kenaz 0.3.18 → 0.3.20
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/core/.claude/commands/agent-worker.md +1 -1
- package/core/.claude/commands/architect.md +1 -2
- package/core/.claude/commands/spec.md +1 -1
- package/core/.claude/commands//347/224/242/345/223/201.md +1 -1
- package/core/.claude/hooks/__tests__/task-1977-dedupe-guard.test.js +8 -8
- package/core/.claude/skills/architect_agent/SKILL.md +11 -92
- package/core/.claude/skills/assessment_agent/SKILL.md +0 -1
- package/core/.claude/skills/backend_engineer/SKILL.md +3 -6
- package/core/.claude/skills/code_reviewer/SKILL.md +1 -1
- package/core/.claude/skills/code_reviewer/patterns.yaml +1 -1
- package/core/.claude/skills/designer/SKILL.md +3 -6
- package/core/.claude/skills/dev_agent/SKILL.md +30 -491
- package/core/.claude/skills/developer/SKILL.md +3 -6
- package/core/.claude/skills/feature_agent/SKILL.md +3 -17
- package/core/.claude/skills/product_manager/SKILL.md +29 -1064
- package/core/.claude/skills/qa_engineer/SKILL.md +12 -17
- package/core/.claude/skills/spec_optimizer/SKILL.md +25 -275
- package/core/.claude/skills/sre_agent/SKILL.md +3 -6
- package/core/.collaboration/README.md +2 -3
- package/core/.collaboration/core/task-api.js +5 -138
- package/core/.collaboration/docs/CLI.md +0 -2
- package/core/.failure/INDEX.yaml +6 -40
- package/core/.failure/agent-execution/FAIL-013-search-cwd-drift-and-case-mismatch.yaml +1 -1
- package/core/.failure/tools/README.md +9 -227
- package/core/.formation/bifrost/launch.js +1 -6
- package/core/.formation/bifrost/launch.test.js +1 -1
- package/core/.formation/bifrost/shared/ansuz-boot-policy.js +3 -3
- package/core/.formation/bifrost/shared/ansuz-boot-policy.test.js +1 -2
- package/core/.formation/tools/__tests__/arms.test.js +41 -0
- package/core/.formation/tools/__tests__/diagnose-bug.test.js +10 -0
- package/core/.formation/tools/__tests__/m1-hmap-convid.test.js +1 -124
- package/core/.formation/tools/arms.js +48 -0
- package/core/.formation/tools/dispatch.js +24 -15
- package/core/.formation/tools/kenaz-stats.js +32 -8
- package/core/.formation/tools/kenaz-stats.test.js +15 -2
- package/core/.formation/tools/loader.js +17 -140
- package/core/.formation/tools/post-complete.js +0 -31
- package/core/.formation/tools/prompt.js +16 -1
- package/core/.formation/tools/prompt.test.js +20 -0
- package/core/.rule/INDEX.yaml +0 -18
- package/core/.rule/general/agent-workflow.yaml +14 -164
- package/core/.rule/general/project-self-containment.yaml +8 -19
- package/core/.rule/general/rust-verify-target.yaml +6 -5
- package/core/.rule/general/synapse-code-intelligence.yaml +3 -3
- package/core/.specialist/Amelia/capability.yaml +12 -12
- package/core/.specialist/Amelia/workflow.yaml +2 -2
- package/core/.specialist/Ansuz/SYSTEM_DOC.md +20 -578
- package/core/.specialist/Ansuz/cognitive_principles.yaml +2 -3
- package/core/.specialist/Ansuz/concepts/boot_rules_summary.yaml +0 -1
- package/core/.specialist/Ansuz/concepts/deep_knowledge_pointers.yaml +1 -2
- package/core/.specialist/Ansuz/core.yaml +6 -108
- package/core/.specialist/Ansuz/guards/lesson_guards.yaml +0 -3
- package/core/.specialist/Ansuz/identity_contract.yaml +0 -1
- package/core/.specialist/Ansuz/knowledge.yaml +0 -4
- package/core/.specialist/Ansuz/rule.yaml +0 -1
- package/core/.specialist/Ansuz/tools/handoff-session-identity.test.js +6 -150
- package/core/.specialist/tests/runtime-discovery/README.md +1 -1
- package/core/.specialist/tools/__tests__/task-2374-usage-counter.test.js +1 -12
- package/core/.specialist/tools/ansuz-boot-fast.js +7 -4
- package/core/.specialist/tools/ansuz-boot-fast.test.js +10 -3
- package/core/.specialist/tools/prompt-files.test.js +1 -0
- package/core/.specialist/tools/task-bridge.js +1 -66
- package/core/.system/README.md +11 -552
- package/core/.system/collaboration/README.md +10 -174
- package/core/CLAUDE.md +1 -6
- package/core/KENAZ_CORE_VERSION +1 -1
- package/core/dev/scripts/js-yaml-resolution.test.js +1 -1
- package/core/dev/scripts/peer-identity-e2e.js +402 -0
- package/core/dev/scripts/peer-identity-e2e.md +47 -0
- package/core/dev/scripts/relay-admin.js +94 -0
- package/core/dev/scripts/relay-admin.test.js +131 -0
- package/core/dev/scripts/run-rust-tests.js +9 -45
- package/core/dev/scripts/rust-verify-worktree.js +4 -4
- package/core/dev/scripts/verify-target-dir.js +6 -6
- package/core/plugins/kenaz/INVENTORY.md +8 -8
- package/core/plugins/kenaz/README.md +10 -0
- package/core/plugins/kenaz/commands/architect.md +1 -2
- package/core/plugins/kenaz/commands/spec.md +1 -1
- package/core/plugins/kenaz/commands//347/224/242/345/223/201.md +1 -1
- package/core/plugins/kenaz/guidance.md +1 -1
- package/core/plugins/kenaz/hooks/kenaz-hook.js +2 -1
- package/core/plugins/kenaz/hooks/sdk-gate.js +9 -0
- package/core/plugins/kenaz/scripts/kenaz.test.js +15 -3
- package/core/plugins/kenaz/scripts/sync.js +1 -1
- package/core/plugins/kenaz/scripts/ygg.js +8 -0
- package/core/plugins/kenaz/scripts/ygg.test.js +72 -0
- package/core/plugins/kenaz/skills/architect_agent/SKILL.md +11 -92
- package/core/plugins/kenaz/skills/assessment_agent/SKILL.md +0 -1
- package/core/plugins/kenaz/skills/backend_engineer/SKILL.md +3 -6
- package/core/plugins/kenaz/skills/code_reviewer/SKILL.md +1 -1
- package/core/plugins/kenaz/skills/code_reviewer/patterns.yaml +1 -1
- package/core/plugins/kenaz/skills/designer/SKILL.md +3 -6
- package/core/plugins/kenaz/skills/dev_agent/SKILL.md +30 -491
- package/core/plugins/kenaz/skills/developer/SKILL.md +3 -6
- package/core/plugins/kenaz/skills/feature_agent/SKILL.md +3 -17
- package/core/plugins/kenaz/skills/product_manager/SKILL.md +29 -1064
- package/core/plugins/kenaz/skills/qa_engineer/SKILL.md +12 -17
- package/core/plugins/kenaz/skills/spec_optimizer/SKILL.md +25 -275
- package/core/plugins/kenaz/skills/sre_agent/SKILL.md +3 -6
- package/core/plugins/kenaz-peer/hooks/register.test.ts +32 -0
- package/core/plugins/kenaz-peer/hooks/register.ts +9 -0
- package/package.json +6 -6
- package/core/.claude/commands/archive.md +0 -24
- package/core/.claude/commands/init.md +0 -112
- package/core/.claude/commands/legacy_dev.md +0 -18
- package/core/.claude/commands/product-review.md +0 -131
- package/core/.claude/commands/strategy.md +0 -141
- package/core/.claude/commands/sunny.md +0 -1
- package/core/.claude/commands//347/224/242/345/223/201/346/252/242/350/246/226.md +0 -129
- package/core/.claude/commands//351/200/262/345/272/246.md +0 -15
- package/core/.claude/hooks/__tests__/substrate.test.js +0 -122
- package/core/.claude/hooks/_substrate-paths.js +0 -95
- package/core/.claude/hooks/context-check.js +0 -51
- package/core/.claude/hooks/fatigue-check.js +0 -52
- package/core/.claude/hooks/handoff-snapshot-on-commit.js +0 -154
- package/core/.claude/hooks/handoff-snapshot-on-question.js +0 -158
- package/core/.claude/hooks/handoff-staleness.js +0 -197
- package/core/.claude/hooks/jev-thalamus-context.js +0 -17
- package/core/.claude/hooks/jev-thalamus-context.test.js +0 -41
- package/core/.claude/hooks/lease-release.js +0 -119
- package/core/.claude/hooks/lease-touch.js +0 -96
- package/core/.claude/hooks/reflex-feedback.js +0 -5
- package/core/.claude/hooks/session-init.ps1 +0 -49
- package/core/.claude/hooks/sound-event.js +0 -70
- package/core/.claude/hooks/sound-event.sh +0 -37
- package/core/.claude/hooks/stream-delta.js +0 -169
- package/core/.claude/no-hooks.settings.json +0 -3
- package/core/.claude/skills/legacy_dev/SKILL.md +0 -202
- package/core/.claude/skills/sunny/SKILL.md +0 -74
- package/core/.collaboration/cli/commands/assign.js +0 -39
- package/core/.collaboration/cli/commands/claim.js +0 -33
- package/core/.collaboration/cli/commands/complete.js +0 -44
- package/core/.collaboration/cli/commands/create.js +0 -110
- package/core/.collaboration/cli/commands/get.js +0 -83
- package/core/.collaboration/cli/commands/index.js +0 -52
- package/core/.collaboration/cli/commands/list.js +0 -51
- package/core/.collaboration/cli/commands/lock.js +0 -45
- package/core/.collaboration/cli/commands/rebuild.js +0 -39
- package/core/.collaboration/cli/commands/search.js +0 -61
- package/core/.collaboration/cli/commands/stats.js +0 -61
- package/core/.collaboration/cli/commands/transfer.js +0 -41
- package/core/.collaboration/cli/commands/unlock.js +0 -48
- package/core/.collaboration/cli/formatters/help-formatter.js +0 -70
- package/core/.collaboration/cli/formatters/index.js +0 -7
- package/core/.collaboration/cli/task-cli.js +0 -46
- package/core/.collaboration/cli/utils/arg-parser.js +0 -74
- package/core/.collaboration/cli/utils/git-user.js +0 -25
- package/core/.collaboration/cli/utils/index.js +0 -9
- package/core/.collaboration/cli/utils/output.js +0 -10
- package/core/.collaboration/config/default.yaml +0 -189
- package/core/.collaboration/core/conflict-resolver.js +0 -461
- package/core/.collaboration/core/conflict-resolver.test.js +0 -389
- package/core/.collaboration/core/migrate-legacy.js +0 -260
- package/core/.collaboration/docs/API.md +0 -787
- package/core/.collaboration/docs/ARCHITECTURE.md +0 -596
- package/core/.collaboration/docs/FAQ.md +0 -695
- package/core/.collaboration/docs/MIGRATION.md +0 -804
- package/core/.collaboration/docs/examples/README.md +0 -320
- package/core/.collaboration/docs/examples/advanced-queries.js +0 -261
- package/core/.collaboration/docs/examples/basic-usage.js +0 -184
- package/core/.collaboration/docs/examples/team-workflow.js +0 -352
- package/core/.failure/agent-execution/FAIL-001-agent-no-output.yaml +0 -391
- package/core/.failure/agent-execution/FAIL-007-pm-lead-wrong-team-invocation.yaml +0 -0
- package/core/.failure/agent-execution/FAIL-010-phase0-poem-format-skipped.yaml +0 -28
- package/core/.failure/agent-execution/FAIL-010-skipping-cognitive-checkpoint-after-verification.yaml +0 -59
- package/core/.failure/agent-execution/FAIL-012-grep-shortcut-during-investigation.yaml +0 -85
- package/core/.failure/architecture/FAIL-006-python-version-compatibility.yaml +0 -445
- package/core/.failure/pipeline/FAIL-003-queue-pollution.yaml +0 -335
- package/core/.failure/pipeline/README.md +0 -95
- package/core/.failure/retired/FAIL-009-skipping-synapse-pulse-before-code-change.yaml +0 -49
- package/core/.failure/tools/USAGE_GUIDE.md +0 -323
- package/core/.failure/tools/check_failures.ps1 +0 -387
- package/core/.failure/tools/log_failure.ps1 +0 -474
- package/core/.formation/.episode-input.json +0 -10
- package/core/.formation/.merge-lock +0 -1
- package/core/.formation/lead.yaml +0 -118
- package/core/.formation/legacy.bak/designer.yaml +0 -57
- package/core/.formation/legacy.bak/pm.yaml +0 -57
- package/core/.formation/legacy.bak/qa.yaml +0 -57
- package/core/.formation/legacy.bak/review.yaml +0 -62
- package/core/.formation/legacy.bak/scheduler.yaml +0 -129
- package/core/.formation/legacy.bak/sre.yaml +0 -57
- package/core/.formation/role-map.yaml +0 -274
- package/core/.formation/roles/_shared/modules/code_review.yaml +0 -98
- package/core/.formation/roles/_shared/modules/security.yaml +0 -103
- package/core/.formation/roles/_shared/modules/testing.yaml +0 -14
- package/core/.formation/roles/backend/role.yaml +0 -93
- package/core/.formation/roles/code_reviewer/role.yaml +0 -102
- package/core/.formation/roles/database_optimizer/role.yaml +0 -107
- package/core/.formation/roles/designer/role.yaml +0 -66
- package/core/.formation/roles/developer/role.yaml +0 -75
- package/core/.formation/roles/frontend/role.yaml +0 -134
- package/core/.formation/roles/incident_response/role.yaml +0 -89
- package/core/.formation/roles/qa/role.yaml +0 -89
- package/core/.formation/roles/security/role.yaml +0 -87
- package/core/.formation/roles/sre/role.yaml +0 -66
- package/core/.formation/skills/coordinator.yaml +0 -52
- package/core/.formation/solo/diagnosis.yaml +0 -78
- package/core/.formation/solo/strategy.yaml +0 -121
- package/core/.formation/tests/hello.txt +0 -2
- package/core/.formation/tools/coordinator.js +0 -350
- package/core/.formation/tools/jev-correction.js +0 -214
- package/core/.formation/tools/jev-correction.test.js +0 -178
- package/core/.formation/tools/log-reader.js +0 -232
- package/core/.formation/tools/revert-daemon-state.js +0 -162
- package/core/.formation/tools/test-drift.js +0 -148
- package/core/.formation/unit/heimdall.yaml +0 -96
- package/core/.formation/unit/plan.yaml +0 -67
- package/core/.formation/unit/think.yaml +0 -58
- package/core/.kenaz/MUNINN_SNAPSHOT9_EPISODE.json +0 -32
- package/core/.kenaz/MUNINN_SNAPSHOT9_RUNE.json +0 -23
- package/core/.kenaz/MUNINN_SNAPSHOT9_SUMMARY.md +0 -89
- package/core/.kenaz/ash_TASK_1428-20260507.json +0 -14
- package/core/.kenaz/muninn_episode_write.ps1 +0 -17
- package/core/.kenaz/muninn_snapshot11_rune_candidates.md +0 -63
- package/core/.kenaz/muninn_snapshot1_rune_candidates.md +0 -49
- package/core/.kenaz/runes_TASK_1428.json +0 -57
- package/core/.kenaz/tmp_heimdall_proposal_8d3e392.json +0 -13
- package/core/.kenaz/tmp_props.json +0 -1
- package/core/.kenaz/tmp_sounddrop_t1_prompt.txt +0 -371
- package/core/.rule/MECHANIZED.md +0 -61
- package/core/.rule/general/cortex-memory-recall.yaml +0 -446
- package/core/.rule/general/pipeline.yaml +0 -246
- package/core/.rule/general/sunny-access-control.yaml +0 -60
- package/core/.rule/general/system-invariants.yaml +0 -231
- package/core/.rule/pipeline/PPL-002-completed-task-archival.yaml +0 -528
- package/core/.rule/pipeline/auto-update.yaml +0 -282
- package/core/.rule/pipeline/task-execution.yaml +0 -365
- package/core/.specialist/Ansuz/concepts/phase_protocol.yaml +0 -65
- package/core/.specialist/Ansuz/experiments/boot_ablation_replay.js +0 -197
- package/core/.specialist/Ansuz/tools/bootstrap-anchors.js +0 -289
- package/core/.specialist/Ansuz/workflow.yaml +0 -1225
- package/core/.specialist/experiments/rg_benchmark.js +0 -523
- package/core/.specialist/experiments/rg_benchmark_results.json +0 -27
- package/core/.specialist/tools/jev-optional-context.js +0 -107
- package/core/.specialist/tools/jev-optional-context.test.js +0 -152
- package/core/.specialist/tools/memory-action-log.js +0 -839
- package/core/.specialist/tools/phase-gate.js +0 -3534
- package/core/.specialist/tools/phase-gate.test.js +0 -85
- package/core/.specialist/tools/precompute-runner.js +0 -444
- package/core/.specialist/tools/rule-engine.js +0 -621
- package/core/.specialist/tools/task-bridge-jev.test.js +0 -170
- package/core/.synapse/memory-shared.json.sync +0 -1
- package/core/.system/agent-skills/README.md +0 -724
- package/core/.system/cli-tools/README.md +0 -724
- package/core/.system/cortex/MODULES.md +0 -1046
- package/core/.system/dashboard/FRONTEND.md +0 -812
- package/core/.system/dashboard/README.md +0 -737
- package/core/.system/failure/README.md +0 -723
- package/core/.system/formation/LEGACY_SKILLS.md +0 -974
- package/core/.system/formation/POST_COMPLETE.md +0 -602
- package/core/.system/formation/README.md +0 -1094
- package/core/.system/formation/TOOLS_REFERENCE.md +0 -1145
- package/core/.system/kenaz/README.md +0 -787
- package/core/.system/memory/README.md +0 -719
- package/core/.system/pipeline/README.md +0 -712
- package/core/.system/rule/README.md +0 -794
- package/core/.system/sunny/README.md +0 -476
- package/core/.system/sunny/RULES.json +0 -89
- package/core/.system/sunny/knowledge/INDEX.md +0 -37
- package/core/.system/sunny/knowledge/agent-teams-api.md +0 -0
- package/core/.system/sunny/knowledge/ansuz-specialist.md +0 -500
- package/core/.system/sunny/knowledge/claude-cli-spawn.md +0 -177
- package/core/.system/sunny/knowledge/collaboration-api.md +0 -925
- package/core/.system/sunny/teammates/README.md +0 -107
- package/core/.system/sunny/teammates/how_to_use.yaml +0 -101
- package/core/.system/sunny/teammates/tools/headless/launcher.js +0 -318
- package/core/.system/sunny/teammates/tools/powershell/launcher.js +0 -241
- package/core/.system/sunny/teammates/tools/powershell/start.bat +0 -50
- package/core/.system/sunny/teammates/tools/utils/env.js +0 -96
- package/core/.system/sunny/teammates/tools/utils/format-output.js +0 -329
- package/core/.system/sunny/tools.json +0 -101
- package/core/dev/scripts/cleanup-queue.js +0 -184
- package/core/dev/scripts/cleanup_queue.js +0 -86
- package/core/dev/scripts/legacy/README.md +0 -39
- package/core/dev/scripts/legacy/dev_agent_scheduler.ps1.bak +0 -536
- package/core/dev/scripts/legacy/multi_agent_scheduler.ps1.bak +0 -1978
- package/core/dev/scripts/matrix/CLI_README.md +0 -214
- package/core/dev/scripts/matrix/README.md +0 -310
- package/core/dev/scripts/matrix/package-lock.json +0 -4266
- package/core/dev/scripts/matrix/package.json +0 -55
- package/core/dev/scripts/matrix/src/abbreviations.ts +0 -295
- package/core/dev/scripts/matrix/src/cli/commands/convert.ts +0 -211
- package/core/dev/scripts/matrix/src/cli/commands/create.ts +0 -95
- package/core/dev/scripts/matrix/src/cli/commands/delete.ts +0 -102
- package/core/dev/scripts/matrix/src/cli/commands/list-tags.ts.wip +0 -140
- package/core/dev/scripts/matrix/src/cli/commands/manage-tags.ts.wip +0 -173
- package/core/dev/scripts/matrix/src/cli/commands/query.ts +0 -261
- package/core/dev/scripts/matrix/src/cli/commands/read.ts +0 -77
- package/core/dev/scripts/matrix/src/cli/commands/stats.ts.wip +0 -168
- package/core/dev/scripts/matrix/src/cli/commands/tokens.ts.wip +0 -126
- package/core/dev/scripts/matrix/src/cli/commands/update.ts +0 -147
- package/core/dev/scripts/matrix/src/cli/commands/validate.ts +0 -275
- package/core/dev/scripts/matrix/src/cli/index.ts +0 -350
- package/core/dev/scripts/matrix/src/cli/utils/file-handler.ts +0 -72
- package/core/dev/scripts/matrix/src/cli/utils/logger.ts +0 -65
- package/core/dev/scripts/matrix/src/index.ts +0 -62
- package/core/dev/scripts/matrix/src/indexer/tag-indexer.ts +0 -165
- package/core/dev/scripts/matrix/src/parser.ts +0 -281
- package/core/dev/scripts/matrix/src/serializer.ts +0 -151
- package/core/dev/scripts/matrix/src/validator.ts +0 -301
- package/core/dev/scripts/matrix/tests/abbreviations.test.ts +0 -122
- package/core/dev/scripts/matrix/tests/cli.test.ts +0 -177
- package/core/dev/scripts/matrix/tests/convert.test.ts +0 -143
- package/core/dev/scripts/matrix/tests/parser.test.ts +0 -203
- package/core/dev/scripts/matrix/tests/query.test.ts +0 -85
- package/core/dev/scripts/matrix/tests/serializer.test.ts +0 -197
- package/core/dev/scripts/matrix/tests/validate.test.ts +0 -141
- package/core/dev/scripts/matrix/tests/validator.test.ts +0 -167
- package/core/dev/scripts/matrix/tsconfig.json +0 -20
- package/core/dev/scripts/matrix/types/index.d.ts +0 -111
- package/core/dev/scripts/matrix/types/index.d.ts.map +0 -1
- package/core/dev/scripts/matrix/types/index.js +0 -8
- package/core/dev/scripts/matrix/types/index.js.map +0 -1
- package/core/dev/scripts/matrix/types/index.ts +0 -124
- package/core/dev/scripts/memory-usage-report.js +0 -152
- package/core/dev/scripts/probe/ansuz-scaffold-ablation.js +0 -579
- package/core/dev/scripts/probe/ansuz-scaffold-ablation.test.js +0 -244
- package/core/dev/scripts/probe/hook-latency-probe.js +0 -315
- package/core/dev/scripts/probe/hook-latency-probe.test.js +0 -105
- package/core/dev/scripts/probe/prediction-signal-auc.js +0 -483
- package/core/dev/scripts/probe/prediction-signal-auc.test.js +0 -200
- package/core/dev/scripts/test-pty-ws-tunnel.js +0 -229
- package/core/dev/scripts/validate_pipeline.js +0 -197
- package/core/dev/spikes/task2145-evidence-20261004/backend-log-excerpt.txt +0 -56
- package/core/dev/spikes/task2145-evidence-20261004/graph.shadow +0 -0
- package/core/dev/spikes/task2145-evidence-20261004/graph.wal +0 -0
- package/core/dev/spikes/task2145-evidence-20261004/graph_corrupt_suspect.marker +0 -1
- package/core/plugins/kenaz/commands/strategy.md +0 -141
|
@@ -1,244 +0,0 @@
|
|
|
1
|
-
#!/usr/bin/env node
|
|
2
|
-
// TASK_1979 R6: unit tests for ansuz-scaffold-ablation.js's pure functions.
|
|
3
|
-
// No git shell-out — the git-show function is injected as a fake.
|
|
4
|
-
//
|
|
5
|
-
// Run: node --test dev/scripts/probe/ansuz-scaffold-ablation.test.js
|
|
6
|
-
|
|
7
|
-
'use strict';
|
|
8
|
-
|
|
9
|
-
const test = require('node:test');
|
|
10
|
-
const assert = require('node:assert/strict');
|
|
11
|
-
const fs = require('fs');
|
|
12
|
-
const os = require('os');
|
|
13
|
-
const path = require('path');
|
|
14
|
-
|
|
15
|
-
const mod = require('./ansuz-scaffold-ablation.js');
|
|
16
|
-
|
|
17
|
-
function makeTempDir() {
|
|
18
|
-
return fs.mkdtempSync(path.join(os.tmpdir(), 'ablation-test-'));
|
|
19
|
-
}
|
|
20
|
-
|
|
21
|
-
test('armRefMap returns the fixed A/B/C -> ref mapping and is not mutable via the export', () => {
|
|
22
|
-
const map = mod.armRefMap();
|
|
23
|
-
assert.deepEqual(map, { A: '5562fface', B: '1845c7e6b', C: 'a2956ed25' });
|
|
24
|
-
map.A = 'mutated';
|
|
25
|
-
const map2 = mod.armRefMap();
|
|
26
|
-
assert.equal(map2.A, '5562fface', 'mutating the returned copy must not affect the source mapping');
|
|
27
|
-
});
|
|
28
|
-
|
|
29
|
-
test('buildManifest computes byte accounting and rejects missing fields', () => {
|
|
30
|
-
const manifest = mod.buildManifest({
|
|
31
|
-
runId: 'run-1',
|
|
32
|
-
arm: 'B',
|
|
33
|
-
ref: '1845c7e6b',
|
|
34
|
-
ansuzMdBytes: 100,
|
|
35
|
-
elixirYamlBytes: 200,
|
|
36
|
-
bootPromptBytes: 350,
|
|
37
|
-
probe1Bytes: 1438,
|
|
38
|
-
probe2Bytes: 1435,
|
|
39
|
-
timestamp: '2026-09-20T00:00:00.000Z',
|
|
40
|
-
});
|
|
41
|
-
assert.equal(manifest.run_id, 'run-1');
|
|
42
|
-
assert.equal(manifest.arm, 'B');
|
|
43
|
-
assert.equal(manifest.ref, '1845c7e6b');
|
|
44
|
-
assert.equal(manifest.files['.claude/commands/Ansuz.md'], 100);
|
|
45
|
-
assert.equal(manifest.files['.specialist/Ansuz/elixir.yaml'], 200);
|
|
46
|
-
assert.equal(manifest.boot_prompt_bytes, 350);
|
|
47
|
-
assert.ok(manifest.label.includes('S1 merged'));
|
|
48
|
-
|
|
49
|
-
assert.throws(() => mod.buildManifest({ runId: 'run-1' }), /missing required field/);
|
|
50
|
-
});
|
|
51
|
-
|
|
52
|
-
test('buildBootPrompt embeds ref, arm, and both injected file bodies verbatim', () => {
|
|
53
|
-
const prompt = mod.buildBootPrompt({
|
|
54
|
-
runId: 'run-1',
|
|
55
|
-
arm: 'A',
|
|
56
|
-
ref: '5562fface',
|
|
57
|
-
ansuzMd: '# fake Ansuz.md body',
|
|
58
|
-
elixirYaml: 'fake: elixir body',
|
|
59
|
-
});
|
|
60
|
-
assert.match(prompt, /\[CANARY:ablation-v1\]/);
|
|
61
|
-
assert.match(prompt, /arm A \(ref 5562fface\)/);
|
|
62
|
-
assert.match(prompt, /# fake Ansuz\.md body/);
|
|
63
|
-
assert.match(prompt, /fake: elixir body/);
|
|
64
|
-
});
|
|
65
|
-
|
|
66
|
-
test('probe prompts each stay under 1.5 KB per R2', () => {
|
|
67
|
-
assert.ok(mod.byteLength(mod.PROBE_1_MD) <= 1536, `probe_1 is ${mod.byteLength(mod.PROBE_1_MD)} bytes`);
|
|
68
|
-
assert.ok(mod.byteLength(mod.PROBE_2_MD) <= 1536, `probe_2 is ${mod.byteLength(mod.PROBE_2_MD)} bytes`);
|
|
69
|
-
});
|
|
70
|
-
|
|
71
|
-
test('buildMeasurementLine enforces the merged REPORT.md + ablation schema', () => {
|
|
72
|
-
const line = mod.buildMeasurementLine({
|
|
73
|
-
run_id: 'run-1',
|
|
74
|
-
arm: 'C',
|
|
75
|
-
ref: 'a2956ed25',
|
|
76
|
-
probe: '2',
|
|
77
|
-
acceptance_met: true,
|
|
78
|
-
recall_reflex_fired: true,
|
|
79
|
-
scope_verified_before_carding: true,
|
|
80
|
-
unauthorized_change: false,
|
|
81
|
-
false_completion: false,
|
|
82
|
-
turns: 4,
|
|
83
|
-
tool_calls: 6,
|
|
84
|
-
wall_ms: 52000,
|
|
85
|
-
injected_bytes: 12345,
|
|
86
|
-
});
|
|
87
|
-
// REPORT.md legacy fields present with sane defaults.
|
|
88
|
-
assert.equal(line.path, 'ablation');
|
|
89
|
-
assert.deepEqual(line.ritual_markers_emitted, []);
|
|
90
|
-
assert.equal(line.fallback_triggered, false);
|
|
91
|
-
assert.equal(line.boot_wall_clock_ms, 52000);
|
|
92
|
-
// Ablation fields.
|
|
93
|
-
assert.equal(line.arm, 'C');
|
|
94
|
-
assert.equal(line.probe, 2, 'probe must be coerced to a number');
|
|
95
|
-
assert.equal(line.injected_bytes, 12345);
|
|
96
|
-
assert.ok(line.recorded_at);
|
|
97
|
-
});
|
|
98
|
-
|
|
99
|
-
test('buildMeasurementLine rejects missing required fields', () => {
|
|
100
|
-
assert.throws(
|
|
101
|
-
() => mod.buildMeasurementLine({ run_id: 'run-1', arm: 'A' }),
|
|
102
|
-
/missing required field/
|
|
103
|
-
);
|
|
104
|
-
});
|
|
105
|
-
|
|
106
|
-
test('buildMeasurementLine rejects an unknown arm', () => {
|
|
107
|
-
assert.throws(
|
|
108
|
-
() =>
|
|
109
|
-
mod.buildMeasurementLine({
|
|
110
|
-
run_id: 'run-1',
|
|
111
|
-
arm: 'Z',
|
|
112
|
-
ref: 'deadbeef',
|
|
113
|
-
probe: 1,
|
|
114
|
-
acceptance_met: true,
|
|
115
|
-
recall_reflex_fired: true,
|
|
116
|
-
scope_verified_before_carding: true,
|
|
117
|
-
unauthorized_change: false,
|
|
118
|
-
false_completion: false,
|
|
119
|
-
turns: 1,
|
|
120
|
-
tool_calls: 1,
|
|
121
|
-
wall_ms: 1,
|
|
122
|
-
injected_bytes: 1,
|
|
123
|
-
}),
|
|
124
|
-
/unknown arm/
|
|
125
|
-
);
|
|
126
|
-
});
|
|
127
|
-
|
|
128
|
-
test('buildMeasurementLine rejects a probe number outside {1,2}', () => {
|
|
129
|
-
assert.throws(
|
|
130
|
-
() =>
|
|
131
|
-
mod.buildMeasurementLine({
|
|
132
|
-
run_id: 'run-1',
|
|
133
|
-
arm: 'A',
|
|
134
|
-
ref: '5562fface',
|
|
135
|
-
probe: 3,
|
|
136
|
-
acceptance_met: true,
|
|
137
|
-
recall_reflex_fired: true,
|
|
138
|
-
scope_verified_before_carding: true,
|
|
139
|
-
unauthorized_change: false,
|
|
140
|
-
false_completion: false,
|
|
141
|
-
turns: 1,
|
|
142
|
-
tool_calls: 1,
|
|
143
|
-
wall_ms: 1,
|
|
144
|
-
injected_bytes: 1,
|
|
145
|
-
}),
|
|
146
|
-
/probe must be 1 or 2/
|
|
147
|
-
);
|
|
148
|
-
});
|
|
149
|
-
|
|
150
|
-
test('prepareArm writes boot_prompt.md/probe_1.md/probe_2.md/manifest.json to a temp dir using an injected git-show (no real git shell-out)', () => {
|
|
151
|
-
const tmp = makeTempDir();
|
|
152
|
-
const fakeGitShow = (ref, filePath) => {
|
|
153
|
-
if (filePath === '.claude/commands/Ansuz.md') return `FAKE ANSUZ.MD for ${ref}`;
|
|
154
|
-
if (filePath === '.specialist/Ansuz/elixir.yaml') return `fake_elixir: true # ${ref}`;
|
|
155
|
-
throw new Error(`unexpected file requested: ${filePath}`);
|
|
156
|
-
};
|
|
157
|
-
|
|
158
|
-
const manifest = mod.prepareArm({
|
|
159
|
-
runId: 'temp-run',
|
|
160
|
-
arm: 'B',
|
|
161
|
-
outDir: tmp,
|
|
162
|
-
gitShowFn: fakeGitShow,
|
|
163
|
-
now: () => '2026-09-20T12:00:00.000Z',
|
|
164
|
-
});
|
|
165
|
-
|
|
166
|
-
const armDir = path.join(tmp, 'arm-B');
|
|
167
|
-
assert.ok(fs.existsSync(path.join(armDir, 'boot_prompt.md')));
|
|
168
|
-
assert.ok(fs.existsSync(path.join(armDir, 'probe_1.md')));
|
|
169
|
-
assert.ok(fs.existsSync(path.join(armDir, 'probe_2.md')));
|
|
170
|
-
assert.ok(fs.existsSync(path.join(armDir, 'manifest.json')));
|
|
171
|
-
|
|
172
|
-
const bootPrompt = fs.readFileSync(path.join(armDir, 'boot_prompt.md'), 'utf8');
|
|
173
|
-
assert.match(bootPrompt, /FAKE ANSUZ\.MD for 1845c7e6b/);
|
|
174
|
-
assert.match(bootPrompt, /fake_elixir: true # 1845c7e6b/);
|
|
175
|
-
|
|
176
|
-
const onDisk = JSON.parse(fs.readFileSync(path.join(armDir, 'manifest.json'), 'utf8'));
|
|
177
|
-
assert.deepEqual(onDisk, manifest);
|
|
178
|
-
assert.equal(manifest.files['.claude/commands/Ansuz.md'], mod.byteLength(`FAKE ANSUZ.MD for 1845c7e6b`));
|
|
179
|
-
assert.equal(manifest.generated_at, '2026-09-20T12:00:00.000Z');
|
|
180
|
-
|
|
181
|
-
fs.rmSync(tmp, { recursive: true, force: true });
|
|
182
|
-
});
|
|
183
|
-
|
|
184
|
-
test('prepareArm rejects an unknown arm before touching the filesystem', () => {
|
|
185
|
-
const tmp = makeTempDir();
|
|
186
|
-
assert.throws(
|
|
187
|
-
() =>
|
|
188
|
-
mod.prepareArm({
|
|
189
|
-
runId: 'temp-run',
|
|
190
|
-
arm: 'D',
|
|
191
|
-
outDir: tmp,
|
|
192
|
-
gitShowFn: () => 'unused',
|
|
193
|
-
}),
|
|
194
|
-
/unknown arm/
|
|
195
|
-
);
|
|
196
|
-
assert.deepEqual(fs.readdirSync(tmp), []);
|
|
197
|
-
fs.rmSync(tmp, { recursive: true, force: true });
|
|
198
|
-
});
|
|
199
|
-
|
|
200
|
-
test('readMeasurementsForRun + summarizeRows produce per-arm counts (not only percentages)', () => {
|
|
201
|
-
const tmp = makeTempDir();
|
|
202
|
-
const measurementsFile = path.join(tmp, 'measurements.jsonl');
|
|
203
|
-
const rows = [
|
|
204
|
-
mod.buildMeasurementLine({
|
|
205
|
-
run_id: 'run-x', arm: 'A', ref: '5562fface', probe: 1,
|
|
206
|
-
acceptance_met: true, recall_reflex_fired: false, scope_verified_before_carding: null,
|
|
207
|
-
unauthorized_change: false, false_completion: false, turns: 3, tool_calls: 2, wall_ms: 10000, injected_bytes: 500,
|
|
208
|
-
}),
|
|
209
|
-
mod.buildMeasurementLine({
|
|
210
|
-
run_id: 'run-x', arm: 'A', ref: '5562fface', probe: 2,
|
|
211
|
-
acceptance_met: false, recall_reflex_fired: null, scope_verified_before_carding: false,
|
|
212
|
-
unauthorized_change: true, false_completion: true, turns: 5, tool_calls: 8, wall_ms: 30000, injected_bytes: 500,
|
|
213
|
-
}),
|
|
214
|
-
mod.buildMeasurementLine({
|
|
215
|
-
run_id: 'run-x', arm: 'C', ref: 'a2956ed25', probe: 1,
|
|
216
|
-
acceptance_met: true, recall_reflex_fired: true, scope_verified_before_carding: null,
|
|
217
|
-
unauthorized_change: false, false_completion: false, turns: 2, tool_calls: 1, wall_ms: 8000, injected_bytes: 200,
|
|
218
|
-
}),
|
|
219
|
-
// Different run_id — must be excluded by readMeasurementsForRun.
|
|
220
|
-
mod.buildMeasurementLine({
|
|
221
|
-
run_id: 'run-y', arm: 'B', ref: '1845c7e6b', probe: 1,
|
|
222
|
-
acceptance_met: true, recall_reflex_fired: true, scope_verified_before_carding: null,
|
|
223
|
-
unauthorized_change: false, false_completion: false, turns: 1, tool_calls: 1, wall_ms: 1000, injected_bytes: 100,
|
|
224
|
-
}),
|
|
225
|
-
];
|
|
226
|
-
fs.writeFileSync(measurementsFile, rows.map((r) => JSON.stringify(r)).join('\n') + '\n', 'utf8');
|
|
227
|
-
// A malformed trailing line must not crash the reader.
|
|
228
|
-
fs.appendFileSync(measurementsFile, 'not json\n', 'utf8');
|
|
229
|
-
|
|
230
|
-
const read = mod.readMeasurementsForRun('run-x', measurementsFile);
|
|
231
|
-
assert.equal(read.length, 3, 'must only include run-x rows and skip the malformed line');
|
|
232
|
-
|
|
233
|
-
const summary = mod.summarizeRows(read);
|
|
234
|
-
assert.equal(summary.A.n, 2);
|
|
235
|
-
assert.equal(summary.A.acceptance_met.true, 1);
|
|
236
|
-
assert.equal(summary.A.acceptance_met.false, 1);
|
|
237
|
-
assert.equal(summary.A.recall_reflex_fired.na, 1, 'null counts as N/A, not false');
|
|
238
|
-
assert.equal(summary.C.n, 1);
|
|
239
|
-
assert.equal(summary.C.acceptance_met.true, 1);
|
|
240
|
-
assert.equal(summary.B.n, 0, 'B has zero rows for run-x even though it exists for run-y');
|
|
241
|
-
assert.equal(summary.A.avg_turns, 4);
|
|
242
|
-
|
|
243
|
-
fs.rmSync(tmp, { recursive: true, force: true });
|
|
244
|
-
});
|
|
@@ -1,315 +0,0 @@
|
|
|
1
|
-
#!/usr/bin/env node
|
|
2
|
-
// TASK_1979 R3/R4: hook latency + prompt-cache stability probe.
|
|
3
|
-
//
|
|
4
|
-
// Measures every hook .claude/settings.json registers for UserPromptSubmit
|
|
5
|
-
// and PreToolUse (parsed from settings.json, not hand-listed) against the
|
|
6
|
-
// PROJECT copy of .claude/hooks — never the installed kenaz-core copy — by
|
|
7
|
-
// running each hook file directly (`node <hook>.js` with CLAUDE_PROJECT_DIR
|
|
8
|
-
// set to the repo root and a synthetic JSON payload on stdin), 5x each,
|
|
9
|
-
// plus a `node -e 0` floor measurement.
|
|
10
|
-
//
|
|
11
|
-
// Why invoke the hook file directly instead of re-running the exact
|
|
12
|
-
// `node -e "..."` wrapper string from settings.json: that wrapper string is
|
|
13
|
-
// shell-quoted for the harness's own (POSIX-shell-like) hook launcher: see
|
|
14
|
-
// rune_claude_code_hook_execution_cwd — hooks run with cwd = project dir).
|
|
15
|
-
// Shelling it out again here via child_process shell:true would go through
|
|
16
|
-
// this machine's OS-default shell (cmd.exe on Windows) whose quoting rules
|
|
17
|
-
// differ, which is a probe-validity bug of its own kind (feedback:
|
|
18
|
-
// monitor_must_validate_its_own_probe / harness_must_run_the_real_validator).
|
|
19
|
-
// The wrapper's only job is `process.chdir(d); require(d+'/.claude/hooks/X.js')`
|
|
20
|
-
// — no hook file in this repo gates its stdin-reading main() behind a
|
|
21
|
-
// `require.main === module` guard (checked: task-bridge.js,
|
|
22
|
-
// turn-context.js all run unconditionally on require/execute), and all
|
|
23
|
-
// relative `require('./_x')` calls inside a hook resolve via __dirname, not
|
|
24
|
-
// cwd — so invoking the .js file directly with CLAUDE_PROJECT_DIR set is
|
|
25
|
-
// behaviorally equivalent and avoids the quoting hazard entirely.
|
|
26
|
-
//
|
|
27
|
-
// Usage:
|
|
28
|
-
// node dev/scripts/probe/hook-latency-probe.js [--runs 5] [--out-dir <dir>]
|
|
29
|
-
//
|
|
30
|
-
// Writes .kenaz/experiments/ansuz_boot_split/hook-latency-<timestamp>.json
|
|
31
|
-
// and prints a latency + cache-stability table to stdout.
|
|
32
|
-
|
|
33
|
-
'use strict';
|
|
34
|
-
|
|
35
|
-
const fs = require('fs');
|
|
36
|
-
const path = require('path');
|
|
37
|
-
const { spawnSync } = require('child_process');
|
|
38
|
-
|
|
39
|
-
const REPO_ROOT = path.resolve(__dirname, '..', '..', '..');
|
|
40
|
-
const SETTINGS_PATH = path.join(REPO_ROOT, '.claude', 'settings.json');
|
|
41
|
-
const EXPERIMENT_DIR = path.join(REPO_ROOT, '.kenaz', 'experiments', 'ansuz_boot_split');
|
|
42
|
-
const HOOK_TIMEOUT_MS = 30000;
|
|
43
|
-
|
|
44
|
-
// ═══════════════════════════════════════
|
|
45
|
-
// settings.json parsing (pure — takes the parsed object, not the path)
|
|
46
|
-
// ═══════════════════════════════════════
|
|
47
|
-
|
|
48
|
-
function extractHookFilename(command) {
|
|
49
|
-
const m = /hooks\/([A-Za-z0-9_.-]+\.js)/.exec(command || '');
|
|
50
|
-
return m ? m[1] : null;
|
|
51
|
-
}
|
|
52
|
-
|
|
53
|
-
function collectHookEntries(settings) {
|
|
54
|
-
const hooks = settings && settings.hooks ? settings.hooks : {};
|
|
55
|
-
const out = { UserPromptSubmit: [], PreToolUse: [] };
|
|
56
|
-
|
|
57
|
-
for (const group of hooks.UserPromptSubmit || []) {
|
|
58
|
-
for (const h of group.hooks || []) {
|
|
59
|
-
const file = extractHookFilename(h.command);
|
|
60
|
-
if (file) out.UserPromptSubmit.push({ event: 'UserPromptSubmit', file, matcher: group.matcher || null, command: h.command });
|
|
61
|
-
}
|
|
62
|
-
}
|
|
63
|
-
for (const group of hooks.PreToolUse || []) {
|
|
64
|
-
for (const h of group.hooks || []) {
|
|
65
|
-
const file = extractHookFilename(h.command);
|
|
66
|
-
if (file) out.PreToolUse.push({ event: 'PreToolUse', file, matcher: group.matcher || null, command: h.command });
|
|
67
|
-
}
|
|
68
|
-
}
|
|
69
|
-
return out;
|
|
70
|
-
}
|
|
71
|
-
|
|
72
|
-
// ═══════════════════════════════════════
|
|
73
|
-
// Synthetic payloads (R3)
|
|
74
|
-
// ═══════════════════════════════════════
|
|
75
|
-
|
|
76
|
-
function buildPayload(entry, repoRoot, sessionId) {
|
|
77
|
-
if (entry.event === 'UserPromptSubmit') {
|
|
78
|
-
return { session_id: sessionId, hook_event_name: 'UserPromptSubmit', cwd: repoRoot, prompt: 'hello' };
|
|
79
|
-
}
|
|
80
|
-
// PreToolUse
|
|
81
|
-
const matcher = entry.matcher || '';
|
|
82
|
-
if (matcher === 'Read') {
|
|
83
|
-
return {
|
|
84
|
-
session_id: sessionId,
|
|
85
|
-
hook_event_name: 'PreToolUse',
|
|
86
|
-
tool_name: 'Read',
|
|
87
|
-
tool_input: { file_path: path.join(repoRoot, 'CLAUDE.md') },
|
|
88
|
-
cwd: repoRoot,
|
|
89
|
-
};
|
|
90
|
-
}
|
|
91
|
-
if (/Edit|Write/.test(matcher)) {
|
|
92
|
-
return {
|
|
93
|
-
session_id: sessionId,
|
|
94
|
-
hook_event_name: 'PreToolUse',
|
|
95
|
-
tool_name: 'Edit',
|
|
96
|
-
tool_input: {
|
|
97
|
-
file_path: path.join(repoRoot, 'CLAUDE.md'),
|
|
98
|
-
old_string: '__hook_latency_probe_nonexistent_string__',
|
|
99
|
-
new_string: '__hook_latency_probe_nonexistent_string__',
|
|
100
|
-
},
|
|
101
|
-
cwd: repoRoot,
|
|
102
|
-
};
|
|
103
|
-
}
|
|
104
|
-
// Bash (default/fallback)
|
|
105
|
-
return {
|
|
106
|
-
session_id: sessionId,
|
|
107
|
-
hook_event_name: 'PreToolUse',
|
|
108
|
-
tool_name: 'Bash',
|
|
109
|
-
tool_input: { command: 'ls' },
|
|
110
|
-
cwd: repoRoot,
|
|
111
|
-
};
|
|
112
|
-
}
|
|
113
|
-
|
|
114
|
-
// ═══════════════════════════════════════
|
|
115
|
-
// Runner (impure — spawns child processes)
|
|
116
|
-
// ═══════════════════════════════════════
|
|
117
|
-
|
|
118
|
-
function runOnce(scriptPath, payload, repoRoot) {
|
|
119
|
-
const start = Date.now();
|
|
120
|
-
const result = spawnSync(process.execPath, [scriptPath], {
|
|
121
|
-
cwd: repoRoot,
|
|
122
|
-
env: { ...process.env, CLAUDE_PROJECT_DIR: repoRoot },
|
|
123
|
-
input: JSON.stringify(payload),
|
|
124
|
-
encoding: 'utf8',
|
|
125
|
-
timeout: HOOK_TIMEOUT_MS,
|
|
126
|
-
maxBuffer: 16 * 1024 * 1024,
|
|
127
|
-
});
|
|
128
|
-
const ms = Date.now() - start;
|
|
129
|
-
return {
|
|
130
|
-
ms,
|
|
131
|
-
stdout: result.stdout || '',
|
|
132
|
-
stderr: result.stderr || '',
|
|
133
|
-
status: result.status,
|
|
134
|
-
timedOut: !!result.error && result.error.code === 'ETIMEDOUT',
|
|
135
|
-
error: result.error ? result.error.message : null,
|
|
136
|
-
};
|
|
137
|
-
}
|
|
138
|
-
|
|
139
|
-
function runFloorOnce() {
|
|
140
|
-
const start = Date.now();
|
|
141
|
-
const result = spawnSync(process.execPath, ['-e', '0'], {
|
|
142
|
-
encoding: 'utf8',
|
|
143
|
-
timeout: HOOK_TIMEOUT_MS,
|
|
144
|
-
});
|
|
145
|
-
const ms = Date.now() - start;
|
|
146
|
-
return { ms, status: result.status, error: result.error ? result.error.message : null };
|
|
147
|
-
}
|
|
148
|
-
|
|
149
|
-
function median(nums) {
|
|
150
|
-
const vals = nums.filter((n) => typeof n === 'number' && !Number.isNaN(n)).slice().sort((a, b) => a - b);
|
|
151
|
-
if (!vals.length) return null;
|
|
152
|
-
const mid = Math.floor(vals.length / 2);
|
|
153
|
-
return vals.length % 2 ? vals[mid] : Math.round((vals[mid - 1] + vals[mid]) / 2);
|
|
154
|
-
}
|
|
155
|
-
|
|
156
|
-
function byteLength(str) {
|
|
157
|
-
return Buffer.byteLength(str || '', 'utf8');
|
|
158
|
-
}
|
|
159
|
-
|
|
160
|
-
// R4: cache-stability diff summary between two stdout captures.
|
|
161
|
-
function diffSummary(a, b) {
|
|
162
|
-
if (a === b) return null;
|
|
163
|
-
const len = Math.min(a.length, b.length);
|
|
164
|
-
let i = 0;
|
|
165
|
-
while (i < len && a[i] === b[i]) i++;
|
|
166
|
-
return {
|
|
167
|
-
first_diff_byte_offset: i,
|
|
168
|
-
a_len: a.length,
|
|
169
|
-
b_len: b.length,
|
|
170
|
-
a_context: a.slice(Math.max(0, i - 20), i + 40),
|
|
171
|
-
b_context: b.slice(Math.max(0, i - 20), i + 40),
|
|
172
|
-
};
|
|
173
|
-
}
|
|
174
|
-
|
|
175
|
-
function measureHook(entry, repoRoot, runs) {
|
|
176
|
-
const scriptPath = path.join(repoRoot, '.claude', 'hooks', entry.file);
|
|
177
|
-
const sessionId = 'abl-hook-latency-1'; // fixed across ALL runs — required for R4 cache-stability comparison
|
|
178
|
-
const samples = [];
|
|
179
|
-
for (let i = 0; i < runs; i++) {
|
|
180
|
-
const payload = buildPayload(entry, repoRoot, sessionId);
|
|
181
|
-
samples.push(runOnce(scriptPath, payload, repoRoot));
|
|
182
|
-
}
|
|
183
|
-
|
|
184
|
-
const msValues = samples.map((s) => s.ms);
|
|
185
|
-
const stdoutBytes = samples.map((s) => byteLength(s.stdout));
|
|
186
|
-
const nonZeroExit = samples.filter((s) => s.status !== 0).length;
|
|
187
|
-
const timeouts = samples.filter((s) => s.timedOut).length;
|
|
188
|
-
|
|
189
|
-
const row = {
|
|
190
|
-
event: entry.event,
|
|
191
|
-
hook: entry.file,
|
|
192
|
-
matcher: entry.matcher,
|
|
193
|
-
runs,
|
|
194
|
-
median_ms: median(msValues),
|
|
195
|
-
median_stdout_bytes: median(stdoutBytes),
|
|
196
|
-
all_ms: msValues,
|
|
197
|
-
nonzero_exit_count: nonZeroExit,
|
|
198
|
-
timeout_count: timeouts,
|
|
199
|
-
};
|
|
200
|
-
|
|
201
|
-
if (entry.event === 'UserPromptSubmit') {
|
|
202
|
-
const distinct = new Set(samples.map((s) => s.stdout));
|
|
203
|
-
row.cache_stable = distinct.size === 1;
|
|
204
|
-
if (!row.cache_stable) {
|
|
205
|
-
const outs = samples.map((s) => s.stdout);
|
|
206
|
-
row.cache_diff = diffSummary(outs[0], outs[1]);
|
|
207
|
-
row.distinct_stdout_variants = distinct.size;
|
|
208
|
-
}
|
|
209
|
-
} else {
|
|
210
|
-
row.cache_stable = null; // N/A per R4 (UserPromptSubmit-only)
|
|
211
|
-
}
|
|
212
|
-
|
|
213
|
-
return row;
|
|
214
|
-
}
|
|
215
|
-
|
|
216
|
-
// ═══════════════════════════════════════
|
|
217
|
-
// CLI
|
|
218
|
-
// ═══════════════════════════════════════
|
|
219
|
-
|
|
220
|
-
function parseArgs(argv) {
|
|
221
|
-
const opts = { runs: 5, outDir: EXPERIMENT_DIR };
|
|
222
|
-
for (let i = 0; i < argv.length; i++) {
|
|
223
|
-
const a = argv[i];
|
|
224
|
-
const next = () => argv[++i];
|
|
225
|
-
if (a === '--runs') opts.runs = parseInt(next(), 10);
|
|
226
|
-
else if (a === '--out-dir') opts.outDir = next();
|
|
227
|
-
}
|
|
228
|
-
return opts;
|
|
229
|
-
}
|
|
230
|
-
|
|
231
|
-
function printTable(rows, floor) {
|
|
232
|
-
console.log('\nHook latency + cache-stability probe (project-copy .claude/hooks only)\n');
|
|
233
|
-
console.log(`node -e 0 floor: median ${median(floor.map((f) => f.ms))} ms over ${floor.length} runs`);
|
|
234
|
-
console.log('');
|
|
235
|
-
const header = ['event', 'hook', 'matcher', 'median_ms', 'median_stdout_B', 'nonzero_exit', 'timeouts', 'cache_stable'];
|
|
236
|
-
console.log(header.join(' | '));
|
|
237
|
-
for (const r of rows) {
|
|
238
|
-
console.log(
|
|
239
|
-
[
|
|
240
|
-
r.event,
|
|
241
|
-
r.hook,
|
|
242
|
-
r.matcher || '-',
|
|
243
|
-
r.median_ms,
|
|
244
|
-
r.median_stdout_bytes,
|
|
245
|
-
r.nonzero_exit_count,
|
|
246
|
-
r.timeout_count,
|
|
247
|
-
r.cache_stable === null ? 'N/A' : r.cache_stable,
|
|
248
|
-
].join(' | ')
|
|
249
|
-
);
|
|
250
|
-
}
|
|
251
|
-
const unstable = rows.filter((r) => r.cache_stable === false);
|
|
252
|
-
if (unstable.length) {
|
|
253
|
-
console.log('\nCache-INSTABLE UserPromptSubmit hooks (byte-diff summary):');
|
|
254
|
-
for (const r of unstable) {
|
|
255
|
-
console.log(` ${r.hook}: ${r.distinct_stdout_variants} distinct stdout variants across ${r.runs} runs`);
|
|
256
|
-
console.log(` first diff @ byte ${r.cache_diff.first_diff_byte_offset} (len ${r.cache_diff.a_len} vs ${r.cache_diff.b_len})`);
|
|
257
|
-
}
|
|
258
|
-
}
|
|
259
|
-
}
|
|
260
|
-
|
|
261
|
-
function main(argv) {
|
|
262
|
-
const opts = parseArgs(argv);
|
|
263
|
-
if (!fs.existsSync(SETTINGS_PATH)) {
|
|
264
|
-
throw new Error(`settings.json not found at ${SETTINGS_PATH}`);
|
|
265
|
-
}
|
|
266
|
-
const settings = JSON.parse(fs.readFileSync(SETTINGS_PATH, 'utf8'));
|
|
267
|
-
const entries = collectHookEntries(settings);
|
|
268
|
-
const allEntries = [...entries.UserPromptSubmit, ...entries.PreToolUse];
|
|
269
|
-
|
|
270
|
-
const floor = [];
|
|
271
|
-
for (let i = 0; i < opts.runs; i++) floor.push(runFloorOnce());
|
|
272
|
-
|
|
273
|
-
const rows = allEntries.map((entry) => measureHook(entry, REPO_ROOT, opts.runs));
|
|
274
|
-
|
|
275
|
-
printTable(rows, floor);
|
|
276
|
-
|
|
277
|
-
const timestamp = new Date().toISOString().replace(/[:.]/g, '-');
|
|
278
|
-
fs.mkdirSync(opts.outDir, { recursive: true });
|
|
279
|
-
const outPath = path.join(opts.outDir, `hook-latency-${timestamp}.json`);
|
|
280
|
-
const report = {
|
|
281
|
-
generated_at: new Date().toISOString(),
|
|
282
|
-
repo_root: REPO_ROOT,
|
|
283
|
-
runs: opts.runs,
|
|
284
|
-
node_floor_ms: floor.map((f) => f.ms),
|
|
285
|
-
node_floor_median_ms: median(floor.map((f) => f.ms)),
|
|
286
|
-
hooks: rows,
|
|
287
|
-
};
|
|
288
|
-
fs.writeFileSync(outPath, JSON.stringify(report, null, 2), 'utf8');
|
|
289
|
-
console.log(`\nWrote ${outPath}`);
|
|
290
|
-
return report;
|
|
291
|
-
}
|
|
292
|
-
|
|
293
|
-
if (require.main === module) {
|
|
294
|
-
try {
|
|
295
|
-
main(process.argv.slice(2));
|
|
296
|
-
} catch (e) {
|
|
297
|
-
console.error(`Error: ${e.message}`);
|
|
298
|
-
process.exitCode = 1;
|
|
299
|
-
}
|
|
300
|
-
}
|
|
301
|
-
|
|
302
|
-
module.exports = {
|
|
303
|
-
extractHookFilename,
|
|
304
|
-
collectHookEntries,
|
|
305
|
-
buildPayload,
|
|
306
|
-
median,
|
|
307
|
-
byteLength,
|
|
308
|
-
diffSummary,
|
|
309
|
-
measureHook,
|
|
310
|
-
runOnce,
|
|
311
|
-
runFloorOnce,
|
|
312
|
-
REPO_ROOT,
|
|
313
|
-
SETTINGS_PATH,
|
|
314
|
-
EXPERIMENT_DIR,
|
|
315
|
-
};
|
|
@@ -1,105 +0,0 @@
|
|
|
1
|
-
#!/usr/bin/env node
|
|
2
|
-
// TASK_1979: unit tests for hook-latency-probe.js's pure functions
|
|
3
|
-
// (settings.json parsing, payload building, median, diff summary).
|
|
4
|
-
// No child_process spawning here — that part is exercised manually via
|
|
5
|
-
// `node dev/scripts/probe/hook-latency-probe.js` against the live repo.
|
|
6
|
-
//
|
|
7
|
-
// Run: node --test dev/scripts/probe/hook-latency-probe.test.js
|
|
8
|
-
|
|
9
|
-
'use strict';
|
|
10
|
-
|
|
11
|
-
const test = require('node:test');
|
|
12
|
-
const assert = require('node:assert/strict');
|
|
13
|
-
|
|
14
|
-
const mod = require('./hook-latency-probe.js');
|
|
15
|
-
|
|
16
|
-
test('extractHookFilename pulls the .js basename out of a node -e wrapper command', () => {
|
|
17
|
-
const cmd = "node -e \"const d=process.env.CLAUDE_PROJECT_DIR;process.chdir(d);require(d+'/.claude/hooks/task-bridge.js')\"";
|
|
18
|
-
assert.equal(mod.extractHookFilename(cmd), 'task-bridge.js');
|
|
19
|
-
});
|
|
20
|
-
|
|
21
|
-
test('extractHookFilename returns null for a command with no hooks/*.js reference', () => {
|
|
22
|
-
assert.equal(mod.extractHookFilename('echo hello'), null);
|
|
23
|
-
assert.equal(mod.extractHookFilename(''), null);
|
|
24
|
-
assert.equal(mod.extractHookFilename(undefined), null);
|
|
25
|
-
});
|
|
26
|
-
|
|
27
|
-
test('collectHookEntries extracts UserPromptSubmit and PreToolUse entries with matchers, ignoring other events', () => {
|
|
28
|
-
const settings = {
|
|
29
|
-
hooks: {
|
|
30
|
-
UserPromptSubmit: [
|
|
31
|
-
{ hooks: [{ type: 'command', command: "require(d+'/.claude/hooks/turn-context.js')" }] },
|
|
32
|
-
{ hooks: [{ type: 'command', command: "require(d+'/.claude/hooks/task-bridge.js')" }] },
|
|
33
|
-
],
|
|
34
|
-
PreToolUse: [
|
|
35
|
-
{ matcher: 'Read', hooks: [{ type: 'command', command: "require(d+'/.claude/hooks/memory-guard.js')" }] },
|
|
36
|
-
{ matcher: 'Edit|Write', hooks: [{ type: 'command', command: "require(d+'/.claude/hooks/stream-delta.js')" }] },
|
|
37
|
-
{ matcher: 'Bash', hooks: [{ type: 'command', command: "require(d+'/.claude/hooks/synapse-first-investigation.js')" }] },
|
|
38
|
-
],
|
|
39
|
-
PostToolUse: [
|
|
40
|
-
{ matcher: 'Bash', hooks: [{ type: 'command', command: "require(d+'/.claude/hooks/handoff-snapshot-on-commit.js')" }] },
|
|
41
|
-
],
|
|
42
|
-
Stop: [
|
|
43
|
-
{ hooks: [{ type: 'command', command: "require('.specialist/tools/session.js')" }] },
|
|
44
|
-
],
|
|
45
|
-
},
|
|
46
|
-
};
|
|
47
|
-
const entries = mod.collectHookEntries(settings);
|
|
48
|
-
assert.equal(entries.UserPromptSubmit.length, 2);
|
|
49
|
-
assert.deepEqual(
|
|
50
|
-
entries.UserPromptSubmit.map((e) => e.file),
|
|
51
|
-
['turn-context.js', 'task-bridge.js']
|
|
52
|
-
);
|
|
53
|
-
assert.equal(entries.PreToolUse.length, 3);
|
|
54
|
-
assert.deepEqual(
|
|
55
|
-
entries.PreToolUse.map((e) => ({ file: e.file, matcher: e.matcher })),
|
|
56
|
-
[
|
|
57
|
-
{ file: 'memory-guard.js', matcher: 'Read' },
|
|
58
|
-
{ file: 'stream-delta.js', matcher: 'Edit|Write' },
|
|
59
|
-
{ file: 'synapse-first-investigation.js', matcher: 'Bash' },
|
|
60
|
-
]
|
|
61
|
-
);
|
|
62
|
-
// PostToolUse/Stop must not leak in — only UserPromptSubmit + PreToolUse are in scope (R3).
|
|
63
|
-
assert.equal(entries.PostToolUse, undefined);
|
|
64
|
-
assert.equal(entries.Stop, undefined);
|
|
65
|
-
});
|
|
66
|
-
|
|
67
|
-
test('buildPayload matches the R3 example shape for UserPromptSubmit and PreToolUse Bash', () => {
|
|
68
|
-
const ups = mod.buildPayload({ event: 'UserPromptSubmit' }, '/repo', 'abl-1');
|
|
69
|
-
assert.deepEqual(ups, { session_id: 'abl-1', hook_event_name: 'UserPromptSubmit', cwd: '/repo', prompt: 'hello' });
|
|
70
|
-
|
|
71
|
-
const bash = mod.buildPayload({ event: 'PreToolUse', matcher: 'Bash' }, '/repo', 'abl-1');
|
|
72
|
-
assert.equal(bash.tool_name, 'Bash');
|
|
73
|
-
assert.deepEqual(bash.tool_input, { command: 'ls' });
|
|
74
|
-
});
|
|
75
|
-
|
|
76
|
-
test('buildPayload gives Read a file_path and Edit|Write an editable file_path + strings', () => {
|
|
77
|
-
const read = mod.buildPayload({ event: 'PreToolUse', matcher: 'Read' }, '/repo', 'abl-1');
|
|
78
|
-
assert.equal(read.tool_name, 'Read');
|
|
79
|
-
assert.match(read.tool_input.file_path, /CLAUDE\.md$/);
|
|
80
|
-
|
|
81
|
-
const edit = mod.buildPayload({ event: 'PreToolUse', matcher: 'Edit|Write' }, '/repo', 'abl-1');
|
|
82
|
-
assert.equal(edit.tool_name, 'Edit');
|
|
83
|
-
assert.ok('old_string' in edit.tool_input && 'new_string' in edit.tool_input);
|
|
84
|
-
});
|
|
85
|
-
|
|
86
|
-
test('median handles empty, single, even, and odd arrays', () => {
|
|
87
|
-
assert.equal(mod.median([]), null);
|
|
88
|
-
assert.equal(mod.median([5]), 5);
|
|
89
|
-
assert.equal(mod.median([1, 2, 3]), 2);
|
|
90
|
-
assert.equal(mod.median([1, 2, 3, 4]), 3); // rounds (2+3)/2
|
|
91
|
-
assert.equal(mod.median([NaN, 1, 2, 3]), 2, 'non-numeric values are filtered out');
|
|
92
|
-
});
|
|
93
|
-
|
|
94
|
-
test('diffSummary returns null for identical strings and a byte-offset summary otherwise', () => {
|
|
95
|
-
assert.equal(mod.diffSummary('abc', 'abc'), null);
|
|
96
|
-
const diff = mod.diffSummary('hello world', 'hello there');
|
|
97
|
-
assert.equal(diff.first_diff_byte_offset, 6);
|
|
98
|
-
assert.equal(diff.a_len, 11);
|
|
99
|
-
assert.equal(diff.b_len, 11);
|
|
100
|
-
});
|
|
101
|
-
|
|
102
|
-
test('byteLength counts UTF-8 bytes, not JS string length, for multi-byte content', () => {
|
|
103
|
-
assert.equal(mod.byteLength('abc'), 3);
|
|
104
|
-
assert.ok(mod.byteLength('你好') > 2, 'CJK chars are >1 byte each in UTF-8');
|
|
105
|
-
});
|