Skip to content

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

fix: address PR #71 review findings and bump version to 2.2.0

Lum110452050e40cb41
diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json
index d9b37a08..c7a58c25 100644
--- a/.claude-plugin/marketplace.json
+++ b/.claude-plugin/marketplace.json
@@ -9,7 +9,7 @@
{
"name": "understand-anything",
"description": "Multi-agent codebase analysis with interactive dashboard, guided tours, and skill commands",
- "version": "2.1.0",
+ "version": "2.2.0",
"source": "./understand-anything-plugin"
}
]
diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json
index a1229dda..73781f5a 100644
--- a/.claude-plugin/plugin.json
+++ b/.claude-plugin/plugin.json
@@ -1,7 +1,7 @@
{
"name": "understand-anything",
"description": "AI-powered codebase understanding — analyze, visualize, and explain any project",
- "version": "2.1.0",
+ "version": "2.2.0",
"author": {
"name": "Lum1104"
},
diff --git a/.cursor-plugin/plugin.json b/.cursor-plugin/plugin.json
index 2255fbac..e32414b2 100644
--- a/.cursor-plugin/plugin.json
+++ b/.cursor-plugin/plugin.json
@@ -2,7 +2,7 @@
"name": "understand-anything",
"displayName": "Understand Anything",
"description": "AI-powered codebase understanding — analyze, visualize, and explain any project",
- "version": "2.1.0",
+ "version": "2.2.0",
"author": {
"name": "Lum1104"
},
diff --git a/understand-anything-plugin/agents/assemble-reviewer.md b/understand-anything-plugin/agents/assemble-reviewer.md
index c4f05fb5..ff611e48 100644
--- a/understand-anything-plugin/agents/assemble-reviewer.md
+++ b/understand-anything-plugin/agents/assemble-reviewer.md
@@ -85,3 +85,13 @@ The merge script combines what each batch produced independently. Batches don't
```
3. Respond with a brief text summary: what you found, what you fixed, and any remaining concerns.
+
+## Writing Results
+
+After completing all steps above:
+
+1. Apply all fixes directly to `assembled-graph.json` (the file path provided in your dispatch prompt).
+2. Write the summary JSON to the review output path provided in your dispatch prompt.
+3. Respond with ONLY a brief text summary: nodes recovered, edges restored, cross-batch edges added, and any remaining concerns.
+
+Do NOT include the full JSON in your text response.
diff --git a/understand-anything-plugin/agents/project-scanner.md b/understand-anything-plugin/agents/project-scanner.md
index cecb17d7..e8814f9a 100644
--- a/understand-anything-plugin/agents/project-scanner.md
+++ b/understand-anything-plugin/agents/project-scanner.md
@@ -265,7 +265,7 @@ Your only task in this phase is to produce the final `description` field:
1. If `rawDescription` is non-empty, use it as the basis. Clean it up if needed (remove marketing fluff, ensure it is 1-2 sentences).
2. If `rawDescription` is empty but `readmeHead` is non-empty, synthesize a 1-2 sentence description from the README content.
3. If both are empty, use: `"No description available"`
-4. If `totalFiles` > 200, append a note: `" Note: this project has over 200 source files; consider scoping analysis to a subdirectory for faster results."`
+4. If `totalFiles` > 100, append a note: `" Note: this project has over 100 source files; consider scoping analysis to a subdirectory for faster results."`
Then assemble the final output JSON:
diff --git a/understand-anything-plugin/package.json b/understand-anything-plugin/package.json
index 527b319b..525c4287 100644
--- a/understand-anything-plugin/package.json
+++ b/understand-anything-plugin/package.json
@@ -1,6 +1,6 @@
{
"name": "@understand-anything/skill",
- "version": "2.1.0",
+ "version": "2.2.0",
"type": "module",
"main": "dist/index.js",
"types": "dist/index.d.ts",
diff --git a/understand-anything-plugin/skills/understand/SKILL.md b/understand-anything-plugin/skills/understand/SKILL.md
index f10b5090..be26f59b 100644
--- a/understand-anything-plugin/skills/understand/SKILL.md
+++ b/understand-anything-plugin/skills/understand/SKILL.md
@@ -39,9 +39,9 @@ Determine whether to run a full analysis or incremental update.
- These flags only set the config — analysis proceeds normally regardless.
4. **Check for subdomain knowledge graphs to merge:**
- List all `*knowledge-graph*.json` files in `$PROJECT_ROOT/.understand-anything/` **excluding** `knowledge-graph.json` itself (e.g. `frontend-knowledge-graph.json`, `backend-knowledge-graph.json`). If any subdomain graphs exist, run the merge script bundled with this skill:
+ List all `*knowledge-graph*.json` files in `$PROJECT_ROOT/.understand-anything/` **excluding** `knowledge-graph.json` itself (e.g. `frontend-knowledge-graph.json`, `backend-knowledge-graph.json`). If any subdomain graphs exist, run the merge script bundled with this skill (located next to this SKILL.md file — use the skill directory path, not the project root):
```bash
- python ./merge-subdomain-graphs.py $PROJECT_ROOT
+ python <SKILL_DIR>/merge-subdomain-graphs.py $PROJECT_ROOT
```
The script discovers subdomain graphs, loads the existing `knowledge-graph.json` as a base (if present), and merges everything into `knowledge-graph.json` (deduplicating nodes and edges). Report the merge summary to the user, then continue with the merged graph.
@@ -164,9 +164,9 @@ Fill in batch-specific parameters below and dispatch:
> 2. `<path>` (<sizeLines> lines, fileCategory: `<fileCategory>`)
> ...
-After ALL batches complete, run the merge-and-normalize script bundled with this skill:
+After ALL batches complete, run the merge-and-normalize script bundled with this skill (located next to this SKILL.md file — use the skill directory path, not the project root):
```bash
-python ./merge-batch-graphs.py $PROJECT_ROOT
+python <SKILL_DIR>/merge-batch-graphs.py $PROJECT_ROOT
```
This script reads all `batch-*.json` files from `$PROJECT_ROOT/.understand-anything/intermediate/`, then in one pass:
@@ -192,7 +192,7 @@ After batches complete:
3. Write the pruned existing nodes/edges as `batch-existing.json` in the intermediate directory
4. Run the same merge script — it will combine `batch-existing.json` with the fresh `batch-*.json` files:
```bash
- python ./merge-batch-graphs.py $PROJECT_ROOT
+ python <SKILL_DIR>/merge-batch-graphs.py $PROJECT_ROOT
```
---
diff --git a/understand-anything-plugin/skills/understand/merge-batch-graphs.py b/understand-anything-plugin/skills/understand/merge-batch-graphs.py
index 78f99280..1896f50d 100644
--- a/understand-anything-plugin/skills/understand/merge-batch-graphs.py
+++ b/understand-anything-plugin/skills/understand/merge-batch-graphs.py
@@ -32,12 +32,14 @@ VALID_NODE_PREFIXES = {
"file", "func", "function", "class", "module", "concept",
"config", "document", "service", "table", "endpoint",
"pipeline", "schema", "resource",
+ "domain", "flow", "step",
}
# node.type → canonical ID prefix
TYPE_TO_PREFIX: dict[str, str] = {
"file": "file",
"function": "function",
+ "func": "function",
"class": "class",
"module": "module",
"concept": "concept",
@@ -49,6 +51,9 @@ TYPE_TO_PREFIX: dict[str, str] = {
"pipeline": "pipeline",
"schema": "schema",
"resource": "resource",
+ "domain": "domain",
+ "flow": "flow",
+ "step": "step",
}
COMPLEXITY_MAP: dict[str, str] = {
@@ -349,8 +354,13 @@ def main() -> None:
print(f"Error: {intermediate_dir} does not exist", file=sys.stderr)
sys.exit(1)
- # Discover batch files
- batch_files = sorted(intermediate_dir.glob("batch-*.json"))
+ # Discover batch files, sorted by numeric index (not lexicographic)
+ batch_files = sorted(
+ intermediate_dir.glob("batch-*.json"),
+ key=lambda p: int(re.search(r"batch-(\d+)", p.stem).group(1))
+ if re.search(r"batch-(\d+)", p.stem)
+ else 0,
+ )
if not batch_files:
print("Error: no batch-*.json files found in intermediate/", file=sys.stderr)
sys.exit(1)
diff --git a/understand-anything-plugin/skills/understand/merge-subdomain-graphs.py b/understand-anything-plugin/skills/understand/merge-subdomain-graphs.py
index 97a8f894..7e6de82a 100644
--- a/understand-anything-plugin/skills/understand/merge-subdomain-graphs.py
+++ b/understand-anything-plugin/skills/understand/merge-subdomain-graphs.py
@@ -116,15 +116,26 @@ def merge_graphs(graphs: list[dict[str, Any]]) -> tuple[dict[str, Any], list[str
if diff:
dropped_layer_refs += diff
- # ── Tour: concatenate, re-number order ────────────────────────────
+ # ── Tour: concatenate, merge steps with same title ─────────────────
all_tour_steps: list[dict] = []
- seen_titles: set[str] = set()
+ title_to_step: dict[str, dict] = {}
for g in graphs:
for step in g.get("tour", []):
title = step.get("title", "")
- if title not in seen_titles:
- seen_titles.add(title)
- all_tour_steps.append({**step})
+ if title in title_to_step:
+ # Merge nodeIds from duplicate-titled steps (e.g. both
+ # subdomains produce a "Project Overview" step 1)
+ existing = title_to_step[title]
+ for nid in step.get("nodeIds", []):
+ if nid not in existing.get("nodeIds", []):
+ existing.setdefault("nodeIds", []).append(nid)
+ # Keep the longer description
+ if len(step.get("description", "")) > len(existing.get("description", "")):
+ existing["description"] = step["description"]
+ else:
+ new_step = {**step}
+ title_to_step[title] = new_step
+ all_tour_steps.append(new_step)
# Drop dangling tour nodeIds and re-number
dropped_tour_refs = 0