WIP Phase 4 ingestion: platform guides, exclusion gate, gitea/vault/graph harvest, payload provenance

platforms/gitea.yml

@@ -0,0 +1,46 @@
+# Platform guide — Gitea.
+#
+# This file is both configuration and public copy. The site shows it so a
+# visitor can see exactly what the assistant reads. Keep the wording honest.
+name: gitea
+enabled: true
+what: >-
+  Self-hosted Git. The source of truth for every current project: README files,
+  file trees, selected source files, recent commit messages and language
+  statistics. This is where the work itself lives.
+fits: [ai, platform, edge, products]
+base: https://gitea.lab.audasmedia.com.au
+auth: GITEA_TOKEN
+include:
+  repos: all
+  # No path include means: every text file the repository rules admit.
+  paths: []
+exclude:
+  repos:
+    # The vault is read by the obsidian guide, so its notes are not harvested
+    # twice under a different platform.
+    - sam/obsidian-vault
+  paths:
+    - "**/node_modules/**"
+    - "**/.venv/**"
+    - "**/venv/**"
+    - "**/.git/**"
+    - "**/.trash/**"
+    - "**/.obsidian/**"
+    - "**/.pi/**"
+    - "**/__pycache__/**"
+    - "**/graphify-out/**"
+    - "**/graphify-out-temp/**"
+    - "**/vendor/**"
+    - "**/third_party/**"
+    - "**/*.min.js"
+    - "**/*.min.css"
+    - "**/*.lock"
+read: [readme, tree, selected_source, commits, languages]
+public: true
+limits:
+  max_documents: 4000
+  max_file_kb: 200
+  max_files_per_repo: 40
+  max_commits: 20
+  max_tree_entries: 3000

platforms/graphify.yml

@@ -0,0 +1,23 @@
+# Platform guide — Graphify knowledge graph.
+#
+# This file is both configuration and public copy.
+name: graphify
+enabled: true
+what: >-
+  A knowledge graph over the notes. It answers "what connects X to Y" rather
+  than "what mentions X": nodes are the things in the estate, edges are the
+  relations between them, and every one points back at the note it came from.
+fits: [ai]
+base: sam/obsidian-vault
+read: [graph_json]
+public: true
+limits:
+  max_documents: 4000
+  # graph.json is the only file this platform reads. These are the places it may
+  # be committed; the first match wins.
+  graph_paths:
+    - graphify-out/graph.json
+    - graph.json
+    - Graph/graph.json
+  max_nodes: 20000
+  max_edges: 40000

platforms/obsidian.yml

@@ -0,0 +1,44 @@
+# Platform guide — Obsidian vault (sam/obsidian-vault, read through Gitea).
+#
+# This file is both configuration and public copy.
+#
+# Privacy note: only project, area and index notes are read. The personal and
+# family folders (000 daily, 400 Personal Family, 500 archive) and the templates
+# are deliberately out of scope. They are not work evidence and they contain
+# third-party personal detail. See docs/content-redaction.md.
+name: obsidian
+enabled: true
+what: >-
+  A personal knowledge base. High-level notes on every system, in Sam's own
+  words: what a system is for, what changed, and what went wrong. Project and
+  area notes only; personal, family and daily notes are not read.
+fits: [about, ai, platform, edge, products]
+base: sam/obsidian-vault
+include:
+  paths:
+    - "010 inbox/**"
+    - "100 Table of Contents/**"
+    - "200 projects/**"
+    - "300 areas/**"
+exclude:
+  paths:
+    - ".obsidian/**"
+    - ".trash/**"
+    - ".venv/**"
+    - "templates/**"
+    - "000 daily/**"
+    - "400 Personal Family/**"
+    - "500 archive/**"
+    - "**/*.excalidraw"
+    - "**/*.png"
+    - "**/*.jpg"
+    - "**/*.jpeg"
+    - "**/*.gif"
+    - "**/*.webp"
+    - "**/*.pdf"
+    - "**/*Bedroom Lights*"
+read: [notes]
+public: true
+limits:
+  max_documents: 4000
+  max_file_kb: 200