Dragan Spiridonov b0e013087f docs(qe-reports): add harness-eval full quality analysis ...

QE-swarm quality analysis of github.com/natea/harness-eval @ 8814640,
produced by a queen-coordinated 7-specialist Agentic QE fleet with a real
captured test run (bun test -> 197 pass / 11 skip / 4 fail).

Reports:
- 00 executive summary (cross-cutting verdict + P0/P1/P2 roadmap)
- 01 code quality (A-)
- 02 complexity & code smells (B; TrialView.tsx God component)
- 03 security audit (High risk: 1 CRITICAL host code-exec + 3 HIGH)
- 04 performance (B)
- 05 quality experience (B+)
- 06 product factors (SFDIPOT) + test strategy & plan
- 07 tests analysis (B-; no test CI, 4 failing)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-07-01 09:53:52 +00:00

..

analysis

…

api

…

architecture

…

benchmarks

feat(benchmarks): ADR-109 interaction benchmark — rubric pre-registered before any data (issue #522)

2026-06-11 11:05:26 +00:00

catalogs

Migrate PACT → PACTS framework (add Structured principle)

2026-06-20 15:35:56 +02:00

demos

…

examples

chore(evals): finish eval model-ID migration across remaining surfaces

2026-06-12 14:52:24 +00:00

guides

Merge remote-tracking branch 'origin/main' into feat/local-model-improvements

2026-07-01 06:24:12 +00:00

implementation

Merge remote-tracking branch 'origin/main' into feat/local-model-improvements

2026-07-01 06:24:12 +00:00

incidents

…

integration

…

metaharness

Darwin-for-QE — Cost Reduction & Plain-English Results

2026-06-26 16:48:21 +00:00

plans

feat(quality): oracle evals, durable-first tests, conservation guard + provider fixes

2026-06-27 15:37:46 +00:00

policies

feat(verification): chaos workflow + VERIFICATION.md + matrix embed (#409, #410)

2026-04-08 09:52:29 +00:00

probes

feat(agents): ADR-101 nested-subagent readiness — provenance, probe, validation

2026-06-10 10:06:05 +00:00

qe-reports/harness-eval

docs(qe-reports): add harness-eval full quality analysis

2026-07-01 09:53:52 +00:00

qe-reports-3-6-3

…

qe-reports-3-6-8

…

qe-reports-3-7-0

fix: security hardening, god-file decomposition, and QE v3.7.0 reports

2026-02-23 21:02:50 +00:00

qe-reports-3-7-10

qe reports March 6, 2026

2026-03-06 13:26:41 +00:00

qe-reports-3-8-3

fix(security): resolve P0/P1 issues from v3.8.3 QE swarm analysis

2026-03-19 13:53:54 +00:00

qe-reports-3-8-13

fix: resolve 3 P0 blockers and CI failures from QE v3.8.13 audit

2026-03-30 16:51:59 +00:00

qe-reports-3-9-13

docs(qe): add v3.9.13 follow-up research memos (guidance strategy, agent recount)

2026-04-20 12:46:40 +00:00

qe-reports-3-10-6

docs(qe): add v3.10.6 QE fleet analysis report set

2026-06-12 12:28:08 +00:00

reference

…

releases

chore(release): bump version to v3.11.4

2026-07-01 06:38:12 +00:00

reports

feat(quality): oracle evals, durable-first tests, conservation guard + provider fixes

2026-06-27 15:37:46 +00:00

research

feat: implement CC-internals improvements IMP-00 through IMP-10 (Waves 0-4)

2026-04-01 17:32:50 +00:00

schemas

feat(quality): oracle evals, durable-first tests, conservation guard + provider fixes

2026-06-27 15:37:46 +00:00

security

feat(adr-093): add Opus 4.7, Sonnet 4.6, Haiku 4.5 to model registry

2026-04-17 12:16:24 +00:00

specs

…

telemetry/production

…

templates

chore(evals): finish eval model-ID migration across remaining surfaces

2026-06-12 14:52:24 +00:00

v3

feat: add CLI code intelligence commands (complexity, --incremental, --git-since) and fix stale references

2026-03-30 09:57:49 +00:00

agentic-qe-intro.md

Migrate PACT → PACTS framework (add Structured principle)

2026-06-20 15:35:56 +02:00

agentic-teams-integration-analysis.md

…

aqe-dream-cycles-neural-learning.md

aqe dream cycles

2026-02-22 19:39:52 +00:00

benchmark-hnsw-vector-loading.md

…

benchmark-kg-assisted-test-generation.md

…

bmad-inspired-improvements.md

feat: YAML pipelines, validation pipeline, cross-phase signals, heartbeat scheduler, context sources

2026-03-12 16:17:04 +00:00

brain-export-improvement-plan.md

chore(release): bump version to v3.7.14

2026-03-08 14:36:26 +00:00

cicd-agentic-workflows-report.md

feat: Phase 0+1 CI-native CLI — 17 bug fixes + exit code 2 for warnings

2026-02-27 12:45:03 +00:00

cicd-best-in-class-plan.md

feat: Phase 0+1 CI-native CLI — 17 bug fixes + exit code 2 for warnings

2026-02-27 12:45:03 +00:00

cli-mcp-verification-test-plan.md

feat: Phase 0+1 CI-native CLI — 17 bug fixes + exit code 2 for warnings

2026-02-27 12:45:03 +00:00

hypergraph-devils-advocate-issues.md

fix: unify hypergraph persistence to memory.db, add CLI/MCP query tools

2026-03-23 13:48:09 +00:00

integration-roadmap.md

feat: wire 26 MCP tools via bridge, add 4 new tools with CLI, cleanup dead code

2026-03-02 10:55:56 +00:00

loki-mode-features.md

feat(loki-mode): integrate 7 adversarial quality gates (ADR-074)

2026-03-04 12:36:19 +00:00

loki-mode-integration-plan.md

feat(loki-mode): integrate 7 adversarial quality gates (ADR-074)

2026-03-04 12:36:19 +00:00

multi-language-goap-implementation-plan.md

feat(multi-lang): add docs, ADRs, tests, and fixtures for multi-language support

2026-03-05 12:00:01 +00:00

multi-language-test-generation-plan.md

feat(test-generation): add multi-language support plan with ADRs (075-079)

2026-03-04 12:39:24 +00:00

multi-platform-integration-plan.md

docs: fix stale plan references — mark all integration tests done, remove deleted file refs

2026-02-27 18:49:23 +00:00

openclaw-research-2026-03-08.md

feat(learning): implement Six Hats Tier 0-2 improvements and fix test flakiness

2026-03-09 17:43:23 +00:00

openclaw-research-v2-2026-03-09.md

feat(learning): implement Six Hats Tier 0-2 improvements and fix test flakiness

2026-03-09 17:43:23 +00:00

opencode-integration-guide.md

feat: complete OpenCode integration — all 40 tasks across 5 workstreams

2026-02-24 18:54:19 +00:00

opencode-integration-plan.md

docs: fix stale skill/agent counts across codebase (75→78 QE skills, restore 60 agents)

2026-02-25 07:54:58 +00:00

phase0-verification-report.md

feat: Phase 0+1 CI-native CLI — 17 bug fixes + exit code 2 for warnings

2026-02-27 12:45:03 +00:00

platform-setup-guide.md

fix: address brutal honesty audit findings

2026-02-27 18:46:53 +00:00

provider-capability-matrix.md

feat: complete OpenCode integration — all 40 tasks across 5 workstreams

2026-02-24 18:54:19 +00:00

PUBLISH-STRUCTURE.md

fix: clean up stale v3/ references and protect memory namespaces post-flatten

2026-03-01 12:27:44 +00:00

qe-skills-improvement-plan.md

feat(learning): use local Nagual instance + add local LLM judge

2026-06-08 11:44:22 +00:00

ruflo-adoption-plan.md

docs(adr): ADR-098 learning-store & routing hardening + mark 2 side-findings fixed

2026-06-02 11:06:24 +00:00

rvf-integration-plan.md

feat: RVF cognitive container integration — 4 workstreams, 246 tests

2026-02-23 07:24:23 +00:00

rvf-master-plan.md

feat: RVF cognitive container integration — 4 workstreams, 246 tests

2026-02-23 07:24:23 +00:00

self-healing-db-recovery-pattern.md

…

self-healing-infra-extension-design.md

…

self-healing-strange-loop-capabilities.md

…

sherlock-persistence-gaps-report.md

…

six-hats-aqe-openclaw-analysis-2026-03-09.md

feat(learning): implement Six Hats Tier 0-2 improvements and fix test flakiness

2026-03-09 17:43:23 +00:00

six-hats-shannon-pentest-analysis.md

…

six-hats-strongdm-analysis.md

…

skill-evaluation-research.md

…

strongdm-implementation-plan.md

…

tier3-baseline-2026-03-10.json

feat(tier3): collect baselines and add instrumentation for Tier 3 features (#334)

2026-03-10 14:08:19 +00:00

tier3-benchmark-baseline-2026-03-10.md

feat(tier3): collect baselines and add instrumentation for Tier 3 features (#334)

2026-03-10 14:08:19 +00:00

tier3-benchmark-baseline-plan.md

feat(tier3): collect baselines and add instrumentation for Tier 3 features (#334)

2026-03-10 14:08:19 +00:00

tool-compatibility.md

feat: complete OpenCode integration — all 40 tasks across 5 workstreams

2026-02-24 18:54:19 +00:00

v3-technical-architecture-glossary.md

Migrate PACT → PACTS framework (add Structured principle)

2026-06-20 15:35:56 +02:00

V3-PERSISTENCE-ANALYSIS.md

fix: clean up stale v3/ references and protect memory namespaces post-flatten

2026-03-01 12:27:44 +00:00

VERIFICATION.md

feat(verification): chaos workflow + VERIFICATION.md + matrix embed (#409, #410)

2026-04-08 09:52:29 +00:00