21c22b2201
Resolves all 5 TBDs and closes all 8 acceptance gates for ADR-0022. TBD-1 (intent oracle): regex seed + field ratification — generate/intent_ratifier.py. RATIFIED / DEMOTED / PASSTHROUGH outcomes; DEMOTED routes through honest refusal. TBD-2 (region intersection algebra): generate/admissibility.py. Token-set composition via sorted set intersection; blade composition via outer product with zero-blade as neutral element; rotor composition via sandwich conjugation routed through algebra.backend.versor_apply (Rust parity preserved by construction). Empty intersections preserved — no silent relaxation. Wiring: propose() and generate() accept an AdmissibilityRegion (default None preserves legacy behavior); pipeline ratifies intent at step 1b.i before graph construction. Eval lane: evals/forward_semantic_control/ — both legs run against CognitiveTurnPipeline (constrained) vs bare ChatRuntime.chat() (unconstrained baseline). Dev (3 cases) and public/v1 (1 case) both report overall_pass=true, causality_gap=1.0, coincidence_rate=0.0. Chain-endpoint probe surfaces 'delta' only under forward semantic control. Bench cost (30 turns): -2.8% wall-clock (within +5% budget the ADR set for the ratification gate on every turn). 138x cheaper than Sonnet 4.5; main was 142x. Tests: 33 new (25 admissibility + 8 ratifier). Full suite 912/913 pass — the single failure is pre-existing pack-size drift on main, unrelated.
53 lines
2 KiB
JSON
53 lines
2 KiB
JSON
{
|
|
"cloud_reference": {
|
|
"hourly_usd": 0.0416,
|
|
"name": "AWS t3.medium (2 vCPU, 4 GiB)",
|
|
"region": "us-east-1, on-demand, Linux",
|
|
"source_note": "aws.amazon.com/ec2/instance-types/t3 — public on-demand rate, captured 2026-05-17. Update source_note + hourly_usd if the price page changes."
|
|
},
|
|
"cpu_seconds_total": 12.377237,
|
|
"cpu_utilization": 0.9973,
|
|
"energy_disclosure": "Joules per turn is not reported. Honest energy measurement requires RAPL (Linux) or IOKit/powermetrics (macOS) with privileged access. cpu_seconds_total is the available CPU-time proxy.",
|
|
"frontier_pricing_comparison": [
|
|
{
|
|
"core_cheaper_by_x": 138.1,
|
|
"frontier_usd_per_1000_turns": 0.66,
|
|
"input_usd_per_million_tokens": 3.0,
|
|
"name": "Anthropic Claude Sonnet 4.5 (API)",
|
|
"output_usd_per_million_tokens": 15.0,
|
|
"source_note": "anthropic.com/pricing — public API rate, captured 2026-05-17."
|
|
},
|
|
{
|
|
"core_cheaper_by_x": 94.1,
|
|
"frontier_usd_per_1000_turns": 0.45,
|
|
"input_usd_per_million_tokens": 2.5,
|
|
"name": "OpenAI GPT-4o (API)",
|
|
"output_usd_per_million_tokens": 10.0,
|
|
"source_note": "openai.com/api/pricing — public API rate, captured 2026-05-17."
|
|
},
|
|
{
|
|
"core_cheaper_by_x": 46.0,
|
|
"frontier_usd_per_1000_turns": 0.22,
|
|
"input_usd_per_million_tokens": 1.0,
|
|
"name": "Anthropic Claude Haiku 4.5 (API)",
|
|
"output_usd_per_million_tokens": 5.0,
|
|
"source_note": "anthropic.com/pricing — public API rate, captured 2026-05-17."
|
|
}
|
|
],
|
|
"frontier_token_assumption": {
|
|
"input_tokens_per_turn": 20,
|
|
"note": "Conservative short-prompt / short-answer turn. Frontier $/1000-turns scales linearly with these counts.",
|
|
"output_tokens_per_turn": 40
|
|
},
|
|
"latency": {
|
|
"max_ms": 512.027,
|
|
"median_ms": 472.218,
|
|
"min_ms": 3.384,
|
|
"p95_ms": 490.456
|
|
},
|
|
"throughput_turns_per_second": 2.4172,
|
|
"turns": 30,
|
|
"usd_per_1000_turns": 0.004781,
|
|
"wall_seconds_total": 12.411292,
|
|
"warmup_turns": 5
|
|
}
|