ci(coverage): risk-weighted coverage policy + diff-coverage gate

Adopt ADR 0004: stop chasing a single global coverage number and
measure what matters instead.

- Omit the genuinely-interactive `cli/init.py` shell (read_tty_line
  prompt loops) alongside the existing `cli/tui.py`, with a rationale
  comment in .coveragerc. Subprocess/backend orchestration is NOT
  omitted — it stays visible and is scored via the integration suite.
- scripts/coverage.sh runs unit + integration under one coverage
  measurement (the policy's yardstick) and can report the critical
  security/logic core held to the >=90% target.
- scripts/diff_coverage.py is a stdlib-only gate (no diff-cover dep):
  new/changed executable lines must be >=90% covered. This is the
  enforced regression guard; the global number is informational.
- CI gains a `coverage` job: combined report + the diff-coverage gate.
- Unit-test `cli/__init__.py` dispatch/exit-code mapping (it's logic,
  not I/O, so it earns tests rather than an omit).

Combined unit+integration coverage now reports 83% global / 87% across
the critical modules; per-module ratcheting toward 90% is the ongoing
work this policy frames.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NkwFXLFff9PYPy4wgVBJp9

scripts/coverage.sh

@@ -0,0 +1,41 @@
+#!/usr/bin/env bash
+# Combined unit + integration coverage (see docs/decisions/0004-coverage-policy.md).
+#
+# Runs the unit suite, then appends the integration suite (which skips
+# cleanly when Docker / the backend CLIs are unavailable), and prints one
+# combined report. The integration suite is what scores the subprocess /
+# backend orchestration modules, so the number here is the policy's
+# yardstick — not the unit-only badge.
+#
+# Usage:
+#   scripts/coverage.sh            # combined report
+#   scripts/coverage.sh critical   # also report just the critical modules
+set -euo pipefail
+
+cd "$(dirname "$0")/.."
+
+PY="${PYTHON:-python3}"
+
+# Critical security/logic core held to the high bar by ADR 0004.
+CRITICAL="bot_bottle/egress_addon.py,bot_bottle/egress_addon_core.py,\
+bot_bottle/dlp_detectors.py,bot_bottle/egress.py,bot_bottle/manifest.py,\
+bot_bottle/manifest_egress.py,bot_bottle/manifest_agent.py,\
+bot_bottle/manifest_schema.py,bot_bottle/git_gate.py,\
+bot_bottle/git_http_backend.py,bot_bottle/supervise.py,\
+bot_bottle/yaml_subset.py,bot_bottle/bottle_state.py"
+
+rm -f .coverage
+
+echo "== unit ==" >&2
+"$PY" -m coverage run -m unittest discover -t . -s tests/unit
+
+echo "== integration (skips without Docker) ==" >&2
+"$PY" -m coverage run --append -m unittest discover -t . -s tests/integration
+
+echo "== combined report ==" >&2
+"$PY" -m coverage report -m
+
+if [ "${1:-}" = "critical" ]; then
+    echo "== critical modules (ADR 0004 target: 90%) ==" >&2
+    "$PY" -m coverage report --include="$CRITICAL"
+fi

scripts/diff_coverage.py

@@ -0,0 +1,126 @@
+#!/usr/bin/env python3
+"""Diff-coverage gate (see docs/decisions/0004-coverage-policy.md).
+
+Fails if too few of the *added/changed* executable lines on this branch
+are covered. Stdlib-only by design — the project carries no runtime deps
+and we are not adding `diff-cover` to satisfy a check.
+
+Reads coverage data already produced by a `coverage run` (e.g. via
+`scripts/coverage.sh`): it shells out to `coverage json` for per-line
+data and to `git diff` for the changed lines. Lines in omitted files
+(the interactive shells) have no coverage data and are skipped, by
+policy.
+
+Usage:
+    scripts/coverage.sh                 # produce .coverage first
+    python3 scripts/diff_coverage.py    # gate against origin/main, min 90%
+    python3 scripts/diff_coverage.py --base main --min 85
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+import re
+import subprocess
+import sys
+import tempfile
+from pathlib import Path
+
+_HUNK_RE = re.compile(r"^@@ -\d+(?:,\d+)? \+(\d+)(?:,(\d+))? @@")
+
+
+def _run(cmd: list[str]) -> str:
+    return subprocess.run(
+        cmd, check=True, capture_output=True, text=True,
+    ).stdout
+
+
+def added_lines_by_file(base: str) -> dict[str, set[int]]:
+    """Map each changed .py file to the set of line numbers added/changed
+    relative to `base`, parsed from a zero-context unified diff."""
+    diff = _run(["git", "diff", "--unified=0", f"{base}...HEAD", "--", "*.py"])
+    out: dict[str, set[int]] = {}
+    current: str | None = None
+    new_line = 0
+    for line in diff.splitlines():
+        if line.startswith("+++ b/"):
+            current = line[6:]
+            out.setdefault(current, set())
+            continue
+        hunk = _HUNK_RE.match(line)
+        if hunk:
+            new_line = int(hunk.group(1))
+            continue
+        if current is None:
+            continue
+        if line.startswith("+") and not line.startswith("+++"):
+            out[current].add(new_line)
+            new_line += 1
+        elif line.startswith("-") and not line.startswith("---"):
+            # Deletion: does not advance the new-file cursor.
+            continue
+    return out
+
+
+def coverage_json() -> dict[str, object]:
+    """Render the existing .coverage data to JSON and load it."""
+    with tempfile.NamedTemporaryFile("r", suffix=".json", delete=True) as fh:
+        _run([sys.executable, "-m", "coverage", "json", "-o", fh.name])
+        return json.load(open(fh.name, encoding="utf-8"))
+
+
+def main() -> int:
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--base", default="origin/main",
+                    help="git ref to diff against (default: origin/main)")
+    ap.add_argument("--min", type=float, default=90.0,
+                    help="minimum %% of changed executable lines covered")
+    args = ap.parse_args()
+
+    if not Path(".coverage").exists():
+        print("diff-coverage: no .coverage data; run scripts/coverage.sh first",
+              file=sys.stderr)
+        return 2
+
+    added = added_lines_by_file(args.base)
+    files = coverage_json().get("files", {})
+    if not isinstance(files, dict):
+        files = {}
+
+    total = 0
+    covered = 0
+    misses: list[str] = []
+    for path, lines in sorted(added.items()):
+        info = files.get(path)
+        if not isinstance(info, dict):
+            # Omitted file or not measured (e.g. a test file) — skip by policy.
+            continue
+        executed = set(info.get("executed_lines", []))
+        missing = set(info.get("missing_lines", []))
+        executable = lines & (executed | missing)
+        for ln in sorted(executable):
+            total += 1
+            if ln in executed:
+                covered += 1
+            else:
+                misses.append(f"{path}:{ln}")
+
+    if total == 0:
+        print("diff-coverage: no measured changed lines to check — pass")
+        return 0
+
+    pct = 100.0 * covered / total
+    print(f"diff-coverage: {covered}/{total} changed lines covered ({pct:.1f}%)")
+    if misses:
+        print("uncovered changed lines:", file=sys.stderr)
+        for m in misses:
+            print(f"  {m}", file=sys.stderr)
+    if pct + 1e-9 < args.min:
+        print(f"diff-coverage: below {args.min:.0f}% threshold", file=sys.stderr)
+        return 1
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())