Skip to content

Commit 16223cc

Browse files
randrand
committed
chore: validate end-to-end flows and harden integration paths
1 parent 1a389a5 commit 16223cc

66 files changed

Lines changed: 4296 additions & 40 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎docs/execution-plan/evidence/2026-02-20/full-system-validation/M5-T01-VG-PERF-001.json‎

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
{
2+
"gate": "VG-PERF-001",
3+
"budget_pct": 10.0,
4+
"baseline_file": "/Users/rand/src/loop/docs/execution-plan/evidence/2026-02-20/full-system-validation/M5-T01-baseline.json",
5+
"candidate_file": "/Users/rand/src/loop/docs/execution-plan/evidence/2026-02-20/full-system-validation/M5-T01-candidate.json",
6+
"checks": {
7+
"startup_p50": 0.024291161099003106,
8+
"startup_p95": -40.1941595198149,
9+
"execute_no_submit_p50": -3.2084446475184407,
10+
"execute_no_submit_p95": -22.18892315721237,
11+
"execute_with_submit_p50": 6.619527388434903,
12+
"execute_with_submit_p95": 2.003107516689084
13+
},
14+
"pass": true
15+
}

‎docs/execution-plan/evidence/2026-02-20/full-system-validation/M5-T01-VG-PERF-002.json‎

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
{
2+
"gate": "VG-PERF-002",
3+
"budget_pct": 10.0,
4+
"baseline_file": "/Users/rand/src/loop/docs/execution-plan/evidence/2026-02-20/full-system-validation/M5-T01-baseline.json",
5+
"candidate_file": "/Users/rand/src/loop/docs/execution-plan/evidence/2026-02-20/full-system-validation/M5-T01-candidate.json",
6+
"checks": {
7+
"throughput_regression_pct": -8.276423986926362,
8+
"error_rate_delta": 0.0
9+
},
10+
"baseline_throughput_ops_per_sec": 7169.123002679003,
11+
"candidate_throughput_ops_per_sec": 7762.470018524983,
12+
"baseline_error_rate": 0.0,
13+
"candidate_error_rate": 0.0,
14+
"pass": true
15+
}

‎docs/execution-plan/evidence/2026-02-20/full-system-validation/M5-T01-baseline.json‎

Lines changed: 60 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,60 @@
1+
{
2+
"label": "baseline",
3+
"timestamp_utc": "2026-02-20T02:21:25Z",
4+
"environment": {
5+
"platform": "macOS-26.3-arm64-arm-64bit",
6+
"python_version": "3.12.11",
7+
"processor": "arm",
8+
"loop_commit": "1a389a519516f55b96eaa436197f83f444517bd5",
9+
"cwd": "/Users/rand/src/loop/rlm-core/python"
10+
},
11+
"config": {
12+
"startup_iters": 15,
13+
"exec_iters": 80,
14+
"submit_iters": 80,
15+
"batch_iters": 80,
16+
"batch_size": 8
17+
},
18+
"metrics": {
19+
"startup_latency_ms": {
20+
"count": 15,
21+
"min_ms": 82.55199999985052,
22+
"max_ms": 318.49391700234264,
23+
"mean_ms": 100.08724166594523,
24+
"p50_ms": 84.04704200074775,
25+
"p95_ms": 157.4725662976559
26+
},
27+
"execute_latency_no_submit_ms": {
28+
"count": 80,
29+
"min_ms": 0.04745900514535606,
30+
"max_ms": 1.1973329965258017,
31+
"mean_ms": 0.07631517464687931,
32+
"p50_ms": 0.05324999801814556,
33+
"p95_ms": 0.12786039769707713
34+
},
35+
"execute_latency_with_submit_ms": {
36+
"count": 80,
37+
"min_ms": 0.04604199784807861,
38+
"max_ms": 0.1878340044640936,
39+
"mean_ms": 0.056001499706326285,
40+
"p50_ms": 0.0497090004500933,
41+
"p95_ms": 0.08786874532233921
42+
},
43+
"batch": {
44+
"cycle_latency_ms": {
45+
"count": 80,
46+
"min_ms": 0.11658299627015367,
47+
"max_ms": 0.3378750043339096,
48+
"mean_ms": 0.1394870752847055,
49+
"p50_ms": 0.12943749970872886,
50+
"p95_ms": 0.19403299629630055
51+
},
52+
"successful_cycles": 80,
53+
"total_cycles": 80,
54+
"error_count": 0,
55+
"error_rate": 0.0,
56+
"batch_size": 8,
57+
"throughput_ops_per_sec": 7169.123002679003
58+
}
59+
}
60+
}

‎docs/execution-plan/evidence/2026-02-20/full-system-validation/M5-T01-candidate.json‎

Lines changed: 60 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,60 @@
1+
{
2+
"label": "candidate",
3+
"timestamp_utc": "2026-02-20T02:21:27Z",
4+
"environment": {
5+
"platform": "macOS-26.3-arm64-arm-64bit",
6+
"python_version": "3.12.11",
7+
"processor": "arm",
8+
"loop_commit": "1a389a519516f55b96eaa436197f83f444517bd5",
9+
"cwd": "/Users/rand/src/loop/rlm-core/python"
10+
},
11+
"config": {
12+
"startup_iters": 15,
13+
"exec_iters": 80,
14+
"submit_iters": 80,
15+
"batch_iters": 80,
16+
"batch_size": 8
17+
},
18+
"metrics": {
19+
"startup_latency_ms": {
20+
"count": 15,
21+
"min_ms": 82.7191250064061,
22+
"max_ms": 95.8659579991945,
23+
"mean_ms": 85.94524153498544,
24+
"p50_ms": 84.0674580031191,
25+
"p95_ms": 94.17779180002981
26+
},
27+
"execute_latency_no_submit_ms": {
28+
"count": 80,
29+
"min_ms": 0.04779200389748439,
30+
"max_ms": 0.21025000023655593,
31+
"mean_ms": 0.05912753722441266,
32+
"p50_ms": 0.051541501306928694,
33+
"p95_ms": 0.09948955230356656
34+
},
35+
"execute_latency_with_submit_ms": {
36+
"count": 80,
37+
"min_ms": 0.04895800520898774,
38+
"max_ms": 0.14887499855831265,
39+
"mean_ms": 0.05847128741152119,
40+
"p50_ms": 0.052999501349404454,
41+
"p95_ms": 0.08962885076471137
42+
},
43+
"batch": {
44+
"cycle_latency_ms": {
45+
"count": 80,
46+
"min_ms": 0.10820900206454098,
47+
"max_ms": 0.3114589999313466,
48+
"mean_ms": 0.128824974217423,
49+
"p50_ms": 0.11820849977084436,
50+
"p95_ms": 0.18302705175301526
51+
},
52+
"successful_cycles": 80,
53+
"total_cycles": 80,
54+
"error_count": 0,
55+
"error_rate": 0.0,
56+
"batch_size": 8,
57+
"throughput_ops_per_sec": 7762.470018524983
58+
}
59+
}
60+
}

‎docs/execution-plan/evidence/2026-02-20/full-system-validation/M5-T01-harness-run.log‎

Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,13 @@
1+
M5 perf harness run starting
2+
date: UTC 2026-02-20 02:21:22
3+
evidence_dir: /Users/rand/src/loop/docs/execution-plan/evidence/2026-02-20/full-system-validation
4+
loop_min_available_mib: 4096
5+
budget_pct: 10
6+
7+
[harness:baseline] running...
8+
[harness:baseline] wrote /Users/rand/src/loop/docs/execution-plan/evidence/2026-02-20/full-system-validation/M5-T01-baseline.json
9+
[harness:candidate] running...
10+
[harness:candidate] wrote /Users/rand/src/loop/docs/execution-plan/evidence/2026-02-20/full-system-validation/M5-T01-candidate.json
11+
12+
M5 perf harness run completed
13+
summary: /Users/rand/src/loop/docs/execution-plan/evidence/2026-02-20/full-system-validation/M5-T01-perf-summary.md

‎docs/execution-plan/evidence/2026-02-20/full-system-validation/M5-T01-perf-summary.md‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,9 @@
1+
# M5-T01 Perf Comparison Summary
2+
Budget: 10.0%
3+
VG-PERF-001: pass
4+
VG-PERF-002: pass
5+
6+
- baseline: `/Users/rand/src/loop/docs/execution-plan/evidence/2026-02-20/full-system-validation/M5-T01-baseline.json`
7+
- candidate: `/Users/rand/src/loop/docs/execution-plan/evidence/2026-02-20/full-system-validation/M5-T01-candidate.json`
8+
- vg-perf-001: `/Users/rand/src/loop/docs/execution-plan/evidence/2026-02-20/full-system-validation/M5-T01-VG-PERF-001.json`
9+
- vg-perf-002: `/Users/rand/src/loop/docs/execution-plan/evidence/2026-02-20/full-system-validation/M5-T01-VG-PERF-002.json`

‎docs/execution-plan/evidence/2026-02-20/full-system-validation/VG-CONTRACT-001.md‎

Lines changed: 30 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,30 @@
1+
# VG-CONTRACT-001
2+
Date: 2026-02-20
3+
Scope: Consumer contract consistency check against active implementations and tuple evidence
4+
5+
## Contract Sources Reviewed
6+
- `docs/execution-plan/contracts/CONSUMER-INTEGRATION.md`
7+
- `docs/execution-plan/contracts/LOOP-AGENT-RUNTIME-SEAM.md`
8+
- `docs/execution-plan/contracts/IO-RFLX-INTEROP-CONTRACT.md`
9+
- `docs/execution-plan/COMPATIBILITY-MATRIX.md`
10+
11+
## Empirical Gate Results
12+
- `VG-RCC-001`: pass (`weekly-cadence-m4/M4-T04-VG-RCC-001.txt`)
13+
- `VG-LA-001`: pass (`weekly-cadence-m4/M4-T04-VG-LA-001.txt`)
14+
- `VG-LA-002` advisory: pass (`1052 passed in 21.31s`)
15+
- `VG-RFLX-001`: pass (`weekly-cadence-m4/M4-T04-VG-RFLX-001.txt`)
16+
- `VG-RFLX-002`: pass (`VG-RFLX-002.txt`)
17+
18+
## Tuple Snapshot
19+
- loop: `1a389a519516f55b96eaa436197f83f444517bd5`
20+
- rlm-claude-code: `528f90018e0d464aa7e7459998191d8cfde27787`
21+
- rlm-claude-code vendor/loop: `6779cdbc970c70f3ce82a998d6dcda59cd171560`
22+
- loop-agent canonical: `2f4e762fbdb6fe40a00fe40b5df67b00b85dbb29`
23+
- io-rflx: `abf11ca4069bac7a740508d02242114483a6cf51`
24+
- loop-agent tuple mode: `clean_clone_committed`
25+
26+
## Gaps
27+
- Claude Code adapter runtime and MCP handlers still include placeholder behavior in `rlm-core/src/adapters/claude_code/adapter.rs` and `rlm-core/src/adapters/claude_code/mcp.rs`; tracked as `loop-7fk` and `loop-3sj`.
28+
29+
## Verdict
30+
- `VG-CONTRACT-001`: PASS with tracked follow-up gaps

‎docs/execution-plan/evidence/2026-02-20/full-system-validation/VG-DOC-SPEC-002.md‎

Lines changed: 23 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,23 @@
1+
# VG-DOC-SPEC-002
2+
Date: 2026-02-20
3+
Scope: SPEC-20..27 completion/status reconciliation against fresh runtime evidence
4+
5+
## Reconciliation Summary
6+
7+
| Spec | Claimed Status | Empirical Check | Result |
8+
|---|---|---|---|
9+
| SPEC-20 Typed Signatures | Implemented | `VG-LOOP-SIG-001`, `VG-LOOP-SIG-002`, `VG-LOOP-REPL-001-rerun`, `VG-LOOP-REPL-002` | Pass |
10+
| SPEC-21 Dual-Model Optimization | Implemented | `VG-LOOP-DUAL-001`, `VG-LOOP-CORE-001-rerun` | Pass |
11+
| SPEC-22 Proof Protocol | Implemented | `VG-LOOP-PROOF-001`, `VG-LOOP-CORE-001-rerun` | Pass |
12+
| SPEC-23 Graph Visualization | Implemented | `VG-LOOP-VIZ-001`, `VG-LOOP-CORE-001-rerun` | Pass |
13+
| SPEC-24 Bootstrap Optimizer | Implemented | `VG-LOOP-OPT-001`, `VG-PERF-003` | Pass |
14+
| SPEC-25 Context Externalization | Implemented | `VG-LOOP-CONTEXT-001`, `VG-LOOP-REPL-001-rerun` | Pass |
15+
| SPEC-26 Batched Queries | Implemented | `VG-LOOP-BATCH-001`, `VG-PERF-002` | Pass |
16+
| SPEC-27 Fallback Extraction | Implemented (runtime primitives) | `VG-LOOP-FALLBACK-001`, `VG-LOOP-CORE-001-rerun` | Pass |
17+
18+
## Notes
19+
- Spec metadata in `docs/spec/SPEC-20-typed-signatures.md` through `docs/spec/SPEC-27-fallback-extraction.md` is consistent with current runtime behavior for tested paths.
20+
- Additional non-SPEC-20..27 gaps discovered in this run are tracked separately under `loop-8hi` children (`loop-7fk`, `loop-3sj`, `loop-xmy`, `loop-rv2`).
21+
22+
## Verdict
23+
- `VG-DOC-SPEC-002`: PASS

‎docs/execution-plan/evidence/2026-02-20/full-system-validation/VG-DP-ENFORCE-PRE-COMMIT.txt‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,4 @@
1+
[VG-DP-ENFORCE-PRE-COMMIT] running
2+
error: Failed to spawn: `dp`
3+
Caused by: No such file or directory (os error 2)
4+
exit_code=2

‎docs/execution-plan/evidence/2026-02-20/full-system-validation/VG-DP-ENFORCE-PRE-PUSH.txt‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,4 @@
1+
[VG-DP-ENFORCE-PRE-PUSH] running
2+
error: Failed to spawn: `dp`
3+
Caused by: No such file or directory (os error 2)
4+
exit_code=2

0 commit comments

Comments
 (0)