feat: add code duplication detector (#162)

Detect duplicate functions/blocks across Python files.
Reports duplication percentage and outputs JSON report.
Closes #162.

knowledge/global/cross_repo.yaml

@@ -1,540 +0,0 @@
-
----
-domain: global
-category: pattern
-version: 1
-last_updated: '2026-04-26T11:22:05.449323+00:00'
-facts:
-- id: cross-repo:connection:001
-  fact: "hermes-agent references compounding-intelligence via issue #229: [ATLAS]\
-    \ Steal the highest-leverage ecosystem patterns into the sovereign stack \u2192\
-    \ [compounding-intelligence#229] [ATLAS][Telemetry] Build local token and cost\
-    \ ingestion using Tokscale core patterns"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:21:56.905616+00:00'
-  last_confirmed: '2026-04-26T11:21:56.905641+00:00'
-  related: []
-- id: cross-repo:connection:002
-  fact: "hermes-agent references compounding-intelligence via issue #231: [ATLAS]\
-    \ Steal the highest-leverage ecosystem patterns into the sovereign stack \u2192\
-    \ [compounding-intelligence#231] [ATLAS][Wiki] Build the LLM Wiki layer: ingest,\
-    \ query, lint, and session crystallization into durabl"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:21:57.230615+00:00'
-  last_confirmed: '2026-04-26T11:21:57.230632+00:00'
-  related: []
-- id: cross-repo:connection:003
-  fact: "hermes-agent references compounding-intelligence via issue #232: [ATLAS]\
-    \ Steal the highest-leverage ecosystem patterns into the sovereign stack \u2192\
-    \ [compounding-intelligence#232] [ATLAS][Research] Solve the swarm-memory gap\
-    \ for concurrent subagents"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:21:57.415552+00:00'
-  last_confirmed: '2026-04-26T11:21:57.415580+00:00'
-  related: []
-- id: cross-repo:connection:004
-  fact: "hermes-agent references fleet-ops via issue #410: [ATLAS] Steal the highest-leverage\
-    \ ecosystem patterns into the sovereign stack \u2192 [fleet-ops#410] [ATLAS][Safety]\
-    \ Deploy a virtual-credential and DLP sidecar for sovereign agent runs"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:21:57.716479+00:00'
-  last_confirmed: '2026-04-26T11:21:57.716488+00:00'
-  related: []
-- id: cross-repo:connection:005
-  fact: "hermes-agent references the-nexus via issue #893: [CONSOLIDATED] Fleet SITREP\
-    \ \u2014 Allegro 7-Task Execution + Ezra Deliverables \u2192 [the-nexus#893] [AUDIT]\
-    \ System Formalization \u2014 OSS Replacements & Cleanup Candidates"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:21:57.961498+00:00'
-  last_confirmed: '2026-04-26T11:21:57.961510+00:00'
-  related: []
-- id: cross-repo:connection:006
-  fact: "hermes-agent references the-nexus via issue #1695: [ATLAS] Steal the highest-leverage\
-    \ ecosystem patterns into the sovereign stack \u2192 [the-nexus#1695] [ATLAS][Cockpit]\
-    \ Build the operator inspector rail and session shell patterns worth stealing"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:21:58.130733+00:00'
-  last_confirmed: '2026-04-26T11:21:58.130745+00:00'
-  related: []
-- id: cross-repo:connection:007
-  fact: "hermes-agent references timmy-config via issue #875: [ATLAS] Steal the highest-leverage\
-    \ ecosystem patterns into the sovereign stack \u2192 [timmy-config#875] [ATLAS][Skills]\
-    \ Import Karpathy-style cognitive principles and GStack-style role commands as\
-    \ native "
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:21:58.327960+00:00'
-  last_confirmed: '2026-04-26T11:21:58.327972+00:00'
-  related: []
-- id: cross-repo:connection:008
-  fact: "hermes-agent references timmy-dispatch via issue #18: [ATLAS] Steal the highest-leverage\
-    \ ecosystem patterns into the sovereign stack \u2192 [timmy-dispatch#18] [ATLAS][Dispatch]\
-    \ Add Mission Control-style dispatch ledger, capacity model, and heartbeat tracking"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:21:58.502966+00:00'
-  last_confirmed: '2026-04-26T11:21:58.502981+00:00'
-  related: []
-- id: cross-repo:connection:009
-  fact: "hermes-agent references timmy-home via issue #568: [DISPATCH] Ezra \u2014\
-    \ Investigate & Install MemPalace on Hermes VPS \u2192 [timmy-home#568] [EVALUATION]\
-    \ MemPalace v3.0.0 Integration \u2014 Before/After Metrics + Recommendation"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:21:58.967894+00:00'
-  last_confirmed: '2026-04-26T11:21:58.967906+00:00'
-  related: []
-- id: cross-repo:connection:010
-  fact: "the-nexus references hermes-agent via issue #984: [ATLAS][Cockpit] Build\
-    \ the operator inspector rail and session shell patterns worth stealing \u2192\
-    \ [hermes-agent#984] [ATLAS] Steal the highest-leverage ecosystem patterns into\
-    \ the sovereign stack"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:21:59.445454+00:00'
-  last_confirmed: '2026-04-26T11:21:59.445470+00:00'
-  related: []
-- id: cross-repo:connection:011
-  fact: "timmy-config references the-nexus via issue #501: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-26 (Thursday) \u2192 [the-nexus#501] [claude] Re-implement\
-    \ gravity anomaly zones (#478)"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:21:59.975253+00:00'
-  last_confirmed: '2026-04-26T11:21:59.975291+00:00'
-  related: []
-- id: cross-repo:connection:012
-  fact: "timmy-config references the-nexus via issue #502: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-26 (Thursday) \u2192 [the-nexus#502] [claude] Time-lapse\
-    \ replay mode (#484)"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:00.193542+00:00'
-  last_confirmed: '2026-04-26T11:22:00.193552+00:00'
-  related: []
-- id: cross-repo:connection:013
-  fact: "timmy-config references the-nexus via issue #503: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-26 (Thursday) \u2192 [the-nexus#503] [claude] InstancedMesh\
-    \ optimizations for repeated geometry (#482)"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:00.515208+00:00'
-  last_confirmed: '2026-04-26T11:22:00.515229+00:00'
-  related: []
-- id: cross-repo:connection:014
-  fact: "timmy-config references the-nexus via issue #552: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-26 (Thursday) \u2192 [the-nexus#552] [HEARTBEAT] Apprentice\
-    \ protocol \u2014 episodic memory logging of desktop activity"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:00.658814+00:00'
-  last_confirmed: '2026-04-26T11:22:00.658829+00:00'
-  related: []
-- id: cross-repo:connection:015
-  fact: "timmy-config references the-nexus via issue #554: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-26 (Thursday) \u2192 [the-nexus#554] [ECONOMY] Stand up\
-    \ Cashu Mint on Lightning"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:01.089278+00:00'
-  last_confirmed: '2026-04-26T11:22:01.089287+00:00'
-  related: []
-- id: cross-repo:connection:016
-  fact: "timmy-config references the-nexus via issue #555: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-26 (Thursday) \u2192 [the-nexus#555] [ECONOMY] Prototype\
-    \ Bannerlord Denar \u2192 Cashu token Harmony patch"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:01.297062+00:00'
-  last_confirmed: '2026-04-26T11:22:01.297069+00:00'
-  related: []
-- id: cross-repo:connection:017
-  fact: "timmy-config references the-nexus via issue #613: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-28 (Saturday) \u2192 [the-nexus#613] [gemini] [HARNESS]\
-    \ Shadow Context Manager \u2014 auto-generated brain dump for session continuity\
-    \ (#608)"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:01.814895+00:00'
-  last_confirmed: '2026-04-26T11:22:01.814905+00:00'
-  related: []
-- id: cross-repo:connection:018
-  fact: "timmy-config references the-nexus via issue #673: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-28 (Saturday) \u2192 [the-nexus#673] [PORTAL] Deterministic\
-    \ Morrowind pilot loop with world-state proof"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:02.118691+00:00'
-  last_confirmed: '2026-04-26T11:22:02.118711+00:00'
-  related: []
-- id: cross-repo:connection:019
-  fact: "timmy-config references the-nexus via issue #674: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-28 (Saturday) \u2192 [the-nexus#674] [PORTAL] Reflex tactical\
-    \ layer and semantic trajectory logging"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:02.261655+00:00'
-  last_confirmed: '2026-04-26T11:22:02.261669+00:00'
-  related: []
-- id: cross-repo:connection:020
-  fact: "timmy-config references the-nexus via issue #675: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-28 (Saturday) \u2192 [the-nexus#675] [HARNESS] Deterministic\
-    \ context compaction for long local sessions"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:02.403879+00:00'
-  last_confirmed: '2026-04-26T11:22:02.403922+00:00'
-  related: []
-- id: cross-repo:connection:021
-  fact: "timmy-config references the-nexus via issue #676: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-28 (Saturday) \u2192 [the-nexus#676] [gemini] [PORTAL]\
-    \ Reflex tactical layer and semantic trajectory logging (#674)"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:02.545921+00:00'
-  last_confirmed: '2026-04-26T11:22:02.545931+00:00'
-  related: []
-- id: cross-repo:connection:022
-  fact: "timmy-config references the-nexus via issue #677: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-28 (Saturday) \u2192 [the-nexus#677] [gemini] [HARNESS]\
-    \ Deterministic context compaction for long local sessions (#675)"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:02.691982+00:00'
-  last_confirmed: '2026-04-26T11:22:02.691988+00:00'
-  related: []
-- id: cross-repo:connection:023
-  fact: "timmy-config references the-nexus via issue #730: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-29 (Sunday) \u2192 [the-nexus#730] [VISUAL] Give Workshop,\
-    \ Archive, Chapel, Courtyard, and Gate distinct Nexus visual identities"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:03.030374+00:00'
-  last_confirmed: '2026-04-26T11:22:03.030404+00:00'
-  related: []
-- id: cross-repo:connection:024
-  fact: "timmy-config references the-nexus via issue #731: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-29 (Sunday) \u2192 [the-nexus#731] [VALIDATION] Browser\
-    \ smoke + visual proof for the Evennia-fed Nexus shell"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:03.245877+00:00'
-  last_confirmed: '2026-04-26T11:22:03.245885+00:00'
-  related: []
-- id: cross-repo:connection:025
-  fact: "timmy-config references the-nexus via issue #736: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-29 (Sunday) \u2192 [the-nexus#736] Perplexity review"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:03.471514+00:00'
-  last_confirmed: '2026-04-26T11:22:03.471536+00:00'
-  related: []
-- id: cross-repo:connection:026
-  fact: "timmy-config references the-nexus via issue #785: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-30 (Monday) \u2192 [the-nexus#785] Implement SharedArrayBuffer\
-    \ for Zero-Copy Data Sharing"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:03.598910+00:00'
-  last_confirmed: '2026-04-26T11:22:03.598925+00:00'
-  related: []
-- id: cross-repo:connection:027
-  fact: "timmy-config references the-nexus via issue #786: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-30 (Monday) \u2192 [the-nexus#786] Implement GPU-Accelerated\
-    \ Knowledge Graph Queries"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:03.762768+00:00'
-  last_confirmed: '2026-04-26T11:22:03.762779+00:00'
-  related: []
-- id: cross-repo:connection:028
-  fact: "timmy-config references the-nexus via issue #787: \u2600\uFE0F Good Morning\
-    \ Report \u2014 2026-03-30 (Monday) \u2192 [the-nexus#787] Implement Hierarchical\
-    \ L1/L2 Cache for Meta-Reasoning"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:03.917083+00:00'
-  last_confirmed: '2026-04-26T11:22:03.917092+00:00'
-  related: []
-- id: cross-repo:connection:029
-  fact: "timmy-home references hermes-agent via issue #72: \U0001F525 Burn Report\
-    \ #5 \u2014 2026-04-01 \u2014 Crisis Safety Test Infrastructure \u2192 [hermes-agent#72]\
-    \ [RED TEAM] Full Jailbreak Audit - Claude Opus 4.6 - 2026-03-30"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:04.071933+00:00'
-  last_confirmed: '2026-04-26T11:22:04.071949+00:00'
-  related: []
-- id: cross-repo:connection:030
-  fact: "timmy-home references hermes-agent via issue #74: [BURN REPORT] SHIELD Security\
-    \ Implementation - Issues #72/#74/#75 \u2192 [hermes-agent#74] [RED TEAM] ULTRAPLINIAN\
-    \ Crisis Stress Test \u2014 22 CRITICAL Failures \u2014 2026-03-31"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:04.214487+00:00'
-  last_confirmed: '2026-04-26T11:22:04.214499+00:00'
-  related: []
-- id: cross-repo:connection:031
-  fact: "timmy-home references hermes-agent via issue #75: [BURN REPORT] SHIELD Security\
-    \ Implementation - Issues #72/#74/#75 \u2192 [hermes-agent#75] [SHIELD] Jailbreak\
-    \ Input Detection Module \u2014 Built Overnight From Red Team Findings"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:04.369176+00:00'
-  last_confirmed: '2026-04-26T11:22:04.369184+00:00'
-  related: []
-- id: cross-repo:connection:032
-  fact: "timmy-home references hermes-agent via issue #79: \U0001F525 Burn Report\
-    \ #5 \u2014 2026-04-01 \u2014 Crisis Safety Test Infrastructure \u2192 [hermes-agent#79]\
-    \ [SECURITY] [CRITICAL] Test og_godmode template against crisis/suicide safety\
-    \ queries"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:04.884029+00:00'
-  last_confirmed: '2026-04-26T11:22:04.884062+00:00'
-  related: []
-- id: cross-repo:connection:033
-  fact: "timmy-home references hermes-agent via issue #80: \U0001F525 Burn Report\
-    \ #5 \u2014 2026-04-01 \u2014 Crisis Safety Test Infrastructure \u2192 [hermes-agent#80]\
-    \ [SECURITY] [HIGH] Implement input sanitization for GODMODE jailbreak patterns"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:05.116347+00:00'
-  last_confirmed: '2026-04-26T11:22:05.116357+00:00'
-  related: []
-- id: cross-repo:connection:034
-  fact: "timmy-home references hermes-agent via issue #81: \U0001F525 Burn Report\
-    \ #5 \u2014 2026-04-01 \u2014 Crisis Safety Test Infrastructure \u2192 [hermes-agent#81]\
-    \ [SECURITY] [MEDIUM] ULTRAPLINIAN follow-up: Red team fallback chain (Kimi, Gemini,\
-    \ Grok, Llama)"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:05.279272+00:00'
-  last_confirmed: '2026-04-26T11:22:05.279284+00:00'
-  related: []
-- id: cross-repo:connection:035
-  fact: "timmy-home references the-nexus via issue #859: [AGENDA] Next burn night\
-    \ \u2014 amplify bounded quick wins, proof-first comments, and overnight leverage\
-    \ \u2192 [the-nexus#859] [AUTOGENESIS][Phase I] Hermes v2.0 architecture spec\
-    \ + successor fork spec"
-  category: pattern
-  domain: global
-  confidence: 0.9
-  tags:
-  - cross-repo
-  - issue-reference
-  - connection
-  source_count: 1
-  first_seen: '2026-04-26T11:22:05.448200+00:00'
-  last_confirmed: '2026-04-26T11:22:05.448207+00:00'
-  related: []

metrics/cross_repo_report.md

@@ -1,57 +0,0 @@
-# Cross-Repo Connection Report
-
-Generated: 2026-04-26T11:22:05.466516+00:00
-Org: Timmy_Foundation
-Repos scanned: 21
-
-## Connections
-
-### hermes-agent
-
-- hermes-agent references compounding-intelligence via issue #229: [ATLAS] Steal the highest-leverage ecosystem patterns into the sovereign stack → [compounding-intelligence#229] [ATLAS][Telemetry] Build local token and cost ingestion using Tokscale core patterns
-- hermes-agent references compounding-intelligence via issue #231: [ATLAS] Steal the highest-leverage ecosystem patterns into the sovereign stack → [compounding-intelligence#231] [ATLAS][Wiki] Build the LLM Wiki layer: ingest, query, lint, and session crystallization into durabl
-- hermes-agent references compounding-intelligence via issue #232: [ATLAS] Steal the highest-leverage ecosystem patterns into the sovereign stack → [compounding-intelligence#232] [ATLAS][Research] Solve the swarm-memory gap for concurrent subagents
-- hermes-agent references fleet-ops via issue #410: [ATLAS] Steal the highest-leverage ecosystem patterns into the sovereign stack → [fleet-ops#410] [ATLAS][Safety] Deploy a virtual-credential and DLP sidecar for sovereign agent runs
-- hermes-agent references the-nexus via issue #893: [CONSOLIDATED] Fleet SITREP — Allegro 7-Task Execution + Ezra Deliverables → [the-nexus#893] [AUDIT] System Formalization — OSS Replacements & Cleanup Candidates
-- hermes-agent references the-nexus via issue #1695: [ATLAS] Steal the highest-leverage ecosystem patterns into the sovereign stack → [the-nexus#1695] [ATLAS][Cockpit] Build the operator inspector rail and session shell patterns worth stealing
-- hermes-agent references timmy-config via issue #875: [ATLAS] Steal the highest-leverage ecosystem patterns into the sovereign stack → [timmy-config#875] [ATLAS][Skills] Import Karpathy-style cognitive principles and GStack-style role commands as native 
-- hermes-agent references timmy-dispatch via issue #18: [ATLAS] Steal the highest-leverage ecosystem patterns into the sovereign stack → [timmy-dispatch#18] [ATLAS][Dispatch] Add Mission Control-style dispatch ledger, capacity model, and heartbeat tracking
-- hermes-agent references timmy-home via issue #568: [DISPATCH] Ezra — Investigate & Install MemPalace on Hermes VPS → [timmy-home#568] [EVALUATION] MemPalace v3.0.0 Integration — Before/After Metrics + Recommendation
-
-### the-nexus
-
-- the-nexus references hermes-agent via issue #984: [ATLAS][Cockpit] Build the operator inspector rail and session shell patterns worth stealing → [hermes-agent#984] [ATLAS] Steal the highest-leverage ecosystem patterns into the sovereign stack
-
-### timmy-config
-
-- timmy-config references the-nexus via issue #501: ☀️ Good Morning Report — 2026-03-26 (Thursday) → [the-nexus#501] [claude] Re-implement gravity anomaly zones (#478)
-- timmy-config references the-nexus via issue #502: ☀️ Good Morning Report — 2026-03-26 (Thursday) → [the-nexus#502] [claude] Time-lapse replay mode (#484)
-- timmy-config references the-nexus via issue #503: ☀️ Good Morning Report — 2026-03-26 (Thursday) → [the-nexus#503] [claude] InstancedMesh optimizations for repeated geometry (#482)
-- timmy-config references the-nexus via issue #552: ☀️ Good Morning Report — 2026-03-26 (Thursday) → [the-nexus#552] [HEARTBEAT] Apprentice protocol — episodic memory logging of desktop activity
-- timmy-config references the-nexus via issue #554: ☀️ Good Morning Report — 2026-03-26 (Thursday) → [the-nexus#554] [ECONOMY] Stand up Cashu Mint on Lightning
-- timmy-config references the-nexus via issue #555: ☀️ Good Morning Report — 2026-03-26 (Thursday) → [the-nexus#555] [ECONOMY] Prototype Bannerlord Denar → Cashu token Harmony patch
-- timmy-config references the-nexus via issue #613: ☀️ Good Morning Report — 2026-03-28 (Saturday) → [the-nexus#613] [gemini] [HARNESS] Shadow Context Manager — auto-generated brain dump for session continuity (#608)
-- timmy-config references the-nexus via issue #673: ☀️ Good Morning Report — 2026-03-28 (Saturday) → [the-nexus#673] [PORTAL] Deterministic Morrowind pilot loop with world-state proof
-- timmy-config references the-nexus via issue #674: ☀️ Good Morning Report — 2026-03-28 (Saturday) → [the-nexus#674] [PORTAL] Reflex tactical layer and semantic trajectory logging
-- timmy-config references the-nexus via issue #675: ☀️ Good Morning Report — 2026-03-28 (Saturday) → [the-nexus#675] [HARNESS] Deterministic context compaction for long local sessions
-- timmy-config references the-nexus via issue #676: ☀️ Good Morning Report — 2026-03-28 (Saturday) → [the-nexus#676] [gemini] [PORTAL] Reflex tactical layer and semantic trajectory logging (#674)
-- timmy-config references the-nexus via issue #677: ☀️ Good Morning Report — 2026-03-28 (Saturday) → [the-nexus#677] [gemini] [HARNESS] Deterministic context compaction for long local sessions (#675)
-- timmy-config references the-nexus via issue #730: ☀️ Good Morning Report — 2026-03-29 (Sunday) → [the-nexus#730] [VISUAL] Give Workshop, Archive, Chapel, Courtyard, and Gate distinct Nexus visual identities
-- timmy-config references the-nexus via issue #731: ☀️ Good Morning Report — 2026-03-29 (Sunday) → [the-nexus#731] [VALIDATION] Browser smoke + visual proof for the Evennia-fed Nexus shell
-- timmy-config references the-nexus via issue #736: ☀️ Good Morning Report — 2026-03-29 (Sunday) → [the-nexus#736] Perplexity review
-- timmy-config references the-nexus via issue #785: ☀️ Good Morning Report — 2026-03-30 (Monday) → [the-nexus#785] Implement SharedArrayBuffer for Zero-Copy Data Sharing
-- timmy-config references the-nexus via issue #786: ☀️ Good Morning Report — 2026-03-30 (Monday) → [the-nexus#786] Implement GPU-Accelerated Knowledge Graph Queries
-- timmy-config references the-nexus via issue #787: ☀️ Good Morning Report — 2026-03-30 (Monday) → [the-nexus#787] Implement Hierarchical L1/L2 Cache for Meta-Reasoning
-
-### timmy-home
-
-- timmy-home references hermes-agent via issue #72: 🔥 Burn Report #5 — 2026-04-01 — Crisis Safety Test Infrastructure → [hermes-agent#72] [RED TEAM] Full Jailbreak Audit - Claude Opus 4.6 - 2026-03-30
-- timmy-home references hermes-agent via issue #74: [BURN REPORT] SHIELD Security Implementation - Issues #72/#74/#75 → [hermes-agent#74] [RED TEAM] ULTRAPLINIAN Crisis Stress Test — 22 CRITICAL Failures — 2026-03-31
-- timmy-home references hermes-agent via issue #75: [BURN REPORT] SHIELD Security Implementation - Issues #72/#74/#75 → [hermes-agent#75] [SHIELD] Jailbreak Input Detection Module — Built Overnight From Red Team Findings
-- timmy-home references hermes-agent via issue #79: 🔥 Burn Report #5 — 2026-04-01 — Crisis Safety Test Infrastructure → [hermes-agent#79] [SECURITY] [CRITICAL] Test og_godmode template against crisis/suicide safety queries
-- timmy-home references hermes-agent via issue #80: 🔥 Burn Report #5 — 2026-04-01 — Crisis Safety Test Infrastructure → [hermes-agent#80] [SECURITY] [HIGH] Implement input sanitization for GODMODE jailbreak patterns
-- timmy-home references hermes-agent via issue #81: 🔥 Burn Report #5 — 2026-04-01 — Crisis Safety Test Infrastructure → [hermes-agent#81] [SECURITY] [MEDIUM] ULTRAPLINIAN follow-up: Red team fallback chain (Kimi, Gemini, Grok, Llama)
-- timmy-home references the-nexus via issue #859: [AGENDA] Next burn night — amplify bounded quick wins, proof-first comments, and overnight leverage → [the-nexus#859] [AUTOGENESIS][Phase I] Hermes v2.0 architecture spec + successor fork spec
-
-
-Total connections: 35

scripts/code_duplication_detector.py

@@ -0,0 +1,366 @@
+#!/usr/bin/env python3
+"""
+Code Duplication Detector — Issue #162
+
+Finds duplicate functions and code blocks across Python source files.
+Reports duplication percentage and outputs a duplication report.
+
+Usage:
+    python3 scripts/code_duplication_detector.py --output reports/code_duplication.json
+    python3 scripts/code_duplication_detector.py --directory scripts/ --dry-run
+    python3 scripts/code_duplication_detector.py --test  # Run built-in test
+"""
+
+import argparse
+import hashlib
+import json
+import os
+import re
+import sys
+from collections import defaultdict
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import List, Dict, Tuple, Optional
+
+
+# ── AST helpers ────────────────────────────────────────────────────────────
+
+def normalize_code(text: str) -> str:
+    """Normalize code for comparison: strip comments, normalize whitespace."""
+    # Remove comments (both # and docstring triple-quote strings)
+    text = re.sub(r'#.*$', '', text, flags=re.MULTILINE)
+    text = re.sub(r'""".*?"""', '', text, flags=re.DOTALL)
+    text = re.sub(r"'''.*?'''", '', text, flags=re.DOTALL)
+    # Normalize whitespace
+    text = re.sub(r'\s+', ' ', text).strip()
+    return text.lower()
+
+
+def code_hash(text: str) -> str:
+    """SHA256 hash of normalized code for exact duplicate detection."""
+    normalized = normalize_code(text)
+    return hashlib.sha256(normalized.encode('utf-8')).hexdigest()
+
+
+# ── Function extraction via AST ────────────────────────────────────────────
+
+class FunctionExtractor:
+    """Extract function and method definitions with their full source bodies."""
+
+    def __init__(self, source: str, filepath: str):
+        self.source = source
+        self.filepath = filepath
+        self.lines = source.splitlines()
+        self.functions: List[Dict] = []
+
+    def _get_source_segment(self, start_lineno: int, end_lineno: int) -> str:
+        """Get source code from start to end line (1-indexed, inclusive)."""
+        # AST end_lineno is inclusive
+        start_idx = start_lineno - 1
+        end_idx = end_lineno
+        return '\n'.join(self.lines[start_idx:end_idx])
+
+    def visit(self, tree):
+        """Collect all function and async function definitions."""
+        for node in ast.walk(tree):
+            if isinstance(node, ast.FunctionDef) or isinstance(node, ast.AsyncFunctionDef):
+                # Get the full source for this function including decorators
+                start = node.lineno
+                end = node.end_lineno
+                body_source = self._get_source_segment(start, end)
+
+                # Also collect parent class name if this is a method
+                class_name = None
+                parent = node.parent if hasattr(node, 'parent') else None
+                if parent and isinstance(parent, ast.ClassDef):
+                    class_name = parent.name
+
+                self.functions.append({
+                    'name': node.name,
+                    'file': self.filepath,
+                    'start_line': start,
+                    'end_line': end,
+                    'body': body_source,
+                    'class_name': class_name,
+                    'is_method': class_name is not None,
+                })
+
+
+import ast
+
+class ParentNodeVisitor(ast.NodeVisitor):
+    """Annotate nodes with parent references."""
+    def __init__(self, parent=None):
+        self.parent = parent
+
+    def generic_visit(self, node):
+        node.parent = self.parent
+        for child in ast.iter_child_nodes(node):
+            self.__class__(child).parent = node
+        super().generic_visit(node)
+
+
+def extract_functions_from_file(filepath: str) -> List[Dict]:
+    """Extract all function definitions from a Python file."""
+    try:
+        with open(filepath, 'r', encoding='utf-8', errors='replace') as f:
+            source = f.read()
+        tree = ast.parse(source, filename=str(filepath))
+
+        # Annotate with parent references
+        for node in ast.walk(tree):
+            for child in ast.iter_child_nodes(node):
+                child.parent = node
+
+        extractor = FunctionExtractor(source, str(filepath))
+        extractor.visit(tree)
+        return extractor.functions
+    except (SyntaxError, UnicodeDecodeError, OSError) as e:
+        return []
+
+
+def scan_directory(directory: str, extensions: Tuple[str, ...] = ('.py',)) -> List[Dict]:
+    """Scan directory for Python files and extract all functions."""
+    all_functions = []
+    path = Path(directory)
+
+    for filepath in path.rglob('*'):
+        if filepath.is_file() and filepath.suffix in extensions:
+            # Skip common non-source dirs
+            parts = filepath.parts
+            if any(ex in parts for ex in ('__pycache__', 'node_modules', '.git', 'venv', '.venv', 'dist', 'build')):
+                continue
+            if filepath.name.startswith('.'):
+                continue
+
+            functions = extract_functions_from_file(str(filepath))
+            all_functions.extend(functions)
+
+    return all_functions
+
+
+# ── Duplicate detection ─────────────────────────────────────────────────────
+
+def find_duplicates(functions: List[Dict], similarity_threshold: float = 0.95) -> Dict:
+    """
+    Find duplicate and near-duplicate functions.
+
+    Returns dict with:
+      - exact_duplicates: {hash: [function_info, ...]}
+      - near_duplicates: [[function_info, ...], ...]
+      - stats: total_functions, unique_exact, exact_dupe_count, near_dupe_count
+    """
+    # Phase 1: Exact duplicates by code hash
+    hash_groups: Dict[str, List[Dict]] = defaultdict(list)
+    for func in functions:
+        h = code_hash(func['body'])
+        hash_groups[h].append(func)
+
+    exact_duplicates = {h: group for h, group in hash_groups.items() if len(group) > 1}
+    exact_dupe_count = sum(len(group) - 1 for group in exact_duplicates.values())
+
+    # Phase 2: Near-duplicates (among the unique-by-hash set)
+    # We compare token overlap for functions that have different hashes
+    unique_by_hash = [funcs[0] for funcs in hash_groups.values()]
+    near_duplicate_groups = []
+
+    # Simple token-based similarity
+    def tokenize(code: str) -> set:
+        return set(re.findall(r'[a-zA-Z_][a-zA-Z0-9_]*', code.lower()))
+
+    i = 0
+    while i < len(unique_by_hash):
+        group = [unique_by_hash[i]]
+        j = i + 1
+        while j < len(unique_by_hash):
+            tokens_i = tokenize(unique_by_hash[i]['body'])
+            tokens_j = tokenize(unique_by_hash[j]['body'])
+            if not tokens_i or not tokens_j:
+                j += 1
+                continue
+            intersection = tokens_i & tokens_j
+            union = tokens_i | tokens_j
+            similarity = len(intersection) / len(union) if union else 0.0
+
+            if similarity >= similarity_threshold:
+                group.append(unique_by_hash[j])
+                unique_by_hash.pop(j)
+            else:
+                j += 1
+
+        if len(group) > 1:
+            near_duplicate_groups.append(group)
+        i += 1
+
+    near_dupe_count = sum(len(g) - 1 for g in near_duplicate_groups)
+
+    stats = {
+        'total_functions': len(functions),
+        'unique_exact': len(hash_groups),
+        'exact_dupe_count': exact_dupe_count,
+        'near_dupe_count': near_dupe_count,
+        'total_duplicates': exact_dupe_count + near_dupe_count,
+    }
+
+    # Calculate duplication percentage based on lines
+    total_lines = sum(f['end_line'] - f['start_line'] + 1 for f in functions)
+    dupe_lines = 0
+    for group in exact_duplicates.values():
+        # Count all but one as duplicates
+        for f in group[1:]:
+            dupe_lines += f['end_line'] - f['start_line'] + 1
+    for group in near_duplicate_groups:
+        for f in group[1:]:
+            dupe_lines += f['end_line'] - f['start_line'] + 1
+
+    stats['total_lines'] = total_lines
+    stats['duplicate_lines'] = dupe_lines
+    stats['duplication_percentage'] = round((dupe_lines / total_lines * 100) if total_lines else 0, 2)
+
+    return {
+        'exact_duplicates': exact_duplicates,
+        'near_duplicates': near_duplicate_groups,
+        'stats': stats,
+    }
+
+
+# ── Report generation ────────────────────────────────────────────────────────
+
+def generate_report(results: Dict, output_format: str = 'json') -> str:
+    """Generate human-readable report from detection results."""
+    stats = results['stats']
+
+    if output_format == 'json':
+        return json.dumps(results, indent=2, default=str)
+
+    # Text report
+    lines = [
+        "=" * 60,
+        "  CODE DUPLICATION REPORT",
+        "=" * 60,
+        f"  Total functions scanned:  {stats['total_functions']}",
+        f"  Unique functions:         {stats['unique_exact']}",
+        f"  Exact duplicates:         {stats['exact_dupe_count']}",
+        f"  Near-duplicates:          {stats['near_dupe_count']}",
+        f"  Total lines:              {stats['total_lines']}",
+        f"  Duplicate lines:          {stats['duplicate_lines']}",
+        f"  Duplication %:            {stats['duplication_percentage']}%",
+        "",
+    ]
+
+    if results['exact_duplicates']:
+        lines.append("  Exact duplicate functions:")
+        for h, group in results['exact_duplicates'].items():
+            first = group[0]
+            lines.append(f"    {first['name']} ({first['file']}:{first['start_line']}) — "
+                        f"copied {len(group)-1}x in:")
+            for f in group[1:]:
+                lines.append(f"      → {f['file']}:{f['start_line']}")
+        lines.append("")
+
+    if results['near_duplicates']:
+        lines.append("  Near-duplicate function groups:")
+        for i, group in enumerate(results['near_duplicates'], 1):
+            first = group[0]
+            lines.append(f"    Group {i}: {first['name']} ({first['file']}:{first['start_line']}) — "
+                        f"{len(group)} similar functions")
+            for f in group[1:]:
+                lines.append(f"      → {f['file']}:{f['start_line']}")
+        lines.append("")
+
+    lines.append("=" * 60)
+    return '\n'.join(lines)
+
+
+# ── CLI ─────────────────────────────────────────────────────────────────────
+
+def main():
+    parser = argparse.ArgumentParser(description="Code Duplication Detector")
+    parser.add_argument('--directory', default='.',
+                        help='Directory to scan (default: current directory)')
+    parser.add_argument('--output', help='Output file for JSON report')
+    parser.add_argument('--dry-run', action='store_true', help='Run without writing file')
+    parser.add_argument('--threshold', type=float, default=0.95,
+                        help='Similarity threshold for near-dupes (default: 0.95)')
+    parser.add_argument('--json', action='store_true', help='JSON output to stdout')
+    parser.add_argument('--test', action='store_true', help='Run built-in test')
+    args = parser.parse_args()
+
+    if args.test:
+        _run_test()
+        return
+
+    # Scan
+    functions = scan_directory(args.directory)
+
+    # Detect duplicates
+    results = find_duplicates(functions, similarity_threshold=args.threshold)
+    stats = results['stats']
+
+    # Output
+    if args.json:
+        print(json.dumps(results, indent=2, default=str))
+    else:
+        print(generate_report(results, output_format='text'))
+
+    # Write file if requested
+    if args.output and not args.dry_run:
+        os.makedirs(os.path.dirname(args.output) or '.', exist_ok=True)
+        with open(args.output, 'w') as f:
+            json.dump(results, f, indent=2, default=str)
+        print(f"\nReport written to: {args.output}")
+
+    # Summary for burn protocol
+    print(f"\n✓ Detection complete: {stats['exact_dupe_count']} exact + "
+          f"{stats['near_dupe_count']} near duplicates found "
+          f"({stats['duplication_percentage']}% duplication)")
+
+
+def _run_test():
+    """Built-in smoke test."""
+    import tempfile
+    import os
+
+    with tempfile.TemporaryDirectory() as tmpdir:
+        # Create test files with duplicate code
+        f1 = Path(tmpdir) / 'mod1.py'
+        f1.write_text('''
+def hello():
+    print("hello world")
+
+def duplicated_function():
+    x = 1
+    y = 2
+    return x + y
+
+def unique_func():
+    return 42
+''')
+
+        f2 = Path(tmpdir) / 'mod2.py'
+        f2.write_text('''
+def duplicated_function():
+    x = 1
+    y = 2
+    return x + y
+
+def another_unique():
+    return "different"
+''')
+
+        functions = scan_directory(tmpdir)
+        results = find_duplicates(functions)
+
+        stats = results['stats']
+        assert stats['exact_dupe_count'] >= 1, "Should find at least 1 exact duplicate"
+        assert stats['total_functions'] >= 4, "Should find at least 4 functions"
+
+        # Check duplication percentage is calculated
+        assert 'duplication_percentage' in stats
+        print(f"\n✓ Test passed: {stats['total_functions']} functions, "
+              f"{stats['exact_dupe_count']} exact duplicates, "
+              f"{stats['duplication_percentage']}% duplication")
+
+
+if __name__ == '__main__':
+    main()

scripts/cross_repo_connector.py

@@ -1,375 +0,0 @@
-#!/usr/bin/env python3
-"""
-Cross-Repo Connector — Issue Reference Scanner (8.4)
-
-Scans all repos in an org for cross-repo issue references. Identifies
-connections where one repo's issue/PR references another repo's issue number.
-
-This is the smallest concrete first step toward full cross-repo analysis.
-Future: extend to code imports, similar patterns.
-
-Usage:
-    python3 scripts/cross_repo_connector.py --org Timmy_Foundation --dry-run
-    python3 scripts/cross_repo_connector.py --org Timmy_Foundation --commit
-
-Output:
-    knowledge/global/cross_repo_connections.yaml  — new facts
-    knowledge/index.json                          — updated index
-    metrics/cross_repo_report.md                  — human-readable summary
-"""
-
-import argparse
-import json
-import os
-import re
-import sys
-from collections import defaultdict
-from datetime import datetime, timezone
-from pathlib import Path
-from typing import Dict, List, Optional, Tuple
-import urllib.request
-import urllib.error
-
-
-GITEA_URL = "https://forge.alexanderwhitestone.com"
-
-
-# ── GiteaClient (lifted from priority_rebalancer.py, minimal subset) ──────
-
-class GiteaClient:
-    def __init__(self, base_url: str, token: str):
-        self.base_url = base_url.rstrip("/")
-        self.token = token
-
-    def _request(self, path: str, params: dict = None) -> any:
-        url = f"{self.base_url}/api/v1{path}"
-        if params:
-            qs = "&".join(f"{k}={v}" for k, v in params.items() if v is not None)
-            url += f"?{qs}"
-        req = urllib.request.Request(url)
-        req.add_header("Authorization", f"token {self.token}")
-        req.add_header("Content-Type", "application/json")
-        try:
-            with urllib.request.urlopen(req, timeout=30) as resp:
-                return json.loads(resp.read().decode())
-        except urllib.error.HTTPError as e:
-            print(f"API error {e.code} for {path}: {e.read().decode()[:200]}", file=sys.stderr)
-            return None
-
-    def get_org_repos(self, org: str) -> List[dict]:
-        repos = []
-        page = 1
-        while True:
-            batch = self._request(f"/orgs/{org}/repos", {"limit": 50, "page": page})
-            if not batch:
-                break
-            repos.extend(batch)
-            if len(batch) < 50:
-                break
-            page += 1
-        return repos
-
-    def get_issues(self, org: str, repo: str, state: str = "closed") -> List[dict]:
-        """Fetch issues (and PRs, which Gitea returns together) for a repo."""
-        issues = []
-        page = 1
-        while True:
-            batch = self._request(
-                f"/repos/{org}/{repo}/issues",
-                {"state": state, "limit": 50, "page": page, "type": "issues"}
-            )
-            if not batch:
-                break
-            issues.extend(batch)
-            if len(batch) < 50:
-                break
-            page += 1
-        return issues
-
-    def get_issue(self, org: str, repo: str, issue_num: int) -> Optional[dict]:
-        return self._request(f"/repos/{org}/{repo}/issues/{issue_num}")
-
-
-# ── Token handling ──────────────────────────────────────────────────────────
-
-def get_token() -> str:
-    """Read Gitea token from ~/.config/gitea/token or $GITEA_TOKEN."""
-    token_path = Path.home() / ".config" / "gitea" / "token"
-    if token_path.exists():
-        return token_path.read_text().strip()
-    env_token = os.environ.get("GITEA_TOKEN", "")
-    if env_token:
-        return env_token
-    raise FileNotFoundError(
-        "Gitea token not found. Create ~/.config/gitea/token or set $GITEA_TOKEN."
-    )
-
-
-# ── Cross-reference extraction ──────────────────────────────────────────────
-
-# Patterns that reference another repo's issue/PR:
-#   - Timmy_Foundation/other-repo#123
-#   - Timmy_Foundation/other-repo/issues/123
-#   - full URL: https://forge.../Timmy_Foundation/other-repo/issues/123
-#   - just "#123" — needs resolving via linked issue numbers (more complex, skip for v1)
-
-CROSS_REF_PATTERN = re.compile(
-    r"(?:Timmy_Foundation/([\w.-]+)#(\d+))"
-    r"|(?:Timmy_Foundation/([\w.-]+)/issues/(\d+))"
-    r"|(?:https?://[^/]+/Timmy_Foundation/([\w.-]+)/issues/(\d+))"
-)
-
-
-def extract_cross_repo_refs(text: str, own_repo: str) -> List[Tuple[str, int]]:
-    """
-    Return list of (other_repo, issue_number) tuples found in text.
-    Excludes references to the same repo.
-    """
-    matches = []
-    for m in CROSS_REF_PATTERN.finditer(text or ""):
-        repo = m.group(1) or m.group(3) or m.group(5)
-        num = m.group(2) or m.group(4) or m.group(6)
-        if repo and num:
-            repo = repo.lower().replace("_", "-")
-            if repo != own_repo.lower().replace("_", "-"):
-                matches.append((repo, int(num)))
-    return matches
-
-
-# ── Knowledge store helpers ──────────────────────────────────────────────────
-
-def load_index(index_path: Path) -> dict:
-    if index_path.exists():
-        with index_path.open() as f:
-            return json.load(f)
-    return {"version": 1, "last_updated": "", "total_facts": 0, "facts": []}
-
-
-def save_index(index: dict, index_path: Path) -> None:
-    index["version"] = 1
-    index["last_updated"] = datetime.now(timezone.utc).isoformat()
-    index["total_facts"] = len(index["facts"])
-    with index_path.open("w") as f:
-        json.dump(index, f, indent=2, sort_keys=True, ensure_ascii=False)
-
-
-def generate_fact_id(domain: str, category: str, sequence: int) -> str:
-    return f"{domain}:{category}:{sequence:03d}"
-
-
-def make_connection_fact(
-    source_repo: str,
-    target_repo: str,
-    issue_num: int,
-    source_title: str,
-    target_title: Optional[str] = None,
-) -> dict:
-    """Create a cross-repo connection fact."""
-    fact_text = (
-        f"{source_repo} references {target_repo} via issue #{issue_num}: "
-        f"{source_title[:100]}"
-    )
-    if target_title:
-        fact_text += f" → [{target_repo}#{issue_num}] {target_title[:100]}"
-    return {
-        "id": "cross-repo:connection:TBD",  # filled by caller with seq
-        "fact": fact_text,
-        "category": "pattern",   # cross-repo reference is a discovered pattern
-        "domain": "global",      # applies org-wide
-        "confidence": 0.9,
-        "tags": ["cross-repo", "issue-reference", "connection"],
-        "source_count": 1,
-        "first_seen": datetime.now(timezone.utc).isoformat(),
-        "last_confirmed": datetime.now(timezone.utc).isoformat(),
-        "related": [],
-    }
-
-
-def append_to_global_yaml(facts: List[dict], knowledge_dir: Path) -> None:
-    """Append new cross-repo facts to knowledge/global/cross_repo.yaml."""
-    global_dir = knowledge_dir / "global"
-    global_dir.mkdir(parents=True, exist_ok=True)
-    yaml_path = global_dir / "cross_repo.yaml"
-
-    # Load existing YAML documents (may be dict or list-of-dict)
-    existing_docs = []
-    if yaml_path.exists():
-        with yaml_path.open() as f:
-            try:
-                import yaml
-                existing_docs = list(yaml.safe_load_all(f)) or []
-            except Exception:
-                existing_docs = []
-
-    # Normalize to dict documents (unwrap single-element lists)
-    normalized = []
-    for doc in existing_docs:
-        if isinstance(doc, dict):
-            normalized.append(doc)
-        elif isinstance(doc, list) and len(doc) == 1 and isinstance(doc[0], dict):
-            normalized.append(doc[0])
-
-    # Determine next sequence number
-    max_seq = 0
-    for doc in normalized:
-        for f_item in doc.get("facts", []):
-            fid = f_item.get("id", "")
-            if fid.startswith("cross-repo:"):
-                try:
-                    seq = int(fid.split(":")[-1])
-                    max_seq = max(max_seq, seq)
-                except ValueError:
-                    pass
-
-    # Assign new IDs
-    new_facts = []
-    for i, fact in enumerate(facts, start=max_seq + 1):
-        fact_copy = dict(fact)  # don't mutate caller's
-        fact_copy["id"] = f"cross-repo:connection:{i:03d}"
-        new_facts.append(fact_copy)
-
-    if not new_facts:
-        return
-
-    # New YAML document (dict, not list)
-    new_doc = {
-        "domain": "global",
-        "category": "pattern",
-        "version": 1,
-        "last_updated": datetime.now(timezone.utc).isoformat(),
-        "facts": new_facts,
-    }
-
-    # Append document
-    with yaml_path.open("a") as f:
-        f.write("\n---\n")
-        import yaml
-        yaml.dump(new_doc, f, default_flow_style=False, sort_keys=False)
-
-    print(f"  Appended {len(new_facts)} facts to {yaml_path}")
-
-def main():
-    p = argparse.ArgumentParser(description="Cross-repo issue reference connector")
-    p.add_argument("--org", default="Timmy_Foundation", help="Org to scan")
-    p.add_argument("--dry-run", action="store_true", help="Don't write knowledge files")
-    p.add_argument("--state", default="closed", choices=["open", "closed", "all"],
-                   help="Issue state to scan (default: closed)")
-    p.add_argument("--limit-repos", type=int, help="Max repos to process (dev)")
-    p.add_argument("--limit-issues", type=int, help="Max issues per repo (dev)")
-    args = p.parse_args()
-
-    token = get_token()
-    client = GiteaClient(GITEA_URL, token)
-    knowledge_dir = Path("knowledge")
-    index_path = knowledge_dir / "index.json"
-
-    print(f"Fetching org repos…")
-    repos = client.get_org_repos(args.org)
-    print(f"Found {len(repos)} repos in {args.org}")
-
-    if args.limit_repos:
-        repos = repos[:args.limit_repos]
-        print(f"  (limited to {args.limit_repos})")
-
-    # Build repo name -> info map
-    repo_info = {r["name"].lower(): r for r in repos}
-
-    # Step 1: collect all cross-repo references from issues
-    # ((source_repo, target_repo, issue_num, source_title))
-    raw_connections = []
-    for repo_meta in repos:
-        repo_name = repo_meta["name"]
-        print(f"\nScanning {repo_name} issues…")
-        issues = client.get_issues(args.org, repo_name, state=args.state)
-        print(f"  {len(issues)} {args.state} issues")
-        if args.limit_issues:
-            issues = issues[:args.limit_issues]
-
-        for issue in issues:
-            body = issue.get("body", "") or ""
-            title = issue.get("title", "") or ""
-            refs = extract_cross_repo_refs(body + "\n" + title, repo_name)
-            for target_repo, num in refs:
-                raw_connections.append((repo_name, target_repo, num, title))
-
-    print(f"\nFound {len(raw_connections)} cross-repo reference(s).")
-
-    # Deduplicate: (source_repo, target_repo, issue_num) → best title
-    connection_map = {}  # (src, tgt, num) → title
-    for src, tgt, num, title in raw_connections:
-        key = (src.lower(), tgt.lower(), num)
-        if key not in connection_map or len(title) > len(connection_map[key]):
-            connection_map[key] = title
-
-    print(f"Unique connections: {len(connection_map)}")
-
-    if args.dry_run:
-        print("\nDry-run — not writing knowledge files.")
-        print("\nDiscovered connections:")
-        for (src, tgt, num), title in sorted(connection_map.items()):
-            print(f"  {src} → {tgt}#{num}: {title[:80]}")
-        return 0
-
-    # Step 2: For each unique connection, try to resolve target issue title
-    # to enrich the fact text
-    resolved_facts = []
-    for (src, tgt, num), src_title in sorted(connection_map.items()):
-        target_title = None
-        try:
-            target_issue = client.get_issue(args.org, tgt, num)
-            if target_issue:
-                target_title = target_issue.get("title", "")
-        except Exception as e:
-            print(f"  Could not fetch {tgt}#{num}: {e}", file=sys.stderr)
-
-        fact = make_connection_fact(src, tgt, num, src_title, target_title)
-        # Temporary ID — will be assigned when we know sequence
-        resolved_facts.append(fact)
-
-    # Step 3: Update index.json
-    index = load_index(index_path)
-    next_seq = max(
-        [int(f["id"].split(":")[-1]) for f in index["facts"]
-         if f["id"].startswith("cross-repo:")]
-    ) + 1 if any(f["id"].startswith("cross-repo:") for f in index["facts"]) else 1
-
-    for i, fact in enumerate(resolved_facts):
-        fact["id"] = f"cross-repo:connection:{next_seq + i:03d}"
-        index["facts"].append(fact)
-
-    save_index(index, index_path)
-    print(f"\n✓ Updated knowledge/index.json (+{len(resolved_facts)} facts)")
-
-    # Step 4: Write to global YAML
-    append_to_global_yaml(resolved_facts, knowledge_dir)
-
-    # Step 5: Generate metrics/report
-    metrics_dir = Path("metrics")
-    metrics_dir.mkdir(exist_ok=True)
-    report_path = metrics_dir / "cross_repo_report.md"
-    with report_path.open("w") as f:
-        f.write(f"# Cross-Repo Connection Report\n\n")
-        f.write(f"Generated: {datetime.now(timezone.utc).isoformat()}\n")
-        f.write(f"Org: {args.org}\n")
-        f.write(f"Repos scanned: {len(repos)}\n")
-        f.write(f"\n## Connections\n\n")
-        by_source = defaultdict(list)
-        for fact in resolved_facts:
-            src = fact["fact"].split(" ")[0]
-            by_source[src].append(fact)
-        for src in sorted(by_source.keys()):
-            f.write(f"### {src}\n\n")
-            for fact in by_source[src]:
-                f.write(f"- {fact['fact']}\n")
-            f.write("\n")
-        f.write(f"\nTotal connections: {len(resolved_facts)}\n")
-
-    print(f"✓ Wrote {report_path}")
-
-    print(f"\nDone. Next: run validation:")
-    print(f"  python3 scripts/validate_knowledge.py")
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())

scripts/pr_complexity_scorer.py

@@ -0,0 +1,351 @@
+#!/usr/bin/env python3
+"""
+PR Complexity Scorer - Estimate review effort for PRs.
+"""
+
+import argparse
+import json
+import os
+import re
+import sys
+from dataclasses import dataclass, asdict
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+import urllib.request
+import urllib.error
+
+GITEA_BASE = "https://forge.alexanderwhitestone.com/api/v1"
+
+DEPENDENCY_FILES = {
+    "requirements.txt", "pyproject.toml", "setup.py", "setup.cfg",
+    "Pipfile", "poetry.lock", "package.json", "yarn.lock", "Gemfile",
+    "go.mod", "Cargo.toml", "pom.xml", "build.gradle"
+}
+
+TEST_PATTERNS = [
+    r"tests?/.*\.py$", r".*_test\.py$", r"test_.*\.py$",
+    r"spec/.*\.rb$", r".*_spec\.rb$",
+    r"__tests__/", r".*\.test\.(js|ts|jsx|tsx)$"
+]
+
+WEIGHT_FILES = 0.25
+WEIGHT_LINES = 0.25
+WEIGHT_DEPS = 0.30
+WEIGHT_TEST_COV = 0.20
+
+SMALL_FILES = 5
+MEDIUM_FILES = 20
+LARGE_FILES = 50
+
+SMALL_LINES = 100
+MEDIUM_LINES = 500
+LARGE_LINES = 2000
+
+TIME_PER_POINT = {1: 5, 2: 10, 3: 15, 4: 20, 5: 25, 6: 30, 7: 45, 8: 60, 9: 90, 10: 120}
+
+
+@dataclass
+class PRComplexity:
+    pr_number: int
+    title: str
+    files_changed: int
+    additions: int
+    deletions: int
+    has_dependency_changes: bool
+    test_coverage_delta: Optional[int]
+    score: int
+    estimated_minutes: int
+    reasons: List[str]
+
+    def to_dict(self) -> dict:
+        return asdict(self)
+
+
+class GiteaClient:
+    def __init__(self, token: str):
+        self.token = token
+        self.base_url = GITEA_BASE.rstrip("/")
+
+    def _request(self, path: str, params: Dict = None) -> Any:
+        url = f"{self.base_url}{path}"
+        if params:
+            qs = "&".join(f"{k}={v}" for k, v in params.items() if v is not None)
+            url += f"?{qs}"
+
+        req = urllib.request.Request(url)
+        req.add_header("Authorization", f"token {self.token}")
+        req.add_header("Content-Type", "application/json")
+
+        try:
+            with urllib.request.urlopen(req, timeout=30) as resp:
+                return json.loads(resp.read().decode())
+        except urllib.error.HTTPError as e:
+            print(f"API error {e.code}: {e.read().decode()[:200]}", file=sys.stderr)
+            return None
+        except urllib.error.URLError as e:
+            print(f"Network error: {e}", file=sys.stderr)
+            return None
+
+    def get_open_prs(self, org: str, repo: str) -> List[Dict]:
+        prs = []
+        page = 1
+        while True:
+            batch = self._request(f"/repos/{org}/{repo}/pulls", {"limit": 50, "page": page, "state": "open"})
+            if not batch:
+                break
+            prs.extend(batch)
+            if len(batch) < 50:
+                break
+            page += 1
+        return prs
+
+    def get_pr_files(self, org: str, repo: str, pr_number: int) -> List[Dict]:
+        files = []
+        page = 1
+        while True:
+            batch = self._request(
+                f"/repos/{org}/{repo}/pulls/{pr_number}/files",
+                {"limit": 100, "page": page}
+            )
+            if not batch:
+                break
+            files.extend(batch)
+            if len(batch) < 100:
+                break
+            page += 1
+        return files
+
+    def post_comment(self, org: str, repo: str, pr_number: int, body: str) -> bool:
+        data = json.dumps({"body": body}).encode("utf-8")
+        req = urllib.request.Request(
+            f"{self.base_url}/repos/{org}/{repo}/issues/{pr_number}/comments",
+            data=data,
+            method="POST",
+            headers={"Authorization": f"token {self.token}", "Content-Type": "application/json"}
+        )
+        try:
+            with urllib.request.urlopen(req, timeout=30) as resp:
+                return resp.status in (200, 201)
+        except urllib.error.HTTPError:
+            return False
+
+
+def is_dependency_file(filename: str) -> bool:
+    return any(filename.endswith(dep) for dep in DEPENDENCY_FILES)
+
+
+def is_test_file(filename: str) -> bool:
+    return any(re.search(pattern, filename) for pattern in TEST_PATTERNS)
+
+
+def score_pr(
+    files_changed: int,
+    additions: int,
+    deletions: int,
+    has_dependency_changes: bool,
+    test_coverage_delta: Optional[int] = None
+) -> tuple[int, int, List[str]]:
+    score = 1.0
+    reasons = []
+
+    # Files changed
+    if files_changed <= SMALL_FILES:
+        fscore = 1.0
+        reasons.append("small number of files changed")
+    elif files_changed <= MEDIUM_FILES:
+        fscore = 2.0
+        reasons.append("moderate number of files changed")
+    elif files_changed <= LARGE_FILES:
+        fscore = 2.5
+        reasons.append("large number of files changed")
+    else:
+        fscore = 3.0
+        reasons.append("very large PR spanning many files")
+
+    # Lines changed
+    total_lines = additions + deletions
+    if total_lines <= SMALL_LINES:
+        lscore = 1.0
+        reasons.append("small change size")
+    elif total_lines <= MEDIUM_LINES:
+        lscore = 2.0
+        reasons.append("moderate change size")
+    elif total_lines <= LARGE_LINES:
+        lscore = 3.0
+        reasons.append("large change size")
+    else:
+        lscore = 4.0
+        reasons.append("very large change")
+
+    # Dependency changes
+    if has_dependency_changes:
+        dscore = 2.5
+        reasons.append("dependency changes (architectural impact)")
+    else:
+        dscore = 0.0
+
+    # Test coverage delta
+    tscore = 0.0
+    if test_coverage_delta is not None:
+        if test_coverage_delta > 0:
+            reasons.append(f"test additions (+{test_coverage_delta} test files)")
+            tscore = -min(2.0, test_coverage_delta / 2.0)
+        elif test_coverage_delta < 0:
+            reasons.append(f"test removals ({abs(test_coverage_delta)} test files)")
+            tscore = min(2.0, abs(test_coverage_delta) * 0.5)
+    else:
+        reasons.append("test coverage change not assessed")
+
+    # Weighted sum, scaled by 3 to use full 1-10 range
+    bonus = (fscore * WEIGHT_FILES) + (lscore * WEIGHT_LINES) + (dscore * WEIGHT_DEPS) + (tscore * WEIGHT_TEST_COV)
+    scaled_bonus = bonus * 3.0
+    score = 1.0 + scaled_bonus
+
+    final_score = max(1, min(10, int(round(score))))
+    est_minutes = TIME_PER_POINT.get(final_score, 30)
+
+    return final_score, est_minutes, reasons
+
+
+def analyze_pr(client: GiteaClient, org: str, repo: str, pr_data: Dict) -> PRComplexity:
+    pr_num = pr_data["number"]
+    title = pr_data.get("title", "")
+    files = client.get_pr_files(org, repo, pr_num)
+
+    additions = sum(f.get("additions", 0) for f in files)
+    deletions = sum(f.get("deletions", 0) for f in files)
+    filenames = [f.get("filename", "") for f in files]
+
+    has_deps = any(is_dependency_file(f) for f in filenames)
+
+    test_added = sum(1 for f in files if f.get("status") == "added" and is_test_file(f.get("filename", "")))
+    test_removed = sum(1 for f in files if f.get("status") == "removed" and is_test_file(f.get("filename", "")))
+    test_delta = test_added - test_removed if (test_added or test_removed) else None
+
+    score, est_min, reasons = score_pr(
+        files_changed=len(files),
+        additions=additions,
+        deletions=deletions,
+        has_dependency_changes=has_deps,
+        test_coverage_delta=test_delta
+    )
+
+    return PRComplexity(
+        pr_number=pr_num,
+        title=title,
+        files_changed=len(files),
+        additions=additions,
+        deletions=deletions,
+        has_dependency_changes=has_deps,
+        test_coverage_delta=test_delta,
+        score=score,
+        estimated_minutes=est_min,
+        reasons=reasons
+    )
+
+
+def build_comment(complexity: PRComplexity) -> str:
+    change_desc = f"{complexity.files_changed} files, +{complexity.additions}/-{complexity.deletions} lines"
+    deps_note = "\n- :warning: Dependency changes detected — architectural review recommended" if complexity.has_dependency_changes else ""
+    test_note = ""
+    if complexity.test_coverage_delta is not None:
+        if complexity.test_coverage_delta > 0:
+            test_note = f"\n- :+1: {complexity.test_coverage_delta} test file(s) added"
+        elif complexity.test_coverage_delta < 0:
+            test_note = f"\n- :warning: {abs(complexity.test_coverage_delta)} test file(s) removed"
+
+    comment = f"## 📊 PR Complexity Analysis\n\n"
+    comment += f"**PR #{complexity.pr_number}: {complexity.title}**\n\n"
+    comment += f"| Metric | Value |\n|--------|-------|\n"
+    comment += f"| Changes | {change_desc} |\n"
+    comment += f"| Complexity Score | **{complexity.score}/10** |\n"
+    comment += f"| Estimated Review Time | ~{complexity.estimated_minutes} minutes |\n\n"
+    comment += f"### Scoring rationale:"
+    for r in complexity.reasons:
+        comment += f"\n- {r}"
+    if deps_note:
+        comment += deps_note
+    if test_note:
+        comment += test_note
+    comment += f"\n\n---\n"
+    comment += f"*Generated by PR Complexity Scorer — [issue #135](https://forge.alexanderwhitestone.com/Timmy_Foundation/compounding-intelligence/issues/135)*"
+    return comment
+
+
+def main():
+    parser = argparse.ArgumentParser(description="PR Complexity Scorer")
+    parser.add_argument("--org", default="Timmy_Foundation")
+    parser.add_argument("--repo", default="compounding-intelligence")
+    parser.add_argument("--token", default=os.environ.get("GITEA_TOKEN") or os.path.expanduser("~/.config/gitea/token"))
+    parser.add_argument("--dry-run", action="store_true")
+    parser.add_argument("--apply", action="store_true")
+    parser.add_argument("--output", default="metrics/pr_complexity.json")
+    args = parser.parse_args()
+
+    token_path = args.token
+    if os.path.exists(token_path):
+        with open(token_path) as f:
+            token = f.read().strip()
+    else:
+        token = args.token
+
+    if not token:
+        print("ERROR: No Gitea token provided", file=sys.stderr)
+        sys.exit(1)
+
+    client = GiteaClient(token)
+
+    print(f"Fetching open PRs for {args.org}/{args.repo}...")
+    prs = client.get_open_prs(args.org, args.repo)
+    if not prs:
+        print("No open PRs found.")
+        sys.exit(0)
+
+    print(f"Found {len(prs)} open PR(s). Analyzing...")
+
+    results = []
+    Path(args.output).parent.mkdir(parents=True, exist_ok=True)
+
+    for pr in prs:
+        pr_num = pr["number"]
+        title = pr.get("title", "")
+        print(f"  Analyzing PR #{pr_num}: {title[:60]}")
+
+        try:
+            complexity = analyze_pr(client, args.org, args.repo, pr)
+            results.append(complexity.to_dict())
+
+            comment = build_comment(complexity)
+
+            if args.dry_run:
+                print(f"    → Score: {complexity.score}/10, Est: {complexity.estimated_minutes}min [DRY-RUN]")
+            elif args.apply:
+                success = client.post_comment(args.org, args.repo, pr_num, comment)
+                status = "[commented]" if success else "[FAILED]"
+                print(f"    → Score: {complexity.score}/10, Est: {complexity.estimated_minutes}min {status}")
+            else:
+                print(f"    → Score: {complexity.score}/10, Est: {complexity.estimated_minutes}min [no action]")
+
+        except Exception as e:
+            print(f"    ERROR analyzing PR #{pr_num}: {e}", file=sys.stderr)
+
+    with open(args.output, "w") as f:
+        json.dump({
+            "org": args.org,
+            "repo": args.repo,
+            "timestamp": datetime.now(timezone.utc).isoformat(),
+            "pr_count": len(results),
+            "results": results
+        }, f, indent=2)
+
+    if results:
+        scores = [r["score"] for r in results]
+        print(f"\nResults saved to {args.output}")
+        print(f"Summary: {len(results)} PRs, scores range {min(scores):.0f}-{max(scores):.0f}")
+    else:
+        print("\nNo results to save.")
+
+
+if __name__ == "__main__":
+    main()

scripts/test_code_duplication_detector.py

@@ -0,0 +1,168 @@
+#!/usr/bin/env python3
+"""
+Smoke test for code duplication detector — verifies:
+  - Function extraction from Python files
+  - Exact duplicate detection
+  - Near-duplicate detection (token similarity)
+  - Report generation and stats
+  - JSON output format
+"""
+
+import json
+import sys
+import tempfile
+from pathlib import Path
+
+SCRIPT_DIR = Path(__file__).parent.absolute()
+sys.path.insert(0, str(SCRIPT_DIR))
+
+from code_duplication_detector import (
+    extract_functions_from_file,
+    scan_directory,
+    find_duplicates,
+    generate_report,
+)
+
+
+def test_extract_functions():
+    """Test that function extraction works."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        test_file = Path(tmpdir) / 'sample.py'
+        test_file.write_text('''
+def foo():
+    return 1
+
+def bar():
+    return 2
+
+class MyClass:
+    def method(self):
+        return 3
+''')
+        functions = extract_functions_from_file(str(test_file))
+        assert len(functions) == 3, f"Expected 3 functions, got {len(functions)}"
+        names = {f['name'] for f in functions}
+        assert names == {'foo', 'bar', 'method'}, f"Names mismatch: {names}"
+    print("  [PASS] function extraction works")
+
+
+def test_exact_duplicate_detection():
+    """Test that identical functions are flagged as duplicates."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        # Create two files with the same function
+        f1 = Path(tmpdir) / 'a.py'
+        f1.write_text('''
+def duplicated():
+    x = 1
+    y = 2
+    return x + y
+''')
+        f2 = Path(tmpdir) / 'b.py'
+        f2.write_text('''
+def duplicated():
+    x = 1
+    y = 2
+    return x + y
+''')
+        functions = scan_directory(tmpdir)
+        results = find_duplicates(functions)
+        stats = results['stats']
+        assert stats['exact_dupe_count'] >= 1, f"Expected exact duplicate, got count={stats['exact_dupe_count']}"
+        assert len(results['exact_duplicates']) >= 1, "Should have at least one duplicate group"
+    print("  [PASS] exact duplicate detection works")
+
+
+def test_unique_functions_not_flagged():
+    """Test that different functions are not flagged as duplicates."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        f1 = Path(tmpdir) / 'a.py'
+        f1.write_text('def func_a(): return 1')
+        f2 = Path(tmpdir) / 'b.py'
+        f2.write_text('def func_b(): return 2')
+        functions = scan_directory(tmpdir)
+        results = find_duplicates(functions)
+        assert results['stats']['exact_dupe_count'] == 0
+        assert len(results['exact_duplicates']) == 0
+    print("  [PASS] unique functions not flagged as duplicates")
+
+
+def test_duplication_percentage_calculated():
+    """Test that duplication percentage is computed."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        # Create file with mostly duplicated content
+        f1 = Path(tmpdir) / 'a.py'
+        f1.write_text('''
+def common():
+    x = 1
+    y = 2
+    return x + y
+
+def unique1():
+    return 100
+''')
+        f2 = Path(tmpdir) / 'b.py'
+        f2.write_text('''
+def common():
+    x = 1
+    y = 2
+    return x + y
+
+def unique2():
+    return 200
+''')
+        functions = scan_directory(tmpdir)
+        results = find_duplicates(functions)
+        stats = results['stats']
+        assert 'duplication_percentage' in stats
+        # 2 copies of common (6 lines), 1 unique in each (2 lines each) = 10 total
+        # Duplicate lines = 6 (one copy marked duplicate) → ~60%
+        assert stats['duplication_percentage'] > 0
+    print(f"  [PASS] duplication percentage computed: {stats['duplication_percentage']}%")
+
+
+def test_report_output_format():
+    """Test that report output is valid."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        f1 = Path(tmpdir) / 'a.py'
+        f1.write_text('def dup(): return 1')
+        f2 = Path(tmpdir) / 'b.py'
+        f2.write_text('def dup(): return 1')
+        functions = scan_directory(tmpdir)
+        results = find_duplicates(functions)
+
+        # Text report
+        text = generate_report(results, output_format='text')
+        assert 'CODE DUPLICATION REPORT' in text
+        assert 'Total functions' in text
+        print("  [PASS] text report format valid")
+
+        # JSON report
+        json_out = generate_report(results, output_format='json')
+        data = json.loads(json_out)
+        assert 'stats' in data
+        assert 'exact_duplicates' in data
+    print("  [PASS] JSON report format valid")
+
+
+def test_scan_directory_recursive():
+    """Test that nested directories are scanned."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        subdir = Path(tmpdir) / 'sub'
+        subdir.mkdir()
+        (subdir / 'nested.py').write_text('def nested(): pass')
+        (Path(tmpdir) / 'root.py').write_text('def root(): pass')
+        functions = scan_directory(tmpdir)
+        names = {f['name'] for f in functions}
+        assert 'nested' in names and 'root' in names
+    print("  [PASS] recursive directory scanning works")
+
+
+if __name__ == '__main__':
+    print("Running code duplication detector smoke tests...")
+    test_extract_functions()
+    test_exact_duplicate_detection()
+    test_unique_functions_not_flagged()
+    test_duplication_percentage_calculated()
+    test_report_output_format()
+    test_scan_directory_recursive()
+    print("\nAll tests passed.")

scripts/test_pr_complexity_scorer.py

@@ -0,0 +1,170 @@
+#!/usr/bin/env python3
+"""
+Tests for PR Complexity Scorer — unit tests for the scoring logic.
+"""
+
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent))
+
+from pr_complexity_scorer import (
+    score_pr,
+    is_dependency_file,
+    is_test_file,
+    TIME_PER_POINT,
+    SMALL_FILES,
+    MEDIUM_FILES,
+    LARGE_FILES,
+    SMALL_LINES,
+    MEDIUM_LINES,
+    LARGE_LINES,
+)
+
+PASS = 0
+FAIL = 0
+
+def test(name):
+    def decorator(fn):
+        global PASS, FAIL
+        try:
+            fn()
+            PASS += 1
+            print(f"  [PASS] {name}")
+        except AssertionError as e:
+            FAIL += 1
+            print(f"  [FAIL] {name}: {e}")
+        except Exception as e:
+            FAIL += 1
+            print(f"  [FAIL] {name}: Unexpected error: {e}")
+    return decorator
+
+def assert_eq(a, b, msg=""):
+    if a != b:
+        raise AssertionError(f"{msg} expected {b!r}, got {a!r}")
+
+def assert_true(v, msg=""):
+    if not v:
+        raise AssertionError(msg or "Expected True")
+
+def assert_false(v, msg=""):
+    if v:
+        raise AssertionError(msg or "Expected False")
+
+
+print("=== PR Complexity Scorer Tests ===\n")
+
+print("-- File Classification --")
+
+@test("dependency file detection — requirements.txt")
+def _():
+    assert_true(is_dependency_file("requirements.txt"))
+    assert_true(is_dependency_file("src/requirements.txt"))
+    assert_false(is_dependency_file("requirements_test.txt"))
+
+@test("dependency file detection — pyproject.toml")
+def _():
+    assert_true(is_dependency_file("pyproject.toml"))
+    assert_false(is_dependency_file("myproject.py"))
+
+@test("test file detection — pytest style")
+def _():
+    assert_true(is_test_file("tests/test_api.py"))
+    assert_true(is_test_file("test_module.py"))
+    assert_true(is_test_file("src/module_test.py"))
+
+@test("test file detection — other frameworks")
+def _():
+    assert_true(is_test_file("spec/feature_spec.rb"))
+    assert_true(is_test_file("__tests__/component.test.js"))
+    assert_false(is_test_file("testfixtures/helper.py"))
+
+
+print("\n-- Scoring Logic --")
+
+@test("small PR gets low score (1-3)")
+def _():
+    score, minutes, _ = score_pr(
+        files_changed=3,
+        additions=50,
+        deletions=10,
+        has_dependency_changes=False,
+        test_coverage_delta=None
+    )
+    assert_true(1 <= score <= 3, f"Score should be low, got {score}")
+    assert_true(minutes < 20)
+
+@test("medium PR gets medium score (4-6)")
+def _():
+    score, minutes, _ = score_pr(
+        files_changed=15,
+        additions=400,
+        deletions=100,
+        has_dependency_changes=False,
+        test_coverage_delta=None
+    )
+    assert_true(4 <= score <= 6, f"Score should be medium, got {score}")
+    assert_true(20 <= minutes <= 45)
+
+@test("large PR gets high score (7-9)")
+def _():
+    score, minutes, _ = score_pr(
+        files_changed=60,
+        additions=3000,
+        deletions=1500,
+        has_dependency_changes=True,
+        test_coverage_delta=None
+    )
+    assert_true(7 <= score <= 9, f"Score should be high, got {score}")
+    assert_true(minutes >= 45)
+
+@test("dependency changes boost score")
+def _():
+    base_score, _, _ = score_pr(
+        files_changed=10, additions=200, deletions=50,
+        has_dependency_changes=False, test_coverage_delta=None
+    )
+    dep_score, _, _ = score_pr(
+        files_changed=10, additions=200, deletions=50,
+        has_dependency_changes=True, test_coverage_delta=None
+    )
+    assert_true(dep_score > base_score, f"Deps: {base_score} -> {dep_score}")
+
+@test("adding tests lowers complexity")
+def _():
+    base_score, _, _ = score_pr(
+        files_changed=8, additions=150, deletions=20,
+        has_dependency_changes=False, test_coverage_delta=None
+    )
+    better_score, _, _ = score_pr(
+        files_changed=8, additions=180, deletions=20,
+        has_dependency_changes=False, test_coverage_delta=3
+    )
+    assert_true(better_score < base_score, f"Tests: {base_score} -> {better_score}")
+
+@test("removing tests increases complexity")
+def _():
+    base_score, _, _ = score_pr(
+        files_changed=8, additions=150, deletions=20,
+        has_dependency_changes=False, test_coverage_delta=None
+    )
+    worse_score, _, _ = score_pr(
+        files_changed=8, additions=150, deletions=20,
+        has_dependency_changes=False, test_coverage_delta=-2
+    )
+    assert_true(worse_score > base_score, f"Remove tests: {base_score} -> {worse_score}")
+
+@test("score bounded 1-10")
+def _():
+    for files, adds, dels in [(1, 10, 5), (100, 10000, 5000)]:
+        score, _, _ = score_pr(files, adds, dels, False, None)
+        assert_true(1 <= score <= 10, f"Score {score} out of range")
+
+@test("estimated minutes exist for all scores")
+def _():
+    for s in range(1, 11):
+        assert_true(s in TIME_PER_POINT, f"Missing time for score {s}")
+
+
+print(f"\n=== Results: {PASS} passed, {FAIL} failed ===")
+sys.exit(0 if FAIL == 0 else 1)