, ["GOOD", "VALUE", "AFTER"], tmp_path)
+    assert got.returncode == 0, got.stderr
+    assert _split(got.stdout) == {"GOOD": "ok", "VALUE": "<unset>", "AFTER": "yes"}
+    assert f"{f}:2: skipped (NUL byte)" in got.stderr and "left" not in got.stderr, got.stderr
+    assert _python_values(env, ["GOOD", "VALUE", "AFTER"]) == {"GOOD": "ok", "VALUE": "<unset>", "AFTER": "yes"}
 
 
 # ---------------------------------------------------------------------------

tests/test_issue26_ints.py

@@ -86,8 +86,8 @@ NOT_ARITHMETIC = {
 
 
 def _expected(value: str, minimum: int):
-    s = value.strip()
-    if not s.isdigit():
+    s = value.strip(" \t\n\r\v\f")  # ASCII blanks only, in every locale (review R2)
+    if not s.isascii() or not s.isdigit():
         return None
     s = s.lstrip("0") or "0"
     if len(s) > 9:
@@ -182,6 +182,28 @@ def test_b1_mam_int_and_positive_int_are_one_rule(tmp_path, minimum):
     assert want[INPUTS.index("0700")] == 700
 
 
+# Review R2: bash's [[:space:]] and [0-9] follow the locale; the rule is ASCII.
+UNICODE_INPUTS = ["\u200330\u2003", "\u00a030", "30\u3000", "\u0663\u0660", "\uff13\uff10"]
+
+
+@pytest.mark.parametrize("locale", ["C", "en_US.UTF-8"])
+@pytest.mark.parametrize("value", UNICODE_INPUTS, ids=lambda v: v.encode("unicode_escape").decode())
+def test_b1_unicode_blanks_and_digits_are_invalid_in_every_locale(tmp_path, locale, value):
+    if str(SKILLS) not in sys.path:
+        sys.path.insert(0, str(SKILLS))
+    from lib_py.loop.runner import _positive_int
+
+    loc = {"LC_ALL": locale, "LANG": locale}
+    res = _bash('mam_int "$PROBE" 1 || echo invalid', tmp_path, {**loc, "PROBE": value})
+    assert res.stdout.strip() == "invalid", (res.stdout, res.stderr)
+    assert _positive_int(value) is None and _expected(value, 1) is None
+    rec = _record(tmp_path, _dry_submit(tmp_path, {**loc, "MAM_JOB_TIMEOUT_S": value}))
+    rres = _runner(tmp_path, {**loc, "MAM_JOB_TIMEOUT_S": value})
+    assert rres.returncode == 0, rres.stderr[-500:]
+    got = json.loads(rres.stdout.strip().splitlines()[-1])
+    assert rec["timeout_sec"] == got["budget"] == 3600, (rec["timeout_sec"], got)
+
+
 @pytest.mark.parametrize("knob", ["SKS_DIALOG_TIMEOUT", "SKS_BUSY_TIMEOUT", "SKS_DELIVERY_GRACE_S"])
 def test_b1_sks_knobs_keep_zero_and_read_decimal(tmp_path, knob):
     minimum, default = INT_KNOBS[knob]
@@ -204,7 +226,7 @@ def test_b2_wrapper_flags_are_decimal_or_refused(tmp_path):
     ok = _dry_submit(tmp_path, None, "--timeout", "30")
     assert _record(tmp_path, ok)["timeout_sec"] == 30
     for flag in ("--timeout", "--idle-timeout", "--heartbeat", "--heartbeat-misses", "--ack-timeout"):
-        for bad in ("abc", "0", "-5", "9999999999", "9" * 5000):
+        for bad in ("abc", "0", "-5", "9999999999", "9" * 5000, ""):  # "" given explicitly (review R3)
             res = _dry_submit(tmp_path, None, flag, bad)
             assert res.returncode == 1, (flag, bad[:20], res.stdout, res.stderr[-500:])
             assert f"ERROR: {flag} {bad}: not a positive decimal integer" in res.stderr, res.stderr[-500:]