code-context-engine 0.4.19__tar.gz → 0.4.21__tar.gz

{code_context_engine-0.4.19/src/code_context_engine.egg-info → code_context_engine-0.4.21}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code-context-engine
-Version: 0.4.19
+Version: 0.4.21
 Summary: Save 94% on Claude Code tokens. Index your codebase locally, AI agents search instead of reading files. Reduce Claude API costs, save tokens on Cursor, VS Code, Gemini CLI. Free, open source MCP server.
 Author-email: Fazle Elahee <felahee@gmail.com>, Raj <rajkumar.sakti@gmail.com>
 License-Expression: MIT
@@ -21,7 +21,6 @@ License-File: LICENSE
 Requires-Dist: click>=8.1
 Requires-Dist: pyyaml>=6.0
 Requires-Dist: sqlite-vec>=0.1.6
-Requires-Dist: fastembed>=0.4
 Requires-Dist: numpy>=1.24
 Requires-Dist: tree-sitter>=0.22
 Requires-Dist: tree-sitter-python>=0.21
@@ -46,6 +45,8 @@ Requires-Dist: pytest-cov>=5.0; extra == "dev"
 Requires-Dist: pytest-xdist>=3.5; extra == "dev"
 Requires-Dist: ruff>=0.13; extra == "dev"
 Provides-Extra: http
+Provides-Extra: local
+Requires-Dist: fastembed>=0.4; extra == "local"
 Dynamic: license-file
 
 <p align="center">
@@ -119,10 +120,10 @@ Dynamic: license-file
 ```bash
 uv tool install code-context-engine
 cd /path/to/your/project
-cce init
+cce init                              # or: cce init --agent all
 ```
 
-That's it. Claude now searches your index instead of reading entire files. No config needed.
+That's it. Your AI coding agent now searches your index instead of reading entire files. No config needed.
 
 ---
 
@@ -148,23 +149,34 @@ cd /path/to/your/project
 cce init                              # index, install hooks, register MCP server
 ```
 
+**Embedding backends:** CCE auto-detects the best available backend. If you have Ollama running, it uses `nomic-embed-text` with zero extra dependencies. For offline/local embedding without Ollama, install the `[local]` extra:
+
+```bash
+uv tool install "code-context-engine[local]"   # includes fastembed + ONNX Runtime
+```
+
 Restart your editor. Done. Every question now hits the index instead of re-reading files.
 
-`cce init` auto-detects your editor and writes the right config:
+`cce init` auto-detects your editor and writes the right config. To target a
+specific agent, use `--agent claude`, `--agent codex`, `--agent copilot`, or
+`--agent all`.
 
 | Editor | Config written | Instructions |
 |--------|---------------|--------------|
 | Claude Code | `.mcp.json` | `CLAUDE.md` |
-| VS Code / Copilot | `.vscode/mcp.json` | |
+| VS Code / Copilot | `.vscode/mcp.json` | `.github/copilot-instructions.md` |
 | Cursor | `.cursor/mcp.json` | `.cursorrules` |
 | Gemini CLI | `.gemini/settings.json` | `GEMINI.md` |
-| OpenAI Codex | `~/.codex/config.toml` (user-global, per-project section) | |
+| OpenAI Codex | `~/.codex/config.toml` (user-global, per-project section) | `AGENTS.md` |
 | OpenCode | `opencode.json` | |
 | Tabnine | `.tabnine/agent/settings.json` | `TABNINE.md` |
 
 Multiple editors in the same project? All get configured in one command.
 
-**Codex note:** Codex CLI reads MCP servers from `~/.codex/config.toml` only — it has no per-project config. `cce init` adds one `[mcp_servers.cce-<project>-<hash>]` section per project so multiple projects coexist; `cce uninstall` removes only the section for the current project.
+**Codex note:** Codex CLI reads MCP servers from `~/.codex/config.toml` only —
+it has no per-project config. `cce init` adds one `[mcp_servers.cce-<project>-<hash>]`
+section per project so multiple projects coexist; `cce uninstall` removes only
+the section for the current project.
 
 ```
   my-project · 38 queries
@@ -425,11 +437,12 @@ Tell Claude: "switch to max compression" or "turn off compression". Code blocks
 
 | Component | Size |
 |-----------|------|
-| Installed package | ~189 MB (ONNX Runtime is 66 MB of that) |
-| Embedding model (one-time download) | ~60 MB |
+| Core install (Ollama backend) | ~17 MB |
+| With `[local]` extra (fastembed + ONNX) | ~189 MB |
+| Embedding model (one-time download) | ~60 MB (fastembed) or managed by Ollama |
 | Index per project (small/medium/large) | 5-60 MB |
 
-No GPU required. Embedding model runs on CPU via ONNX Runtime.
+No GPU required. With Ollama, embeddings are handled by the Ollama server. With the `[local]` extra, the embedding model runs on CPU via ONNX Runtime.
 
 ---
 
@@ -479,6 +492,55 @@ All other text files are chunked by line range. Binary files are skipped.
 
 ---
 
+## FAQ
+
+### Does CCE affect response quality?
+
+No. Quality stays the same or slightly improves.
+
+CCE replaces "dump the entire file" with "search for the relevant function." The model still gets the code it needs (0.90 Recall@10 in benchmarks). Less irrelevant context means less noise competing for attention, which can improve the model's focus on your actual question.
+
+### How do I increase output token savings?
+
+Set the output compression level in your project config (`cce.yaml`):
+
+```yaml
+compression:
+  output: max       # off | lite | standard | max
+```
+
+Or change it at runtime via the MCP tool:
+
+```
+set_output_level output_level=max
+```
+
+| Level | Savings | What it does |
+|-------|---------|--------------|
+| `off` | 0% | No compression |
+| `lite` | ~25% | Removes filler/hedging/pleasantries + diff-only for code changes |
+| `standard` | ~70% | Drops articles, fragments, short synonyms + diff-only for code |
+| `max` | ~80% | Telegraphic style + diff-only for code |
+
+Default is `standard`. All levels include **code output rules** that instruct the model to show only changed lines (not full file rewrites), which is where most output tokens go in coding sessions. The `max` level produces very terse prose (similar to "caveman mode"). Code blocks, paths, and commands are never compressed regardless of level.
+
+### Where do the savings come from?
+
+Most savings are **input tokens** (what goes into the model):
+
+| Layer | Type | Typical savings |
+|-------|------|-----------------|
+| Retrieval | Input | 94% (full files → relevant chunks) |
+| Chunk compression | Input | 89% (chunks → signatures) |
+| Grammar compression | Input | 13% (article/filler removal) |
+| Turn summarization | Input | varies (session history) |
+| Progressive disclosure | Input | varies (tool payloads) |
+| Output compression | Output | 25-80% (depends on level) |
+
+Output tokens cost 5x more per token (e.g. Opus: $15/1M input vs $75/1M output), so even a small output reduction has outsized cost impact.
+
+---
+
 ## Roadmap
 
 - [x] Multi-repo benchmarks (FastAPI, chi, fiber)

{code_context_engine-0.4.19 → code_context_engine-0.4.21}/README.md

@@ -69,10 +69,10 @@
 ```bash
 uv tool install code-context-engine
 cd /path/to/your/project
-cce init
+cce init                              # or: cce init --agent all
 ```
 
-That's it. Claude now searches your index instead of reading entire files. No config needed.
+That's it. Your AI coding agent now searches your index instead of reading entire files. No config needed.
 
 ---
 
@@ -98,23 +98,34 @@ cd /path/to/your/project
 cce init                              # index, install hooks, register MCP server
 ```
 
+**Embedding backends:** CCE auto-detects the best available backend. If you have Ollama running, it uses `nomic-embed-text` with zero extra dependencies. For offline/local embedding without Ollama, install the `[local]` extra:
+
+```bash
+uv tool install "code-context-engine[local]"   # includes fastembed + ONNX Runtime
+```
+
 Restart your editor. Done. Every question now hits the index instead of re-reading files.
 
-`cce init` auto-detects your editor and writes the right config:
+`cce init` auto-detects your editor and writes the right config. To target a
+specific agent, use `--agent claude`, `--agent codex`, `--agent copilot`, or
+`--agent all`.
 
 | Editor | Config written | Instructions |
 |--------|---------------|--------------|
 | Claude Code | `.mcp.json` | `CLAUDE.md` |
-| VS Code / Copilot | `.vscode/mcp.json` | |
+| VS Code / Copilot | `.vscode/mcp.json` | `.github/copilot-instructions.md` |
 | Cursor | `.cursor/mcp.json` | `.cursorrules` |
 | Gemini CLI | `.gemini/settings.json` | `GEMINI.md` |
-| OpenAI Codex | `~/.codex/config.toml` (user-global, per-project section) | |
+| OpenAI Codex | `~/.codex/config.toml` (user-global, per-project section) | `AGENTS.md` |
 | OpenCode | `opencode.json` | |
 | Tabnine | `.tabnine/agent/settings.json` | `TABNINE.md` |
 
 Multiple editors in the same project? All get configured in one command.
 
-**Codex note:** Codex CLI reads MCP servers from `~/.codex/config.toml` only — it has no per-project config. `cce init` adds one `[mcp_servers.cce-<project>-<hash>]` section per project so multiple projects coexist; `cce uninstall` removes only the section for the current project.
+**Codex note:** Codex CLI reads MCP servers from `~/.codex/config.toml` only —
+it has no per-project config. `cce init` adds one `[mcp_servers.cce-<project>-<hash>]`
+section per project so multiple projects coexist; `cce uninstall` removes only
+the section for the current project.
 
 ```
   my-project · 38 queries
@@ -375,11 +386,12 @@ Tell Claude: "switch to max compression" or "turn off compression". Code blocks
 
 | Component | Size |
 |-----------|------|
-| Installed package | ~189 MB (ONNX Runtime is 66 MB of that) |
-| Embedding model (one-time download) | ~60 MB |
+| Core install (Ollama backend) | ~17 MB |
+| With `[local]` extra (fastembed + ONNX) | ~189 MB |
+| Embedding model (one-time download) | ~60 MB (fastembed) or managed by Ollama |
 | Index per project (small/medium/large) | 5-60 MB |
 
-No GPU required. Embedding model runs on CPU via ONNX Runtime.
+No GPU required. With Ollama, embeddings are handled by the Ollama server. With the `[local]` extra, the embedding model runs on CPU via ONNX Runtime.
 
 ---
 
@@ -429,6 +441,55 @@ All other text files are chunked by line range. Binary files are skipped.
 
 ---
 
+## FAQ
+
+### Does CCE affect response quality?
+
+No. Quality stays the same or slightly improves.
+
+CCE replaces "dump the entire file" with "search for the relevant function." The model still gets the code it needs (0.90 Recall@10 in benchmarks). Less irrelevant context means less noise competing for attention, which can improve the model's focus on your actual question.
+
+### How do I increase output token savings?
+
+Set the output compression level in your project config (`cce.yaml`):
+
+```yaml
+compression:
+  output: max       # off | lite | standard | max
+```
+
+Or change it at runtime via the MCP tool:
+
+```
+set_output_level output_level=max
+```
+
+| Level | Savings | What it does |
+|-------|---------|--------------|
+| `off` | 0% | No compression |
+| `lite` | ~25% | Removes filler/hedging/pleasantries + diff-only for code changes |
+| `standard` | ~70% | Drops articles, fragments, short synonyms + diff-only for code |
+| `max` | ~80% | Telegraphic style + diff-only for code |
+
+Default is `standard`. All levels include **code output rules** that instruct the model to show only changed lines (not full file rewrites), which is where most output tokens go in coding sessions. The `max` level produces very terse prose (similar to "caveman mode"). Code blocks, paths, and commands are never compressed regardless of level.
+
+### Where do the savings come from?
+
+Most savings are **input tokens** (what goes into the model):
+
+| Layer | Type | Typical savings |
+|-------|------|-----------------|
+| Retrieval | Input | 94% (full files → relevant chunks) |
+| Chunk compression | Input | 89% (chunks → signatures) |
+| Grammar compression | Input | 13% (article/filler removal) |
+| Turn summarization | Input | varies (session history) |
+| Progressive disclosure | Input | varies (tool payloads) |
+| Output compression | Output | 25-80% (depends on level) |
+
+Output tokens cost 5x more per token (e.g. Opus: $15/1M input vs $75/1M output), so even a small output reduction has outsized cost impact.
+
+---
+
 ## Roadmap
 
 - [x] Multi-repo benchmarks (FastAPI, chi, fiber)

{code_context_engine-0.4.19 → code_context_engine-0.4.21}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "code-context-engine"
-version = "0.4.19"
+version = "0.4.21"
 description = "Save 94% on Claude Code tokens. Index your codebase locally, AI agents search instead of reading files. Reduce Claude API costs, save tokens on Cursor, VS Code, Gemini CLI. Free, open source MCP server."
 readme = {file = "README.md", content-type = "text/markdown"}
 license = "MIT"
@@ -23,7 +23,6 @@ dependencies = [
     "click>=8.1",
     "pyyaml>=6.0",
     "sqlite-vec>=0.1.6",
-    "fastembed>=0.4",
     "numpy>=1.24",
     "tree-sitter>=0.22",
     "tree-sitter-python>=0.21",
@@ -60,6 +59,11 @@ dev = [
     "ruff>=0.13",
 ]
 http = []  # back-compat: aiohttp is now a core dependency
+# Local on-device embedding via fastembed (ONNX). ~172 MB install
+# footprint; needed only if you don't have Ollama running. Without
+# this extra, CCE auto-detects Ollama at localhost:11434 and uses
+# nomic-embed-text via /api/embed.
+local = ["fastembed>=0.4"]
 
 [project.scripts]
 cce = "context_engine.cli:main"

{code_context_engine-0.4.19 → code_context_engine-0.4.21/src/code_context_engine.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code-context-engine
-Version: 0.4.19
+Version: 0.4.21
 Summary: Save 94% on Claude Code tokens. Index your codebase locally, AI agents search instead of reading files. Reduce Claude API costs, save tokens on Cursor, VS Code, Gemini CLI. Free, open source MCP server.
 Author-email: Fazle Elahee <felahee@gmail.com>, Raj <rajkumar.sakti@gmail.com>
 License-Expression: MIT
@@ -21,7 +21,6 @@ License-File: LICENSE
 Requires-Dist: click>=8.1
 Requires-Dist: pyyaml>=6.0
 Requires-Dist: sqlite-vec>=0.1.6
-Requires-Dist: fastembed>=0.4
 Requires-Dist: numpy>=1.24
 Requires-Dist: tree-sitter>=0.22
 Requires-Dist: tree-sitter-python>=0.21
@@ -46,6 +45,8 @@ Requires-Dist: pytest-cov>=5.0; extra == "dev"
 Requires-Dist: pytest-xdist>=3.5; extra == "dev"
 Requires-Dist: ruff>=0.13; extra == "dev"
 Provides-Extra: http
+Provides-Extra: local
+Requires-Dist: fastembed>=0.4; extra == "local"
 Dynamic: license-file
 
 <p align="center">
@@ -119,10 +120,10 @@ Dynamic: license-file
 ```bash
 uv tool install code-context-engine
 cd /path/to/your/project
-cce init
+cce init                              # or: cce init --agent all
 ```
 
-That's it. Claude now searches your index instead of reading entire files. No config needed.
+That's it. Your AI coding agent now searches your index instead of reading entire files. No config needed.
 
 ---
 
@@ -148,23 +149,34 @@ cd /path/to/your/project
 cce init                              # index, install hooks, register MCP server
 ```
 
+**Embedding backends:** CCE auto-detects the best available backend. If you have Ollama running, it uses `nomic-embed-text` with zero extra dependencies. For offline/local embedding without Ollama, install the `[local]` extra:
+
+```bash
+uv tool install "code-context-engine[local]"   # includes fastembed + ONNX Runtime
+```
+
 Restart your editor. Done. Every question now hits the index instead of re-reading files.
 
-`cce init` auto-detects your editor and writes the right config:
+`cce init` auto-detects your editor and writes the right config. To target a
+specific agent, use `--agent claude`, `--agent codex`, `--agent copilot`, or
+`--agent all`.
 
 | Editor | Config written | Instructions |
 |--------|---------------|--------------|
 | Claude Code | `.mcp.json` | `CLAUDE.md` |
-| VS Code / Copilot | `.vscode/mcp.json` | |
+| VS Code / Copilot | `.vscode/mcp.json` | `.github/copilot-instructions.md` |
 | Cursor | `.cursor/mcp.json` | `.cursorrules` |
 | Gemini CLI | `.gemini/settings.json` | `GEMINI.md` |
-| OpenAI Codex | `~/.codex/config.toml` (user-global, per-project section) | |
+| OpenAI Codex | `~/.codex/config.toml` (user-global, per-project section) | `AGENTS.md` |
 | OpenCode | `opencode.json` | |
 | Tabnine | `.tabnine/agent/settings.json` | `TABNINE.md` |
 
 Multiple editors in the same project? All get configured in one command.
 
-**Codex note:** Codex CLI reads MCP servers from `~/.codex/config.toml` only — it has no per-project config. `cce init` adds one `[mcp_servers.cce-<project>-<hash>]` section per project so multiple projects coexist; `cce uninstall` removes only the section for the current project.
+**Codex note:** Codex CLI reads MCP servers from `~/.codex/config.toml` only —
+it has no per-project config. `cce init` adds one `[mcp_servers.cce-<project>-<hash>]`
+section per project so multiple projects coexist; `cce uninstall` removes only
+the section for the current project.
 
 ```
   my-project · 38 queries
@@ -425,11 +437,12 @@ Tell Claude: "switch to max compression" or "turn off compression". Code blocks
 
 | Component | Size |
 |-----------|------|
-| Installed package | ~189 MB (ONNX Runtime is 66 MB of that) |
-| Embedding model (one-time download) | ~60 MB |
+| Core install (Ollama backend) | ~17 MB |
+| With `[local]` extra (fastembed + ONNX) | ~189 MB |
+| Embedding model (one-time download) | ~60 MB (fastembed) or managed by Ollama |
 | Index per project (small/medium/large) | 5-60 MB |
 
-No GPU required. Embedding model runs on CPU via ONNX Runtime.
+No GPU required. With Ollama, embeddings are handled by the Ollama server. With the `[local]` extra, the embedding model runs on CPU via ONNX Runtime.
 
 ---
 
@@ -479,6 +492,55 @@ All other text files are chunked by line range. Binary files are skipped.
 
 ---
 
+## FAQ
+
+### Does CCE affect response quality?
+
+No. Quality stays the same or slightly improves.
+
+CCE replaces "dump the entire file" with "search for the relevant function." The model still gets the code it needs (0.90 Recall@10 in benchmarks). Less irrelevant context means less noise competing for attention, which can improve the model's focus on your actual question.
+
+### How do I increase output token savings?
+
+Set the output compression level in your project config (`cce.yaml`):
+
+```yaml
+compression:
+  output: max       # off | lite | standard | max
+```
+
+Or change it at runtime via the MCP tool:
+
+```
+set_output_level output_level=max
+```
+
+| Level | Savings | What it does |
+|-------|---------|--------------|
+| `off` | 0% | No compression |
+| `lite` | ~25% | Removes filler/hedging/pleasantries + diff-only for code changes |
+| `standard` | ~70% | Drops articles, fragments, short synonyms + diff-only for code |
+| `max` | ~80% | Telegraphic style + diff-only for code |
+
+Default is `standard`. All levels include **code output rules** that instruct the model to show only changed lines (not full file rewrites), which is where most output tokens go in coding sessions. The `max` level produces very terse prose (similar to "caveman mode"). Code blocks, paths, and commands are never compressed regardless of level.
+
+### Where do the savings come from?
+
+Most savings are **input tokens** (what goes into the model):
+
+| Layer | Type | Typical savings |
+|-------|------|-----------------|
+| Retrieval | Input | 94% (full files → relevant chunks) |
+| Chunk compression | Input | 89% (chunks → signatures) |
+| Grammar compression | Input | 13% (article/filler removal) |
+| Turn summarization | Input | varies (session history) |
+| Progressive disclosure | Input | varies (tool payloads) |
+| Output compression | Output | 25-80% (depends on level) |
+
+Output tokens cost 5x more per token (e.g. Opus: $15/1M input vs $75/1M output), so even a small output reduction has outsized cost impact.
+
+---
+
 ## Roadmap
 
 - [x] Multi-repo benchmarks (FastAPI, chi, fiber)

{code_context_engine-0.4.19 → code_context_engine-0.4.21}/src/code_context_engine.egg-info/SOURCES.txt

@@ -65,6 +65,7 @@ src/context_engine/storage/graph_store.py
 src/context_engine/storage/local_backend.py
 src/context_engine/storage/remote_backend.py
 src/context_engine/storage/vector_store.py
+tests/test_cli_init_agents.py
 tests/test_cli_init_probe.py
 tests/test_cli_mcp_config.py
 tests/test_cli_safe_cwd.py

{code_context_engine-0.4.19 → code_context_engine-0.4.21}/src/code_context_engine.egg-info/requires.txt

@@ -1,7 +1,6 @@
 click>=8.1
 pyyaml>=6.0
 sqlite-vec>=0.1.6
-fastembed>=0.4
 numpy>=1.24
 tree-sitter>=0.22
 tree-sitter-python>=0.21
@@ -28,3 +27,6 @@ pytest-xdist>=3.5
 ruff>=0.13
 
 [http]
+
+[local]
+fastembed>=0.4