gcf-python 0.2.0__py3-none-any.whl → 0.3.1__py3-none-any.whl

gcf/generic.py

@@ -59,6 +59,10 @@ def _encode_array(items: list, name: str, lines: list[str], depth: int) -> None:
 
     if _is_uniform_dict_list(items):
         _encode_tabular(items, name, lines, depth)
+    elif all(not isinstance(item, (dict, list)) for item in items):
+        # Primitive array: inline as comma-separated values.
+        vals = ",".join(_format_value(item) for item in items)
+        lines.append(f"{prefix}{name}[{len(items)}]: {vals}")
     else:
         lines.append(f"{prefix}## {name} [{len(items)}]")
         for i, item in enumerate(items):

{gcf_python-0.2.0.dist-info → gcf_python-0.3.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gcf-python
-Version: 0.2.0
+Version: 0.3.1
 Summary: Python implementation of GCF (Graph Compact Format): token-optimized wire format for LLM tool responses
 Project-URL: Homepage, https://github.com/blackwell-systems/gcf-python
 Project-URL: Documentation, https://blackwell-systems.github.io/gcf/
@@ -32,7 +32,7 @@ Description-Content-Type: text/markdown
 
 Python implementation of [GCF (Graph Compact Format)](https://gcformat.com/) — the most token-efficient wire format for LLMs. A drop-in alternative to JSON and TOON for any structured data.
 
-**79% fewer input tokens than JSON. 75% fewer output tokens. 52% smaller than TOON. 100% LLM comprehension at 500 symbols, where JSON fails at 66.7%.**
+**79% fewer input tokens than JSON. 75% fewer output tokens. 52% smaller than TOON. 100% LLM comprehension at 500 symbols, where JSON scores 76.9% and TOON scores 92.3%.**
 
 Docs: [gcformat.com](https://gcformat.com/) · [Playground](https://gcformat.com/playground.html) · [GCF vs TOON](https://gcformat.com/guide/vs-toon.html)
 
@@ -189,15 +189,17 @@ Works on dicts, lists, and primitives. Lists of uniform dicts get tabular rows.
 
 ## Comprehension Eval
 
-Rigorous 3-way benchmark (GCF vs TOON vs JSON) at 500 symbols, 200 edges. Six structured extraction questions sent to an LLM:
+Rigorous 3-way benchmark (GCF vs TOON vs JSON) at 500 symbols, 200 edges. 13 structured extraction questions sent to an LLM with zero format instructions:
 
 | Format | Accuracy | Tokens | vs JSON |
 |--------|----------|--------|---------|
-| **GCF** | **100%** (6/6) | **11,090** | **79% fewer** |
-| TOON | 100% (6/6) | 16,378 | 69% fewer |
-| JSON | 66.7% (4/6) | 53,341 | baseline |
+| **GCF** | **100%** (13/13) | **11,090** | **79% fewer** |
+| TOON | 92.3% (12/13) | 16,378 | 69% fewer |
+| JSON | 76.9% (10/13) | 53,341 | baseline |
 
-JSON failed on counting tasks. GCF and TOON both achieved perfect accuracy. GCF does it in 32% fewer tokens.
+GCF is the only format with perfect accuracy at scale, at 32% fewer tokens than TOON.
+
+Reproduce: `git clone https://github.com/blackwell-systems/gcf-go && cd gcf-go/eval && GOWORK=off go test -run TestComprehension -v -timeout 0`
 
 ## Token Efficiency (TOON's Own Benchmark)
 
@@ -205,13 +207,13 @@ Running [TOON's benchmark harness](https://github.com/blackwell-systems/toon/tre
 
 | Track | GCF | TOON | Result |
 |-------|-----|------|--------|
-| Mixed-structure (nested, semi-uniform) | 169,554 | 227,896 | **GCF 34% smaller** |
-| Flat-only (tabular) | 66,026 | 67,837 | **GCF 3% smaller** |
-| Semi-uniform event logs | 107,269 | 154,032 | **GCF 44% smaller** |
+| Mixed-structure (nested, semi-uniform) | 170,367 | 227,896 | **GCF 34% smaller** |
+| Flat-only (tabular) | 66,029 | 67,837 | **GCF 3% smaller** |
+| Semi-uniform event logs | 108,158 | 154,032 | **GCF 42% smaller** |
 
-GCF wins on every dataset except deeply nested config (75 tokens on a 618-token payload). On semi-uniform data, GCF uses 44% fewer tokens than TOON.
+GCF wins all 6 datasets. On semi-uniform data (the most common real-world pattern), GCF uses 42% fewer tokens than TOON.
 
-Reproducible: [blackwell-systems/toon@gcf-comparison](https://github.com/blackwell-systems/toon/tree/gcf-comparison)
+Reproduce: `git clone https://github.com/blackwell-systems/toon && cd toon && git checkout gcf-comparison && cd benchmarks && pnpm install && pnpm benchmark:tokens`
 
 ## Links
 

{gcf_python-0.2.0.dist-info → gcf_python-0.3.1.dist-info}/RECORD

@@ -4,11 +4,11 @@ gcf/constants.py,sha256=cmZ8YJSOB0im_eyfN8v4UvrLpBC6Fuf4cfcKZGbutxY,638
 gcf/decode.py,sha256=48G6XmBilGYl0-c_Xy7MX0iTwOxGW9bn3wC4UyNApc4,5465
 gcf/delta.py,sha256=xU0ujtSq1iF7yU8yk_WNQKh8iove-WUV_nKSuvW1XVk,1656
 gcf/encode.py,sha256=Oljb1r5b7SHmng1XYvcvuJMpaRfJVJ81VOyocPf_kAs,2915
-gcf/generic.py,sha256=xSXCufl4uK3xaDDPsKb4g5Mf0B-HVePzzwnwKYXJ8OU,5200
+gcf/generic.py,sha256=Nf1Ii0pYS0dgZ4o2ghl-3Qhnms-kCKY2D3q-3-oGpe8,5454
 gcf/session.py,sha256=4_ARRL06Tg2CI8D2eyi0V5nFphFAFMfOKBXYnAbI6Nk,4690
 gcf/types.py,sha256=AWm-LQoSqLHAYtEjcAxWQZqJ4JXqNreLUKO2mJFgNMA,1465
-gcf_python-0.2.0.dist-info/METADATA,sha256=2YETOadgxh76qeHmHYZKOcpAo-4HGLyBQBh3BC148cA,7929
-gcf_python-0.2.0.dist-info/WHEEL,sha256=mffPy8wBnZQn2VnJUU5jE99KsxaSfiyMHV9Yt0aLVxs,87
-gcf_python-0.2.0.dist-info/entry_points.txt,sha256=aFT6gqlkh8iGfM8cblE-LUMxHH08_v71IIoZtDdRIVA,37
-gcf_python-0.2.0.dist-info/licenses/LICENSE,sha256=txSvg3E4LugiB7MOOTci6WKd6wMOrOJTvaITeFJ2SgU,1074
-gcf_python-0.2.0.dist-info/RECORD,,
+gcf_python-0.3.1.dist-info/METADATA,sha256=xQxbAQEk1jr_c_GTsFQM1zyCmuz_MmgcbSxc1hNcKz0,8127
+gcf_python-0.3.1.dist-info/WHEEL,sha256=mffPy8wBnZQn2VnJUU5jE99KsxaSfiyMHV9Yt0aLVxs,87
+gcf_python-0.3.1.dist-info/entry_points.txt,sha256=aFT6gqlkh8iGfM8cblE-LUMxHH08_v71IIoZtDdRIVA,37
+gcf_python-0.3.1.dist-info/licenses/LICENSE,sha256=txSvg3E4LugiB7MOOTci6WKd6wMOrOJTvaITeFJ2SgU,1074
+gcf_python-0.3.1.dist-info/RECORD,,