code-context-engine 0.4.17__tar.gz → 0.4.18__tar.gz

{code_context_engine-0.4.17/src/code_context_engine.egg-info → code_context_engine-0.4.18}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code-context-engine
-Version: 0.4.17
+Version: 0.4.18
 Summary: Index your codebase. AI searches instead of re-reading files. 94% token savings, benchmarked on FastAPI. Works with Claude Code, Cursor, VS Code, Gemini CLI, Codex, and OpenCode.
 Author-email: Fazle Elahee <felahee@gmail.com>, Raj <rajkumar.sakti@gmail.com>
 License-Expression: MIT
@@ -216,14 +216,25 @@ We benchmarked CCE against [FastAPI](https://github.com/fastapi/fastapi) (53 sou
 
 Output compression (reducing Claude's reply length) provides additional savings (~65% estimated) but is not included in the headline number above.
 
+### Multi-language benchmarks
+
+| Repo | Language | Files | Retrieval savings | Recall@10 |
+|------|----------|-------|-------------------|-----------|
+| [FastAPI](benchmarks/results/fastapi.md) | Python | 53 | **94%** | 0.90 |
+| [chi](benchmarks/results/chi.md) | Go | 94 | **76%** | 0.67 |
+| [fiber](benchmarks/results/fiber.md) | Go (monorepo) | 396 | **93%** | 0.07 |
+
+Go's shorter files reduce the retrieval headroom (smaller baseline). Monorepos dilute recall at top-10 (fiber). Middleware queries with one-feature-per-file hit R=1.00 consistently.
+
 **Reproduce it yourself:**
 
 ```bash
 pip install code-context-engine
 python benchmarks/run_benchmark.py --repo https://github.com/fastapi/fastapi.git --source-dir fastapi
+python benchmarks/run_benchmark.py --repo https://github.com/go-chi/chi.git --source-dir .
 ```
 
-Full results in [`benchmarks/results/fastapi.md`](benchmarks/results/fastapi.md). Queries and methodology in [`benchmarks/`](benchmarks/).
+Full results in [`benchmarks/results/`](benchmarks/results/). Queries and methodology in [`benchmarks/`](benchmarks/).
 
 ---
 
@@ -446,7 +457,8 @@ No GPU required. Embedding model runs on CPU via ONNX Runtime.
 
 ## Roadmap
 
-- [ ] Multi-repo benchmarks (Django, Express, a Go project)
+- [x] Multi-repo benchmarks (FastAPI, chi, fiber)
+- [ ] More benchmarks (Django, Express)
 - [ ] Tree-sitter support for C, C++, Ruby, Swift, Kotlin
 - [ ] Docker support for remote mode
 

{code_context_engine-0.4.17 → code_context_engine-0.4.18}/README.md

@@ -167,14 +167,25 @@ We benchmarked CCE against [FastAPI](https://github.com/fastapi/fastapi) (53 sou
 
 Output compression (reducing Claude's reply length) provides additional savings (~65% estimated) but is not included in the headline number above.
 
+### Multi-language benchmarks
+
+| Repo | Language | Files | Retrieval savings | Recall@10 |
+|------|----------|-------|-------------------|-----------|
+| [FastAPI](benchmarks/results/fastapi.md) | Python | 53 | **94%** | 0.90 |
+| [chi](benchmarks/results/chi.md) | Go | 94 | **76%** | 0.67 |
+| [fiber](benchmarks/results/fiber.md) | Go (monorepo) | 396 | **93%** | 0.07 |
+
+Go's shorter files reduce the retrieval headroom (smaller baseline). Monorepos dilute recall at top-10 (fiber). Middleware queries with one-feature-per-file hit R=1.00 consistently.
+
 **Reproduce it yourself:**
 
 ```bash
 pip install code-context-engine
 python benchmarks/run_benchmark.py --repo https://github.com/fastapi/fastapi.git --source-dir fastapi
+python benchmarks/run_benchmark.py --repo https://github.com/go-chi/chi.git --source-dir .
 ```
 
-Full results in [`benchmarks/results/fastapi.md`](benchmarks/results/fastapi.md). Queries and methodology in [`benchmarks/`](benchmarks/).
+Full results in [`benchmarks/results/`](benchmarks/results/). Queries and methodology in [`benchmarks/`](benchmarks/).
 
 ---
 
@@ -397,7 +408,8 @@ No GPU required. Embedding model runs on CPU via ONNX Runtime.
 
 ## Roadmap
 
-- [ ] Multi-repo benchmarks (Django, Express, a Go project)
+- [x] Multi-repo benchmarks (FastAPI, chi, fiber)
+- [ ] More benchmarks (Django, Express)
 - [ ] Tree-sitter support for C, C++, Ruby, Swift, Kotlin
 - [ ] Docker support for remote mode
 

{code_context_engine-0.4.17 → code_context_engine-0.4.18}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "code-context-engine"
-version = "0.4.17"
+version = "0.4.18"
 description = "Index your codebase. AI searches instead of re-reading files. 94% token savings, benchmarked on FastAPI. Works with Claude Code, Cursor, VS Code, Gemini CLI, Codex, and OpenCode."
 readme = {file = "README.md", content-type = "text/markdown"}
 license = "MIT"

{code_context_engine-0.4.17 → code_context_engine-0.4.18/src/code_context_engine.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code-context-engine
-Version: 0.4.17
+Version: 0.4.18
 Summary: Index your codebase. AI searches instead of re-reading files. 94% token savings, benchmarked on FastAPI. Works with Claude Code, Cursor, VS Code, Gemini CLI, Codex, and OpenCode.
 Author-email: Fazle Elahee <felahee@gmail.com>, Raj <rajkumar.sakti@gmail.com>
 License-Expression: MIT
@@ -216,14 +216,25 @@ We benchmarked CCE against [FastAPI](https://github.com/fastapi/fastapi) (53 sou
 
 Output compression (reducing Claude's reply length) provides additional savings (~65% estimated) but is not included in the headline number above.
 
+### Multi-language benchmarks
+
+| Repo | Language | Files | Retrieval savings | Recall@10 |
+|------|----------|-------|-------------------|-----------|
+| [FastAPI](benchmarks/results/fastapi.md) | Python | 53 | **94%** | 0.90 |
+| [chi](benchmarks/results/chi.md) | Go | 94 | **76%** | 0.67 |
+| [fiber](benchmarks/results/fiber.md) | Go (monorepo) | 396 | **93%** | 0.07 |
+
+Go's shorter files reduce the retrieval headroom (smaller baseline). Monorepos dilute recall at top-10 (fiber). Middleware queries with one-feature-per-file hit R=1.00 consistently.
+
 **Reproduce it yourself:**
 
 ```bash
 pip install code-context-engine
 python benchmarks/run_benchmark.py --repo https://github.com/fastapi/fastapi.git --source-dir fastapi
+python benchmarks/run_benchmark.py --repo https://github.com/go-chi/chi.git --source-dir .
 ```
 
-Full results in [`benchmarks/results/fastapi.md`](benchmarks/results/fastapi.md). Queries and methodology in [`benchmarks/`](benchmarks/).
+Full results in [`benchmarks/results/`](benchmarks/results/). Queries and methodology in [`benchmarks/`](benchmarks/).
 
 ---
 
@@ -446,7 +457,8 @@ No GPU required. Embedding model runs on CPU via ONNX Runtime.
 
 ## Roadmap
 
-- [ ] Multi-repo benchmarks (Django, Express, a Go project)
+- [x] Multi-repo benchmarks (FastAPI, chi, fiber)
+- [ ] More benchmarks (Django, Express)
 - [ ] Tree-sitter support for C, C++, Ruby, Swift, Kotlin
 - [ ] Docker support for remote mode
 

{code_context_engine-0.4.17 → code_context_engine-0.4.18}/src/context_engine/indexer/embedder.py

@@ -27,7 +27,9 @@ _DEFAULT_MODEL = "BAAI/bge-small-en-v1.5"
 # Even parallel=1 takes the multiprocessing path — and that path deadlocks on
 # macOS (workers idle on SimpleQueue.get while the main thread sits in
 # asyncio.poll, leaving `cce init` stuck after the file-scan progress bar
-# hits 100%). Default to None on darwin; allow override via CCE_EMBED_PARALLEL.
+# hits 100%). On Windows, ONNX Runtime worker processes crash with
+# ACCESS_VIOLATION (0xC0000005) due to DLL handle inheritance issues.
+# Default to None on darwin and win32; allow override via CCE_EMBED_PARALLEL.
 def _resolve_parallel() -> int | None:
     override = os.environ.get("CCE_EMBED_PARALLEL")
     if override:
@@ -37,6 +39,8 @@ def _resolve_parallel() -> int | None:
             pass
     if sys.platform == "darwin":
         return None
+    if sys.platform == "win32":
+        return None
     return min(os.cpu_count() or 2, 4)