Auto-generated by npm run benchmark:comprehensive
Last run: 2026-08-03T07:45:44.869Z
Commit: 05a798172a6cff9d0d3d6df8d155bcf3e52305cb
| Component | Score | Weight |
|---|
| Indexing | 100.0% | 15% |
| Compression | 64.7% | 20% |
| Planning | 100.0% | 20% |
| Learning | 100.0% | 15% |
| Bridge | 100.0% | 15% |
| Performance | 99.7% | 15% |
| Overall | 92.9% | 100% |
| Metric | Value |
|---|
| Total nodes | 2,007 |
| Total edges | 7,067 |
| Files indexed | 181 |
| Indexing time | 0.55s |
| Node type breakdown | File: 181, Module: 196, Symbol: 1630 |
| Edge type breakdown | depends_on: 181, defines: 1630, imports: 717, part_of: 120, next_section: 59, references: 2466, calls: 1869, inherits: 25 |
| Metric | Value |
|---|
| Avg summary tokens | 472 |
| Avg anchor count | 15.0 |
| Avg total tokens | 707 |
| Layer distribution | L1: 270, L2: 30 |
| Task | Expected | Actual | Correct |
|---|
| fix typo in readme | simple | simple | Y |
| add unit test for utils | simple | simple | Y |
| update config default value | simple | simple | Y |
| refactor the database module and add migration sup | complex | complex | Y |
| multi-module architecture redesign with parallel m | complex | complex | Y |
| implement caching layer and refactor all API endpo | complex | complex | Y |
| add logging | simple | simple | Y |
| create graph-based context compression with pagera | complex | complex | Y |
| Task | Nodes | Has deps | Within bounds |
|---|
| refactor orchestrator and add tests | 3 | Y | Y |
| fix bug in config loader | 4 | Y | Y |
| implement new feature: graph visualization with in | 3 | Y | Y |
| add python indexer support | 4 | Y | Y |
| setup CI pipeline | 4 | Y | Y |
| Task | Nodes | Rounds | Parallelism |
|---|
| refactor orchestrator and add tests | 3 | 2 | 1.50x |
| fix bug in config loader | 4 | 3 | 1.33x |
| implement new feature: graph visualization with in | 3 | 2 | 1.50x |
| add python indexer support | 4 | 3 | 1.33x |
| setup CI pipeline | 4 | 3 | 1.33x |
| Avg parallelism | | | 1.40x |
| Metric | Value |
|---|
| Episodes recorded | 5 |
| Episode recall hits | 3 |
| Skill hints generated | 3 |
| Skill outcome recorded | Y |
| Episode roundtrip | PASS |
| Task | Plan nodes | Assignments | Specialty coverage |
|---|
| refactor the authentication module and add OAuth2 | 3 | 3 | 100.0% |
| implement caching layer for graph queries with inv | 4 | 4 | 100.0% |
| multi-language indexer: add Rust and Go support wi | 3 | 3 | 100.0% |
| Avg | | 3.3 | 100.0% |
| Metric | Value |
|---|
| Graph build time | 0.55s |
| Avg query latency | 3ms |
| P50 query latency | 3ms |
| P95 query latency | 10ms |
| Peak memory (RSS) | 276MB |
- Node:
v22.20.0
- Platform:
linux x64
- Wall-clock: 0.81s
npm install && npm run benchmark:comprehensive