#!/usr/bin/env bash
set -euo pipefail

usage() {
  cat <<EOF
Usage: validate-provenance.sh <agent-file>

Validate that an agent's sources provenance chain is complete and internally consistent.
Operates at plugin/APM scope only (a single vendor-neutral .apm/agents/<name>.agent.md
inside a package with a type:-bearing apm.yml) — exits 0 silently for project and user
scope agents.

Arguments:
  agent-file  Path to either the Claude Code .md or Copilot .agent.md agent file.

Exit codes:
  0  All checks passed (or nothing to validate, or not plugin scope)
  1  One or more checks failed
  2  Script error (unrecognized file extension — expected .md or .agent.md)

Checks performed:
  0  source_keys present in agent pair but sources.md absent
  1  FILL IN: placeholders in sources.md
  2  source_keys in agent files → slug exists in sources.md
  3  Contributing files listed in sources.md exist on disk (plugin-root
     relative). An explicit '(none)' skips silently; a Contributing files block
     this parser cannot read is reported as an INFO saying checks 3 and 4 did
     not run, never skipped silently.
  4  Contributing files back-reference the parent slug in their source_keys
  5  Research doc field present and not placeholder
EOF
}

if [[ "${1:-}" == "--help" || "${1:-}" == "-h" ]]; then
  usage
  exit 0
fi

if [[ $# -lt 1 ]]; then
  echo "Error: agent-file is required." >&2
  echo "" >&2
  usage >&2
  exit 1
fi

python3 -u - "$1" <<'PYTHON'
import sys
import os
import re

agent_file = os.path.abspath(sys.argv[1])
fname = os.path.basename(agent_file)
agent_dir = os.path.dirname(agent_file)

# --- Sanity-check extension (single vendor-neutral .agent.md file at plugin/APM scope) ---
if not (fname.endswith('.agent.md') or fname.endswith('.md')):
    print(f"Error: unrecognized extension '{fname}' — expected .md or .agent.md", file=sys.stderr)
    sys.exit(2)

# Matches a top-level `type:` line whose value is exactly one of the four
# package content types — identical to validate.sh's APM_TYPE_RE. Group 1's
# optional quote must be closed by \1 (or nothing), and the value must be
# followed by whitespace/end-of-line so a malformed value like `prompts-only`
# doesn't false-match on the `prompts` prefix.
TYPE_RE = re.compile(r"^type:\s*(['\"]?)(instructions|skill|hybrid|prompts)\1(?:\s|$)")

# --- Find package root: walk up for the nearest ancestor apm.yml that
# declares a top-level type: field. An apm.yml with no type: field is a
# marketplace-only manifest (see monorepo-and-repo-shapes.md) — skip it and
# keep walking. Stop at a $HOME boundary, a .git boundary, or the filesystem
# root: none of these is plugin/APM scope, so this script has nothing to
# check there.
def find_plugin_root(start_dir):
    home = os.path.expanduser('~')
    current = os.path.abspath(start_dir)
    while True:
        apm_yml = os.path.join(current, 'apm.yml')
        if os.path.isfile(apm_yml):
            with open(apm_yml) as f:
                if any(TYPE_RE.match(line) for line in f):
                    return current
        # $HOME is a non-plugin-scope boundary — checked before the .git test
        # below (mirrors validate.sh's detect_scope ordering), so a
        # dotfiles-managed $HOME (yadm, chezmoi bare-repo, etc.) can't shadow
        # this check by being its own .git repo. Without this, the walk could
        # continue past $HOME toward the filesystem root looking for a
        # type-bearing apm.yml, misclassifying a user/project-scope file as
        # plugin scope in rare ancestor layouts.
        if current == home:
            return None
        # .git is a directory in a normal checkout but a file (`gitdir: ...`)
        # in a git worktree — exists() covers both.
        if os.path.exists(os.path.join(current, '.git')):
            return None
        parent = os.path.dirname(current)
        if parent == current:
            return None
        current = parent

plugin_root = find_plugin_root(agent_dir)
if plugin_root is None:
    sys.exit(0)

sources_md_path = os.path.join(plugin_root, 'sources.md')

# --- Helpers ---
PLACEHOLDER_RE = re.compile(r'(?<!`)FILL IN:[^`\n]')

def parse_frontmatter(content):
    m = re.match(r'^---\n(.*?)\n---', content, re.DOTALL)
    if not m:
        return None, content
    return m.group(1), content[m.end():]

def parse_source_keys(fm):
    """Extract top-level source_keys list from frontmatter string."""
    if fm is None:
        return []
    keys = []
    in_source_keys = False
    for line in fm.splitlines():
        if re.match(r'^source_keys:', line):
            in_source_keys = True
            continue
        if in_source_keys:
            m = re.match(r'^[ \t]+-\s+(\S+)', line)
            if m:
                keys.append(m.group(1).strip())
            elif line and not line[0].isspace():
                in_source_keys = False
    return keys

def parse_h2_slugs(content):
    return re.findall(r'^## (.+)$', content, re.MULTILINE)

# ===== BEGIN SHARED CONTRIBUTING-FILES PARSER =====
# ONE parser, embedded VERBATIM in two scripts:
#   plugins/kyberforge/.apm/skills/skill-audit/scripts/validate-provenance.sh
#   plugins/kyberforge/.apm/skills/agent-audit/scripts/validate-provenance.sh
# The block between these markers must stay byte-identical in both. It is
# copied rather than imported because a cache-installed plugin's scripts cannot
# read files outside their own plugin directory, so there is no single file both
# can share — the same constraint that forces the ADR-0020 boundary resolver to
# be duplicated across three scripts. Edit one copy, then paste it over the
# other.
#
# tests/test-adr0020-contract.sh hashes both copies and fails on drift. Before
# it did, the agent-audit copy's docstring merely ASSERTED the two were
# "behaviourally identical" and nothing checked it — which is how the two
# already-diverged spellings of the bullet loop went unnoticed.
#
# Requires: re (imported by the host script).


def parse_contributing_files(content, slug):
    """Find the Contributing files for a given slug H2 in content.

    Both authored forms are accepted, because both are in use across the
    corpus and only recognising the first silently skipped the contributing-
    file checks on every sources.md written the other way:

        - **Contributing files:** SKILL.md, references/a.md

        **Contributing files:**
        - SKILL.md (what this source contributed)
        - references/a.md (what this source contributed)

    Returns a list of paths with any trailing parenthetical note stripped.
    Note the bullet form's notes may themselves contain commas, so the list
    is built per bullet rather than by splitting the joined value.

    The three return values are NOT interchangeable, and callers depend on
    the distinction:

        [path, ...]  the entry names contributing files
        []           the entry EXPLICITLY records "(none)"
        None         the entry says nothing this parser can read

    Only an explicit "(none)" yields []. A "Contributing files:" heading
    followed by a numbered list, by `*` bullets, or by prose parses nothing
    and returns None, never [] — a caller reads [] as a deliberate "no
    contributing files" record and SKIPS its check on that basis, so a parse
    failure returning [] would silently disable the check instead of leaving
    the unreadable entry exposed to it.
    """
    pattern = re.compile(
        r'^## ' + re.escape(slug) + r'\s*\n(.*?)(?=^## |\Z)',
        re.MULTILINE | re.DOTALL
    )
    m = pattern.search(content)
    if not m:
        return None
    block = m.group(1)

    def strip_note(entry):
        # "references/a.md (why)" -> "references/a.md"
        return re.sub(r'\s*\(.*$', '', entry).strip()

    # Inline form: value on the same line, comma-separated, no notes.
    cf_m = re.search(r'^\- \*\*Contributing files:\*\* (.+)$', block, re.MULTILINE)
    if cf_m:
        value = cf_m.group(1).strip()
        if value.startswith("(none"):
            return []
        return [p for p in (strip_note(x) for x in value.split(","))
                if p] or None

    # Bullet form: heading on its own line, one file per following bullet.
    cf_m = re.search(r'^\*\*Contributing files:\*\*\s*$', block, re.MULTILINE)
    if not cf_m:
        return None
    files = []
    for line in block[cf_m.end():].splitlines():
        line = line.strip()
        if not line:
            if files:
                break
            continue
        if not line.startswith("- "):
            break
        entry = line[2:].strip()
        if entry.startswith("(none"):
            return []
        entry = strip_note(entry)
        if entry:
            files.append(entry)
    return files or None
# ===== END SHARED CONTRIBUTING-FILES PARSER =====

def parse_research_doc(content, slug):
    pattern = re.compile(
        r'^## ' + re.escape(slug) + r'\s*\n(.*?)(?=^## |\Z)',
        re.MULTILINE | re.DOTALL
    )
    m = pattern.search(content)
    if not m:
        return None
    block = m.group(1)
    rd_m = re.search(r'^\- \*\*Research doc:\*\* (.+)$', block, re.MULTILINE)
    if not rd_m:
        return None
    return rd_m.group(1).strip()

findings = []
has_fail = False

def emit_fail(desc, fpath, why, fix):
    global has_fail
    has_fail = True
    findings.append(("FAIL", desc, fpath, why, fix, None))

# INFO does not set has_fail and does not change the exit code. It is for a
# check that could not RUN — an unverified entry, not a broken one — and it
# exists so that "did not run" is never spelled the same way as "passed".
def emit_info(desc, fpath, note):
    findings.append(("INFO", desc, fpath, None, None, note))

def print_findings():
    for entry in findings:
        kind = entry[0]
        desc = entry[1]
        fpath = entry[2]
        why = entry[3]
        fix = entry[4]
        note = entry[5]
        if kind == "FAIL":
            print(f"FAIL  {desc} — {fpath}")
            print(f"      Why: {why}")
            print(f"      Fix: {fix}")
            print()
        else:
            print(f"INFO  {desc} — {fpath}")
            print(f"      Note: {note}")
            print()

# --- Collect source_keys from agent pair ---
def get_source_keys_from_file(fpath):
    if not os.path.isfile(fpath):
        return []
    try:
        with open(fpath) as f:
            content = f.read()
    except Exception:
        return []
    fm, _ = parse_frontmatter(content)
    return parse_source_keys(fm)

# Plugin/APM scope is a single vendor-neutral file — no counterpart to merge.
given_keys = get_source_keys_from_file(agent_file)
all_source_keys = given_keys

sources_md_exists = os.path.isfile(sources_md_path)

# Early exit: nothing to validate
if not all_source_keys and not sources_md_exists:
    sys.exit(0)

sources_content = None
sources_slugs = set()
if sources_md_exists:
    with open(sources_md_path) as f:
        sources_content = f.read()
    sources_slugs = set(parse_h2_slugs(sources_content))

# --- Check 0: source_keys present but sources.md absent ---
if not sources_md_exists and all_source_keys:
    rel_given = os.path.relpath(agent_file, plugin_root)
    emit_fail(
        "source_keys declared but sources.md is absent",
        rel_given,
        "source_keys references research provenance that has no sources index to validate against.",
        "Create sources.md with an H2 entry for each slug referenced by source_keys."
    )
    print_findings()
    sys.exit(1)

# --- Check 1: FILL IN: placeholders in sources.md ---
for line in sources_content.splitlines():
    if PLACEHOLDER_RE.search(line):
        emit_fail(
            "Unfilled FILL IN: placeholder",
            "sources.md",
            "sources.md contains an unfilled placeholder, meaning provenance is incomplete.",
            "Replace all 'FILL IN:' values in sources.md with real content."
        )
        break

# --- Check 2: source_keys in the agent file → slug exists in sources.md ---
for fpath, keys in [(agent_file, given_keys)]:
    if not keys:
        continue
    rel = os.path.relpath(fpath, plugin_root)
    for slug in keys:
        if slug not in sources_slugs:
            emit_fail(
                f"source_keys slug '{slug}' not found in sources.md",
                rel,
                f"'{rel}' declares '{slug}' as a source but there is no '## {slug}' heading in sources.md.",
                f"Add '## {slug}' entry to sources.md or remove '{slug}' from {rel} source_keys."
            )

# --- Checks 3, 4, 5: Per-slug checks in sources.md ---
for slug in parse_h2_slugs(sources_content):
    # Checks 3 and 4: Contributing files exist (paths relative to plugin root),
    # and back-reference the slug. `[]` and None are NOT the same answer here.
    # `[]` is the author writing "(none)" — there is nothing to check and the
    # skip is correct. None is a Contributing-files block this parser cannot
    # read, and skipping THAT silently disables both checks on the one entry
    # least likely to be right, which is the failure mode
    # parse_contributing_files' own docstring warns about. Say so out loud.
    cf_files = parse_contributing_files(sources_content, slug)
    if cf_files is None:
        emit_info(
            f"Contributing-file checks skipped for '{slug}' — the Contributing files block could not be parsed",
            f"sources.md (## {slug})",
            f"The '## {slug}' entry has no Contributing files list this parser can read — a missing field, a bare heading, '*' bullets, a numbered list, or prose all read as unparsable rather than as an empty declaration. "
            f"Checks 3 and 4 did not run for this slug, so nothing verified that its contributing files exist or name it back. "
            f"Write the value as '- **Contributing files:** <comma-separated paths>', or as a '**Contributing files:**' heading followed by '- ' bullets — "
            f"or record '(none)' if this source contributed no files."
        )
    elif cf_files:
        for cf_rel in cf_files:
            cf_abs = os.path.join(plugin_root, cf_rel)
            if not os.path.isfile(cf_abs):
                emit_fail(
                    f"Contributing file '{cf_rel}' does not exist",
                    f"sources.md (## {slug})",
                    f"sources.md claims '{cf_rel}' was contributed to by slug '{slug}' but the file does not exist.",
                    f"Create '{cf_rel}' relative to the plugin root, or correct the path in sources.md."
                )
            else:
                # Check 4: Bidirectional — file should list slug in its source_keys
                with open(cf_abs) as f:
                    cf_content = f.read()
                cf_fm, _ = parse_frontmatter(cf_content)
                cf_keys = parse_source_keys(cf_fm)
                if slug not in cf_keys:
                    emit_fail(
                        f"Contributing file '{cf_rel}' does not list '{slug}' in its source_keys",
                        f"sources.md (## {slug})",
                        f"sources.md says '{cf_rel}' was informed by '{slug}', but '{cf_rel}' does not declare '{slug}' in its top-level source_keys.",
                        f"Add '{slug}' to the top-level source_keys frontmatter in '{cf_rel}'."
                    )

    # Check 5: Research doc field required
    rd_value = parse_research_doc(sources_content, slug)
    if rd_value is None:
        emit_fail(
            "Research doc field missing",
            f"sources.md (## {slug})",
            f"The '## {slug}' entry in sources.md has no '- **Research doc:**' line.",
            f"Add '- **Research doc:** <path-or-(none)>' to the '## {slug}' entry in sources.md."
        )
    elif rd_value == "" or PLACEHOLDER_RE.search(rd_value):
        emit_fail(
            "Research doc field is empty or placeholder",
            f"sources.md (## {slug})",
            f"The '## {slug}' entry has an unfilled Research doc value.",
            "Set '- **Research doc:**' to a real path relative to repo root, or '(none)' if not applicable."
        )

print_findings()
sys.exit(1 if has_fail else 0)
PYTHON