Files
echo/echo-memory.plugin.src/skills/echo-memory/eval/perf/results/m-resolve.json
T
Jason Stedwell b4605a52f2 ver 1.3 and 1.3.1
2026-06-23 22:17:39 -05:00

360 lines
10 KiB
JSON

{
"env": {
"date": "2026-06-23T20:12:19",
"endpoint": "https://obsidian.example.com",
"commit": "af16598",
"echo_workers": 8,
"echo_timeout": 30,
"python": "3.10.12",
"iterations": 6,
"count_k": 50
},
"run_id": "20260623-201219-819b5e",
"metrics": {
"resolve": {
"result": {
"cases": [
{
"mention": "echo",
"expect": "exact",
"expect_slug": "echo",
"resolved_slug": "echo",
"candidate_slugs": [
"2026-06-19-other-vault-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-other-vault-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-other-vault-full-echo-architect",
"example-isp-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": "other-vault",
"expect": "exact",
"expect_slug": "other-vault",
"resolved_slug": "other-vault",
"candidate_slugs": [
"2026-06-19-other-vault-full-echo-architect",
"other-vault"
],
"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": "example subject",
"expect": "exact",
"expect_slug": "example-subject",
"resolved_slug": "example-subject",
"candidate_slugs": [
"example-subject",
"operator-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": "operator",
"expect": "candidates",
"expect_slug": "example-subject",
"resolved_slug": "example-subject",
"candidate_slugs": [
"operator-mcp-gateway",
"example-subject"
],
"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": []
}
}
}