docs(RP13): throughput/quality metrics for real runs #161 + #163 #283

Merged
conductor merged 3 commits from rp13-metrics into master 2026-09-09 14:01:58 +01:00
+188
View File
@@ -0,0 +1,188 @@
{
"runs": {
"161": {
"issue": 161,
"stages": {
"ISSUE": {
"elapsed_s": 0.0,
"tool_calls": 0,
"queries": 0,
"sources_read": 0,
"tool_failures": 0
},
"INWARD": {
"elapsed_s": 0.0,
"tool_calls": 0,
"queries": 0,
"sources_read": 0,
"tool_failures": 0
},
"OUTWARD": {
"elapsed_s": 0.0,
"tool_calls": 22,
"queries": 4,
"sources_read": 4,
"tool_failures": 0
},
"APPLICABILITY": {
"elapsed_s": 0.0,
"tool_calls": 20,
"queries": 0,
"sources_read": 0,
"tool_failures": 0
},
"ADVERSARIAL": {
"elapsed_s": 0.0,
"tool_calls": 25,
"queries": 0,
"sources_read": 2,
"tool_failures": 0
},
"SYNTHESIS": {
"elapsed_s": 0.0,
"tool_calls": 14,
"queries": 0,
"sources_read": 0,
"tool_failures": 1
},
"QUALIFY": {
"elapsed_s": 310.1,
"tool_calls": 20,
"queries": 0,
"sources_read": 0,
"tool_failures": 0
}
},
"totals": {
"cognition_elapsed_s": 310.1,
"tool_calls": 101
},
"research": {
"queries": 4,
"sources_discovered": 16,
"sources_read": 4,
"contradictions": 4,
"limitations": 8
},
"adversarial": {
"attacks": 16,
"survivors": 6,
"rejected": 1,
"mitigations": 10,
"kill_tests": 7,
"disposition": "SURVIVES_WITH_MITIGATIONS"
}
},
"163": {
"issue": 163,
"stages": {
"ISSUE": {
"elapsed_s": 0.0,
"tool_calls": 0,
"queries": 0,
"sources_read": 0,
"tool_failures": 0
},
"INWARD": {
"elapsed_s": 0.0,
"tool_calls": 0,
"queries": 0,
"sources_read": 0,
"tool_failures": 0
},
"OUTWARD": {
"elapsed_s": 0.0,
"tool_calls": 34,
"queries": 5,
"sources_read": 10,
"tool_failures": 2
},
"APPLICABILITY": {
"elapsed_s": 300.1,
"tool_calls": 8,
"queries": 0,
"sources_read": 0,
"tool_failures": 0
},
"INNOVATION": {
"elapsed_s": 422.1,
"tool_calls": 9,
"queries": 0,
"sources_read": 0,
"tool_failures": 1
},
"ADVERSARIAL": {
"elapsed_s": 0.0,
"tool_calls": 25,
"queries": 0,
"sources_read": 0,
"tool_failures": 0
},
"SYNTHESIS": {
"elapsed_s": 677.1,
"tool_calls": 15,
"queries": 0,
"sources_read": 0,
"tool_failures": 0
},
"QUALIFY": {
"elapsed_s": 305.1,
"tool_calls": 12,
"queries": 0,
"sources_read": 0,
"tool_failures": 0
}
},
"totals": {
"cognition_elapsed_s": 1704.3,
"tool_calls": 103
},
"research": {
"queries": 5,
"sources_discovered": 45,
"sources_read": 10,
"contradictions": 4,
"limitations": 8
},
"adversarial": {
"attacks": 13,
"survivors": 4,
"rejected": 1,
"mitigations": 7,
"kill_tests": 6,
"disposition": "SURVIVES_WITH_MITIGATIONS"
}
}
},
"old_process_baseline": {
"foreground_sleep_per_batch_s": 300,
"batches_observed_in_rsc0_red": "N (300s x N while child productive)",
"wall_clock_issue_245_era": "hours (multiple restarts, no durable state)",
"source_receipts": "model-claimed only (no relay receipts)",
"read_provenance": "none \u2014 snippets counted as evidence"
},
"quality_outcomes": {
"161": {
"architectural_mistakes_prevented": [
"MemoryAdapter second protocol rejected (duplicate authority vs memory_selector registry)",
"Harness would have silently validated non-hybrid mode (A1: _embed degradation) \u2014 kill-test FT1 forced mode observability",
"Cache-pollution benchmark hazard (A4) \u2014 forced cache bypass invariants"
],
"implementation_ambiguity_reduction": "QUALIFY 13/13 checks + source-verified interface review; implementation merged first try, 0 CI code failures (2 CI-contract failures were master debt)",
"rework": "1 REFINE loop none; implementation PR #279 merged without implementation rework"
},
"163": {
"architectural_mistakes_prevented": [
"External graph DB adoption blocked (3 candidates CONFLICTS_WITH_RUNE \u2014 would replace SQLite tier)",
"False bi-temporal claim corrected from code (graph_memory is transaction-time append) before synthesis",
"INN-1 filter formulation falsified (A2) \u2014 synthesis v2 corrected"
],
"implementation_ambiguity_reduction": "QUALIFY round 1 caught 3 concrete interface gaps (DDL, parameter, alias ordering) \u2014 REFINE_SYNTHESIS fixed all in one loop",
"rework": "1 REFINE_SYNTHESIS loop (targeted, synthesis-only \u2014 no research restart)"
}
},
"comparison_principles": {
"cognition_vs_orchestration": "cognition = MiMo stage elapsed (measured where recorded); orchestration/wait = runner queue + CI latency \u2014 NOT attributed to the pipeline",
"wall_clock": "#161 research chain \u2248 75 min git-window (00:16\u219201:31) incl. live CI defect discovery/fixes; #163 persisted in one batch (stage elapsed recorded per-stage)"
}
}