Download Latest Version v2.3.7 source code.zip (5.9 MB)
Email in envelope

Get an email when there's a new version of code-review-graph

Home / v2.3.5
Name Modified Size InfoDownloads / Week
Parent folder
README.md 2026-05-25 2.8 kB
v2.3.5 -- Real-time token savings, visible to humans source code.tar.gz 2026-05-25 5.5 MB
v2.3.5 -- Real-time token savings, visible to humans source code.zip 2026-05-25 5.7 MB
Totals: 3 Items   11.2 MB 0

Real-time token savings, visible to humans. The estimated context-savings metric introduced in 2.3.4 was JSON-only. In 2.3.5 it surfaces as a clean boxed panel on the CLI and is verifiable against a real tokenizer in one flag β€” so when you reach for code-review-graph to review a change, you can immediately see how much of your context window the graph just kept out.

Token Savings demo

Highlights

  • πŸͺŸ Token Savings panel on both code-review-graph detect-changes --brief and the new code-review-graph update --brief. Per-category breakdown (Functions / Tests / Risk / Other) that sums exactly to the graph response size.
  • βœ… --verify flag cross-checks the displayed numbers against OpenAI's cl100k_base tokenizer. Calibration shows the estimate stays within +0.5% of real GPT-4 tokens in aggregate across 222 mixed-language source files (data in docs/REPRODUCING.md).
  • πŸ” Deterministic eval pipeline β€” pinned upstream SHAs, full clones with returncode checks, fixed Leiden seed. Two contributors running the benchmark recipe on different machines on different days now produce identical numbers.
  • 🎯 Multi-hop retrieval benchmark + richer embedding text + identifier-aware search boost lift compound-query accuracy from 0.545 β†’ 0.909.
  • πŸ“¦ code-review-graph embed CLI subcommand for explicit embedding generation. Previously only reachable via MCP.

What the panel looks like

```text β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€ Token Savings ────────────────────────┐ β”‚ Full context would be: 12,921 tokens β”‚ β”‚ Graph context used: 762 tokens β”‚ β”‚ Saved: 12,159 tokens (~94%) β”‚ β”‚ Breakdown: Functions 244 Β· Tests 191 Β· Risk 244 Β· Other 83 β”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ ```

Add --verify to grow a Verified (tiktoken) row so the numbers are no longer just an estimate.

Reproduction

End-to-end recipe with canonical numbers in docs/REPRODUCING.md (github.com). All 6 test repos pin upstream SHAs, embeddings are deterministic on CPU, Leiden detection is seeded.

Full release notes

CHANGELOG.md β€” v2.3.5 [entry](https://github.com/tirth8205/code-review-graph/blob/main/CHANGELOG.md#235

Source: README.md, updated 2026-05-25