Compare commits
3 Commits
step35/147
...
main
| Author | SHA1 | Date | |
|---|---|---|---|
| 2a4e73aa03 | |||
|
|
4b5a675355 | ||
|
|
b1a728f5f4 |
@@ -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: []
|
||||
1060
knowledge/index.json
1060
knowledge/index.json
File diff suppressed because it is too large
Load Diff
@@ -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
|
||||
@@ -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())
|
||||
351
scripts/pr_complexity_scorer.py
Normal file
351
scripts/pr_complexity_scorer.py
Normal file
@@ -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()
|
||||
@@ -22,114 +22,95 @@ import sys
|
||||
from pathlib import Path
|
||||
from typing import Optional
|
||||
|
||||
from session_reader import extract_conversation, read_session
|
||||
|
||||
|
||||
def compute_hash(text: str) -> str:
|
||||
"""Content hash for deduplication."""
|
||||
return hashlib.sha256(text.encode()).hexdigest()[:16]
|
||||
|
||||
|
||||
def extract_pairs_from_session(session_data: dict, min_ratio: float = 1.5,
|
||||
def extract_pairs_from_conversation(conversation: list, session_id: str, model: str,
|
||||
min_ratio: float = 1.5,
|
||||
min_response_words: int = 20) -> list:
|
||||
"""Extract terse→rich pairs from a single session object."""
|
||||
"""Extract terse→rich pairs from a normalized conversation."""
|
||||
pairs = []
|
||||
conversations = session_data.get("conversations", [])
|
||||
session_id = session_data.get("id", "unknown")
|
||||
model = session_data.get("model", "unknown")
|
||||
|
||||
seen_hashes = set()
|
||||
|
||||
for i, msg in enumerate(conversations):
|
||||
# Look for assistant/gpt responses
|
||||
if msg.get("from") not in ("gpt", "assistant"):
|
||||
for i, msg in enumerate(conversation):
|
||||
# Look for assistant responses
|
||||
if msg.get('role') != 'assistant':
|
||||
continue
|
||||
|
||||
response_text = msg.get("value", "")
|
||||
response_text = msg.get('content', '')
|
||||
if not response_text or len(response_text.split()) < min_response_words:
|
||||
continue
|
||||
|
||||
# Find the preceding human message
|
||||
# Find the preceding user message
|
||||
prompt_text = ""
|
||||
for j in range(i - 1, -1, -1):
|
||||
if conversations[j].get("from") == "human":
|
||||
prompt_text = conversations[j].get("value", "")
|
||||
if conversation[j].get('role') == 'user':
|
||||
prompt_text = conversation[j].get('content', '')
|
||||
break
|
||||
|
||||
if not prompt_text:
|
||||
continue
|
||||
|
||||
# Filter: skip tool results, system messages embedded as human
|
||||
if prompt_text.startswith("{") and "output" in prompt_text[:100]:
|
||||
continue # likely a tool result
|
||||
if prompt_text.startswith("# SOUL.md") or prompt_text.startswith("You are"):
|
||||
continue # system prompt leak
|
||||
if prompt_text.startswith('{') and 'output' in prompt_text[:100]:
|
||||
continue
|
||||
if prompt_text.startswith('# SOUL.md') or prompt_text.startswith('You are'):
|
||||
continue
|
||||
|
||||
# Quality filters
|
||||
prompt_words = len(prompt_text.split())
|
||||
response_words = len(response_text.split())
|
||||
|
||||
# Must have meaningful length ratio
|
||||
if prompt_words == 0 or response_words == 0:
|
||||
continue
|
||||
ratio = response_words / prompt_words
|
||||
if ratio < min_ratio:
|
||||
continue
|
||||
|
||||
# Skip responses that are mostly code
|
||||
code_blocks = response_text.count("```")
|
||||
if code_blocks >= 4 and len(response_text.replace("```", "").strip()) < 50:
|
||||
code_blocks = response_text.count('```')
|
||||
if code_blocks >= 4 and len(response_text.replace('```', '').strip()) < 50:
|
||||
continue
|
||||
|
||||
# Skip responses with tool call artifacts
|
||||
if "tool_call" in response_text[:100] or "function_call" in response_text[:100]:
|
||||
if 'tool_call' in response_text[:100] or 'function_call' in response_text[:100]:
|
||||
continue
|
||||
|
||||
# Deduplicate by content hash
|
||||
content_hash = compute_hash(prompt_text + response_text[:200])
|
||||
if content_hash in seen_hashes:
|
||||
continue
|
||||
seen_hashes.add(content_hash)
|
||||
|
||||
# Clean up response: remove markdown headers if too many
|
||||
clean_response = response_text
|
||||
|
||||
pairs.append({
|
||||
"terse": prompt_text.strip(),
|
||||
"rich": clean_response.strip(),
|
||||
"source": session_id,
|
||||
"model": model,
|
||||
"prompt_words": prompt_words,
|
||||
"response_words": response_words,
|
||||
"ratio": round(ratio, 2),
|
||||
'terse': prompt_text.strip(),
|
||||
'rich': clean_response.strip(),
|
||||
'source': session_id,
|
||||
'model': model,
|
||||
'prompt_words': prompt_words,
|
||||
'response_words': response_words,
|
||||
'ratio': round(ratio, 2),
|
||||
})
|
||||
|
||||
return pairs
|
||||
|
||||
|
||||
def extract_from_jsonl_file(filepath: str, **kwargs) -> list:
|
||||
"""Extract pairs from a session JSONL file."""
|
||||
pairs = []
|
||||
path = Path(filepath)
|
||||
|
||||
if not path.exists():
|
||||
print(f"Warning: {filepath} not found", file=sys.stderr)
|
||||
return pairs
|
||||
|
||||
content = path.read_text()
|
||||
lines = content.strip().split("\n")
|
||||
|
||||
for line in lines:
|
||||
line = line.strip()
|
||||
if not line:
|
||||
continue
|
||||
try:
|
||||
session = json.loads(line)
|
||||
except json.JSONDecodeError:
|
||||
continue
|
||||
|
||||
session_pairs = extract_pairs_from_session(session, **kwargs)
|
||||
pairs.extend(session_pairs)
|
||||
|
||||
return pairs
|
||||
def extract_from_jsonl_file(path: str, **kwargs) -> list:
|
||||
"""Read a session file and extract training pairs using normalized conversation."""
|
||||
session_messages = read_session(path)
|
||||
if not session_messages:
|
||||
return []
|
||||
conversation = extract_conversation(session_messages)
|
||||
# Derive session_id and model from first real message metadata
|
||||
first_msg = next((m for m in session_messages if m.get('role') or m.get('from')), {})
|
||||
session_id = first_msg.get('meta_session_id', Path(path).name)
|
||||
model = first_msg.get('model', 'unknown')
|
||||
return extract_pairs_from_conversation(conversation, session_id, model, **kwargs)
|
||||
|
||||
|
||||
def deduplicate_pairs(pairs: list) -> list:
|
||||
|
||||
170
scripts/test_pr_complexity_scorer.py
Normal file
170
scripts/test_pr_complexity_scorer.py
Normal file
@@ -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)
|
||||
118
tests/test_session_pair_harvester.py
Normal file
118
tests/test_session_pair_harvester.py
Normal file
@@ -0,0 +1,118 @@
|
||||
"""
|
||||
Tests for session_pair_harvester — training pair extraction from sessions.
|
||||
"""
|
||||
|
||||
import json
|
||||
import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
import sys
|
||||
from pathlib import Path
|
||||
sys.path.insert(0, str(Path(__file__).parent.parent / "scripts"))
|
||||
from session_pair_harvester import (
|
||||
extract_pairs_from_conversation,
|
||||
extract_from_jsonl_file,
|
||||
deduplicate_pairs,
|
||||
compute_hash,
|
||||
)
|
||||
|
||||
|
||||
class TestSessionPairHarvester(unittest.TestCase):
|
||||
def test_compute_hash_consistent(self):
|
||||
h1 = compute_hash("hello world")
|
||||
h2 = compute_hash("hello world")
|
||||
self.assertEqual(h1, h2)
|
||||
self.assertEqual(len(h1), 16)
|
||||
|
||||
def test_extract_simple_qa_pair(self):
|
||||
"""A simple user→assistant exchange produces one pair."""
|
||||
conversation = [
|
||||
{"role": "user", "content": "What is the capital of France?"},
|
||||
{"role": "assistant", "content": "The capital of France is Paris. It is a major European city renowned for its art, fashion, gastronomy, cultural heritage, and historical significance. The city attracts millions of tourists annually."},
|
||||
]
|
||||
pairs = extract_pairs_from_conversation(conversation, "test_session", "test-model")
|
||||
self.assertEqual(len(pairs), 1)
|
||||
self.assertEqual(pairs[0]["terse"], "What is the capital of France?")
|
||||
self.assertIn("Paris", pairs[0]["rich"])
|
||||
self.assertEqual(pairs[0]["source"], "test_session")
|
||||
|
||||
def test_min_ratio_filter(self):
|
||||
"""Very short responses are filtered out."""
|
||||
conversation = [
|
||||
{"role": "user", "content": "Yes"},
|
||||
{"role": "assistant", "content": "No."},
|
||||
]
|
||||
# Default min_ratio = 1.5, min_words = 20 for response
|
||||
pairs = extract_pairs_from_conversation(conversation, "s", "m", min_response_words=3)
|
||||
self.assertEqual(len(pairs), 0)
|
||||
|
||||
def test_min_words_filter(self):
|
||||
"""Assistant responses below min word count are skipped."""
|
||||
conversation = [
|
||||
{"role": "user", "content": "Explain the project architecture in detail"},
|
||||
{"role": "assistant", "content": "OK."},
|
||||
]
|
||||
pairs = extract_pairs_from_conversation(conversation, "s", "m", min_response_words=5)
|
||||
self.assertEqual(len(pairs), 0)
|
||||
|
||||
def test_skip_non_assistant_messages(self):
|
||||
"""System and tool messages are ignored."""
|
||||
conversation = [
|
||||
{"role": "system", "content": "You are a helpful assistant."},
|
||||
{"role": "user", "content": "Hello"},
|
||||
{"role": "assistant", "content": "Hi there! How can I help you today?"},
|
||||
]
|
||||
pairs = extract_pairs_from_conversation(conversation, "s", "m", min_response_words=3)
|
||||
self.assertEqual(len(pairs), 1)
|
||||
self.assertEqual(pairs[0]["terse"], "Hello")
|
||||
|
||||
def test_multiple_pairs_from_one_session(self):
|
||||
"""A conversation with several Q&A turns yields multiple pairs."""
|
||||
conversation = [
|
||||
{"role": "user", "content": "First question?"},
|
||||
{"role": "assistant", "content": "Here is a detailed and comprehensive answer that thoroughly explores multiple aspects of the subject. It provides background context and practical implications for the reader."},
|
||||
{"role": "user", "content": "Second?"},
|
||||
{"role": "assistant", "content": "Another comprehensive response with detailed examples. This includes practical code blocks and thorough explanations to ensure deep understanding of the topic at hand."},
|
||||
]
|
||||
pairs = extract_pairs_from_conversation(conversation, "s", "m", min_ratio=1.0)
|
||||
self.assertEqual(len(pairs), 2)
|
||||
|
||||
def test_deduplication_removes_duplicates(self):
|
||||
"""Identical pairs across sessions are deduplicated."""
|
||||
pairs = [
|
||||
{"terse": "q1", "rich": "a1", "source": "s1", "model": "m"},
|
||||
{"terse": "q1", "rich": "a1", "source": "s2", "model": "m"},
|
||||
{"terse": "q2", "rich": "a2", "source": "s1", "model": "m"},
|
||||
]
|
||||
unique = deduplicate_pairs(pairs)
|
||||
self.assertEqual(len(unique), 2)
|
||||
sources = {p["source"] for p in unique}
|
||||
# First unique pair can be from either s1 or s2
|
||||
self.assertIn("s1", sources)
|
||||
|
||||
def test_integration_with_test_sessions(self):
|
||||
"""Harvester finds pairs in real test session files."""
|
||||
repo_root = Path(__file__).parent.parent
|
||||
test_sessions_dir = repo_root / "test_sessions"
|
||||
if not test_sessions_dir.exists():
|
||||
self.skipTest("test_sessions not found")
|
||||
|
||||
pairs = []
|
||||
for jsonl_file in sorted(test_sessions_dir.glob("*.jsonl")):
|
||||
pairs.extend(extract_from_jsonl_file(str(jsonl_file)))
|
||||
|
||||
self.assertGreater(len(pairs), 0, "Should extract at least one pair from test_sessions")
|
||||
for p in pairs:
|
||||
self.assertIn("terse", p)
|
||||
self.assertIn("rich", p)
|
||||
self.assertIn("source", p)
|
||||
self.assertIn("model", p)
|
||||
# Verify content exists
|
||||
self.assertGreater(len(p["terse"]), 0)
|
||||
self.assertGreater(len(p["rich"]), 0)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
Reference in New Issue
Block a user