hd-lang

Daily goal metrics

hd is built for programs written by coding agents, so we judge it with the Agentic Programming Language Arena: three pillars that ask what agent-driven development actually costs and produces. Each pillar is kept on its own and compared on a Pareto frontier rather than folded into one score, because a faster compiler that makes agents retry more is not a win. Compiler correctness is a gate in front of all three. Every metric is a script with a fixed target; no AI or agent run is involved, and the same scripts run against any hd binary. They run twice a day, at 00:00 and 12:00 UTC.

First: correctness

Correctness gate2 of 3 met
Is the compiler right? Conformance and incremental soundness. A faster wrong result is not better, so this is a prerequisite rather than a pillar.

The three pillars

Single-agent development cost226 of 230 met
How cheaply does one agent get a correct program? Compile and test latency is agent wait time; clear, short, well-placed diagnostics and fix-its that resolve mistakes are fewer retries and fewer tokens.
Agent scalability38 of 47 met
How much useful work do N agents do on one machine? CPU, memory and disk per check, startup, behaviour under concurrency, and caches that are shared, bounded and safe to write at once.
Artifact quality20 of 35 met
How good is the program the agents produced? The user's program, not the compiler: test speed, runtime against Node, allocations, binary size, host-call and serde cost, memory over time.

Trend

The share of each pillar's targets that the run met. A line going up is progress; a drop after a commit is a regression worth reading. Hover a point for its run.

0%50%100%10-25 12:0511-19 05:24Single-agent development cost, 10-25 12:05: 33% of targets metSingle-agent development cost, 10-26 03:35: 76% of targets metSingle-agent development cost, 10-26 18:48: 80% of targets metSingle-agent development cost, 10-27 02:55: 80% of targets metSingle-agent development cost, 10-27 18:05: 80% of targets metSingle-agent development cost, 10-28 03:03: 80% of targets metSingle-agent development cost, 10-28 18:30: 78% of targets metSingle-agent development cost, 10-29 03:26: 76% of targets metSingle-agent development cost, 10-29 18:34: 76% of targets metSingle-agent development cost, 10-30 03:28: 78% of targets metSingle-agent development cost, 10-30 18:06: 78% of targets metSingle-agent development cost, 10-31 03:23: 76% of targets metSingle-agent development cost, 10-31 17:18: 76% of targets metSingle-agent development cost, 11-01 03:06: 80% of targets metSingle-agent development cost, 11-01 18:05: 80% of targets metSingle-agent development cost, 11-02 03:22: 81% of targets metSingle-agent development cost, 11-02 21:57: 81% of targets metSingle-agent development cost, 11-03 04:36: 80% of targets metSingle-agent development cost, 11-03 19:43: 81% of targets metSingle-agent development cost, 11-04 04:04: 81% of targets metSingle-agent development cost, 11-04 19:54: 81% of targets metSingle-agent development cost, 11-05 04:23: 81% of targets metSingle-agent development cost, 11-05 20:14: 81% of targets metSingle-agent development cost, 11-06 04:15: 78% of targets metSingle-agent development cost, 11-06 19:28: 78% of targets metSingle-agent development cost, 11-07 03:47: 78% of targets metSingle-agent development cost, 11-07 17:57: 81% of targets metSingle-agent development cost, 11-08 03:13: 81% of targets metSingle-agent development cost, 11-08 18:10: 78% of targets metSingle-agent development cost, 11-09 03:36: 81% of targets metSingle-agent development cost, 11-09 22:26: 80% of targets metSingle-agent development cost, 11-10 05:15: 81% of targets metSingle-agent development cost, 11-10 19:44: 85% of targets metSingle-agent development cost, 11-11 03:47: 80% of targets metSingle-agent development cost, 11-11 19:45: 85% of targets metSingle-agent development cost, 11-12 04:58: 85% of targets metSingle-agent development cost, 11-12 19:59: 85% of targets metSingle-agent development cost, 11-13 04:12: 83% of targets metSingle-agent development cost, 11-13 19:45: 80% of targets metSingle-agent development cost, 11-14 04:12: 87% of targets metSingle-agent development cost, 11-14 18:04: 89% of targets metSingle-agent development cost, 11-15 03:45: 97% of targets metSingle-agent development cost, 11-15 19:02: 97% of targets metSingle-agent development cost, 11-16 03:47: 98% of targets metSingle-agent development cost, 11-16 22:10: 98% of targets metSingle-agent development cost, 11-17 05:50: 98% of targets metSingle-agent development cost, 11-17 21:02: 96% of targets metSingle-agent development cost, 11-18 05:29: 98% of targets metSingle-agent development cost, 11-18 20:39: 98% of targets metSingle-agent development cost, 11-19 05:24: 98% of targets metAgent scalability, 10-25 12:05: 18% of targets metAgent scalability, 10-26 03:35: 77% of targets metAgent scalability, 10-26 18:48: 77% of targets metAgent scalability, 10-27 02:55: 77% of targets metAgent scalability, 10-27 18:05: 77% of targets metAgent scalability, 10-28 03:03: 77% of targets metAgent scalability, 10-28 18:30: 77% of targets metAgent scalability, 10-29 03:26: 77% of targets metAgent scalability, 10-29 18:34: 79% of targets metAgent scalability, 10-30 03:28: 77% of targets metAgent scalability, 10-30 18:06: 77% of targets metAgent scalability, 10-31 03:23: 77% of targets metAgent scalability, 10-31 17:18: 77% of targets metAgent scalability, 11-01 03:06: 77% of targets metAgent scalability, 11-01 18:05: 77% of targets metAgent scalability, 11-02 03:22: 77% of targets metAgent scalability, 11-02 21:57: 77% of targets metAgent scalability, 11-03 04:36: 77% of targets metAgent scalability, 11-03 19:43: 77% of targets metAgent scalability, 11-04 04:04: 77% of targets metAgent scalability, 11-04 19:54: 77% of targets metAgent scalability, 11-05 04:23: 77% of targets metAgent scalability, 11-05 20:14: 77% of targets metAgent scalability, 11-06 04:15: 77% of targets metAgent scalability, 11-06 19:28: 77% of targets metAgent scalability, 11-07 03:47: 77% of targets metAgent scalability, 11-07 17:57: 77% of targets metAgent scalability, 11-08 03:13: 77% of targets metAgent scalability, 11-08 18:10: 74% of targets metAgent scalability, 11-09 03:36: 74% of targets metAgent scalability, 11-09 22:26: 72% of targets metAgent scalability, 11-10 05:15: 74% of targets metAgent scalability, 11-10 19:44: 74% of targets metAgent scalability, 11-11 03:47: 74% of targets metAgent scalability, 11-11 19:45: 74% of targets metAgent scalability, 11-12 04:58: 74% of targets metAgent scalability, 11-12 19:59: 74% of targets metAgent scalability, 11-13 04:12: 74% of targets metAgent scalability, 11-13 19:45: 74% of targets metAgent scalability, 11-14 04:12: 74% of targets metAgent scalability, 11-14 18:04: 74% of targets metAgent scalability, 11-15 03:45: 79% of targets metAgent scalability, 11-15 19:02: 79% of targets metAgent scalability, 11-16 03:47: 79% of targets metAgent scalability, 11-16 22:10: 77% of targets metAgent scalability, 11-17 05:50: 86% of targets metAgent scalability, 11-17 21:02: 86% of targets metAgent scalability, 11-18 05:29: 84% of targets metAgent scalability, 11-18 20:39: 86% of targets metAgent scalability, 11-19 05:24: 86% of targets metArtifact quality, 10-25 12:05: 22% of targets metArtifact quality, 10-26 03:35: 63% of targets metArtifact quality, 10-26 18:48: 66% of targets metArtifact quality, 10-27 02:55: 69% of targets metArtifact quality, 10-27 18:05: 63% of targets metArtifact quality, 10-28 03:03: 69% of targets metArtifact quality, 10-28 18:30: 63% of targets metArtifact quality, 10-29 03:26: 69% of targets metArtifact quality, 10-29 18:34: 66% of targets metArtifact quality, 10-30 03:28: 69% of targets metArtifact quality, 10-30 18:06: 69% of targets metArtifact quality, 10-31 03:23: 63% of targets metArtifact quality, 10-31 17:18: 63% of targets metArtifact quality, 11-01 03:06: 60% of targets metArtifact quality, 11-01 18:05: 60% of targets metArtifact quality, 11-02 03:22: 60% of targets metArtifact quality, 11-02 21:57: 54% of targets metArtifact quality, 11-03 04:36: 54% of targets metArtifact quality, 11-03 19:43: 57% of targets metArtifact quality, 11-04 04:04: 51% of targets metArtifact quality, 11-04 19:54: 54% of targets metArtifact quality, 11-05 04:23: 60% of targets metArtifact quality, 11-05 20:14: 63% of targets metArtifact quality, 11-06 04:15: 63% of targets metArtifact quality, 11-06 19:28: 57% of targets metArtifact quality, 11-07 03:47: 60% of targets metArtifact quality, 11-07 17:57: 63% of targets metArtifact quality, 11-08 03:13: 57% of targets metArtifact quality, 11-08 18:10: 63% of targets metArtifact quality, 11-09 03:36: 54% of targets metArtifact quality, 11-09 22:26: 60% of targets metArtifact quality, 11-10 05:15: 54% of targets metArtifact quality, 11-10 19:44: 54% of targets metArtifact quality, 11-11 03:47: 63% of targets metArtifact quality, 11-11 19:45: 66% of targets metArtifact quality, 11-12 04:58: 69% of targets metArtifact quality, 11-12 19:59: 71% of targets metArtifact quality, 11-13 04:12: 69% of targets metArtifact quality, 11-13 19:45: 69% of targets metArtifact quality, 11-14 04:12: 69% of targets metArtifact quality, 11-14 18:04: 69% of targets metArtifact quality, 11-15 03:45: 66% of targets metArtifact quality, 11-15 19:02: 63% of targets metArtifact quality, 11-16 03:47: 69% of targets metArtifact quality, 11-16 22:10: 66% of targets metArtifact quality, 11-17 05:50: 71% of targets metArtifact quality, 11-17 21:02: 69% of targets metArtifact quality, 11-18 05:29: 68% of targets metArtifact quality, 11-18 20:39: 71% of targets metArtifact quality, 11-19 05:24: 65% of targets metCorrectness gate, 10-25 12:05: 67% of targets metCorrectness gate, 10-26 03:35: 100% of targets metCorrectness gate, 10-26 18:48: 67% of targets metCorrectness gate, 10-27 02:55: 67% of targets metCorrectness gate, 10-27 18:05: 67% of targets metCorrectness gate, 10-28 03:03: 67% of targets metCorrectness gate, 10-28 18:30: 100% of targets metCorrectness gate, 10-29 03:26: 67% of targets metCorrectness gate, 10-29 18:34: 100% of targets metCorrectness gate, 10-30 03:28: 67% of targets metCorrectness gate, 10-30 18:06: 100% of targets metCorrectness gate, 10-31 03:23: 100% of targets metCorrectness gate, 10-31 17:18: 100% of targets metCorrectness gate, 11-01 03:06: 100% of targets metCorrectness gate, 11-01 18:05: 100% of targets metCorrectness gate, 11-02 03:22: 100% of targets metCorrectness gate, 11-02 21:57: 100% of targets metCorrectness gate, 11-03 04:36: 100% of targets metCorrectness gate, 11-03 19:43: 67% of targets metCorrectness gate, 11-04 04:04: 67% of targets metCorrectness gate, 11-04 19:54: 100% of targets metCorrectness gate, 11-05 04:23: 100% of targets metCorrectness gate, 11-05 20:14: 100% of targets metCorrectness gate, 11-06 04:15: 100% of targets metCorrectness gate, 11-06 19:28: 100% of targets metCorrectness gate, 11-07 03:47: 100% of targets metCorrectness gate, 11-07 17:57: 100% of targets metCorrectness gate, 11-08 03:13: 100% of targets metCorrectness gate, 11-08 18:10: 100% of targets metCorrectness gate, 11-09 03:36: 100% of targets metCorrectness gate, 11-09 22:26: 100% of targets metCorrectness gate, 11-10 05:15: 100% of targets metCorrectness gate, 11-10 19:44: 100% of targets metCorrectness gate, 11-11 03:47: 67% of targets metCorrectness gate, 11-11 19:45: 100% of targets metCorrectness gate, 11-12 04:58: 100% of targets metCorrectness gate, 11-12 19:59: 100% of targets metCorrectness gate, 11-13 04:12: 100% of targets metCorrectness gate, 11-13 19:45: 100% of targets metCorrectness gate, 11-14 04:12: 100% of targets metCorrectness gate, 11-14 18:04: 100% of targets metCorrectness gate, 11-15 03:45: 100% of targets metCorrectness gate, 11-15 19:02: 100% of targets metCorrectness gate, 11-16 03:47: 100% of targets metCorrectness gate, 11-16 22:10: 100% of targets metCorrectness gate, 11-17 05:50: 100% of targets metCorrectness gate, 11-17 21:02: 67% of targets metCorrectness gate, 11-18 05:29: 67% of targets metCorrectness gate, 11-18 20:39: 67% of targets metCorrectness gate, 11-19 05:24: 67% of targets metSingle-agent development cost 98%Agent scalability 86%Correctness gate 67%Artifact quality 65%

Single-agent development cost

How cheaply does one agent get a correct program? Each bar is one metric, drawn at its worst target's distance from the goal: left of the dashed line meets it, right of it misses by that multiple. Metrics without a numeric goal show only met or missed. The full list of targets is in the table below.

goal3× or worserecheck-precision: 2 target(s); worst modules rechecked, public signature edit: 9 vs ≤ 3recheck-precision✗ 9 vs ≤ 3mistakes: 4 target(s); worst fix-it makes hd check pass: 52.9% vs ≥ 80.0%mistakes✗ 52.9% vs ≥ 80.0%check-cost: 1 target(s); worst checked run time / unchecked run time: 1.83x vs ≤ 1.30xcheck-cost✗ 1.83x vs ≤ 1.30xfixit-safety: 1 target(s); worst fix-its that add no error: 100.0% vs ≥ 100.0%fixit-safety✓ 100.0% vs ≥ 100.0%scale: 176 target(s); worst coverage: node kinds: 119/119 vs 119/119scale✓ 119/119 vs 119/119diag-location: 1 target(s); worst diagnostics on the mistake's line: 98.6% vs ≥ 95.0%diag-location✓ 98.6% vs ≥ 95.0%edit-latency: 2 target(s); worst p50 check after an edit: 43 ms vs ≤ 50 msedit-latency✓ 43 ms vs ≤ 50 mspathological: 30 target(s); worst big-file: growth exponent: 1.11 vs ≤ 1.30pathological✓ 1.11 vs ≤ 1.30test-latency: 1 target(s); worst median edit-then-test: 153 ms vs ≤ 300 mstest-latency✓ 153 ms vs ≤ 300 msdev-speed: 2 target(s); worst geomean dev / optimized: 1.81x vs ≤ 4.00xdev-speed✓ 1.81x vs ≤ 4.00xanswer-size: 4 target(s); worst one failing hd test, text: 318 B vs ≤ 800 Banswer-size✓ 318 B vs ≤ 800 Bcold-check: 1 target(s); worst median cold check, 10k lines: 234 ms vs ≤ 1000 mscold-check✓ 234 ms vs ≤ 1000 msfmt: 2 target(s); worst hd fmt, 10k lines: 37 ms vs ≤ 200 msfmt✓ 37 ms vs ≤ 200 msdeterminism: 1 target(s); worst inputs with byte-identical output: metdeterminism✓ meterrors-per-run: 2 target(s); worst semantic: 10 mistakes reported once: meterrors-per-run✓ met

Agent scalability

How much useful work do N agents do on one machine? Each bar is one metric, drawn at its worst target's distance from the goal: left of the dashed line meets it, right of it misses by that multiple. Metrics without a numeric goal show only met or missed. The full list of targets is in the table below.

goal3× or worsecache-contention: 4 target(s); worst dependency cache, 8 concurrent fetches: fetched once: 16 vs ≤ 2, one check's connections (8.0× goal)cache-contention✗ 16 vs ≤ 2, one check's connections (8.0× goal)long-session: 1 target(s); worst RSS growth, REPL inputs 100 to 1000: 70.7 MB vs ≤ 22.0 MB (3.2× goal)long-session✗ 70.7 MB vs ≤ 22.0 MB (3.2× goal)cache-growth: 1 target(s); worst cache size after 100 edits, cap 5 MB: 14.2 MB vs ≤ 5.0 MBcache-growth✗ 14.2 MB vs ≤ 5.0 MBstartup: 12 target(s); worst hd check empty.hd, just written: peak RSS: 19.0 MB vs ≤ 10.0 MBstartup✗ 19.0 MB vs ≤ 10.0 MBparallel-speedup: 1 target(s); worst speedup, 50k lines, 4 threads vs 1: 1.87x vs ≥ 2.40xparallel-speedup✗ 1.87x vs ≥ 2.40xio-per-check: 1 target(s); worst source files read, warm check after one edit: 1 vs ≤ 1io-per-check✓ 1 vs ≤ 1concurrency: 3 target(s); worst p95 latency at N = 4 vs N = 1: 1.39x vs ≤ 1.50xconcurrency✓ 1.39x vs ≤ 1.50xresources: 20 target(s); worst warm check, 10k lines: peak RSS: 28.1 MB vs ≤ 50.0 MBresources✓ 28.1 MB vs ≤ 50.0 MBdisk: 3 target(s); worst artifacts per worktree: 0.0 MB vs ≤ 10.0 MBdisk✗ 0.0 MB vs ≤ 10.0 MBfetch-dedup: 1 target(s); worst connections to the remote, 4 worktrees: metfetch-dedup✓ met

Artifact quality

How good is the program the agents produced? Each bar is one metric, drawn at its worst target's distance from the goal: left of the dashed line meets it, right of it misses by that multiple. Metrics without a numeric goal show only met or missed. The full list of targets is in the table below.

goal3× or worsetext-throughput: 3 target(s); worst regex find_all, hd / Node MB/s: 0.05x vs ≥ 0.50x (10.0× goal)text-throughput✗ 0.05x vs ≥ 0.50x (10.0× goal)serde-throughput: 2 target(s); worst JSON encode, hd / Node MB/s: 0.13x vs ≥ 0.50x (3.8× goal)serde-throughput✗ 0.13x vs ≥ 0.50x (3.8× goal)host-call-overhead: 3 target(s); worst serde boundary (list_dir!), per call: 19 µs vs ≤ 5.0 µs (3.8× goal)host-call-overhead✗ 19 µs vs ≤ 5.0 µs (3.8× goal)size-startup-heap: 4 target(s); worst tiny program, release Wasm size: 5014 B vs ≤ 2048 Bsize-startup-heap✗ 5014 B vs ≤ 2048 Bintegration-test-perf: 3 target(s); worst setup per integration test program: 25 ms vs ≤ 20 msintegration-test-perf✗ 25 ms vs ≤ 20 msproptest-perf: 2 target(s); worst property cases per second: 88k/s vs ≥ 100k/sproptest-perf✗ 88k/s vs ≥ 100k/sdead-code: 2 target(s); worst Wasm bytes per 1,000 lines: 6516 B vs ≤ 10240 Bdead-code✓ 6516 B vs ≤ 10240 Bruntime: 6 target(s); worst map: hd / Node: 1.17x vs ≤ 3.00xruntime✓ 1.17x vs ≤ 3.00xsuspension-overhead: 3 target(s); worst race! of two ready tasks, throughput: 4.8M/s vs ≥ 1.0M/ssuspension-overhead✓ 4.8M/s vs ≥ 1.0M/sunit-test-perf: 2 target(s); worst 1,000 unit tests, warm: 151 ms vs ≤ 1000 msunit-test-perf✓ 151 ms vs ≤ 1000 mslong-run-memory: 1 target(s); worst RSS growth after warm-up, 1 min: 0.0 MB vs ≤ 10.0 MBlong-run-memory✓ 0.0 MB vs ≤ 10.0 MBallocations: 4 target(s); worst counted loop, bytes per iteration: n/aallocations– n/a

Correctness gate

Is the compiler right? Each bar is one metric, drawn at its worst target's distance from the goal: left of the dashed line meets it, right of it misses by that multiple. Metrics without a numeric goal show only met or missed. The full list of targets is in the table below.

goal3× or worseconformance: 2 target(s); worst pass rate, known failures excluded: 100.0% vs ≥ 100.0%conformance✗ 100.0% vs ≥ 100.0%incremental-soundness: 1 target(s); worst incremental equals clean, after each edit: 100.0% vs ≥ 100.0%incremental-soundness✓ 100.0% vs ≥ 100.0%

All targets

Latest run: 2026-11-19 05:24 UTC. History and raw data: the metrics-data branch.

Every target, latest run
PillarMetricTargetValueGoalStatus
Single-agent development costedit-latencyp50 check after an edit43 ms≤ 50 ms✓ met
Single-agent development costedit-latencyp95 check after an edit44 ms≤ 200 ms✓ met
Single-agent development costcold-checkmedian cold check, 10k lines234 ms≤ 1000 ms✓ met
Single-agent development costtest-latencymedian edit-then-test153 ms≤ 300 ms✓ met
Single-agent development costmistakesprograms with exactly one diagnostic100.0%≥ 95.0%✓ met
Single-agent development costmistakesone diagnostic with the expected code100.0%≥ 95.0%✓ met
Single-agent development costmistakesfix-it makes hd check pass52.9%≥ 80.0%✗ missed
Single-agent development costmistakeslargest diagnostic text (bytes / 4)85 tokens≤ 60 tokens✗ missed
Single-agent development costanswer-sizehd doc of a data type153 B≤ 1000 B✓ met
Single-agent development costanswer-sizeone failing hd test, text318 B≤ 800 B✓ met
Single-agent development costanswer-sizeone failing test, JSON object139 B≤ 400 B✓ met
Single-agent development costanswer-sizeone diagnostic, JSON object170 B≤ 600 B✓ met
Single-agent development costdeterminisminputs with byte-identical output8 of 8all identical✓ met
Single-agent development costpathologicaloverlapping-from: time at 4x54 ms≤ 2000 ms✓ met
Single-agent development costpathologicaloverlapping-from: peak RSS at 4x28.5 MB≤ 200.0 MB✓ met
Single-agent development costpathologicaloverlapping-from: growth exponentnoise≤ 1.3✓ met
Single-agent development costpathologicaldeep-blocks: time at 4x25 ms≤ 2000 ms✓ met
Single-agent development costpathologicaldeep-blocks: peak RSS at 4x23.0 MB≤ 200.0 MB✓ met
Single-agent development costpathologicaldeep-blocks: growth exponentnoise≤ 1.3✓ met
Single-agent development costpathologicaldeep-parens: time at 4x25 ms≤ 2000 ms✓ met
Single-agent development costpathologicaldeep-parens: peak RSS at 4x23.2 MB≤ 200.0 MB✓ met
Single-agent development costpathologicaldeep-parens: growth exponentnoise≤ 1.3✓ met
Single-agent development costpathologicalmethod-chain: time at 4x31 ms≤ 2000 ms✓ met
Single-agent development costpathologicalmethod-chain: peak RSS at 4x24.8 MB≤ 200.0 MB✓ met
Single-agent development costpathologicalmethod-chain: growth exponentnoise≤ 1.3✓ met
Single-agent development costpathologicaliterator-chain: time at 4x35 ms≤ 2000 ms✓ met
Single-agent development costpathologicaliterator-chain: peak RSS at 4x24.7 MB≤ 200.0 MB✓ met
Single-agent development costpathologicaliterator-chain: growth exponentnoise≤ 1.3✓ met
Single-agent development costpathologicalwide-list-literal: time at 4x58 ms≤ 2000 ms✓ met
Single-agent development costpathologicalwide-list-literal: peak RSS at 4x28.4 MB≤ 200.0 MB✓ met
Single-agent development costpathologicalwide-list-literal: growth exponentnoise≤ 1.3✓ met
Single-agent development costpathologicallarge-enum-match: time at 4x37 ms≤ 2000 ms✓ met
Single-agent development costpathologicallarge-enum-match: peak RSS at 4x26.5 MB≤ 200.0 MB✓ met
Single-agent development costpathologicallarge-enum-match: growth exponentnoise≤ 1.3✓ met
Single-agent development costpathologicaldeep-generic: time at 4x26 ms≤ 2000 ms✓ met
Single-agent development costpathologicaldeep-generic: peak RSS at 4x23.7 MB≤ 200.0 MB✓ met
Single-agent development costpathologicaldeep-generic: growth exponentnoise≤ 1.3✓ met
Single-agent development costpathologicalquestion-chain: time at 4x33 ms≤ 2000 ms✓ met
Single-agent development costpathologicalquestion-chain: peak RSS at 4x27.0 MB≤ 200.0 MB✓ met
Single-agent development costpathologicalquestion-chain: growth exponentnoise≤ 1.3✓ met
Single-agent development costpathologicalbig-file: time at 4x185 ms≤ 2000 ms✓ met
Single-agent development costpathologicalbig-file: peak RSS at 4x56.8 MB≤ 200.0 MB✓ met
Single-agent development costpathologicalbig-file: growth exponent1.11≤ 1.30✓ met
Single-agent development costrecheck-precisionmodules rechecked, private body edit1≤ 1✓ met
Single-agent development costrecheck-precisionmodules rechecked, public signature edit9≤ 3✗ missed
Single-agent development costerrors-per-runsemantic: 10 mistakes reported once10 of 10all, once✓ met
Single-agent development costerrors-per-runmixed: 10 mistakes reported once10 of 10all, once✓ met
Single-agent development costdiag-locationdiagnostics on the mistake's line98.6%≥ 95.0%✓ met
Single-agent development costfixit-safetyfix-its that add no error100.0%≥ 100.0%✓ met
Otherlookup-latencyp95 hd callers-– n/a
Otherlookup-latencyp95 hd needs-– n/a
Single-agent development costfmthd fmt, 10k lines37 ms≤ 200 ms✓ met
Single-agent development costfmtsecond hd fmt changes nothingno changeidempotent✓ met
Single-agent development costcheck-costchecked run time / unchecked run time1.83x≤ 1.30x✗ missed
Single-agent development costdev-speedgeomean dev / optimized1.81x≤ 4.00x✓ met
Single-agent development costdev-speedworst case dev / optimized3.65x≤ 10.00x✓ met
Agent scalabilityresourceswarm check, 10k lines: CPU time40 ms≤ 200 ms✓ met
Agent scalabilityresourceswarm check, 10k lines: peak RSS28.1 MB≤ 50.0 MB✓ met
Agent scalabilityresourcescheck, small, cold0.20 CPU-s, 39.1 MBcompletes ≤ 30 s✓ met
Agent scalabilityresourcescheck, small, warm0.01 CPU-s, 20.0 MBcompletes ≤ 30 s✓ met
Agent scalabilityresourcestest, small, cold1.20 CPU-s, 118.3 MBcompletes ≤ 30 s✓ met
Agent scalabilityresourcestest, small, warm0.08 CPU-s, 54.5 MBcompletes ≤ 30 s✓ met
Agent scalabilityresourcesbuild, small, cold1.01 CPU-s, 90.7 MBcompletes ≤ 30 s✓ met
Agent scalabilityresourcesbuild, small, warm0.03 CPU-s, 33.2 MBcompletes ≤ 30 s✓ met
Agent scalabilityresourcescheck, 10k, cold0.54 CPU-s, 61.5 MBcompletes ≤ 30 s✓ met
Agent scalabilityresourcescheck, 10k, warm0.04 CPU-s, 28.1 MBcompletes ≤ 30 s✓ met
Agent scalabilityresourcestest, 10k, cold1.98 CPU-s, 166.2 MBcompletes ≤ 30 s✓ met
Agent scalabilityresourcestest, 10k, warm0.19 CPU-s, 72.3 MBcompletes ≤ 30 s✓ met
Agent scalabilityresourcesbuild, 10k, cold1.40 CPU-s, 113.7 MBcompletes ≤ 30 s✓ met
Agent scalabilityresourcesbuild, 10k, warm0.06 CPU-s, 36.7 MBcompletes ≤ 30 s✓ met
Agent scalabilityresourcescheck, 50k, cold2.07 CPU-s, 166.7 MBcompletes ≤ 150 s✓ met
Agent scalabilityresourcescheck, 50k, warm0.17 CPU-s, 58.3 MBcompletes ≤ 150 s✓ met
Agent scalabilityresourcestest, 50k, cold5.16 CPU-s, 375.7 MBcompletes ≤ 150 s✓ met
Agent scalabilityresourcestest, 50k, warm0.58 CPU-s, 156.1 MBcompletes ≤ 150 s✓ met
Agent scalabilityresourcesbuild, 50k, cold2.97 CPU-s, 215.2 MBcompletes ≤ 150 s✓ met
Agent scalabilityresourcesbuild, 50k, warm0.18 CPU-s, 67.0 MBcompletes ≤ 150 s✓ met
Agent scalabilitylong-sessionRSS growth, REPL inputs 100 to 100070.7 MB≤ 22.0 MB✗ missed
Agent scalabilitystartuphd help (no version command): wall time4.4 ms≤ 20 ms✓ met
Agent scalabilitystartuphd help (no version command): CPU time0.0 ms≤ 20 ms✓ met
Agent scalabilitystartuphd help (no version command): peak RSS5.0 MB≤ 10.0 MB✓ met
Agent scalabilitystartuphd check empty.hd: wall time21 ms✗ missed
Agent scalabilitystartuphd check empty.hd: CPU time10 ms✓ met
Agent scalabilitystartuphd check empty.hd: peak RSS17.4 MB✗ missed
Agent scalabilityconcurrencyp95 latency at N = 4 vs N = 11.39x≤ 1.50x✓ met
Agent scalabilityconcurrencyp95 latency at N = 16 vs N = 11.95x≤ 6.00x✓ met
Agent scalabilityconcurrencytotal CPU growth exponent, N = 1 to 160.33< 1.00 (sublinear)✓ met
Agent scalabilitydiskartifacts plus toolchain per worktree22.8 MB✗ missed
Agent scalabilityparallel-speedupspeedup, 50k lines, 4 threads vs 11.87x≥ 2.40x✗ missed
Agent scalabilitycache-contentiondependency cache, 8 concurrent fetches: no corruptionintactno corruption✓ met
Agent scalabilitycache-contentiondependency cache, 8 concurrent fetches: fetched once16≤ 2, one check's connections✗ missed
Agent scalabilitycache-contentioncompilation cache, 8 concurrent checks: no corruptionintactno corruption✓ met
Agent scalabilitycache-contentioncompilation cache, 8 concurrent checks: written once220 filesthe files of one check's cache✗ missed
Agent scalabilitycache-growthcache size after 100 edits, cap 5 MB14.2 MB≤ 5.0 MB✗ missed
Agent scalabilityio-per-checksource files read, warm check after one edit1≤ 1✓ met
Agent scalabilityfetch-dedupconnections to the remote, 4 worktrees2= the first worktree's✓ met
Artifact qualityproptest-perfproperty cases per second88k/s≥ 100k/s✗ missed
Artifact qualityproptest-perftime to shrink a known failure28 ms≤ 1000 ms✓ met
Artifact qualityunit-test-perf1,000 unit tests, warm151 ms≤ 1000 ms✓ met
Artifact qualityunit-test-perfoverhead per unit test0.1 ms≤ 1.0 ms✓ met
Artifact qualityintegration-test-perfsetup per integration test program25 ms≤ 20 ms✗ missed
Artifact qualityintegration-test-perftotal time growth in programs0.884exponent < 1 (sublinear)✓ met
Artifact qualityintegration-test-perfcost per doc test20 ms≤ 20 ms✗ missed
Artifact qualityruntimegeomean hd / Node0.57x≤ 1.50x✓ met
Artifact qualityruntimefib: hd / Node0.75x≤ 3.00x✓ met
Artifact qualityruntimesum: hd / Node0.18x≤ 3.00x✓ met
Artifact qualityruntimestring-build: hd / Node0.78x≤ 3.00x✓ met
Artifact qualityruntimemap: hd / Node1.17x≤ 3.00x✓ met
Artifact qualityruntimesort: hd / Node0.52x≤ 3.00x✓ met
Artifact qualityallocationscounted loop, bytes per iteration-0 allocations (< 1 B/iter)– n/a
Artifact qualityallocationslist loop, bytes per iteration-0 allocations (< 1 B/iter)– n/a
Artifact qualityallocationsmap loop, bytes per iteration-0 allocations (< 1 B/iter)– n/a
Artifact qualityallocationsiterator chain, bytes per iteration-≤ 1 allocation (≤ 32 B/iter)– n/a
Artifact qualitysize-startup-heaptiny program, release Wasm size5014 B≤ 2048 B✗ missed
Artifact qualityhost-call-overheadConsole println, per call2.9 µs≤ 1.0 µs✗ missed
Artifact qualityhost-call-overheadFs read_text!, per call12 µs≤ 10 µs✗ missed
Artifact qualityhost-call-overheadserde boundary (list_dir!), per call19 µs≤ 5.0 µs✗ missed
Artifact qualitysuspension-overheadawait of a ready value, per await15 ns≤ 100 ns✓ met
Artifact qualitysuspension-overheadall! of two ready tasks, throughput7.4M/s≥ 1.0M/s✓ met
Artifact qualitysuspension-overheadrace! of two ready tasks, throughput4.8M/s≥ 1.0M/s✓ met
Artifact qualityserde-throughputJSON encode, hd / Node MB/s0.13x≥ 0.50x✗ missed
Artifact qualityserde-throughputJSON decode, hd / Node MB/s0.15x≥ 0.50x✗ missed
Artifact qualitytext-throughputstring build, hd / Node MB/s1.46x≥ 0.50x✓ met
Artifact qualitytext-throughputsplit, hd / Node MB/s0.74x≥ 0.50x✓ met
Artifact qualitytext-throughputregex find_all, hd / Node MB/s0.05x≥ 0.50x✗ missed
Artifact qualitydead-codeWasm bytes per 1,000 lines6516 B≤ 10240 B✓ met
Artifact qualitydead-codeno unused std in the programnonenone✓ met
Artifact qualitylong-run-memoryRSS growth after warm-up, 1 min0.0 MB≤ 10.0 MB✓ met
Correctness gateconformancepass rate, known failures excluded100.0%≥ 100.0%✓ met
Correctness gateconformancelisted known failures3≤ 0✗ missed
Correctness gateincremental-soundnessincremental equals clean, after each edit100.0%≥ 100.0%✓ met
Artifact qualitysize-startup-heaptiny program, start to first output9.4 ms≤ 5.0 ms✗ missed
Artifact qualitysize-startup-heappeak heap, map: hd / Node0.91x≤ 2.00x✓ met
Artifact qualitysize-startup-heappeak heap, string-build: hd / Node0.46x≤ 2.00x✓ met
Single-agent development costscalefn-items check4.04x≤ 5x✓ met
Single-agent development costscalefn-items fmt4.01x≤ 5x✓ met
Single-agent development costscalefn-items build4.01x≤ 5x✓ met
Single-agent development costscalestruct-items check4.03x≤ 5x✓ met
Single-agent development costscalestruct-items fmt4.01x≤ 5x✓ met
Single-agent development costscalestruct-items build4.00x≤ 5x✓ met
Single-agent development costscaleenum-items check4.00x≤ 5x✓ met
Single-agent development costscaleenum-items fmt4.00x≤ 5x✓ met
Single-agent development costscaleenum-items build4.00x≤ 5x✓ met
Single-agent development costscaletrait-items check4.00x≤ 5x✓ met
Single-agent development costscaletrait-items fmt4.00x≤ 5x✓ met
Single-agent development costscaletrait-items build4.02x≤ 5x✓ met
Single-agent development costscaleimpl-methods check4.00x≤ 5x✓ met
Single-agent development costscaleimpl-methods fmt3.97x≤ 5x✓ met
Single-agent development costscaleimpl-methods build4.00x≤ 5x✓ met
Single-agent development costscaleimpls-of-one-trait check4.00x≤ 5x✓ met
Single-agent development costscaleimpls-of-one-trait fmt4.01x≤ 5x✓ met
Single-agent development costscaleimpls-of-one-trait build4.00x≤ 5x✓ met
Single-agent development costscaleoperator-impls check4.00x≤ 5x✓ met
Single-agent development costscaleoperator-impls fmt4.01x≤ 5x✓ met
Single-agent development costscaleoperator-impls build4.00x≤ 5x✓ met
Single-agent development costscalederive-items check4.00x≤ 5x✓ met
Single-agent development costscalederive-items fmt4.01x≤ 5x✓ met
Single-agent development costscalederive-items build4.00x≤ 5x✓ met
Single-agent development costscaledyn-values check4.00x≤ 5x✓ met
Single-agent development costscaledyn-values fmt4.01x≤ 5x✓ met
Single-agent development costscaledyn-values build4.00x≤ 5x✓ met
Single-agent development costscaleconsts check3.97x≤ 5x✓ met
Single-agent development costscaleconsts fmt3.89x≤ 5x✓ met
Single-agent development costscaleconsts build4.00x≤ 5x✓ met
Single-agent development costscalelocal-items check4.00x≤ 5x✓ met
Single-agent development costscalelocal-items fmt4.01x≤ 5x✓ met
Single-agent development costscalelocal-items build4.00x≤ 5x✓ met
Single-agent development costscalesyntax-items check4.00x≤ 5x✓ met
Single-agent development costscalesyntax-items fmt4.00x≤ 5x✓ met
Single-agent development costscalesyntax-items build4.00x≤ 5x✓ met
Single-agent development costscalestruct-chain check4.04x≤ 5x✓ met
Single-agent development costscalestruct-chain fmt4.01x≤ 5x✓ met
Single-agent development costscalemodules check4.00x≤ 5x✓ met
Single-agent development costscalemodules fmt4.00x≤ 5x✓ met
Single-agent development costscalemodules build4.00x≤ 5x✓ met
Single-agent development costscaleuse-names check4.04x≤ 5x✓ met
Single-agent development costscaleuse-names fmt4.01x≤ 5x✓ met
Single-agent development costscaleuse-names build4.02x≤ 5x✓ met
Single-agent development costscalegeneric-fns check4.03x≤ 5x✓ met
Single-agent development costscalegeneric-fns fmt4.01x≤ 5x✓ met
Single-agent development costscalegeneric-fns build4.01x≤ 5x✓ met
Single-agent development costscalegeneric-params check4.08x≤ 5x✓ met
Single-agent development costscalegeneric-params fmt4.10x≤ 10x✓ met
Single-agent development costscalegeneric-params build4.00x≤ 5x✓ met
Single-agent development costscaleparam-bounds check4.01x≤ 5x✓ met
Single-agent development costscaleparam-bounds fmt4.04x≤ 5x✓ met
Single-agent development costscaleparam-bounds build4.00x≤ 5x✓ met
Single-agent development costscaletype-defaults check4.00x≤ 5x✓ met
Single-agent development costscaletype-defaults fmt4.00x≤ 5x✓ met
Single-agent development costscaletype-defaults build4.01x≤ 5x✓ met
Single-agent development costscalerow-chain check4.02x≤ 5x✓ met
Single-agent development costscalerow-chain fmt4.01x≤ 5x✓ met
Single-agent development costscalerow-chain build4.01x≤ 5x✓ met
Single-agent development costscalerow-traits check4.00x≤ 5x✓ met
Single-agent development costscalerow-traits fmt4.04x≤ 5x✓ met
Single-agent development costscalerow-traits build4.00x≤ 5x✓ met
Single-agent development costscaleclosures check4.00x≤ 5x✓ met
Single-agent development costscaleclosures fmt3.94x≤ 5x✓ met
Single-agent development costscaleclosures build4.00x≤ 5x✓ met
Single-agent development costscalelet-statements check3.96x≤ 5x✓ met
Single-agent development costscalelet-statements fmt3.94x≤ 5x✓ met
Single-agent development costscalelet-statements build4.00x≤ 5x✓ met
Single-agent development costscalematches check4.00x≤ 5x✓ met
Single-agent development costscalematches fmt3.97x≤ 5x✓ met
Single-agent development costscalematches build4.42x≤ 5x✓ met
Single-agent development costscaleenum-arms check4.00x≤ 5x✓ met
Single-agent development costscaleenum-arms fmt3.91x≤ 5x✓ met
Single-agent development costscaleenum-arms build4.00x≤ 5x✓ met
Single-agent development costscaletuple-patterns check4.00x≤ 5x✓ met
Single-agent development costscaletuple-patterns fmt3.95x≤ 5x✓ met
Single-agent development costscaletuple-patterns build4.00x≤ 5x✓ met
Single-agent development costscalerange-patterns check4.02x≤ 5x✓ met
Single-agent development costscalerange-patterns fmt4.01x≤ 5x✓ met
Single-agent development costscalerange-patterns build4.01x≤ 5x✓ met
Single-agent development costscalewide-struct check4.00x≤ 5x✓ met
Single-agent development costscalewide-struct fmt3.95x≤ 5x✓ met
Single-agent development costscalewide-struct build4.00x≤ 5x✓ met
Single-agent development costscalecall-args check4.42x≤ 5x✓ met
Single-agent development costscalecall-args fmt4.10x≤ 10x✓ met
Single-agent development costscalecall-args build4.00x≤ 5x✓ met
Single-agent development costscalebinary-chain check4.00x≤ 5x✓ met
Single-agent development costscalebinary-chain fmt3.78x≤ 5x✓ met
Single-agent development costscalebinary-chain build4.02x≤ 5x✓ met
Single-agent development costscaleinterpolation check4.00x≤ 5x✓ met
Single-agent development costscaleinterpolation fmt-≤ 5x✓ met
Single-agent development costscaleinterpolation build4.04x≤ 5x✓ met
Single-agent development costscalelist-literal check4.00x≤ 5x✓ met
Single-agent development costscalelist-literal fmt3.82x≤ 5x✓ met
Single-agent development costscalelist-literal build4.01x≤ 5x✓ met
Single-agent development costscalemethod-chain check4.00x≤ 5x✓ met
Single-agent development costscalemethod-chain fmt4.04x≤ 10x✓ met
Single-agent development costscalemethod-chain build4.00x≤ 5x✓ met
Single-agent development costscalepipe-chain check4.00x≤ 5x✓ met
Single-agent development costscalepipe-chain fmt3.77x≤ 5x✓ met
Single-agent development costscalepipe-chain build3.98x≤ 5x✓ met
Single-agent development costscalequestion-chain check4.00x≤ 5x✓ met
Single-agent development costscalequestion-chain fmt3.94x≤ 5x✓ met
Single-agent development costscalequestion-chain build3.99x≤ 5x✓ met
Single-agent development costscaleif-nest check3.92x≤ 15.11x✓ met
Single-agent development costscaleif-nest fmt-≤ 15.11x✓ met
Single-agent development costscaleif-nest build4.00x≤ 15.11x✓ met
Single-agent development costscaleblock-nest check3.95x≤ 15.29x✓ met
Single-agent development costscaleblock-nest fmt-≤ 15.29x✓ met
Single-agent development costscaleblock-nest build3.95x≤ 15.29x✓ met
Single-agent development costscalefor-nest check5.23x≤ 14.5x✓ met
Single-agent development costscalefor-nest fmt-≤ 14.5x✓ met
Single-agent development costscalefor-nest build4.69x≤ 14.5x✓ met
Single-agent development costscalewhile-nest check3.88x≤ 15.11x✓ met
Single-agent development costscalewhile-nest fmt-≤ 15.11x✓ met
Single-agent development costscalewhile-nest build4.00x≤ 15.11x✓ met
Single-agent development costscalematch-nest check4.87x≤ 16.03x✓ met
Single-agent development costscalematch-nest fmt-≤ 16.03x✓ met
Single-agent development costscalematch-nest build4.34x≤ 16.03x✓ met
Single-agent development costscaleclosure-nest check3.95x≤ 11.45x✓ met
Single-agent development costscaleclosure-nest fmt-≤ 11.45x✓ met
Single-agent development costscaleclosure-nest build4.00x≤ 11.45x✓ met
Single-agent development costscaleoption-nest check4.18x≤ 5x✓ met
Single-agent development costscaleoption-nest fmt-≤ 5x✓ met
Single-agent development costscaleoption-nest build4.04x≤ 5x✓ met
Single-agent development costscalelist-type-nest check4.27x≤ 5x✓ met
Single-agent development costscalelist-type-nest fmt-≤ 5x✓ met
Single-agent development costscalelist-type-nest build4.27x≤ 5x✓ met
Single-agent development costscalegeneric-nest check4.34x≤ 5x✓ met
Single-agent development costscalegeneric-nest fmt-≤ 5x✓ met
Single-agent development costscalegeneric-nest build4.04x≤ 5x✓ met
Single-agent development costscaleparen-nest check-≤ 5x✓ met
Single-agent development costscaleparen-nest fmt-≤ 5x✓ met
Single-agent development costscaleparen-nest build4.16x≤ 5x✓ met
Single-agent development costscalearith-nest check4.00x≤ 5x✓ met
Single-agent development costscalearith-nest fmt-≤ 5x✓ met
Single-agent development costscalearith-nest build4.16x≤ 5x✓ met
Single-agent development costscalebool-nest check3.95x≤ 5x✓ met
Single-agent development costscalebool-nest fmt-≤ 5x✓ met
Single-agent development costscalebool-nest build4.24x≤ 5x✓ met
Single-agent development costscalebit-nest check3.99x≤ 5x✓ met
Single-agent development costscalebit-nest fmt-≤ 5x✓ met
Single-agent development costscalebit-nest build4.09x≤ 5x✓ met
Single-agent development costscaletuple-nest check4.06x≤ 5x✓ met
Single-agent development costscaletuple-nest fmt-≤ 5x✓ met
Single-agent development costscaletuple-nest build4.18x≤ 5x✓ met
Single-agent development costscaleif-expr-nest check3.76x≤ 5x✓ met
Single-agent development costscaleif-expr-nest fmt-≤ 5x✓ met
Single-agent development costscaleif-expr-nest build3.82x≤ 5x✓ met
Single-agent development costscalecall-nest check3.89x≤ 5x✓ met
Single-agent development costscalecall-nest fmt-≤ 5x✓ met
Single-agent development costscalecall-nest build3.33x≤ 5x✓ met
Single-agent development costscaleindex-nest check-≤ 5x✓ met
Single-agent development costscaleindex-nest fmt-≤ 5x✓ met
Single-agent development costscaleindex-nest build4.16x≤ 5x✓ met
Single-agent development costscalefn-nest check4.03x≤ 13.42x✓ met
Single-agent development costscalefn-nest fmt-≤ 13.42x✓ met
Single-agent development costscalefn-nest build4.00x≤ 13.42x✓ met
Single-agent development costscalemodule-path-nest check1.58x≤ 5x✓ met
Single-agent development costscalemodule-path-nest fmt-≤ 5x✓ met
Single-agent development costscalemodule-path-nest build1.55x≤ 5x✓ met
Single-agent development costscalecoverage: node kinds119/119119/119✓ met
Single-agent development costscalecoverage: node kinds repeated110/119reported✓ met
Single-agent development costscalecoverage: node kinds nested57/119reported✓ met
Single-agent development costscaletraits-of-one-struct check4.00x≤ 5x✓ met
Single-agent development costscaletraits-of-one-struct fmt4.01x≤ 5x✓ met
Single-agent development costscaletraits-of-one-struct build4.00x≤ 5x✓ met
Single-agent development costscalestruct-chain-values check4.04x≤ 5x✓ met
Single-agent development costscalestruct-chain-values fmt4.02x≤ 5x✓ met
Single-agent development costscalestruct-chain-values build4.00x≤ 5x✓ met
Single-agent development costscalealias-chain check4.01x≤ 5x✓ met
Single-agent development costscalealias-chain fmt4.03x≤ 5x✓ met
Single-agent development costscalealias-chain build4.00x≤ 5x✓ met
Agent scalabilitystartuphd check empty.hd, just written: wall time18 ms≤ 20 ms✓ met
Agent scalabilitystartuphd check empty.hd, just written: CPU time10 ms≤ 20 ms✓ met
Agent scalabilitystartuphd check empty.hd, just written: peak RSS19.0 MB≤ 10.0 MB✗ missed
Agent scalabilitystartuphd check empty.hd, settled: wall time7.1 ms≤ 20 ms✓ met
Agent scalabilitystartuphd check empty.hd, settled: CPU time0.0 ms≤ 20 ms✓ met
Agent scalabilitystartuphd check empty.hd, settled: peak RSS9.8 MB≤ 10.0 MB✓ met
Agent scalabilitydiskartifacts per worktree0.0 MB≤ 10.0 MB✓ met
Agent scalabilitydisktoolchain, once per machine32.0 MBrecorded, no target✓ met
Single-agent development costscalegeneric-local-fns check4.03x≤ 5x✓ met
Single-agent development costscalegeneric-local-fns fmt4.01x≤ 5x✓ met
Single-agent development costscalegeneric-local-fns build4.01x≤ 5x✓ met