Files
echo/echo-memory.plugin.src/skills/echo-memory/eval/perf/results/SUMMARY.json
T

931 lines
24 KiB
JSON
Raw Normal View History

2026-06-23 17:17:00 -05:00
{
"env": {
"date": "2026-06-23T20:17:09",
"endpoint": "https://echoapi.alwisp.com",
"commit": "af16598",
"echo_workers": 8,
"echo_timeout": 30,
"python": "3.10.12",
"iterations": 4,
"count_k": 50
},
"metrics": {
"bulk-append": {
"result": {
"k": 30,
"append_write": {
"n": 30,
"min_ms": 87.11,
"median_ms": 104.08,
"p90_ms": 190.63,
"p95_ms": 198.89,
"max_ms": 241.91,
"mean_ms": 117.22
},
"append_skip": {
"n": 30,
"min_ms": 47.57,
"median_ms": 51.42,
"p90_ms": 59.82,
"p95_ms": 61.57,
"max_ms": 73.49,
"mean_ms": 53.22
},
"skips_confirmed": 30,
"all_skipped_second_pass": true
},
"gates": [
{
"rule": {
"field": "all_skipped_second_pass",
"op": ">=",
"min": 1,
"why": "second pass of identical lines must be 100% idempotent skips (boolean true coerced to 1)"
},
"value": true,
"pass": true
}
]
},
"bulk-get": {
"result": {
"k": 30,
"workers": 8,
"serial": {
"n": 5,
"min_ms": 1520.47,
"median_ms": 1606.86,
"p90_ms": 1805.72,
"p95_ms": 1835.83,
"max_ms": 1865.94,
"mean_ms": 1658.6,
"warmup": {
"n": 1,
"min_ms": 1601.2,
"median_ms": 1601.2,
"p90_ms": 1601.2,
"p95_ms": 1601.2,
"max_ms": 1601.2,
"mean_ms": 1601.2
}
},
"concurrent": {
"n": 5,
"min_ms": 340.31,
"median_ms": 356.48,
"p90_ms": 358.82,
"p95_ms": 359.32,
"max_ms": 359.83,
"mean_ms": 351.42,
"warmup": {
"n": 2,
"min_ms": 353.43,
"median_ms": 434.94,
"p90_ms": 500.15,
"p95_ms": 508.3,
"max_ms": 516.45,
"mean_ms": 434.94
}
},
"speedup_ratio": 4.51
},
"gates": [
{
"rule": {
"field": "speedup_ratio",
"op": ">=",
"min": 1.5,
"why": "controlled-K concurrent vs serial; lower bar than full-vault since K is small"
},
"value": 4.51,
"pass": true
}
]
},
"bulk-put": {
"result": {
"k": 30,
"per_put": {
"n": 30,
"min_ms": 100.09,
"median_ms": 114.98,
"p90_ms": 212.46,
"p95_ms": 236.18,
"max_ms": 330.77,
"mean_ms": 143.25
},
"total_ms": 4297.5,
"puts_per_sec": 7.0
},
"gates": []
},
"cache": {
"result": {
"requested": 60,
"unique": 20,
"returned": 20,
"deduped": true,
"elapsed_ms": 307.13
},
"gates": [
{
"rule": {
"field": "deduped",
"op": ">=",
"min": 1,
"why": "read_many must collapse a 3x-duplicated path list to the unique set"
},
"value": true,
"pass": true
}
]
},
"expand-graph": {
"result": {
"subjects": [
{
"label": "hub-echo",
"query": "echo",
"neighbours": 120,
"serial_ms": 2227.67,
"concurrent_ms": 642.2,
"speedup": 3.47,
"ranking_identical": true,
"scores_identical": true
},
{
"label": "hub-prefs",
"query": "operator preferences",
"neighbours": 126,
"serial_ms": 2910.46,
"concurrent_ms": 698.8,
"speedup": 4.16,
"ranking_identical": true,
"scores_identical": true
}
],
"min_speedup": 3.47,
"all_ranking_identical": true,
"all_scores_identical": true
},
"gates": [
{
"rule": {
"field": "min_speedup",
"op": ">=",
"min": 2.0,
"why": "recall()'s graph layer must fetch each BFS hop concurrently (read_many), not serially per node; <2x means expand_graph regressed to the pre-fix serial walk"
},
"value": 3.47,
"pass": true
},
{
"rule": {
"field": "all_ranking_identical",
"op": ">=",
"min": 1,
"why": "the concurrent expansion must return the same ranked neighbours as the serial reference"
},
"value": true,
"pass": true
},
{
"rule": {
"field": "all_scores_identical",
"op": ">=",
"min": 1,
"why": "decayed scores must match the serial reference to within float tolerance"
},
"value": true,
"pass": true
}
]
},
"index": {
"result": {
"script": "sweep.py",
"elapsed_ms": 4629.0,
"exit_code": 0,
"ok": true,
"stderr_tail": []
},
"gates": []
},
"lint": {
"result": {
"script": "vault_lint.py",
"elapsed_ms": 5126.4,
"exit_code": 1,
"ok": true,
"stderr_tail": []
},
"gates": []
},
"lock": {
"result": {
"acquire_free_ms": 159.18,
"acquire_free_rc": 0,
"contended_ms": 57.89,
"contended_rc_expected_75": 75,
"release_ms": 132.92,
"ok": true
},
"gates": [
{
"rule": {
"field": "ok",
"op": ">=",
"min": 1,
"why": "free acquire returns 0 and a contended acquire fast-fails with exit 75"
},
"value": true,
"pass": true
}
]
},
"pool-warmup": {
"result": {
"probe": "_agent/echo-vault.md",
"cold_ms": 163.25,
"warm": {
"n": 12,
"min_ms": 45.64,
"median_ms": 50.29,
"p90_ms": 52.51,
"p95_ms": 53.79,
"max_ms": 55.28,
"mean_ms": 50.26,
"warmup": {
"n": 1,
"min_ms": 51.68,
"median_ms": 51.68,
"p90_ms": 51.68,
"p95_ms": 51.68,
"max_ms": 51.68,
"mean_ms": 51.68
}
},
"cold_over_warm_ratio": 3.25
},
"gates": [
{
"rule": {
"field": "cold_over_warm_ratio",
"op": ">=",
"min": 1.5,
"why": "cold request must be meaningfully slower than warm \u2014 proves keep-alive is reusing the connection; a ratio near 1.0 means every request is re-handshaking (the pre-1.1.0 bug)"
},
"value": 3.25,
"pass": true
}
]
},
"queue": {
"result": {
"k": 10,
"enqueue": {
"n": 10,
"min_ms": 0.07,
"median_ms": 0.08,
"p90_ms": 0.18,
"p95_ms": 0.2,
"max_ms": 0.22,
"mean_ms": 0.1
},
"pending_after_enqueue": 10,
"note": "flush replay intentionally not run against the live vault; enqueue path timed only. See README queue caveat."
},
"gates": []
},
"read-full": {
"result": {
"note_count": 197,
"workers": 8,
"serial": {
"n": 1,
"min_ms": 11376.08,
"median_ms": 11376.08,
"p90_ms": 11376.08,
"p95_ms": 11376.08,
"max_ms": 11376.08,
"mean_ms": 11376.08
},
"concurrent": {
"n": 4,
"min_ms": 1559.79,
"median_ms": 1595.31,
"p90_ms": 1740.92,
"p95_ms": 1768.05,
"max_ms": 1795.17,
"mean_ms": 1636.4,
"warmup": {
"n": 2,
"min_ms": 1641.35,
"median_ms": 1652.91,
"p90_ms": 1662.17,
"p95_ms": 1663.32,
"max_ms": 1664.48,
"mean_ms": 1652.91
}
},
"speedup_ratio": 7.13,
"notes_per_sec_concurrent": 123.5
},
"gates": [
{
"rule": {
"field": "speedup_ratio",
"op": ">=",
"min": 1.8,
"why": "concurrent read_many must beat serial by the 1.1.0 concurrency margin; <1.8 means concurrency regressed"
},
"value": 7.13,
"pass": true
}
]
},
"resolve": {
"result": {
"cases": [
{
"mention": "echo",
"expect": "exact",
"expect_slug": "echo",
"resolved_slug": "echo",
"candidate_slugs": [
"2026-06-19-goldbrain-full-echo-architect",
"echo",
"echo-memory-codex-plugin",
"echo-plugin-build",
"echo-skill-improvements"
],
"verdict": "PASS",
"resolve_timing": {
"n": 6,
"min_ms": 0.0,
"median_ms": 0.0,
"p90_ms": 0.0,
"p95_ms": 0.0,
"max_ms": 0.0,
"mean_ms": 0.0,
"warmup": {
"n": 2,
"min_ms": 0.01,
"median_ms": 0.1,
"p90_ms": 0.17,
"p95_ms": 0.18,
"max_ms": 0.19,
"mean_ms": 0.1
}
},
"fuzzy_timing": {
"n": 6,
"min_ms": 1.35,
"median_ms": 1.49,
"p90_ms": 1.67,
"p95_ms": 1.68,
"max_ms": 1.68,
"mean_ms": 1.51,
"warmup": {
"n": 2,
"min_ms": 1.82,
"median_ms": 1.83,
"p90_ms": 1.84,
"p95_ms": 1.84,
"max_ms": 1.85,
"mean_ms": 1.83
}
}
},
{
"mention": "echo memory",
"expect": "candidates",
"expect_slug": "echo",
"resolved_slug": "echo",
"candidate_slugs": [
"echo",
"echo-memory-codex-plugin",
"echo-plugin-build",
"echo-skill-improvements",
"2026-06-19-goldbrain-full-echo-architect"
],
"verdict": "INFO",
"resolve_timing": {
"n": 6,
"min_ms": 0.55,
"median_ms": 0.56,
"p90_ms": 0.57,
"p95_ms": 0.58,
"max_ms": 0.58,
"mean_ms": 0.56,
"warmup": {
"n": 2,
"min_ms": 0.61,
"median_ms": 0.61,
"p90_ms": 0.61,
"p95_ms": 0.61,
"max_ms": 0.61,
"mean_ms": 0.61
}
},
"fuzzy_timing": {
"n": 6,
"min_ms": 0.97,
"median_ms": 0.99,
"p90_ms": 1.06,
"p95_ms": 1.09,
"max_ms": 1.11,
"mean_ms": 1.01,
"warmup": {
"n": 2,
"min_ms": 1.15,
"median_ms": 1.18,
"p90_ms": 1.2,
"p95_ms": 1.21,
"max_ms": 1.21,
"mean_ms": 1.18
}
}
},
{
"mention": "ECHO plugin",
"expect": "candidates",
"expect_slug": "echo",
"resolved_slug": "echo",
"candidate_slugs": [
"echo",
"echo-memory-codex-plugin",
"echo-plugin-build",
"2026-06-19-goldbrain-full-echo-architect",
"alabama-wisp-brand-docs"
],
"verdict": "INFO",
"resolve_timing": {
"n": 6,
"min_ms": 0.41,
"median_ms": 0.41,
"p90_ms": 0.42,
"p95_ms": 0.42,
"max_ms": 0.42,
"mean_ms": 0.41,
"warmup": {
"n": 2,
"min_ms": 0.42,
"median_ms": 0.45,
"p90_ms": 0.47,
"p95_ms": 0.48,
"max_ms": 0.48,
"mean_ms": 0.45
}
},
"fuzzy_timing": {
"n": 6,
"min_ms": 0.79,
"median_ms": 0.8,
"p90_ms": 0.88,
"p95_ms": 0.9,
"max_ms": 0.92,
"mean_ms": 0.83,
"warmup": {
"n": 2,
"min_ms": 0.89,
"median_ms": 0.89,
"p90_ms": 0.9,
"p95_ms": 0.9,
"max_ms": 0.9,
"mean_ms": 0.89
}
}
},
{
"mention": "goldbrain",
"expect": "exact",
"expect_slug": "goldbrain",
"resolved_slug": "goldbrain",
"candidate_slugs": [
"2026-06-19-goldbrain-full-echo-architect",
"goldbrain"
],
"verdict": "PASS",
"resolve_timing": {
"n": 6,
"min_ms": 0.0,
"median_ms": 0.0,
"p90_ms": 0.0,
"p95_ms": 0.0,
"max_ms": 0.0,
"mean_ms": 0.0,
"warmup": {
"n": 2,
"min_ms": 0.0,
"median_ms": 0.0,
"p90_ms": 0.0,
"p95_ms": 0.0,
"max_ms": 0.0,
"mean_ms": 0.0
}
},
"fuzzy_timing": {
"n": 6,
"min_ms": 0.73,
"median_ms": 0.75,
"p90_ms": 0.85,
"p95_ms": 0.88,
"max_ms": 0.91,
"mean_ms": 0.78,
"warmup": {
"n": 2,
"min_ms": 0.8,
"median_ms": 0.81,
"p90_ms": 0.82,
"p95_ms": 0.82,
"max_ms": 0.82,
"mean_ms": 0.81
}
}
},
{
"mention": "jason stedwell",
"expect": "exact",
"expect_slug": "jason-stedwell",
"resolved_slug": "jason-stedwell",
"candidate_slugs": [
"jason-stedwell",
"jason-mcp-gateway"
],
"verdict": "PASS",
"resolve_timing": {
"n": 6,
"min_ms": 0.0,
"median_ms": 0.0,
"p90_ms": 0.0,
"p95_ms": 0.0,
"max_ms": 0.0,
"mean_ms": 0.0,
"warmup": {
"n": 2,
"min_ms": 0.0,
"median_ms": 0.0,
"p90_ms": 0.0,
"p95_ms": 0.0,
"max_ms": 0.0,
"mean_ms": 0.0
}
},
"fuzzy_timing": {
"n": 6,
"min_ms": 0.69,
"median_ms": 0.72,
"p90_ms": 0.75,
"p95_ms": 0.75,
"max_ms": 0.75,
"mean_ms": 0.72,
"warmup": {
"n": 2,
"min_ms": 0.74,
"median_ms": 0.74,
"p90_ms": 0.75,
"p95_ms": 0.75,
"max_ms": 0.75,
"mean_ms": 0.74
}
}
},
{
"mention": "jason",
"expect": "candidates",
"expect_slug": "jason-stedwell",
"resolved_slug": "jason-stedwell",
"candidate_slugs": [
"jason-mcp-gateway",
"jason-stedwell"
],
"verdict": "INFO",
"resolve_timing": {
"n": 6,
"min_ms": 0.61,
"median_ms": 0.65,
"p90_ms": 0.66,
"p95_ms": 0.67,
"max_ms": 0.67,
"mean_ms": 0.64,
"warmup": {
"n": 2,
"min_ms": 0.66,
"median_ms": 0.68,
"p90_ms": 0.69,
"p95_ms": 0.69,
"max_ms": 0.69,
"mean_ms": 0.68
}
},
"fuzzy_timing": {
"n": 6,
"min_ms": 0.63,
"median_ms": 0.63,
"p90_ms": 0.65,
"p95_ms": 0.65,
"max_ms": 0.66,
"mean_ms": 0.64,
"warmup": {
"n": 2,
"min_ms": 0.68,
"median_ms": 0.69,
"p90_ms": 0.7,
"p95_ms": 0.7,
"max_ms": 0.7,
"mean_ms": 0.69
}
}
},
{
"mention": "zzqx nonexistent entity",
"expect": "miss",
"expect_slug": null,
"resolved_slug": null,
"candidate_slugs": [],
"verdict": "PASS",
"resolve_timing": {
"n": 6,
"min_ms": 0.62,
"median_ms": 0.63,
"p90_ms": 0.67,
"p95_ms": 0.67,
"max_ms": 0.68,
"mean_ms": 0.64,
"warmup": {
"n": 2,
"min_ms": 0.66,
"median_ms": 0.67,
"p90_ms": 0.67,
"p95_ms": 0.67,
"max_ms": 0.67,
"mean_ms": 0.67
}
},
"fuzzy_timing": {
"n": 6,
"min_ms": 0.61,
"median_ms": 0.62,
"p90_ms": 0.65,
"p95_ms": 0.65,
"max_ms": 0.66,
"mean_ms": 0.62,
"warmup": {
"n": 2,
"min_ms": 0.62,
"median_ms": 0.63,
"p90_ms": 0.64,
"p95_ms": 0.64,
"max_ms": 0.64,
"mean_ms": 0.63
}
}
}
],
"passes": 4,
"needs_tuning": 3,
"note": "verdicts are PASS/INFO only; promote to FAIL once the table is confirmed against the live vault"
},
"gates": []
},
"soak": {
"result": {
"seconds": 22,
"iterations": 15,
"errors": 0,
"per_pass": {
"n": 15,
"min_ms": 1472.88,
"median_ms": 1551.67,
"p90_ms": 1648.45,
"p95_ms": 1702.66,
"max_ms": 1820.58,
"mean_ms": 1569.81
},
"early_mean_ms": 1575.63,
"late_mean_ms": 1564.72,
"drift_ratio_late_over_early": 0.99
},
"gates": [
{
"rule": {
"field": "errors",
"op": "<=",
"min": 0,
"why": "no read errors across the soak window \u2014 connection leaks/pool exhaustion would surface here"
},
"value": 0,
"pass": true
},
{
"rule": {
"field": "drift_ratio_late_over_early",
"op": "<=",
"min": 1.5,
"why": "late passes must not be much slower than early ones; >1.5 suggests a leak or degrading pool"
},
"value": 0.99,
"pass": true
}
]
},
"subject-pull": {
"result": {
"subjects": [
{
"label": "apta",
"query": "APTA",
"resolve_floor": {
"n": 1,
"min_ms": 0.75,
"median_ms": 0.75,
"p90_ms": 0.75,
"p95_ms": 0.75,
"max_ms": 0.75,
"mean_ms": 0.75
},
"search_only": {
"n": 1,
"min_ms": 61.87,
"median_ms": 61.87,
"p90_ms": 61.87,
"p95_ms": 61.87,
"max_ms": 61.87,
"mean_ms": 61.87
},
"recall_total": {
"n": 1,
"min_ms": 2231.31,
"median_ms": 2231.31,
"p90_ms": 2231.31,
"p95_ms": 2231.31,
"max_ms": 2231.31,
"mean_ms": 2231.31
}
},
{
"label": "capmetro",
"query": "CapMetro",
"resolve_floor": {
"n": 1,
"min_ms": 0.03,
"median_ms": 0.03,
"p90_ms": 0.03,
"p95_ms": 0.03,
"max_ms": 0.03,
"mean_ms": 0.03
},
"search_only": {
"n": 1,
"min_ms": 57.73,
"median_ms": 57.73,
"p90_ms": 57.73,
"p95_ms": 57.73,
"max_ms": 57.73,
"mean_ms": 57.73
},
"recall_total": {
"n": 1,
"min_ms": 2116.06,
"median_ms": 2116.06,
"p90_ms": 2116.06,
"p95_ms": 2116.06,
"max_ms": 2116.06,
"mean_ms": 2116.06
}
},
{
"label": "hub-echo",
"query": "echo",
"resolve_floor": {
"n": 1,
"min_ms": 0.03,
"median_ms": 0.03,
"p90_ms": 0.03,
"p95_ms": 0.03,
"max_ms": 0.03,
"mean_ms": 0.03
},
"search_only": {
"n": 1,
"min_ms": 70.56,
"median_ms": 70.56,
"p90_ms": 70.56,
"p95_ms": 70.56,
"max_ms": 70.56,
"mean_ms": 70.56
},
"recall_total": {
"n": 1,
"min_ms": 2403.62,
"median_ms": 2403.62,
"p90_ms": 2403.62,
"p95_ms": 2403.62,
"max_ms": 2403.62,
"mean_ms": 2403.62
}
},
{
"label": "hub-prefs",
"query": "operator preferences",
"resolve_floor": {
"n": 1,
"min_ms": 0.04,
"median_ms": 0.04,
"p90_ms": 0.04,
"p95_ms": 0.04,
"max_ms": 0.04,
"mean_ms": 0.04
},
"search_only": {
"n": 1,
"min_ms": 2011.13,
"median_ms": 2011.13,
"p90_ms": 2011.13,
"p95_ms": 2011.13,
"max_ms": 2011.13,
"mean_ms": 2011.13
},
"recall_total": {
"n": 1,
"min_ms": 2994.84,
"median_ms": 2994.84,
"p90_ms": 2994.84,
"p95_ms": 2994.84,
"max_ms": 2994.84,
"mean_ms": 2994.84
}
},
{
"label": "leaf-rivnut",
"query": "rivnut torque spec",
"resolve_floor": {
"n": 1,
"min_ms": 2.15,
"median_ms": 2.15,
"p90_ms": 2.15,
"p95_ms": 2.15,
"max_ms": 2.15,
"mean_ms": 2.15
},
"search_only": {
"n": 1,
"min_ms": 2013.58,
"median_ms": 2013.58,
"p90_ms": 2013.58,
"p95_ms": 2013.58,
"max_ms": 2013.58,
"mean_ms": 2013.58
},
"recall_total": {
"n": 1,
"min_ms": 2371.32,
"median_ms": 2371.32,
"p90_ms": 2371.32,
"p95_ms": 2371.32,
"max_ms": 2371.32,
"mean_ms": 2371.32
}
}
]
},
"gates": []
},
"worker-sweep": {
"result": {
"note_count": 197,
"sweep": [
{
"workers": 1,
"median_ms": 11917.49,
"p95_ms": 11917.49
},
{
"workers": 2,
"median_ms": 5740.0,
"p95_ms": 5740.0
},
{
"workers": 4,
"median_ms": 3034.3,
"p95_ms": 3034.3
},
{
"workers": 8,
"median_ms": 1583.83,
"p95_ms": 1583.83
},
{
"workers": 16,
"median_ms": 1277.77,
"p95_ms": 1277.77
}
],
"knee_workers": 16,
"default_workers": 8
},
"gates": []
}
}
}