holocron/plugins/kyberforge/.apm/skills/skill-audit/tests/validate-provenance.bats

#!/usr/bin/env bats

setup() {
    REPO_ROOT="$(cd "$BATS_TEST_DIRNAME/../../../../../../" && pwd)"
    load "$REPO_ROOT/tests/test_helper/bats-support/load"
    load "$REPO_ROOT/tests/test_helper/bats-assert/load"

    SCRIPT="$(cd "$BATS_TEST_DIRNAME/../scripts" && pwd)/validate-provenance.sh"
    TMPDIR="$(mktemp -d)"

    # Helper: create a minimal skill directory with no sources.md and no source_keys
    make_clean_skill() {
        local dir="$1"
        local name
        name="$(basename "$dir")"
        mkdir -p "$dir"
        cat > "$dir/SKILL.md" <<EOF
---
name: $name
description: A valid skill description.
---

## Step 1

Do the thing.
EOF
    }

    # Helper: create a skill with source_keys in SKILL.md
    make_skill_with_source_keys() {
        local dir="$1"
        local name
        name="$(basename "$dir")"
        mkdir -p "$dir"
        cat > "$dir/SKILL.md" <<EOF
---
name: $name
description: A valid skill description.
metadata:
  source_keys:
    - my-source
---

## Step 1

Do the thing.
EOF
    }

    # Helper: create a valid sources.md with one entry
    make_sources_md() {
        local dir="$1"
        local slug="${2:-my-source}"
        local contrib="${3:-SKILL.md}"
        local research="${4:-(none)}"
        mkdir -p "$dir/references"
        cat > "$dir/references/sources.md" <<EOF
# Sources

## ${slug}

- **URL:** https://example.com/${slug}
- **Description:** A test source.
- **Contributing files:** ${contrib}
- **Research doc:** ${research}
- **Status:** \`extracted\`
EOF
    }

    # Helper: create a fake repo (a .git marker makes find_repo_root stop there)
    # holding one skill whose single sources.md slug points at the given
    # Research doc value. Checks 7 and 8 only run for a skill inside a checkout,
    # so every upstream case needs this shape; the research doc itself is
    # written per test into "$repo/docs/research/sources.md".
    make_upstream_skill() {
        local repo="$1"
        local research="${2:-docs/research/sources.md}"
        local skill="$repo/my-skill"
        mkdir -p "$skill/references" "$repo/docs/research"
        touch "$repo/.git"
        cat > "$skill/SKILL.md" <<EOF
---
name: my-skill
description: A valid skill description.
metadata:
  source_keys:
    - my-source
---

## Step 1

Do the thing.
EOF
        cat > "$skill/references/sources.md" <<EOF
# Sources

## my-source

- **URL:** https://example.com/my-source
- **Description:** A test source.
- **Contributing files:** SKILL.md
- **Research doc:** ${research}
- **Status:** \`extracted\`
EOF
    }
}

teardown() {
    rm -rf "$TMPDIR"
}

# ---------------------------------------------------------------------------
# Cycle 1 — --help
# ---------------------------------------------------------------------------

@test "--help exits 0" {
    run bash "$SCRIPT" --help
    assert_success
    assert_output --partial "Usage:"
}

# ---------------------------------------------------------------------------
# Cycle 2 — Early exit: no sources.md, no source_keys → exit 0, no output
# ---------------------------------------------------------------------------

@test "clean pass: no sources.md and no source_keys anywhere → exit 0, no output" {
    local skill="$TMPDIR/my-skill"
    make_clean_skill "$skill"
    run bash "$SCRIPT" "$skill"
    assert_success
    assert_output ""
}

# ---------------------------------------------------------------------------
# Cycle 3 — Check 0: source_keys present but no sources.md → FAIL
# ---------------------------------------------------------------------------

@test "FAIL: source_keys in SKILL.md but sources.md absent" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "FAIL"
}

# ---------------------------------------------------------------------------
# Cycle 4 — Check 1: FILL IN: placeholder in sources.md → FAIL
# ---------------------------------------------------------------------------

@test "FAIL: FILL IN: placeholder in sources.md" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    mkdir -p "$skill/references"
    cat > "$skill/references/sources.md" <<EOF
# Sources

## my-source

- **URL:** FILL IN: add url
- **Description:** A test source.
- **Contributing files:** SKILL.md
- **Research doc:** (none)
- **Status:** \`extracted\`
EOF
    run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "FAIL"
}

@test "FILL IN: inside backticks in sources.md does not fail" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill"
    echo "Use \`FILL IN: value\` as example." >> "$skill/references/sources.md"
    run bash "$SCRIPT" "$skill"
    assert_success
}

# ---------------------------------------------------------------------------
# Cycle 5 — Check 2: source_keys slug missing from sources.md → FAIL
# ---------------------------------------------------------------------------

@test "FAIL: source_keys slug in SKILL.md not present as H2 in sources.md" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    mkdir -p "$skill/references"
    cat > "$skill/references/sources.md" <<EOF
# Sources

## different-source

- **URL:** https://example.com/different-source
- **Description:** A different source.
- **Contributing files:** SKILL.md
- **Research doc:** (none)
- **Status:** \`extracted\`
EOF
    run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "FAIL"
}

# ---------------------------------------------------------------------------
# Cycle 6 — Check 4: Contributing file path doesn't exist → FAIL
# ---------------------------------------------------------------------------

@test "FAIL: Contributing file listed in sources.md does not exist" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill" "my-source" "references/nonexistent.md"
    run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "FAIL"
}

@test "pass: (none) in Contributing files is skipped" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill" "my-source" "(none — not used directly)"
    run bash "$SCRIPT" "$skill"
    assert_success
}

# ---------------------------------------------------------------------------
# Cycle 7 — Check 6: Research doc field missing → FAIL
# ---------------------------------------------------------------------------

@test "FAIL: Research doc field missing from sources.md entry" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    mkdir -p "$skill/references"
    cat > "$skill/references/sources.md" <<EOF
# Sources

## my-source

- **URL:** https://example.com/my-source
- **Description:** A test source.
- **Contributing files:** SKILL.md
- **Status:** \`extracted\`
EOF
    run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "FAIL"
}

@test "FAIL: Research doc field is FILL IN: placeholder" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    mkdir -p "$skill/references"
    cat > "$skill/references/sources.md" <<EOF
# Sources

## my-source

- **URL:** https://example.com/my-source
- **Description:** A test source.
- **Contributing files:** SKILL.md
- **Research doc:** FILL IN: path to research doc
- **Status:** \`extracted\`
EOF
    run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "FAIL"
}

# ---------------------------------------------------------------------------
# Cycle 8 — Check 5: Bidirectional mismatch → FAIL
# ---------------------------------------------------------------------------

@test "FAIL: Contributing file exists but does not list parent slug in source_keys" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill" "my-source" "SKILL.md"
    # SKILL.md has source_keys: my-source, but let's change it to NOT have my-source
    cat > "$skill/SKILL.md" <<EOF
---
name: my-skill
description: A valid skill description.
metadata:
  source_keys:
    - other-source
---

## Step 1

Do the thing.
EOF
    mkdir -p "$skill/references"
    cat > "$skill/references/sources.md" <<EOF
# Sources

## other-source

- **URL:** https://example.com/other-source
- **Description:** A test source.
- **Contributing files:** SKILL.md
- **Research doc:** (none)
- **Status:** \`extracted\`
EOF
    # Now add my-source that references SKILL.md but SKILL.md doesn't back-reference it
    cat >> "$skill/references/sources.md" <<EOF

## my-source

- **URL:** https://example.com/my-source
- **Description:** Another source.
- **Contributing files:** SKILL.md
- **Research doc:** (none)
- **Status:** \`extracted\`
EOF
    run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "FAIL"
}

# ---------------------------------------------------------------------------
# Cycle 9 — Check 3: references/*.md with no source_keys → INFO (exit 0)
# ---------------------------------------------------------------------------

@test "INFO: references doc with no source_keys frontmatter emits INFO but exits 0" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill"
    mkdir -p "$skill/references"
    cat > "$skill/references/extra.md" <<EOF
# Extra Reference

No frontmatter here.
EOF
    run bash "$SCRIPT" "$skill"
    assert_success
    assert_output --partial "INFO"
}

@test "pass: references doc with source_keys all matching sources.md exits 0" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill"
    mkdir -p "$skill/references"
    cat > "$skill/references/extra.md" <<EOF
---
source_keys:
  - my-source
---

# Extra Reference

Content here.
EOF
    run bash "$SCRIPT" "$skill"
    assert_success
}

# ---------------------------------------------------------------------------
# Cycle 10 — Clean full pass: valid sources.md, all source_keys match, files exist
# ---------------------------------------------------------------------------

@test "clean full pass: all checks satisfied" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill"
    run bash "$SCRIPT" "$skill"
    assert_success
}

# ---------------------------------------------------------------------------
# Cycle 11 — Check 7: Upstream forward: slug in sources.md not in research doc → INFO
# ---------------------------------------------------------------------------

@test "INFO: slug in sources.md not found in research doc → INFO, exits 0" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"

    # Create a research doc that does NOT have the slug
    local research_dir="$TMPDIR/research"
    mkdir -p "$research_dir"
    cat > "$research_dir/sources.md" <<EOF
# Research

## different-slug

- **Contributing files:** (none)
- **Status:** \`extracted\`
EOF

    # Use a path relative to repo root — we'll place research doc inside TMPDIR
    # and reference it as absolute for test purposes.
    # The script finds repo root by walking up from skill-dir until .git is found.
    # Since TMPDIR won't have .git, we simulate a repo structure.
    local fake_repo="$TMPDIR/fakerepo"
    mkdir -p "$fake_repo"
    touch "$fake_repo/.git"  # fake .git marker

    local skill2="$fake_repo/my-skill"
    mkdir -p "$skill2"
    cat > "$skill2/SKILL.md" <<EOF
---
name: my-skill
description: A valid skill description.
metadata:
  source_keys:
    - my-source
---

## Step 1

Do the thing.
EOF

    mkdir -p "$skill2/references"
    mkdir -p "$fake_repo/docs/research"
    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Research

## different-slug

- **Contributing files:** (none)
- **Status:** \`extracted\`
EOF

    cat > "$skill2/references/sources.md" <<EOF
# Sources

## my-source

- **URL:** https://example.com/my-source
- **Description:** A test source.
- **Contributing files:** SKILL.md
- **Research doc:** docs/research/sources.md
- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$skill2"
    assert_success
    assert_output --partial "INFO"
}

# ---------------------------------------------------------------------------
# Cycle 12 — Check 8: Upstream reverse: extracted slug in research doc not in sources.md → FAIL
# ---------------------------------------------------------------------------

@test "FAIL: extracted non-(none) slug in research doc missing from skill sources.md" {
    local fake_repo="$TMPDIR/fakerepo"
    mkdir -p "$fake_repo"
    touch "$fake_repo/.git"

    local skill="$fake_repo/my-skill"
    mkdir -p "$skill"
    cat > "$skill/SKILL.md" <<EOF
---
name: my-skill
description: A valid skill description.
metadata:
  source_keys:
    - my-source
---

## Step 1

Do the thing.
EOF

    mkdir -p "$skill/references"
    mkdir -p "$fake_repo/docs/research"

    # Research doc has my-source (extracted, with a contributing file) AND extra-source (also extracted)
    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Research

## my-source

- **Contributing files:** some-skill/SKILL.md
- **Status:** \`extracted\`

## extra-source

- **Contributing files:** some-skill/references/extra.md
- **Status:** \`extracted\`
EOF

    cat > "$skill/references/sources.md" <<EOF
# Sources

## my-source

- **URL:** https://example.com/my-source
- **Description:** A test source.
- **Contributing files:** SKILL.md
- **Research doc:** docs/research/sources.md
- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "FAIL"
}

@test "pass: extracted slug in research doc with (none) contributing files is not required in sources.md" {
    local fake_repo="$TMPDIR/fakerepo"
    mkdir -p "$fake_repo"
    touch "$fake_repo/.git"

    local skill="$fake_repo/my-skill"
    mkdir -p "$skill"
    cat > "$skill/SKILL.md" <<EOF
---
name: my-skill
description: A valid skill description.
metadata:
  source_keys:
    - my-source
---

## Step 1

Do the thing.
EOF

    mkdir -p "$skill/references"
    mkdir -p "$fake_repo/docs/research"

    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Research

## my-source

- **Contributing files:** some-skill/SKILL.md
- **Status:** \`extracted\`

## extra-source

- **Contributing files:** (none — not relevant)
- **Status:** \`extracted\`
EOF

    cat > "$skill/references/sources.md" <<EOF
# Sources

## my-source

- **URL:** https://example.com/my-source
- **Description:** A test source.
- **Contributing files:** SKILL.md
- **Research doc:** docs/research/sources.md
- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$skill"
    assert_success
}

# ---------------------------------------------------------------------------
# Cycle 13 — parse_contributing_files: None ("could not parse") is NOT []
#            ("explicitly (none)")
#
# Check 8 reads [] as "the research doc deliberately records no contributing
# files" and SKIPS the slug on that basis. A block the parser cannot read must
# therefore return None, so the slug stays exposed to check 8. Each case below
# asserts that CONSEQUENCE — check 8 firing on the unreadable entry — not the
# parser's return value, because returning [] is exactly the shape that makes
# the check silently do nothing while still exiting 0.
# ---------------------------------------------------------------------------

@test "check 8 runs: bullet form with '*' asterisk bullets is unparsable, not '(none)'" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo"

    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Research

## my-source

- **Contributing files:** some-skill/SKILL.md
- **Status:** \`extracted\`

## extra-source

**Contributing files:**
* some-skill/references/extra.md

- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_failure
    assert_output --partial "FAIL"
    assert_output --partial "extra-source"
}

@test "check 8 runs: bullet form with a numbered list is unparsable, not '(none)'" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo"

    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Research

## my-source

- **Contributing files:** some-skill/SKILL.md
- **Status:** \`extracted\`

## extra-source

**Contributing files:**
1. some-skill/references/extra.md

- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_failure
    assert_output --partial "FAIL"
    assert_output --partial "extra-source"
}

@test "check 8 runs: bullet form followed by prose is unparsable, not '(none)'" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo"

    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Research

## my-source

- **Contributing files:** some-skill/SKILL.md
- **Status:** \`extracted\`

## extra-source

**Contributing files:**
See the table below for the file list.

- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_failure
    assert_output --partial "FAIL"
    assert_output --partial "extra-source"
}

@test "check 8 runs: bullet form heading with a blank line and nothing after is unparsable, not '(none)'" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo"

    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Research

## my-source

- **Contributing files:** some-skill/SKILL.md
- **Status:** \`extracted\`

## extra-source

- **Status:** \`extracted\`

**Contributing files:**

EOF

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_failure
    assert_output --partial "FAIL"
    assert_output --partial "extra-source"
}

@test "check 8 runs: inline form whose whole value is a parenthetical is unparsable, not '(none)'" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo"

    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Research

## my-source

- **Contributing files:** some-skill/SKILL.md
- **Status:** \`extracted\`

## extra-source

- **Contributing files:** (see notes below)
- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_failure
    assert_output --partial "FAIL"
    assert_output --partial "extra-source"
}

@test "check 4 runs: bullet form with '-' hyphen bullets still parses each path" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    mkdir -p "$skill/references"
    cat > "$skill/references/sources.md" <<EOF
# Sources

## my-source

- **URL:** https://example.com/my-source
- **Description:** A test source.

**Contributing files:**
- SKILL.md (the dispatch table, with a comma in the note)
- references/nonexistent.md (why this one matters)

- **Research doc:** (none)
- **Status:** \`extracted\`
EOF
    run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "Contributing file 'references/nonexistent.md' does not exist"
}

@test "check 4 runs: inline comma-separated form still parses each path" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill" "my-source" "SKILL.md, references/nonexistent.md"
    run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "Contributing file 'references/nonexistent.md' does not exist"
}

@test "check 8 skips: bullet form '- (none)' is an explicit declaration" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo"

    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Research

## my-source

- **Contributing files:** some-skill/SKILL.md
- **Status:** \`extracted\`

## extra-source

**Contributing files:**
- (none — nothing was extracted from this section)

- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_success
}

@test "check 8 skips: inline bare '(none)' is an explicit declaration" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo"

    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Research

## my-source

- **Contributing files:** some-skill/SKILL.md
- **Status:** \`extracted\`

## extra-source

- **Contributing files:** (none)
- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_success
}

# ---------------------------------------------------------------------------
# Cycle 14 — Check 3 (#111): an explicit 'source_keys: []' is a house-authored
#            declaration, a bare 'source_keys:' is truncation
#
# Three states, three outcomes. Only the middle one — declared empty — is
# silent; collapsing any pair of them is the defect #111 filed.
# ---------------------------------------------------------------------------

@test "check 3 silent: references doc with top-level 'source_keys: []' emits nothing" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill"
    cat > "$skill/references/extra.md" <<EOF
---
source_keys: []
---

# Extra Reference

House-authored, no external source.
EOF
    run bash "$SCRIPT" "$skill"
    assert_success
    assert_output ""
}

@test "check 3 silent: references doc with 'source_keys: []' nested under metadata: emits nothing" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill"
    cat > "$skill/references/extra.md" <<EOF
---
metadata:
  source_keys: []
---

# Extra Reference

House-authored, no external source.
EOF
    run bash "$SCRIPT" "$skill"
    assert_success
    assert_output ""
}

@test "INFO: references doc with a bare 'source_keys:' and no value still emits INFO" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill"
    cat > "$skill/references/extra.md" <<EOF
---
source_keys:
---

# Extra Reference

Truncated frontmatter — this is not a decision.
EOF
    run bash "$SCRIPT" "$skill"
    assert_success
    assert_output --partial "INFO"
    assert_output --partial "No source_keys frontmatter"
}

@test "INFO: references doc with frontmatter but no source_keys key still emits INFO" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill"
    cat > "$skill/references/extra.md" <<EOF
---
title: Extra Reference
---

# Extra Reference

Never said either way.
EOF
    run bash "$SCRIPT" "$skill"
    assert_success
    assert_output --partial "INFO"
    assert_output --partial "No source_keys frontmatter"
}

# ---------------------------------------------------------------------------
# Cycle 15 — Checks 7 and 8: Research doc annotation stripping, and the INFO
#            that replaced the silent skip
#
# A Research doc value is very often a path PLUS a section annotation, and
# os.path.isfile() is false for every such string. Before the strip, checks 7
# and 8 skipped SILENTLY on those — so the negative assertions here (an INFO
# that must appear) are what distinguishes a running check from a dead one.
# ---------------------------------------------------------------------------

@test "check 7 runs: '§' section annotation is stripped before the path is resolved" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo" 'docs/research/sources.md § "Some Section"'

    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Research

## different-slug

- **Contributing files:** (none)
- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_success
    assert_output --partial "Slug 'my-source' not found as H2 in research doc 'docs/research/sources.md'"
    refute_output --partial "§"
}

@test "check 7 runs: '→' section annotation is stripped before the path is resolved" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo" 'docs/research/sources.md → `## Pushing`'

    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Research

## different-slug

- **Contributing files:** (none)
- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_success
    assert_output --partial "Slug 'my-source' not found as H2 in research doc 'docs/research/sources.md'"
    refute_output --partial "→"
}

@test "check 7 runs: parenthetical annotation is stripped before the path is resolved" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo" "docs/research/sources.md (whole-document reference)"

    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Research

## different-slug

- **Contributing files:** (none)
- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_success
    assert_output --partial "Slug 'my-source' not found as H2 in research doc 'docs/research/sources.md'"
    refute_output --partial "whole-document reference"
}

@test "check 7 runs: a bare path with no annotation survives the strip intact" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo" "docs/research/sources.md"

    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Research

## my-source

- **Contributing files:** (none)
- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_success
    assert_output ""
}

@test "checks 7 and 8 skipped silently: Research doc '(none)' is recognised before the strip" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo" "(none)"

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_success
    assert_output ""
}

@test "checks 7 and 8 skipped silently: bare 'none — reason' is recognised as a declaration" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo" "none — org convention, no upstream research doc"

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_success
    assert_output ""
}

@test "INFO: a stripped path that does not resolve names the slug instead of skipping silently" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo" 'docs/research/missing.md § "Some Section"'

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_success
    assert_output --partial "INFO"
    assert_output --partial "Upstream checks skipped for 'my-source' — research doc 'docs/research/missing.md' does not exist"
}

@test "INFO: a Research doc value that is entirely annotation names the slug instead of skipping silently" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo" '§ "Some Section"'

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_success
    assert_output --partial "INFO"
    assert_output --partial "Upstream checks skipped for 'my-source' — Research doc value names no path"
}

@test "INFO: no repo root above the skill directory names the slug instead of skipping silently" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill" "my-source" "SKILL.md" "docs/research/sources.md"

    run bash "$SCRIPT" "$skill"
    assert_success
    assert_output --partial "INFO"
    assert_output --partial "Upstream checks skipped for 'my-source' — no repo root above the skill directory"
}

# ---------------------------------------------------------------------------
# Cycle 16 — Checks 4 and 5: None ("could not parse") is NOT [] ("explicitly
#            (none)"), on the sources.md side this time
#
# Cycle 13 pinned the distinction for check 8, which reads the parser's output
# against a RESEARCH doc. Checks 4 and 5 read it against the skill's own
# sources.md and honoured neither half: a truthiness test collapsed None into
# [], so an unreadable Contributing files block disabled both checks and the
# script still exited 0 with no output — the failure mode
# parse_contributing_files' docstring names in as many words. The assertions
# below are therefore about the INFO appearing; a silent exit 0 is exactly the
# bug.
# ---------------------------------------------------------------------------

@test "INFO: an unparsable Contributing files block names the slug instead of skipping checks 4 and 5 silently" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    mkdir -p "$skill/references"
    cat > "$skill/references/sources.md" <<EOF
# Sources

## my-source

- **URL:** https://example.com/my-source
- **Description:** A test source.
- **Research doc:** (none)
**Contributing files:**
* references/ghost.md (asterisk bullets are not the bullet form)
- **Status:** \`extracted\`
EOF
    run bash "$SCRIPT" "$skill"
    assert_success
    assert_output --partial "INFO"
    assert_output --partial "Contributing-file checks skipped for 'my-source' — the Contributing files block could not be parsed"
}

@test "INFO: an entry with no Contributing files field at all is reported, not skipped silently" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    mkdir -p "$skill/references"
    cat > "$skill/references/sources.md" <<EOF
# Sources

## my-source

- **URL:** https://example.com/my-source
- **Description:** A test source.
- **Research doc:** (none)
- **Status:** \`extracted\`
EOF
    run bash "$SCRIPT" "$skill"
    assert_success
    assert_output --partial "INFO"
    assert_output --partial "Contributing-file checks skipped for 'my-source' — the Contributing files block could not be parsed"
}

@test "checks 4 and 5 skipped silently: an explicit '(none)' emits no INFO" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill" "my-source" "(none — not used directly)"
    run bash "$SCRIPT" "$skill"
    assert_success
    assert_output ""
}

@test "checks 4 and 5 still run: a parseable Contributing files list is not diverted to the INFO" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill" "my-source" "references/nonexistent.md"
    run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "FAIL"
    assert_output --partial "Contributing file 'references/nonexistent.md' does not exist"
    refute_output --partial "could not be parsed"
}

# ---------------------------------------------------------------------------
# Cycle 17 — Check 3 (#111): 'source_keys: []' only declares anything in the
#            two positions parse_source_keys() actually reads
#
# The declaration and the parse have to agree on WHERE the key lives. They did
# not: the declaration regex accepted any indent, so a `source_keys: []` buried
# under an unrelated key — a position parse_source_keys() never reads — passed
# as a house-authored declaration and silenced the INFO for a file that had
# declared nothing.
# ---------------------------------------------------------------------------

@test "INFO: 'source_keys: []' nested under an unrelated key is not a declaration" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill"
    cat > "$skill/references/extra.md" <<EOF
---
title: Extra Reference
unrelated:
  nested:
      source_keys: []
---

# Extra Reference

The empty list is nested where parse_source_keys never looks.
EOF
    run bash "$SCRIPT" "$skill"
    assert_success
    assert_output --partial "INFO"
    assert_output --partial "No source_keys frontmatter"
}

@test "INFO: a four-space-indented 'source_keys: []' is not a declaration either" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill"
    cat > "$skill/references/extra.md" <<EOF
---
metadata:
    source_keys: []
---

# Extra Reference

Two spaces is the position parse_source_keys reads under metadata:, not four.
EOF
    run bash "$SCRIPT" "$skill"
    assert_success
    assert_output --partial "INFO"
    assert_output --partial "No source_keys frontmatter"
}

# ---------------------------------------------------------------------------
# Cycle 20 — F: checks 7 and 8 apply only to a research SOURCE INDEX, and
# every skip announces itself
# ---------------------------------------------------------------------------

@test "F: a topic-doc Research doc is reported as not applicable, not as a missing slug" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo" "docs/research/remotes.md"
    cat > "$fake_repo/docs/research/remotes.md" <<EOF
# Remotes

## Core Philosophy

Prose about remotes.
EOF

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_success
    assert_output --partial "Upstream checks not applicable for 'my-source'"
    assert_output --partial "is a topic document, not a source index"
    refute_output --partial "not found as H2 in research doc"
}

@test "F: check 7 still runs when the Research doc IS a source index" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo"
    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Sources

## different-slug

- **Contributing files:** (none)
- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_success
    assert_output --partial "Slug 'my-source' not found as H2 in research doc 'docs/research/sources.md'"
    refute_output --partial "not applicable"
}

@test "F: check 8 announces the slug it skipped for a non-extracted Status" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo"
    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Sources

## my-source

- **Contributing files:** some-skill/SKILL.md
- **Status:** \`extracted\`

## extra-source

- **Contributing files:** some-skill/references/extra.md
- **Status:** \`referenced\`
EOF

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_success
    assert_output --partial "Check 8 skipped for research-doc slug 'extra-source'"
    assert_output --partial "its Status is \`referenced\`, not \`extracted\`"
}

@test "F: a Status with a trailing note after the backticked value still reads as extracted" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo"
    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Sources

## my-source

- **Contributing files:** some-skill/SKILL.md
- **Status:** \`extracted\`

## extra-source

- **Contributing files:** some-skill/references/extra.md
- **Status:** \`extracted\` — partial fetch, section 3 only
EOF

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_failure
    assert_output --partial "Research doc slug 'extra-source' missing from skill sources.md"
}

@test "F: a bullet-form Status still reads as extracted" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo"
    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Sources

## my-source

- **Contributing files:** some-skill/SKILL.md
- **Status:** \`extracted\`

## extra-source

- **Contributing files:** some-skill/references/extra.md

**Status:**
- \`extracted\`
EOF

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_failure
    assert_output --partial "Research doc slug 'extra-source' missing from skill sources.md"
}

@test "F: a research-doc slug with no Status line at all is announced, not skipped silently" {
    local fake_repo="$TMPDIR/fakerepo"
    make_upstream_skill "$fake_repo"
    cat > "$fake_repo/docs/research/sources.md" <<EOF
# Sources

## my-source

- **Contributing files:** some-skill/SKILL.md
- **Status:** \`extracted\`

## extra-source

- **Contributing files:** some-skill/references/extra.md
EOF

    run bash "$SCRIPT" "$fake_repo/my-skill"
    assert_success
    assert_output --partial "Check 8 skipped for research-doc slug 'extra-source'"
    assert_output --partial "its Status is absent, not \`extracted\`"
}

# ---------------------------------------------------------------------------
# Cycle 21 — G1: a bad target is a hard error, not a silent pass
# ---------------------------------------------------------------------------

@test "G1: a nonexistent directory is a hard error (exit 2), not a silent exit 0" {
    run bash "$SCRIPT" "$TMPDIR/does-not-exist"
    [ "$status" -eq 2 ]
    assert_output --partial "not a directory"
}

@test "G1: a directory with no SKILL.md is a hard error (exit 2), not a silent exit 0" {
    mkdir -p "$TMPDIR/not-a-skill/references"
    run bash "$SCRIPT" "$TMPDIR/not-a-skill"
    [ "$status" -eq 2 ]
    assert_output --partial "not a skill directory"
}

# ---------------------------------------------------------------------------
# Cycle 22 — G2: a UTF-8 BOM does not disable check 2
# ---------------------------------------------------------------------------

@test "G2: a BOM at the head of SKILL.md does not silently disable check 2" {
    local skill="$TMPDIR/my-skill"
    mkdir -p "$skill/references"
    printf '\xef\xbb\xbf' > "$skill/SKILL.md"
    cat >> "$skill/SKILL.md" <<EOF
---
name: my-skill
description: A valid skill description.
metadata:
  source_keys:
    - my-source
---

## Step 1

Do the thing.
EOF
    cat > "$skill/references/sources.md" <<EOF
# Sources

## different-source

- **URL:** https://example.com/different-source
- **Description:** A test source.
- **Contributing files:** references/sources.md
- **Research doc:** (none)
- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "source_keys slug 'my-source' not found in sources.md"
}

# ---------------------------------------------------------------------------
# Cycle 23 — G3: reads are UTF-8 and an unreadable file is a finding
# ---------------------------------------------------------------------------

@test "G3: an em dash under LC_ALL=C is read, not turned into a traceback or a silent pass" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill"
    cat > "$skill/references/topic.md" <<EOF
---
source_keys:
  - ghost-source
---

Prose — with an em dash.
EOF

    LC_ALL=C PYTHONUTF8=0 PYTHONCOERCECLOCALE=0 run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "source_keys slug 'ghost-source' not found in sources.md"
    refute_output --partial "Traceback"
}

@test "G3: a file that is genuinely not UTF-8 is a FAIL, not a clean pass" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill"
    printf -- '---\nsource_keys:\n  - my-source\n---\n\nLatin-1 byte: \xe9\n' \
        > "$skill/references/topic.md"

    run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "not valid UTF-8"
    assert_output --partial "references/topic.md"
}

# ---------------------------------------------------------------------------
# Cycle 24 — G4: check 3 walks references/ recursively
# ---------------------------------------------------------------------------

@test "G4: a source_keys file in references/<subdir>/ is validated, not skipped" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill"
    mkdir -p "$skill/references/nested"
    cat > "$skill/references/nested/topic.md" <<EOF
---
source_keys:
  - ghost-source
---

Nested prose.
EOF

    run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "source_keys slug 'ghost-source' not found in sources.md"
    assert_output --partial "references/nested/topic.md"
}

# ---------------------------------------------------------------------------
# Cycle 25 — G5: a placeholder at end of line is still a placeholder
# ---------------------------------------------------------------------------

@test "G5: 'FILL IN:' at end of line is caught by check 1" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    mkdir -p "$skill/references"
    cat > "$skill/references/sources.md" <<EOF
# Sources

## my-source

- **URL:** https://example.com/my-source
- **Description:** FILL IN:
- **Contributing files:** SKILL.md
- **Research doc:** (none)
- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "Unfilled FILL IN: placeholder"
}

@test "G5: a Research doc value that is a bare 'FILL IN:' is caught by check 6" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    make_sources_md "$skill" "my-source" "SKILL.md" "FILL IN:"
    run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "Research doc field is empty or placeholder"
}

# ---------------------------------------------------------------------------
# Cycle 26 — G6/G7: duplicated entries and duplicated fields are announced
# ---------------------------------------------------------------------------

@test "G6: a duplicate '## slug' block is announced, not half-checked in silence" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    mkdir -p "$skill/references"
    cat > "$skill/references/sources.md" <<EOF
# Sources

## my-source

- **URL:** https://example.com/my-source
- **Description:** A test source.
- **Contributing files:** SKILL.md
- **Research doc:** (none)
- **Status:** \`extracted\`

## my-source

- **URL:** https://example.com/my-source-again
- **Description:** The same slug a second time.
- **Contributing files:** references/nonexistent.md
- **Research doc:** (none)
- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$skill"
    assert_success
    assert_output --partial "Duplicate '## my-source' entry in sources.md"
    assert_output --partial "only the first block is checked"
}

@test "G7: a second '- **Research doc:**' line in one entry is announced" {
    local skill="$TMPDIR/my-skill"
    make_skill_with_source_keys "$skill"
    mkdir -p "$skill/references"
    cat > "$skill/references/sources.md" <<EOF
# Sources

## my-source

- **URL:** https://example.com/my-source
- **Description:** A test source.
- **Contributing files:** SKILL.md
- **Research doc:** (none)
- **Research doc:** docs/research/sources.md
- **Status:** \`extracted\`
EOF

    run bash "$SCRIPT" "$skill"
    assert_success
    assert_output --partial "Multiple '- **Research doc:**' lines for 'my-source'"
}

# ---------------------------------------------------------------------------
# Cycle 27 — G8: usage and environment errors exit 2, never 1
# ---------------------------------------------------------------------------

@test "G8: a missing argument exits 2, not 1" {
    run bash "$SCRIPT"
    [ "$status" -eq 2 ]
    assert_output --partial "skill-dir is required"
}

@test "G8: an extra positional argument is rejected, not silently ignored" {
    local skill="$TMPDIR/my-skill"
    make_clean_skill "$skill"
    run bash "$SCRIPT" "$skill" extra
    [ "$status" -eq 2 ]
    assert_output --partial "expected exactly one argument"
}

@test "G8: a missing python3 is reported by name and exits 2, not 127" {
    local skill="$TMPDIR/my-skill"
    make_clean_skill "$skill"
    local stub="$TMPDIR/emptybin"
    mkdir -p "$stub"
    for cmd in bash cat sed; do
        ln -s "$(command -v "$cmd")" "$stub/$cmd"
    done
    PATH="$stub" run bash "$SCRIPT" "$skill"
    [ "$status" -eq 2 ]
    assert_output --partial "python3 is required"
}

@test "G3: an unreadable file is reported even when there is nothing else to validate" {
    local skill="$TMPDIR/my-skill"
    make_clean_skill "$skill"
    mkdir -p "$skill/references"
    printf -- '---\nsource_keys:\n  - my-source\n---\n\nLatin-1 byte: \xe9\n' \
        > "$skill/references/topic.md"

    run bash "$SCRIPT" "$skill"
    assert_failure
    assert_output --partial "not valid UTF-8"
}