mdengine 0.8.0__tar.gz → 0.9.0__tar.gz

{mdengine-0.8.0/src/mdengine.egg-info → mdengine-0.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mdengine
-Version: 0.8.0
+Version: 0.9.0
 Summary: Convert PDF, Office, images, audio, video, text/JSON/XML, ZIP archives, web URLs, databases, graphs, and OpenAPI specs to Markdown.
 Author: mdengine contributors
 License-Expression: MIT
@@ -43,6 +43,8 @@ Requires-Dist: paddlepaddle>=2.5.0; extra == "image-ocr"
 Requires-Dist: paddleocr>=2.7.0.3; extra == "image-ocr"
 Requires-Dist: easyocr>=1.7.0; extra == "image-ocr"
 Provides-Extra: text
+Requires-Dist: xmltodict>=0.13.0; extra == "text"
+Requires-Dist: lxml>=5.0.0; extra == "text"
 Provides-Extra: archive
 Requires-Dist: Pillow>=10.0.0; extra == "archive"
 Requires-Dist: pytesseract>=0.3.10; extra == "archive"
@@ -106,6 +108,9 @@ Requires-Dist: openapi-spec-validator>=0.7.0; extra == "openapi"
 Provides-Extra: codeflow
 Requires-Dist: networkx>=3.2.0; extra == "codeflow"
 Requires-Dist: javalang>=0.13.0; extra == "codeflow"
+Provides-Extra: codeflow-worker
+Requires-Dist: celery>=5.3.0; extra == "codeflow-worker"
+Requires-Dist: redis>=5.0.0; extra == "codeflow-worker"
 Provides-Extra: codeflow-treesitter
 Requires-Dist: tree-sitter>=0.21.0; extra == "codeflow-treesitter"
 Requires-Dist: tree-sitter-javascript>=0.21.0; extra == "codeflow-treesitter"
@@ -113,6 +118,22 @@ Requires-Dist: tree-sitter-typescript>=0.23.0; extra == "codeflow-treesitter"
 Requires-Dist: tree-sitter-cpp>=0.23.0; extra == "codeflow-treesitter"
 Provides-Extra: codeflow-clang
 Requires-Dist: clang>=16.0.0; extra == "codeflow-clang"
+Provides-Extra: codeflow-semantic
+Requires-Dist: numpy>=1.24.0; extra == "codeflow-semantic"
+Requires-Dist: scikit-learn>=1.3.0; extra == "codeflow-semantic"
+Requires-Dist: sentence-transformers>=3.0.0; extra == "codeflow-semantic"
+Provides-Extra: log
+Requires-Dist: pandas>=2.0.0; extra == "log"
+Requires-Dist: python-dateutil>=2.8.0; extra == "log"
+Requires-Dist: pyyaml>=6.0.0; extra == "log"
+Provides-Extra: log-cluster
+Requires-Dist: scikit-learn>=1.3.0; extra == "log-cluster"
+Provides-Extra: log-semantic
+Requires-Dist: numpy>=1.24.0; extra == "log-semantic"
+Requires-Dist: scikit-learn>=1.3.0; extra == "log-semantic"
+Requires-Dist: sentence-transformers>=3.0.0; extra == "log-semantic"
+Provides-Extra: log-pretty
+Requires-Dist: loguru>=0.7.0; extra == "log-pretty"
 Provides-Extra: api
 Requires-Dist: fastapi>=0.115.0; extra == "api"
 Requires-Dist: uvicorn[standard]>=0.32.0; extra == "api"
@@ -141,6 +162,8 @@ Requires-Dist: mdengine[graph]; extra == "dev"
 Requires-Dist: mdengine[openapi]; extra == "dev"
 Requires-Dist: mdengine[codeflow]; extra == "dev"
 Requires-Dist: mdengine[codeflow-treesitter]; extra == "dev"
+Requires-Dist: mdengine[log]; extra == "dev"
+Requires-Dist: mdengine[log-cluster]; extra == "dev"
 Provides-Extra: all
 Requires-Dist: pymupdf>=1.24.0; extra == "all"
 Requires-Dist: pdfplumber>=0.11.0; extra == "all"
@@ -389,19 +412,19 @@ python pdf-to-md\converter.py input.pdf out.md
 PYTHONPATH=src python pdf-to-md/converter.py input.pdf out.md
 ```
 
-### 6. Convert every file in `docs/` (strictly command-line)
+### 6. Convert every file in `example/` (strictly command-line)
 
-To process **all supported files** under the [`docs/`](docs/) folder using only the installed **`md-*`** tools (no Python snippets), use the batch driver:
+To process **all supported files** under the [`example/`](example/) folder using only the installed **`md-*`** tools (no Python snippets), use the batch driver:
 
 | Platform | Command (run from **repository root** unless noted) |
 |----------|------------------------------------------------------|
 | Windows | `powershell -ExecutionPolicy Bypass -File scripts/run-docs-cli.ps1` |
-| Windows | Or double-click / run [`docs/run-all-cli.cmd`](docs/run-all-cli.cmd) (changes to repo root, then runs the script on `docs\`) |
+| Windows | Or double-click / run [`example/run-all-cli.cmd`](example/run-all-cli.cmd) (changes to repo root, then runs the script on `example\`) |
 | macOS / Linux | `bash scripts/run-docs-cli.sh` |
 
 Optional environment variables for the shell script: `DOCS_DIR`, `OUT_DIR`, `IMAGE_ENGINES` (default `tess`). PowerShell script parameters: `-DocsDir`, `-OutDir`, `-ImageEngines`.
 
-Outputs are written to **`docs/cli-output/<basename>/`** (one subfolder per input file). **`.csv`** files are converted with **`md-xlsx`** (same engine as Excel). **`.md`** files are skipped.
+Outputs are written to **`example/cli-output/<basename>/`** (one subfolder per input file). **`.csv`** files are converted with **`md-xlsx`** (same engine as Excel). **`.md`** files are skipped.
 
 ---
 
@@ -876,6 +899,29 @@ python -m pytest
 
 Tests live under each legacy folder’s `tests/` directory (e.g. `pdf-to-md/tests/`), **`graph-to-md/tests/`**, **`openapi-to-md/tests/`**, and **[`tool-assistant/tests/`](tool-assistant/tests/)** for the skill SDK; `pyproject.toml` sets `pythonpath = ["src"]` so **`md_generator`** (including **`md_generator.tools.assistant`**) resolves without a manual `PYTHONPATH` when you use `pytest` from the config.
 
+### Codeflow (`md_generator.codeflow`)
+
+Static call graphs and per-entry Markdown/Mermaid/JSON for **Python**, **Java** (Spring REST, Kafka listeners, **Liferay / JSR-286 portlets**), and other parsers. Output is **static only** (`graph-full.json` can include unresolved `unknown::*` callees).
+
+More detail: **[`codeflow-to-md/docs/graph-and-outputs.md`](codeflow-to-md/docs/graph-and-outputs.md)** (node/edge model, `graph-schema.json`, `methods/` layout).
+
+- **Formats:** pass **`--formats md,mermaid,json,html`** (comma-separated). **`--output`** is the **output directory**, not the format list.
+- **Graph schema export:** optional **`--emit-graph-schema`** (with `json` in formats) writes **`graph-schema.json`** — stable Node/Edge view with derived File/Class nodes and `CONTAINS` edges. **`graph-full.json`** stays unchanged for existing consumers.
+- **Markdown intelligence:** flow and entry Markdown include **Called By** and **Impact** lists (capped with **`--intelligence-list-cap`**, default 80).
+- **IR / CFG (optional):** **`--emit-cfg`** builds a language-agnostic IR and writes **`cfg.json`**, **`cfg.mmd`**, and appends a CFG Mermaid block to **`flow.md`** (when `md` is in formats). Cap with **`--cfg-max-nodes`** (default 500).
+- **Entries:** use `--entry` (comma-separated symbol ids), **`--entries-file`** (one id per line, `#` comments allowed), or rely on detectors. **`--emit-entry-per-method`** emits one output directory per method/entry symbol under **`methods/<slug>/`**; cap volume with **`--emit-entry-max`** (default cap **10000** when the flag is set and max is omitted). **`--entry-fallback`** `none` \| `roots` \| `first_n` controls behavior when nothing is detected (default **`roots`**, in-degree 0 symbols, limited by **`--entry-fallback-max`**).
+- **Java flow:** edges can record **branch context** from enclosing `if`, `switch`, or ternary expressions (`condition` / `labels` on edges). **Business rules** Markdown picks up validation-style **`@NotNull`** / **`@Size`** / **`@Valid`** (name heuristics) and throws such as **`IllegalArgumentException`**.
+- **JavaScript / TypeScript / TSX:** Tree-sitter adds **`condition_label`** from enclosing control flow, **`fr.branches`** for `if` / `switch`, and **`fr.rules`** for **`throw`** and common **`assert` / `console.assert`** calls (slice-scoped in the collector).
+- **C++ (tree-sitter path):** **`condition_label`** on calls, **`fr.branches`** for `if` / `switch`, plus **`rules/cpp_rules.py`** for **`throw`** / **`assert`** when methods appear in the slice. (Clang-only parses still get throw/assert via the same extractor when tree-sitter is installed.)
+- **Go:** the **`codeflow_go_dump`** helper emits **`condition`** on calls inside `if` / `switch` / `for` / `range`, and **`rules`** for **`panic`** / **`log.Fatal` / `Fatalf`**; **`fr.rules`** are merged slice-scoped.
+- **PHP:** the **`codeflow_php_dump`** helper adds **`condition`** on calls (from enclosing **`if` / `case`**), **`rules`** for **`throw`**, and **`branches`** for documentation. Install PHP + Composer deps under `codeflow-to-md/examples/codeflow_php_dump` (or mirror under `tools/codeflow_php_dump`) for PHP scans.
+- **Kinds / filters:** `--include` accepts aliases such as **`portlet`** / **`liferay`** for portlet entries.
+- **Operators:** each run writes **`scan-summary.md`** at the output root (counts, warnings, fallback mode) unless **`--no-scan-summary`** is set.
+
+```bash
+python -m md_generator.codeflow.cli.main scan path/to/src --output ./codeflow-out --lang java
+```
+
 ---
 
 ## Repository layout

{mdengine-0.8.0 → mdengine-0.9.0}/README.md

@@ -218,19 +218,19 @@ python pdf-to-md\converter.py input.pdf out.md
 PYTHONPATH=src python pdf-to-md/converter.py input.pdf out.md
 ```
 
-### 6. Convert every file in `docs/` (strictly command-line)
+### 6. Convert every file in `example/` (strictly command-line)
 
-To process **all supported files** under the [`docs/`](docs/) folder using only the installed **`md-*`** tools (no Python snippets), use the batch driver:
+To process **all supported files** under the [`example/`](example/) folder using only the installed **`md-*`** tools (no Python snippets), use the batch driver:
 
 | Platform | Command (run from **repository root** unless noted) |
 |----------|------------------------------------------------------|
 | Windows | `powershell -ExecutionPolicy Bypass -File scripts/run-docs-cli.ps1` |
-| Windows | Or double-click / run [`docs/run-all-cli.cmd`](docs/run-all-cli.cmd) (changes to repo root, then runs the script on `docs\`) |
+| Windows | Or double-click / run [`example/run-all-cli.cmd`](example/run-all-cli.cmd) (changes to repo root, then runs the script on `example\`) |
 | macOS / Linux | `bash scripts/run-docs-cli.sh` |
 
 Optional environment variables for the shell script: `DOCS_DIR`, `OUT_DIR`, `IMAGE_ENGINES` (default `tess`). PowerShell script parameters: `-DocsDir`, `-OutDir`, `-ImageEngines`.
 
-Outputs are written to **`docs/cli-output/<basename>/`** (one subfolder per input file). **`.csv`** files are converted with **`md-xlsx`** (same engine as Excel). **`.md`** files are skipped.
+Outputs are written to **`example/cli-output/<basename>/`** (one subfolder per input file). **`.csv`** files are converted with **`md-xlsx`** (same engine as Excel). **`.md`** files are skipped.
 
 ---
 
@@ -705,6 +705,29 @@ python -m pytest
 
 Tests live under each legacy folder’s `tests/` directory (e.g. `pdf-to-md/tests/`), **`graph-to-md/tests/`**, **`openapi-to-md/tests/`**, and **[`tool-assistant/tests/`](tool-assistant/tests/)** for the skill SDK; `pyproject.toml` sets `pythonpath = ["src"]` so **`md_generator`** (including **`md_generator.tools.assistant`**) resolves without a manual `PYTHONPATH` when you use `pytest` from the config.
 
+### Codeflow (`md_generator.codeflow`)
+
+Static call graphs and per-entry Markdown/Mermaid/JSON for **Python**, **Java** (Spring REST, Kafka listeners, **Liferay / JSR-286 portlets**), and other parsers. Output is **static only** (`graph-full.json` can include unresolved `unknown::*` callees).
+
+More detail: **[`codeflow-to-md/docs/graph-and-outputs.md`](codeflow-to-md/docs/graph-and-outputs.md)** (node/edge model, `graph-schema.json`, `methods/` layout).
+
+- **Formats:** pass **`--formats md,mermaid,json,html`** (comma-separated). **`--output`** is the **output directory**, not the format list.
+- **Graph schema export:** optional **`--emit-graph-schema`** (with `json` in formats) writes **`graph-schema.json`** — stable Node/Edge view with derived File/Class nodes and `CONTAINS` edges. **`graph-full.json`** stays unchanged for existing consumers.
+- **Markdown intelligence:** flow and entry Markdown include **Called By** and **Impact** lists (capped with **`--intelligence-list-cap`**, default 80).
+- **IR / CFG (optional):** **`--emit-cfg`** builds a language-agnostic IR and writes **`cfg.json`**, **`cfg.mmd`**, and appends a CFG Mermaid block to **`flow.md`** (when `md` is in formats). Cap with **`--cfg-max-nodes`** (default 500).
+- **Entries:** use `--entry` (comma-separated symbol ids), **`--entries-file`** (one id per line, `#` comments allowed), or rely on detectors. **`--emit-entry-per-method`** emits one output directory per method/entry symbol under **`methods/<slug>/`**; cap volume with **`--emit-entry-max`** (default cap **10000** when the flag is set and max is omitted). **`--entry-fallback`** `none` \| `roots` \| `first_n` controls behavior when nothing is detected (default **`roots`**, in-degree 0 symbols, limited by **`--entry-fallback-max`**).
+- **Java flow:** edges can record **branch context** from enclosing `if`, `switch`, or ternary expressions (`condition` / `labels` on edges). **Business rules** Markdown picks up validation-style **`@NotNull`** / **`@Size`** / **`@Valid`** (name heuristics) and throws such as **`IllegalArgumentException`**.
+- **JavaScript / TypeScript / TSX:** Tree-sitter adds **`condition_label`** from enclosing control flow, **`fr.branches`** for `if` / `switch`, and **`fr.rules`** for **`throw`** and common **`assert` / `console.assert`** calls (slice-scoped in the collector).
+- **C++ (tree-sitter path):** **`condition_label`** on calls, **`fr.branches`** for `if` / `switch`, plus **`rules/cpp_rules.py`** for **`throw`** / **`assert`** when methods appear in the slice. (Clang-only parses still get throw/assert via the same extractor when tree-sitter is installed.)
+- **Go:** the **`codeflow_go_dump`** helper emits **`condition`** on calls inside `if` / `switch` / `for` / `range`, and **`rules`** for **`panic`** / **`log.Fatal` / `Fatalf`**; **`fr.rules`** are merged slice-scoped.
+- **PHP:** the **`codeflow_php_dump`** helper adds **`condition`** on calls (from enclosing **`if` / `case`**), **`rules`** for **`throw`**, and **`branches`** for documentation. Install PHP + Composer deps under `codeflow-to-md/examples/codeflow_php_dump` (or mirror under `tools/codeflow_php_dump`) for PHP scans.
+- **Kinds / filters:** `--include` accepts aliases such as **`portlet`** / **`liferay`** for portlet entries.
+- **Operators:** each run writes **`scan-summary.md`** at the output root (counts, warnings, fallback mode) unless **`--no-scan-summary`** is set.
+
+```bash
+python -m md_generator.codeflow.cli.main scan path/to/src --output ./codeflow-out --lang java
+```
+
 ---
 
 ## Repository layout

{mdengine-0.8.0 → mdengine-0.9.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "mdengine"
-version = "0.8.0"
+version = "0.9.0"
 description = "Convert PDF, Office, images, audio, video, text/JSON/XML, ZIP archives, web URLs, databases, graphs, and OpenAPI specs to Markdown."
 readme = "README.md"
 requires-python = ">=3.10"
@@ -45,7 +45,7 @@ image-ocr = [
   "paddleocr>=2.7.0.3",
   "easyocr>=1.7.0",
 ]
-text = []
+text = ["xmltodict>=0.13.0", "lxml>=5.0.0"]
 archive = ["Pillow>=10.0.0", "pytesseract>=0.3.10"]
 url = [
   "httpx>=0.27.0",
@@ -115,6 +115,11 @@ codeflow = [
   "networkx>=3.2.0",
   "javalang>=0.13.0",
 ]
+# Optional: horizontal workers for codeflow API (Celery + Redis). Default job path uses threads.
+codeflow-worker = [
+  "celery>=5.3.0",
+  "redis>=5.0.0",
+]
 codeflow-treesitter = [
   "tree-sitter>=0.21.0",
   "tree-sitter-javascript>=0.21.0",
@@ -124,6 +129,28 @@ codeflow-treesitter = [
 codeflow-clang = [
   "clang>=16.0.0",
 ]
+# Embeddings + semantic clustering (SentenceTransformers pulls torch; large install).
+codeflow-semantic = [
+  "numpy>=1.24.0",
+  "scikit-learn>=1.3.0",
+  "sentence-transformers>=3.0.0",
+]
+log = [
+  "pandas>=2.0.0",
+  "python-dateutil>=2.8.0",
+  "pyyaml>=6.0.0",
+]
+log-cluster = [
+  "scikit-learn>=1.3.0",
+]
+log-semantic = [
+  "numpy>=1.24.0",
+  "scikit-learn>=1.3.0",
+  "sentence-transformers>=3.0.0",
+]
+log-pretty = [
+  "loguru>=0.7.0",
+]
 api = [
   "fastapi>=0.115.0",
   "uvicorn[standard]>=0.32.0",
@@ -150,6 +177,8 @@ dev = [
   "mdengine[openapi]",
   "mdengine[codeflow]",
   "mdengine[codeflow-treesitter]",
+  "mdengine[log]",
+  "mdengine[log-cluster]",
 ]
 all = [
   "pymupdf>=1.24.0",
@@ -218,6 +247,9 @@ md-codeflow = "md_generator.codeflow.cli.main:main"
 codeflow = "md_generator.codeflow.cli.main:main"
 md-codeflow-api = "md_generator.codeflow.api.run:main"
 md-codeflow-mcp = "md_generator.codeflow.api.mcp_server:main"
+md-log = "md_generator.log.cli.main:main"
+md-log-api = "md_generator.log.api.run:main"
+md-log-mcp = "md_generator.log.api.mcp_server:main"
 mdengine = "md_generator.engine_cli:main"
 
 [tool.setuptools.packages.find]
@@ -228,6 +260,7 @@ include = ["md_generator*"]
 "md_generator.db.config" = ["*.yaml"]
 "md_generator.graph.config" = ["*.yaml"]
 "md_generator.openapi.config" = ["*.yaml"]
+"md_generator.log.config" = ["*.yaml", "presets/*.yaml"]
 "md_generator.tools.assistant" = ["data/**/*"]
 
 [tool.pytest.ini_options]
@@ -250,5 +283,6 @@ testpaths = [
   "graph-to-md/tests",
   "openapi-to-md/tests",
   "codeflow-to-md/tests",
+  "log-to-md/tests",
 ]
 markers = ["integration: optional dependency or slower checks"]

{mdengine-0.8.0 → mdengine-0.9.0}/src/md_generator/__init__.py

@@ -1,5 +1,5 @@
 """md_generator: PDF, Office, image, text, and ZIP to Markdown conversion."""
 
-__version__ = "0.8.0"
+__version__ = "0.9.0"
 
 __all__ = ["__version__"]

{mdengine-0.8.0 → mdengine-0.9.0}/src/md_generator/codeflow/analyzers/flow_analyzer.py

@@ -4,6 +4,9 @@ from dataclasses import dataclass, field
 
 import networkx as nx
 
+from md_generator.codeflow.graph import relations as rel
+from md_generator.codeflow.graph.multigraph_utils import CodeflowGraph, collapsed_digraph_for_relations
+
 
 @dataclass(slots=True)
 class FlowSlice:
@@ -15,16 +18,25 @@ class FlowSlice:
     truncated: bool = False
 
 
+_DEFAULT_FLOW_RELATIONS = frozenset({rel.REL_CALLS})
+
+
 def walk_with_depth(
-    g: nx.DiGraph,
+    g: CodeflowGraph,
     start: str,
     max_depth: int,
+    *,
+    relations: frozenset[str] | None = None,
 ) -> tuple[set[str], list[tuple[str, str, dict]], set[str], bool]:
-    """Reachability from start within ``max_depth`` hops (shortest-path layering)."""
+    """Reachability from ``start`` within ``max_depth`` hops over selected relations (default: CALLS only)."""
     if start not in g:
         return {start}, [], set(), False
+    rels = relations if relations is not None else _DEFAULT_FLOW_RELATIONS
+    cg = collapsed_digraph_for_relations(g, rels)
+    if start not in cg:
+        return {start}, [], set(), False
     try:
-        plen = nx.single_source_shortest_path_length(g, start, cutoff=max_depth)
+        plen = nx.single_source_shortest_path_length(cg, start, cutoff=max_depth)
     except nx.NetworkXError:
         plen = {start: 0}
 
@@ -36,13 +48,18 @@ def walk_with_depth(
     for u in nodes:
         du = plen[u]
         if du >= max_depth:
-            succ = list(g.successors(u))
+            succ = list(cg.successors(u))
             if succ:
                 truncated = True
             continue
-        for v in g.successors(u):
-            ed = dict(g.edges[u, v])
-            edges_out.append((u, v, ed))
+        for v in cg.successors(u):
+            if not g.has_edge(u, v):
+                continue
+            for _k, ed in g[u][v].items():
+                er = ed.get("relation") or ed.get("kind") or rel.REL_CALLS
+                if er not in rels:
+                    continue
+                edges_out.append((u, v, dict(ed)))
             dv = plen.get(v)
             if dv is not None and dv <= du:
                 cycle_guess.add(v)
@@ -53,11 +70,13 @@ def walk_with_depth(
 
 
 def slice_from_entry(
-    g: nx.DiGraph,
+    g: CodeflowGraph,
     entry_id: str,
     max_depth: int,
+    *,
+    relations: frozenset[str] | None = None,
 ) -> FlowSlice:
-    nodes, edges, cycles, truncated = walk_with_depth(g, entry_id, max_depth)
+    nodes, edges, cycles, truncated = walk_with_depth(g, entry_id, max_depth, relations=relations)
     return FlowSlice(
         entry_id=entry_id,
         nodes=nodes,

{mdengine-0.8.0 → mdengine-0.9.0}/src/md_generator/codeflow/api/job_manager.py

@@ -7,7 +7,7 @@ import threading
 import time
 import uuid
 import zipfile
-from dataclasses import dataclass
+from dataclasses import dataclass, replace
 from pathlib import Path
 from typing import Any
 
@@ -101,24 +101,7 @@ class CodeflowJobManager:
             zf.extractall(src)
 
         out = ws / "out"
-        cfg = ScanConfig(
-            project_root=src,
-            output_path=out,
-            formats=cfg_template.formats,
-            depth=cfg_template.depth,
-            languages=cfg_template.languages,
-            entry=cfg_template.entry,
-            include=cfg_template.include,
-            exclude=cfg_template.exclude,
-            include_internal=cfg_template.include_internal,
-            async_mode=cfg_template.async_mode,
-            jobs=True,
-            runtime=cfg_template.runtime,
-            paths_override=cfg_template.paths_override,
-            business_rules=cfg_template.business_rules,
-            business_rules_sql=cfg_template.business_rules_sql,
-            business_rules_combined=cfg_template.business_rules_combined,
-        )
+        cfg = replace(cfg_template, project_root=src, output_path=out, jobs=True)
         now = time.time()
         cfg_dump = json.dumps(scan_config_dump(cfg), sort_keys=True)
         assert self._conn is not None
@@ -223,6 +206,11 @@ class CodeflowJobManager:
                 lw = LoadedWorkspace(root=cfg.project_root, cleanup_dir=None)
 
                 self.update_progress(job_id, 10, "scan")
+                cm = cfg.cache_clear_mode
+                if cm and str(cm).strip().lower() in ("git", "all"):
+                    from md_generator.codeflow.core.cache_manager import apply_git_cache_clear
+
+                    apply_git_cache_clear()
                 run_scan(cfg, workspace=lw)
                 on_prog(90, "zip")