understand-diff

/understand-diff

Analyze the current code changes against the knowledge graph at .understand-anything/knowledge-graph.json.

Graph Structure Reference

The knowledge graph JSON has this structure:

• project — {name, description, languages, frameworks, analyzedAt, gitCommitHash}
• nodes[] — each has {id, type, name, filePath?, summary, tags[], complexity, languageNotes?}
• Code node types: file, function, class, module, concept
• Non-code node types: config, document, service, table, endpoint, pipeline, schema, resource
• Domain/knowledge node types: domain, flow, step, article, entity, topic, claim, source
• IDs use the node type as prefix, e.g. file:path, function:path:name, config:path, article:path
• edges[] — each has {source, target, type, direction, weight}
• Key types: imports, contains, calls, depends_on, configures, documents, deploys, triggers, contains_flow, flow_step, related, cites
• layers[] — each has {id, name, description, nodeIds[]}
• tour[] — each has {order, title, description, nodeIds[]}

How to Read Efficiently

1. Use Grep to search within the JSON for relevant entries BEFORE reading the full file
2. Only read sections you need — don't dump the entire graph into context
3. Node names and summaries are the most useful fields for understanding
4. Edges tell you how components connect — follow imports and calls for dependency chains

Instructions

1. Check that .understand-anything/knowledge-graph.json exists. If not, tell the user to run /understand first.

1. Get the changed files list (do NOT read the graph yet):
2. If on a branch with uncommitted changes: git diff --name-only
3. If on a feature branch: git diff main...HEAD --name-only (or the base branch)
4. If the user specifies a PR number: get the diff from that PR

1. Read project metadata only — use Grep or Read with a line limit to extract just the "project" section for context.

1. Find nodes for changed files — for each changed file path, use Grep to search the knowledge graph for:
2. Nodes with matching "filePath" values (e.g., grep "changed/file/path")
3. This finds file-level nodes (including non-code types) AND function/class nodes defined in those files
4. Note the id values of all matched nodes

1. Find connected edges (1-hop) — for each matched node ID, Grep for that ID in the edges to find:
2. What imports or depends on the changed nodes (upstream callers)
3. What the changed nodes import or call (downstream dependencies)
4. These are the "affected components" — things that might break or need updating

1. Identify affected layers — Grep for the matched node IDs in the "layers" section to determine which architectural layers are touched.

1. Provide structured analysis:
2. Changed Components: What was directly modified (with summaries from matched nodes)
3. Affected Components: What might be impacted (from 1-hop edges)
4. Affected Layers: Which architectural layers are touched and cross-layer concerns
5. Risk Assessment: Based on node complexity values, number of cross-layer edges, and blast radius (number of affected components)
6. Suggest what to review carefully and any potential issues

1. Write diff overlay for dashboard — after producing the analysis, write the diff data to .understand-anything/diff-overlay.json so the dashboard can visualize changed and affected components. The file contains:

``json { "version": "1.0.0", "baseBranch": "<the base branch used>", "generatedAt": "<ISO timestamp>", "changedFiles": ["<list of changed file paths>"], "changedNodeIds": ["<node IDs from step 4>"], "affectedNodeIds": ["<node IDs from step 5, excluding changedNodeIds>"] } ` After writing, tell the user they can run /understand-anything:understand-dashboard` to see the diff overlay visually.