arborist/docs/diagrams/arborist-modules.dot
russell@unturf.com 6e42dbf026
docs/diagrams: rename aborist-modules → arborist-modules (post-rename cleanup)
The top-level module diagram still used the old aborist- (one R) prefix
from before the package rename. arborist.unturf.com served from the
symlinked docs/_source/diagrams/, so the live URL
arborist.unturf.com/en/diagrams/arborist-modules.svg 404'd because the
file on disk was aborist-modules.svg.

Other diagram base names (ingest-pipeline, mesh-*, query-pipeline,
verifier-ladder) were never aborist-prefixed; only this one needed it.
2026-05-08 07:50:28 -04:00

144 lines
6.2 KiB
Text

// Arborist module graph — top-level packages & their dependencies.
//
// Arrows point in the import direction (A → B means A imports from B).
// Cluster boxes group modules with shared concerns (storage, retrieval,
// federation, etc.).
//
// Render: dot -Tsvg arborist-modules.dot -o arborist-modules.svg
digraph arborist_modules {
rankdir=LR
node [shape=box, style="rounded,filled", fontname="Helvetica", fontsize=10]
edge [fontname="Helvetica", fontsize=9]
bgcolor="white"
// ---- Substrate (pure crypto / serialization, no SQL) ----
subgraph cluster_substrate {
label="substrate"
style="rounded,dashed"
color="#999999"
merkle [label="merkle.py\n(Python port of Go merkle.go)", fillcolor="#fff7e6"]
document [label="document.py\nDocument · Edge · Chunker", fillcolor="#fff7e6"]
wikitext [label="wikitext.py\nto_base() prose-strip", fillcolor="#fff7e6"]
}
// ---- Storage layer ----
subgraph cluster_storage {
label="storage"
style="rounded,dashed"
color="#999999"
store [label="store.py\nv9.8 SQLite schema +\naudit chain helpers", fillcolor="#e6f0ff"]
ingest [label="ingest.py\nnormalize → chunk → merkle → upsert", fillcolor="#e6f0ff"]
evict [label="evict.py\nhot ↔ cold tier", fillcolor="#e6f0ff"]
}
// ---- Sources (corpus producers) ----
subgraph cluster_sources {
label="sources/"
style="rounded,dashed"
color="#999999"
wikipedia [label="wikipedia.py\ncur + old SQL dumps", fillcolor="#e7ffe7"]
wiki_xml [label="wikipedia_xml.py\nphase IV iterparse", fillcolor="#e7ffe7"]
html_page [label="html_page.py\nselectolax + httpx", fillcolor="#e7ffe7"]
crawler [label="crawler/\nasync HTML BFS", fillcolor="#e7ffe7"]
grok [label="grok.py\nxAI export", fillcolor="#e7ffe7"]
vcs [label="vcs.py\ngit + Mercurial", fillcolor="#e7ffe7"]
}
// ---- Retrieval & verifier ----
subgraph cluster_retrieval {
label="retrieval & verifier"
style="rounded,dashed"
color="#999999"
search [label="search/\nFTS5 backend + ABC", fillcolor="#ffe6f0"]
concepts [label="concepts/\nsynonym & rivalry overlay\n(per-shard concept_relations)", fillcolor="#ffe6f0"]
qa_query [label="qa/query.py\nmulti-source RAG", fillcolor="#ffe6f0"]
qa_verify [label="qa/verify.py\nquote/span/entity/paraphrase\n+ claim_lattice (7 hard checks)", fillcolor="#ffe6f0"]
qa_warrant[label="qa/warrant.py\n5 anchor classes\n(proper-noun · date · count\n · entity-list · cause)", fillcolor="#ffe6f0"]
qa_evidence[label="qa/evidence.py\nEvidenceObject + spotlight", fillcolor="#ffe6f0"]
qa_runner [label="qa/runner.py\nask(): single-doc Q&A", fillcolor="#ffe6f0"]
qa_dag [label="qa/dag.py\nper-run Merkle DAG\n(7/8 quote · 9/10 CTI · 3 reject)\npreflight_node_hash + 5 clauses", fillcolor="#ffe6f0"]
qa_keys [label="qa/keys.py\n8-dim cache_key + question_hash", fillcolor="#ffe6f0"]
qa_inspect[label="qa/inspect.py\nsidecar diagnostic\n(read-only)", fillcolor="#ffe6f0"]
// Preflight modules (Tickets #000008 + #000010)
qa_quantifier [label="qa/quantifier.py\n10-rung intensity classifier\n(#000008)", fillcolor="#ffe6f0"]
qa_model_profiles [label="qa/model_profiles.py\nper-model claim-cap profiles\n(#000008)", fillcolor="#ffe6f0"]
qa_quantifier_reminder[label="qa/quantifier_reminder.py\nbroad-query reminder text\n(#000008)", fillcolor="#ffe6f0"]
qa_metacognition [label="qa/metacognition.py\nQuestionState + 4 detectors\n(temporal · contradiction ·\n false-premise · out-of-corpus)\n(#000010)", fillcolor="#ffe6f0"]
}
// ---- Distill (surface → core) ----
distill [label="distill/\nDistiller ABC + tfidf + first_sentence", fillcolor="#fff0e0"]
// ---- Federation (off by default) ----
mesh [label="mesh/\nfederation: identity, roster,\nAEAD epoch secret, gossip wire", fillcolor="#f0e6ff"]
// ---- Entry point ----
cli [label="cli.py\nargparse entrypoint\n(make targets call into here)", fillcolor="#dddddd", shape=note]
// Substrate dependencies
document -> merkle
store -> merkle
store -> document
ingest -> store
ingest -> document
// Sources -> ingest path
wikipedia -> ingest
wiki_xml -> ingest
html_page -> ingest [label="parse_html →\nedges rows"]
crawler -> html_page
grok -> ingest
vcs -> ingest
// Retrieval pipeline
qa_query -> search
qa_query -> concepts [label="synonym_expand /\nrivalry_excluded"]
qa_query -> qa_keys
qa_query -> qa_verify
qa_query -> qa_evidence
qa_query -> qa_dag
qa_query -> wikitext [label="to_base()"]
qa_verify -> qa_warrant
qa_verify -> qa_evidence
qa_runner -> qa_query
qa_inspect -> qa_query [style=dashed, label="read-only sidecar"]
// Preflight wiring (#000008 + #000010 → #000009 DAG binding)
qa_query -> qa_quantifier [label="classify_question_quantifier"]
qa_query -> qa_model_profiles [label="cap_for_intensity"]
qa_query -> qa_quantifier_reminder [label="broad_quantifier_reminder"]
qa_query -> qa_metacognition [label="preflight_question"]
qa_runner -> qa_quantifier
qa_runner -> qa_model_profiles
qa_runner -> qa_quantifier_reminder
qa_runner -> qa_metacognition
qa_dag -> qa_quantifier [style=dotted, label="preflight clause"]
qa_dag -> qa_metacognition [style=dotted, label="preflight clause"]
// Concepts reads existing edges
concepts -> store [label="reads edges,\nwrites concept_relations"]
// Search reads chunks
search -> store
// Distill consumes store, writes derivations
distill -> store
distill -> document
// Eviction
evict -> store
// Mesh
mesh -> store
// CLI dispatches everywhere
cli -> ingest
cli -> qa_runner
cli -> qa_query
cli -> qa_inspect
cli -> distill
cli -> evict
cli -> mesh
cli -> concepts
}