knowledge-base/projects/dttb/graphify-out/GRAPH_REPORT.md

Graph Report - dttb (2026-05-06)

Corpus Check

• 1 files · ~22,438 words
• Verdict: corpus is large enough that graph structure adds value.

Summary

• 18 nodes · 28 edges · 4 communities (3 shown, 1 thin omitted)
• Extraction: 100% EXTRACTED · 0% INFERRED · 0% AMBIGUOUS
• Token cost: 0 input · 0 output

Graph Freshness

• Built from commit: 3220238c
• Run git rev-parse HEAD and compare to check if the graph is stale.
• Run graphify update . after code changes (no API cost).

Community Hubs (Navigation)

• _COMMUNITY_Community 0
• _COMMUNITY_Community 1
• _COMMUNITY_Community 2
• _COMMUNITY_Community 3

God Nodes (most connected - your core abstractions)

1. nc_request() - 6 edges
2. main() - 6 edges
3. send_message() - 5 edges
4. build_system_prompt() - 4 edges
5. get_last_message_id() - 4 edges
6. poll_new_messages() - 4 edges
7. join_room() - 4 edges
8. load_knowledge_base() - 3 edges
9. get_ai_reply() - 3 edges
10. Load all .md files from knowledge-base repo into context string - 1 edges

Surprising Connections (you probably didn't know these)

• main() --calls--> build_system_prompt() [EXTRACTED] nextcloud-talk-bot.py → nextcloud-talk-bot.py Bridges community 2 → community 0
• get_last_message_id() --calls--> nc_request() [EXTRACTED] nextcloud-talk-bot.py → nextcloud-talk-bot.py Bridges community 1 → community 3
• poll_new_messages() --calls--> nc_request() [EXTRACTED] nextcloud-talk-bot.py → nextcloud-talk-bot.py Bridges community 1 → community 0
• main() --calls--> get_last_message_id() [EXTRACTED] nextcloud-talk-bot.py → nextcloud-talk-bot.py Bridges community 3 → community 0

Communities (4 total, 1 thin omitted)

Community 0 - "Community 0"

Cohesion: 0.47 Nodes (5): get_ai_reply(), main(), poll_new_messages(), Long-poll for new messages after last_id, Get reply from Claude via cliproxy

Community 1 - "Community 1"

Cohesion: 0.4 Nodes (6): join_room(), nc_request(), Join conversation as bot user, Send message as bot user, Nextcloud OCS API request, send_message()

Community 2 - "Community 2"

Cohesion: 0.5 Nodes (4): build_system_prompt(), load_knowledge_base(), Load all .md files from knowledge-base repo into context string, Build system prompt with knowledge base

Knowledge Gaps

• 8 isolated node(s): Load all .md files from knowledge-base repo into context string, Build system prompt with knowledge base, Nextcloud OCS API request, Get the highest message ID in the conversation, Long-poll for new messages after last_id (+3 more) These have ≤1 connection - possible missing edges or undocumented components.
• 1 thin communities (<3 nodes) omitted from report — run graphify query to explore isolated nodes.

Suggested Questions

Questions this graph is uniquely positioned to answer:

• Why does nc_request() connect Community 1 to Community 0, Community 3? High betweenness centrality (0.176) - this node is a cross-community bridge.
• Why does main() connect Community 0 to Community 1, Community 2, Community 3? High betweenness centrality (0.132) - this node is a cross-community bridge.
• Why does send_message() connect Community 1 to Community 0? High betweenness centrality (0.129) - this node is a cross-community bridge.
• What connects Load all .md files from knowledge-base repo into context string, Build system prompt with knowledge base, Nextcloud OCS API request to the rest of the system? 8 weakly-connected nodes found - possible documentation gaps or missing edges.