feat(tests): update docs

Statistics: 6 files changed, 179 insertions, 27 deletions

Summary:
- Dirs: .=2, src=2, tests=2
- Exts: .py=4, .md=1, .lock=1
- A/M/D: 0/6/0
- Symbols: test_code2llm_analysis_emits_refactor_items, _scan_code2llm_analysis, test_code2llm_analysis_emits_dup_ticket, test_code2llm_analysis_emits_cc_ticket

Modified files:
- README.md (+4/-4)
- src/koru/autonomous.py (+23/-2)
- src/koru/scan.py (+112/-18)
- tests/test_autonomous.py (+1/-0)
- tests/test_scan.py (+38/-2)
- uv.lock (+1/-1)

Changes (notes):
- README.md (+4/-4): update documentation
- src/koru/autonomous.py (+23/-2): update
- src/koru/scan.py (+112/-18): update
- tests/test_autonomous.py (+1/-0): update
- tests/test_scan.py (+38/-2): add functions: test_code2llm_analysis_emits_cc_ticket, test_code2llm_analysis_emits_dup_ticket, test_code2llm_analysis_emits_refactor_items
- uv.lock (+1/-1): update

Implementation notes (heuristics):
- Type inferred from file paths + diff keywords + add/delete ratio
- Scope prefers 'goal' when goal/* is touched; otherwise based on top-level dirs
- For <=6 files: generate short per-file notes from added lines (defs/classes/click options/headings)
- A/M/D derived from git name-status; per-file +X/-X from git numstat

Author: tom-sapletta-com

CHANGELOG.md

@@ -74,6 +74,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   `quality:regix` ↔ `gate:regix`, `quality:redup*` ↔ `gate:redup`,
   `quality:sumr:*` ↔ `gate:sumr`.
 
+## [0.1.61] - 2026-05-12
+
+### Docs
+- Update README.md
+
+### Test
+- Update tests/test_autonomous.py
+- Update tests/test_scan.py
+
+### Other
+- Update uv.lock
+
 ## [0.1.60] - 2026-05-12
 
 ### Docs

README.md

@@ -4,11 +4,11 @@
 
 ## AI Cost Tracking
 
-![PyPI](https://img.shields.io/badge/pypi-costs-blue) ![Version](https://img.shields.io/badge/version-0.1.60-blue) ![Python](https://img.shields.io/badge/python-3.9+-blue) ![License](https://img.shields.io/badge/license-Apache--2.0-green)
-![AI Cost](https://img.shields.io/badge/AI%20Cost-$3.42-orange) ![Human Time](https://img.shields.io/badge/Human%20Time-27.2h-blue) ![Model](https://img.shields.io/badge/Model-openrouter%2Fqwen%2Fqwen3--coder--next-lightgrey)
+![PyPI](https://img.shields.io/badge/pypi-costs-blue) ![Version](https://img.shields.io/badge/version-0.1.61-blue) ![Python](https://img.shields.io/badge/python-3.9+-blue) ![License](https://img.shields.io/badge/license-Apache--2.0-green)
+![AI Cost](https://img.shields.io/badge/AI%20Cost-$3.34-orange) ![Human Time](https://img.shields.io/badge/Human%20Time-27.9h-blue) ![Model](https://img.shields.io/badge/Model-openrouter%2Fqwen%2Fqwen3--coder--next-lightgrey)
 
-- 🤖 **LLM usage:** $3.4184 (84 commits)
-- 👤 **Human dev:** ~$2718 (27.2h @ $100/h, 30min dedup)
+- 🤖 **LLM usage:** $3.3440 (85 commits)
+- 👤 **Human dev:** ~$2795 (27.9h @ $100/h, 30min dedup)
 
 Generated on 2026-05-12 using [openrouter/qwen/qwen3-coder-next](https://openrouter.ai/qwen/qwen3-coder-next)
 

VERSION

@@ -1 +1 @@
-0.1.60
+0.1.61

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "koru"
-version = "0.1.60"
+version = "0.1.61"
 description = "Closed-loop automation across semcod/* repositories."
 readme = "README.md"
 requires-python = ">=3.12"

src/koru/autonomous.py

@@ -159,11 +159,28 @@ def _build_parser() -> argparse.ArgumentParser:
         action="store_true",
         help="Force `koru --init` re-initialization if project is already initialized.",
     )
+    up.add_argument(
+        "--semcod-artifacts",
+        action="store_true",
+        default=None,
+        help=(
+            "Include semcod quality artifacts in `koru scan` "
+            "(jscpd, code2llm/SUMR refactor analysis, testql export, redup). "
+            "Enabled by default in autonomous mode."
+        ),
+    )
+    up.add_argument(
+        "--no-semcod-artifacts",
+        dest="semcod_artifacts",
+        action="store_false",
+        help="Disable semcod artifact scanning.",
+    )
     up.set_defaults(
         submit=True,
         enable_autopilot=True,
         enable_serve=True,
         stop_on_waiting_input=True,
+        semcod_artifacts=True,
     )
 
     return parser
@@ -217,12 +234,15 @@ def _run_cycle(
     autopilot_ide: str,
     drive_prompt: str,
     submit: bool,
+    include_semcod_artifacts: bool | None,
     client: AutopilotClient | None,
 ) -> tuple[ScanResult | None, QueueLoopResult, str]:
     scan_result: ScanResult | None = None
     if enable_scan:
-        print("+ koru scan --apply")
-        scan_result = run_scan(project=project, apply=True)
+        print("+ koru scan --apply" + (" --semcod-artifacts" if include_semcod_artifacts else ""))
+        scan_result = run_scan(
+            project=project, apply=True, include_semcod_artifacts=include_semcod_artifacts
+        )
         print(
             f"  scan: suggestions={len(scan_result.suggestions)} "
             f"applied={len(scan_result.applied)} skipped={len(scan_result.skipped)}"
@@ -340,6 +360,7 @@ def _action_up(args: argparse.Namespace) -> int:
                 autopilot_ide=autopilot_ide,
                 drive_prompt=args.drive_prompt,
                 submit=args.submit,
+                include_semcod_artifacts=args.semcod_artifacts,
                 client=client,
             )
 

src/koru/scan.py

@@ -473,6 +473,23 @@ def _scan_jscpd_report(project: Path) -> list[Suggestion]:
     ]
 
 
+_TOON_GOD_RE = re.compile(
+    r"^\s*🔴\s+GOD\s+(?P<path>\S+)\s*=\s*(?P<loc>\d+)L,\s*(?P<classes>\d+)\s+classes?,\s*(?P<methods>\d+)m",
+    re.MULTILINE,
+)
+_TOON_CC_RE = re.compile(
+    r"^\s*🟡\s+CC\s+(?P<func>\S+)\s+CC=(?P<cc>\d+)\s+\(limit:\s*(?P<limit>\d+)\)",
+    re.MULTILINE,
+)
+_TOON_DUP_RE = re.compile(
+    r"^\s*🔴\s+DUP\s+(?P<count>\d+)\s+classes?\s+duplicated",
+    re.MULTILINE,
+)
+_TOON_REFACTOR_ITEM_RE = re.compile(
+    r"^\s*(?P<num>\d+)\.\s+(?P<desc>.+?)\s*\((?P<note>[^)]+)\)\s*$"
+)
+
+
 def _scan_code2llm_analysis(project: Path) -> list[Suggestion]:
     candidates = (
         project / "project" / "analysis.toon.yaml",
@@ -483,28 +500,105 @@ def _scan_code2llm_analysis(project: Path) -> list[Suggestion]:
     if path is None:
         return []
     try:
-        lines = path.read_text(encoding="utf-8", errors="ignore").splitlines()
+        text = path.read_text(encoding="utf-8", errors="ignore")
     except OSError:
         return []
-    god = sum(1 for ln in lines if "🔴 GOD" in ln)
-    critical = sum(1 for ln in lines if "🔴" in ln)
-    if god < 1 and critical < 8:
-        return []
     rel = str(path.relative_to(project))
-    pr = "high" if god >= 3 else "normal"
-    return [
-        Suggestion(
-            signal="code2llm_analysis",
-            title="Execute code2llm REFACTOR plan (god modules / critical)",
-            description=(
-                f"`{rel}` lists ~{god} god-module rows and {critical} critical (🔴) markers. "
-                "Work through the REFACTOR section; re-run `code2llm ./ -f toon` to refresh."
-            ),
-            priority=pr,
-            labels=("code2llm", "refactor", "scan"),
-            files=(rel,),
+
+    suggestions: list[Suggestion] = []
+
+    # --- HEALTH: DUP ---
+    dup_match = _TOON_DUP_RE.search(text)
+    if dup_match:
+        count = int(dup_match.group("count"))
+        suggestions.append(
+            Suggestion(
+                signal="code2llm_dup",
+                title=f"Remove {count} duplicated classes (code2llm analysis)",
+                description=(
+                    f"`{rel}` reports **{count}** duplicated classes. "
+                    "Extract shared helpers/modules; re-run `code2llm ./ -f toon` to refresh."
+                ),
+                priority="high",
+                labels=("code2llm", "duplication", "refactor", "scan"),
+                files=(rel,),
+            )
         )
-    ]
+
+    # --- HEALTH: GOD modules ---
+    for m in _TOON_GOD_RE.finditer(text):
+        file_path = m.group("path").strip()
+        loc = m.group("loc")
+        classes = m.group("classes")
+        methods = m.group("methods")
+        suggestions.append(
+            Suggestion(
+                signal="code2llm_god",
+                title=f"Split god module: {file_path}",
+                description=(
+                    f"`{rel}` flags `{file_path}` as a god module "
+                    f"({loc} lines, {classes} classes, {methods} methods). "
+                    "Split into focused submodules by responsibility."
+                ),
+                priority="high",
+                labels=("code2llm", "god-module", "refactor", "scan"),
+                files=(file_path, rel),
+            )
+        )
+
+    # --- HEALTH: high-CC methods ---
+    cc_seen: set[str] = set()
+    for m in _TOON_CC_RE.finditer(text):
+        func = m.group("func").strip()
+        cc = int(m.group("cc"))
+        limit = int(m.group("limit"))
+        if func in cc_seen:
+            continue
+        cc_seen.add(func)
+        suggestions.append(
+            Suggestion(
+                signal="code2llm_cc",
+                title=f"Reduce cyclomatic complexity: {func} (CC={cc}, limit={limit})",
+                description=(
+                    f"`{rel}` reports `{func}` with CC={cc} (limit={limit}). "
+                    "Extract sub-functions, simplify conditionals, or split into strategy pattern."
+                ),
+                priority="normal",
+                labels=("code2llm", "complexity", "refactor", "scan"),
+                files=(rel,),
+            )
+        )
+
+    # --- REFACTOR plan items ---
+    in_refactor = False
+    for line in text.splitlines():
+        if line.startswith("REFACTOR"):
+            in_refactor = True
+            continue
+        if in_refactor and line.startswith(("HEALTH", "PIPELINES", "LAYERS")):
+            break
+        if not in_refactor:
+            continue
+        rm = _TOON_REFACTOR_ITEM_RE.match(line)
+        if not rm:
+            continue
+        desc = rm.group("desc").strip()
+        note = rm.group("note").strip()
+        suggestions.append(
+            Suggestion(
+                signal="code2llm_refactor",
+                title=f"code2llm refactor: {desc}",
+                description=(
+                    f"REFACTOR item from `{rel}`: **{desc}** ({note}). "
+                    "Execute this refactor step; re-run `code2llm ./ -f toon` to verify."
+                ),
+                priority="normal",
+                labels=("code2llm", "refactor", "scan"),
+                files=(rel,),
+            )
+        )
+
+    return suggestions
 
 
 def _scan_testql_export(project: Path) -> list[Suggestion]:

tests/test_autonomous.py

@@ -258,6 +258,7 @@ def drive(self, *_args, **_kwargs):
         autopilot_ide="auto",
         drive_prompt="continue with the next ticket",
         submit=True,
+        include_semcod_artifacts=True,
         client=FailIfDrivenClient(),
     )
 

tests/test_scan.py

@@ -370,11 +370,47 @@ def test_code2llm_analysis_emits_when_god_rows(self) -> None:
             project = Path(tmp)
             (project / "project").mkdir()
             (project / "project" / "analysis.toon.yaml").write_text(
-                "HEALTH:\n  🔴 GOD   big.py = 900L\n",
+                "HEALTH[1]:\n  🔴 GOD   big.py = 900L, 5 classes, 16m, max CC=11\n",
                 encoding="utf-8",
             )
             out = scan_semcod_quality_artifacts(project)
-            self.assertTrue(any(s.signal == "code2llm_analysis" for s in out))
+            self.assertTrue(any(s.signal == "code2llm_god" for s in out))
+
+    def test_code2llm_analysis_emits_dup_ticket(self) -> None:
+        with tempfile.TemporaryDirectory() as tmp:
+            project = Path(tmp)
+            (project / "project").mkdir()
+            (project / "project" / "analysis.toon.yaml").write_text(
+                "HEALTH[1]:\n  🔴 DUP   28 classes duplicated\n",
+                encoding="utf-8",
+            )
+            out = scan_semcod_quality_artifacts(project)
+            self.assertTrue(any(s.signal == "code2llm_dup" for s in out))
+
+    def test_code2llm_analysis_emits_cc_ticket(self) -> None:
+        with tempfile.TemporaryDirectory() as tmp:
+            project = Path(tmp)
+            (project / "project").mkdir()
+            (project / "project" / "analysis.toon.yaml").write_text(
+                "HEALTH[1]:\n  🟡 CC    my_func CC=18 (limit:15)\n",
+                encoding="utf-8",
+            )
+            out = scan_semcod_quality_artifacts(project)
+            self.assertTrue(any(s.signal == "code2llm_cc" for s in out))
+
+    def test_code2llm_analysis_emits_refactor_items(self) -> None:
+        with tempfile.TemporaryDirectory() as tmp:
+            project = Path(tmp)
+            (project / "project").mkdir()
+            (project / "project" / "analysis.toon.yaml").write_text(
+                "REFACTOR[2]:\n"
+                "  1. rm duplicates  (-28 dup classes)\n"
+                "  2. split big.py  (god module)\n",
+                encoding="utf-8",
+            )
+            out = scan_semcod_quality_artifacts(project)
+            refactor_tickets = [s for s in out if s.signal == "code2llm_refactor"]
+            self.assertEqual(len(refactor_tickets), 2)
 
     def test_testql_export_emits_when_many_failures(self) -> None:
         with tempfile.TemporaryDirectory() as tmp: