opencode-rag-plugin 2.12.0 → 2.12.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/ReadMe.md +282 -216
- package/dist/cli/commands/setup.js +83 -10
- package/dist/cli/commands/workspace-helpers.js +3 -0
- package/dist/cli/ollama.d.ts +12 -0
- package/dist/cli/ollama.js +26 -0
- package/dist/cli/prompt.d.ts +37 -0
- package/dist/cli/prompt.js +83 -21
- package/dist/cli/types.d.ts +19 -6
- package/dist/cli/wizard/apply.d.ts +4 -2
- package/dist/cli/wizard/apply.js +12 -3
- package/dist/cli/wizard/flow.d.ts +39 -1
- package/dist/cli/wizard/flow.js +155 -10
- package/dist/cli/wizard/presets.d.ts +55 -0
- package/dist/cli/wizard/presets.js +70 -0
- package/dist/cli/wizard/repair.d.ts +54 -0
- package/dist/cli/wizard/repair.js +266 -0
- package/dist/cli/wizard/types.d.ts +5 -0
- package/dist/cli/workspace.d.ts +24 -7
- package/dist/cli/workspace.js +168 -83
- package/dist/core/auto-scaffold.d.ts +21 -0
- package/dist/core/auto-scaffold.js +80 -0
- package/dist/core/config.d.ts +11 -0
- package/dist/core/config.js +11 -1
- package/dist/core/global-plugin.d.ts +48 -0
- package/dist/core/global-plugin.js +114 -0
- package/dist/core/setup-runtime.js +40 -26
- package/dist/embedder/health.js +44 -2
- package/dist/v2/v2-adapter.js +9 -0
- package/package.json +3 -2
- package/scripts/postinstall-setup.js +16 -0
package/ReadMe.md
CHANGED
|
@@ -1,62 +1,89 @@
|
|
|
1
1
|
# OpenCodeRAG
|
|
2
2
|
|
|
3
|
-
**
|
|
4
|
-
|
|
5
|
-
OpenCodeRAG indexes your repository as AST-aware chunks with embeddings, then answers natural-language queries with the most relevant code, so an agent no longer has to read whole files to find one function. It installs as an [OpenCode](https://opencode.ai) plugin and also runs as an MCP server or a standalone CLI for other AI harnesses. Everything works locally with [Ollama](https://ollama.ai) by default, and small embedding models run fine on a modern CPU — no dedicated GPU required.
|
|
3
|
+
**A local-first toolkit that gives AI coding agents search, memory, judgment, and guardrails.**
|
|
6
4
|
|
|
7
5
|
[](https://www.npmjs.com/package/opencode-rag-plugin)
|
|
6
|
+
[](LICENSE)
|
|
7
|
+
|
|
8
|
+
AI coding agents are capable, but they have four recurring weaknesses: they read whole files to find one function, they forget everything between sessions, they interrupt you with questions they could settle themselves, and they may run risky shell commands without a second opinion.
|
|
9
|
+
|
|
10
|
+
OpenCodeRAG addresses all these problems and more in one package:
|
|
11
|
+
|
|
12
|
+
- **Semantic Search**: retrieval tools that find relevant code parts by a rough description only
|
|
13
|
+
- **Persistent Memory**: vectorized memory, which keeps gotchas and decisions across sessions and automatically injects them into the context when necessary
|
|
14
|
+
- **Knowledge Base**: agents use and maintain a project wiki to understand the code base better
|
|
15
|
+
- **Basic Judgment**: a small local decision model that answers classification and routing questions
|
|
16
|
+
- **Guardrails**: shell guard, which evaluates shell commands for malignancy before they run
|
|
17
|
+
- **Image Description**: describes images with a local vision model for non-multimodal LLMs
|
|
18
|
+
- **Documentation Assistant**: maintains and adds code documentation where it is still missing or unclear
|
|
8
19
|
|
|
9
|
-
|
|
20
|
+
OpenCodeRAG is primarily built as an [OpenCode](https://opencode.ai) plugin. But it can also be run as a MCP server for other AI coding platforms or used as a standalone command-line tool. By default it works fully locally via Ollama, but it can also use OpenAI-compatible APIs.
|
|
10
21
|
|
|
11
|
-
|
|
22
|
+
No GPU is required, although it is recommended when using code and image descriptions. Smaller embedding models can still run fine on a modern CPU.
|
|
23
|
+
|
|
24
|
+
---
|
|
12
25
|
|
|
13
26
|
## Contents
|
|
14
27
|
|
|
15
|
-
- [
|
|
16
|
-
- [Quick
|
|
17
|
-
- [How
|
|
18
|
-
- [
|
|
19
|
-
- [
|
|
20
|
-
- [
|
|
21
|
-
- [
|
|
22
|
-
- [
|
|
23
|
-
- [
|
|
24
|
-
- [
|
|
25
|
-
- [
|
|
26
|
-
- [
|
|
27
|
-
- [
|
|
28
|
-
- [Documentation and Wiki Modes](#documentation-and-wiki-modes)
|
|
29
|
-
- [Image Indexing](#image-indexing)
|
|
30
|
-
- [Web UI](#web-ui)
|
|
31
|
-
- [Evaluation and Calibration](#evaluation-and-calibration)
|
|
28
|
+
- [What you get](#what-you-get)
|
|
29
|
+
- [Quick start](#quick-start)
|
|
30
|
+
- [How it works](#how-it-works)
|
|
31
|
+
- [Ways to use it](#ways-to-use-it)
|
|
32
|
+
- [Capabilities in detail](#capabilities-in-detail)
|
|
33
|
+
- [1. Semantic code search](#1-semantic-code-search)
|
|
34
|
+
- [2. Quirk memory](#2-quirk-memory)
|
|
35
|
+
- [3. Decision model](#3-decision-model)
|
|
36
|
+
- [4. Shell Guard](#4-shell-guard)
|
|
37
|
+
- [5. Documentation and wiki modes](#5-documentation-and-wiki-modes)
|
|
38
|
+
- [6. Image indexing](#6-image-indexing)
|
|
39
|
+
- [7. Web UI, evaluation, and calibration](#7-web-ui-evaluation-and-calibration)
|
|
40
|
+
- [Tool reference](#tool-reference)
|
|
32
41
|
- [Configuration](#configuration)
|
|
33
|
-
- [
|
|
34
|
-
- [
|
|
35
|
-
- [
|
|
36
|
-
- [Contributing and
|
|
42
|
+
- [Privacy and security](#privacy-and-security)
|
|
43
|
+
- [Limitations](#limitations)
|
|
44
|
+
- [Documentation index](#documentation-index)
|
|
45
|
+
- [Contributing and support](#contributing-and-support)
|
|
37
46
|
- [License](#license)
|
|
38
47
|
|
|
39
|
-
|
|
48
|
+
---
|
|
49
|
+
|
|
50
|
+
## What you get
|
|
51
|
+
|
|
52
|
+
| Capability | What it does for your agent | On by default |
|
|
53
|
+
|---|---|:---:|
|
|
54
|
+
| **Search** | Finds the relevant code by meaning and by exact symbol name, instead of reading whole files | Yes |
|
|
55
|
+
| **Memory** | Remembers gotchas, decisions, and past tool failures across sessions | Yes |
|
|
56
|
+
| **Decisions** | Classifies, routes, and scores short text locally, without spending agent tokens | No |
|
|
57
|
+
| **Protection** | Checks every shell command for destructive or malicious intent before it runs | No |
|
|
58
|
+
| **Documentation** | Drives the agent to document undocumented code (`/doc`) and to maintain a project wiki (`/wiki`) | Wiki: yes, Doc: no |
|
|
59
|
+
| **Vision** | Makes screenshots and diagrams searchable through generated descriptions | Yes |
|
|
60
|
+
| **Measurement** | Tracks token use, retrieval quality, and decision accuracy, with a web dashboard | Tools, always available |
|
|
40
61
|
|
|
41
|
-
|
|
42
|
-
- **Search the way code is written.** AST-aware chunking keeps functions and classes intact, and hybrid vector + keyword search catches both meaning ("where is auth handled?") and exact symbol names.
|
|
43
|
-
- **Local by default.** Embeddings, the vector store, and the optional decision model run on your machine. No source code leaves the workspace unless you explicitly configure a hosted provider.
|
|
44
|
-
- **Scales with the repository.** Incremental indexing, a background watcher, and an optional shared ClickHouse store keep large or multi-machine workspaces searchable.
|
|
62
|
+
**Why it is built this way**
|
|
45
63
|
|
|
46
|
-
|
|
64
|
+
- **Fewer tokens.** The agent gets the handful of relevant chunks, not entire files.
|
|
65
|
+
- **Search the way code is written.** AST-aware chunking keeps functions and classes intact. Hybrid vector and keyword search catches both meaning ("where is auth handled?") and exact names.
|
|
66
|
+
- **Local by default.** Embeddings, the vector store, and the optional decision model run on your machine. No source code leaves the workspace unless you configure a hosted provider.
|
|
67
|
+
- **Scales with the repository.** Incremental indexing and a background watcher keep the index current. An optional shared ClickHouse store supports large or multi-machine workspaces.
|
|
47
68
|
|
|
48
|
-
|
|
69
|
+
---
|
|
70
|
+
|
|
71
|
+
## Quick start
|
|
72
|
+
|
|
73
|
+
> **Package name:** only install `opencode-rag-plugin`. The npm package `opencode-rag` is an unrelated, discontinued project by a different author.
|
|
74
|
+
|
|
75
|
+
**Prerequisites:** Node.js v22+ and [Ollama](https://ollama.ai) (the default provider). OpenCode is optional; the CLI and MCP server work without it.
|
|
49
76
|
|
|
50
77
|
```bash
|
|
51
78
|
# 1. Install the plugin and the CLI
|
|
52
79
|
npm install -g opencode-rag-plugin
|
|
53
80
|
|
|
54
81
|
# 2. Set up the runtime, the workspace, and your models
|
|
55
|
-
# (a short interactive wizard
|
|
82
|
+
# (a short interactive wizard guides you through the configuration)
|
|
56
83
|
cd /path/to/your/project
|
|
57
84
|
opencode-rag setup
|
|
58
85
|
|
|
59
|
-
# 3. Build the index
|
|
86
|
+
# 3. Build the index (may take a while)
|
|
60
87
|
opencode-rag index
|
|
61
88
|
|
|
62
89
|
# 4. Search from the terminal
|
|
@@ -65,7 +92,7 @@ opencode-rag query "authentication middleware"
|
|
|
65
92
|
|
|
66
93
|
Example output:
|
|
67
94
|
|
|
68
|
-
```
|
|
95
|
+
```
|
|
69
96
|
Querying: "authentication middleware"
|
|
70
97
|
Top-K: 10
|
|
71
98
|
Searching 1240 indexed chunks...
|
|
@@ -77,30 +104,43 @@ Searching 1240 indexed chunks...
|
|
|
77
104
|
...
|
|
78
105
|
```
|
|
79
106
|
|
|
80
|
-
|
|
107
|
+
Open OpenCode in the same directory and the agent can use the tools right away.
|
|
108
|
+
|
|
109
|
+
<details>
|
|
110
|
+
<summary><strong>What does <code>opencode-rag setup</code> do?</strong></summary>
|
|
111
|
+
|
|
112
|
+
It handles the whole onboarding in one command:
|
|
113
|
+
|
|
114
|
+
- installs or verifies the machine-level runtime in `~/.opencode/`
|
|
115
|
+
- scaffolds the current workspace (`.opencode/` config, plugin entries, skill files)
|
|
116
|
+
- on the first run, or with `--reconfigure`, starts a **model wizard** for the embedding, description, vision, and decision models
|
|
81
117
|
|
|
82
|
-
|
|
118
|
+
A plain re-run only syncs the workspace files. The wizard is scriptable (`--yes`, `--provider`, `--base-url`, `--embedding-model`, `--description off`, and more), and `--skip-runtime` limits the run to the workspace. Use `opencode-rag update` to upgrade the runtime to a newer release.
|
|
83
119
|
|
|
84
|
-
|
|
120
|
+
`pnpm add -g`, `yarn global add`, and `bun add -g` work as drop-in replacements for npm. Setup and update detect which package manager owns the install.
|
|
121
|
+
|
|
122
|
+
</details>
|
|
85
123
|
|
|
86
124
|
### Optional add-ons
|
|
87
125
|
|
|
88
|
-
These
|
|
126
|
+
These are off by default and can be enabled later:
|
|
127
|
+
|
|
128
|
+
| Add-on | Enable with | Requires |
|
|
129
|
+
|---|---|---|
|
|
130
|
+
| [Shell Guard](#4-shell-guard) | `shellGuard.enabled` or `setup --shell-guard on` | tev1 via Ollama ≥ 0.35 |
|
|
131
|
+
| [Decision model](#3-decision-model) | `decision.enabled` or `setup --decision on` | tev1 via Ollama ≥ 0.35 |
|
|
132
|
+
| [Documentation mode](#documentation-mode-doc) | `documentationMode.enabled` | nothing extra |
|
|
133
|
+
| [Shared ClickHouse Vector Database](doc/clickhouse.md) | `vectorStore.provider: "clickhouse"` or `setup --vector-store clickhouse` | a ClickHouse server |
|
|
89
134
|
|
|
90
|
-
|
|
91
|
-
|---|---|---|---|
|
|
92
|
-
| [Shell Guard](#shell-guard-optional) | off | `shellGuard.enabled` (or `setup --shell-guard on`) | tev1 via Ollama ≥ 0.35 |
|
|
93
|
-
| [Decision model](#decision-model-make_decision) | off | `decision.enabled` (or `setup --decision on`) | tev1 via Ollama ≥ 0.35 |
|
|
94
|
-
| [Documentation mode](#documentation-mode-doc) | off | `documentationMode.enabled` | nothing extra |
|
|
95
|
-
| [Shared ClickHouse store](doc/clickhouse.md) | off | `vectorStore.provider: "clickhouse"` (or `setup --vector-store clickhouse`) | a ClickHouse server |
|
|
135
|
+
Two features are **on** by default and worth disabling if they do not fit your setup: [image descriptions](#6-image-indexing) (`imageDescription.enabled`, needs a vision model) and [wiki mode](#wiki-mode-wiki) (`wikiMode.enabled`).
|
|
96
136
|
|
|
97
|
-
|
|
137
|
+
> **Contributors:** clone the repo and run `npm install --legacy-peer-deps; npm run build`. See the [development docs](doc/development.md).
|
|
98
138
|
|
|
99
|
-
|
|
139
|
+
---
|
|
100
140
|
|
|
101
|
-
## How
|
|
141
|
+
## How it works
|
|
102
142
|
|
|
103
|
-
```
|
|
143
|
+
```
|
|
104
144
|
Workspace files
|
|
105
145
|
│ tree-sitter chunking (AST-aware)
|
|
106
146
|
▼
|
|
@@ -111,84 +151,37 @@ Chunks ─────► embeddings ─────► vector store (LanceDB by
|
|
|
111
151
|
Query ─► vector search + keyword search ─► weighted fusion ─► top-K chunks
|
|
112
152
|
```
|
|
113
153
|
|
|
114
|
-
1. **Index
|
|
115
|
-
2. **Retrieve
|
|
116
|
-
3. **Use
|
|
117
|
-
|
|
118
|
-
## Features
|
|
119
|
-
|
|
120
|
-
**Retrieval**
|
|
121
|
-
|
|
122
|
-
- AST chunking for 26 languages via tree-sitter, plus documents (Markdown, LaTeX, PDF, DOCX, Excel) and images.
|
|
123
|
-
- Hybrid search combining vector similarity with TF×IDF keyword matching; the keyword index is repaired from the store whenever it drifts behind it, so the BM25 half never covers only part of the corpus.
|
|
124
|
-
- Retrieval calibration with `opencode-rag eval:tune` against a labelled golden set.
|
|
125
|
-
- Context optimization: dedup, per-file chunk limits, adjacent-chunk merging.
|
|
126
|
-
- Configurable parsers — remap file extensions to any parser via `chunking.parsers` (e.g. `.c` → `cpp`); the override applies to chunking, `get_file_skeleton`, and read labels ([docs](doc/chunking.md#parser-overrides-per-extension-chunkingparsers)).
|
|
127
|
-
|
|
128
|
-
**Agent integration**
|
|
129
|
-
|
|
130
|
-
- OpenCode plugin with three discovery paths: skill files, system-prompt guidance, and on-demand RAG context on `Ctrl+Enter` / `Ctrl+Alt+Enter`.
|
|
131
|
-
- MCP server for Claude Desktop, Cursor, and any other MCP-compatible client.
|
|
132
|
-
- Read-tool override that adds supplementary RAG chunks to normal file reads.
|
|
133
|
-
- TUI settings panel for models, retrieval options, and keybindings.
|
|
134
|
-
- `AGENTS.md` directive: workspace setup merges a tool-usage directive into `AGENTS.md` via sentinel markers.
|
|
135
|
-
|
|
136
|
-
**Memory and decisions**
|
|
137
|
-
|
|
138
|
-
- [Quirk memory](#quirk-memory): persistent, cross-session gotchas and decisions with automatic injection into the agent's context.
|
|
139
|
-
- [Decision model](#decision-model-make_decision): local classification, routing, and scoring of short text — no agent tokens spent.
|
|
140
|
-
- Failed tool calls are recorded as quirks, so a later session starts with the fix already known.
|
|
141
|
-
|
|
142
|
-
**Operations**
|
|
143
|
-
|
|
144
|
-
- Incremental indexing with a file-hash manifest, background watcher, and automatic rebuild on corruption.
|
|
145
|
-
- Optional ClickHouse backend for one shared index across many machines and workspaces, with HNSW ANN, epoch rebuilds, and state sync ([docs](doc/clickhouse.md)).
|
|
146
|
-
- Session-level token and cost analysis: RAG-on vs RAG-off comparison with tiktoken BPE counting.
|
|
147
|
-
- Alternate providers: embedding via Ollama, OpenAI-compatible endpoints, or Cohere; description and vision via Anthropic, Google Gemini, or OpenAI-compatible endpoints, with API-key auto-resolution.
|
|
148
|
-
- Proxy-aware HTTP with a raw-socket localhost bypass.
|
|
154
|
+
1. **Index.** Files are split into semantic chunks, optionally described by a local LLM, embedded, and stored next to a TF×IDF keyword index. A file-hash manifest means only changed files are reprocessed, and a background watcher keeps the index current while you work.
|
|
155
|
+
2. **Retrieve.** The query is embedded and matched against both signals. The scores are fused and post-processed (deduplication, per-file chunk limits, adjacent-chunk merging) to fit the context window.
|
|
156
|
+
3. **Use.** The agent calls `search_semantic`, `get_file_skeleton`, or `find_usages` instead of reading entire files.
|
|
149
157
|
|
|
150
|
-
|
|
158
|
+
The other capabilities build on the same foundation. For example, quirk memories are embedded and stored in the same vector store as your code.
|
|
151
159
|
|
|
152
|
-
|
|
160
|
+
---
|
|
153
161
|
|
|
154
|
-
|
|
162
|
+
## Ways to use it
|
|
155
163
|
|
|
156
|
-
|
|
|
164
|
+
| Mode | Best for | How to start |
|
|
157
165
|
|---|---|---|
|
|
158
|
-
|
|
|
159
|
-
|
|
|
160
|
-
|
|
|
161
|
-
| `describe_image` | Describes an image with the configured vision model | When the task involves a screenshot, diagram, or other asset |
|
|
162
|
-
| `make_decision` | Classifies, routes, or scores short text (needs `decision.enabled`) | When the answer reduces to a choice, a yes/no check, or a rubric score |
|
|
163
|
-
|
|
164
|
-
### Plugin-Only Tools
|
|
165
|
-
|
|
166
|
-
The quirk tools are registered by the OpenCode plugin (not served over MCP):
|
|
167
|
-
|
|
168
|
-
| Tool | What it does |
|
|
169
|
-
|---|---|
|
|
170
|
-
| `recall_quirks` | Recalls stored gotchas, preferences, and decisions from past sessions |
|
|
171
|
-
| `add_quirk` | Stores a new non-obvious fact, workaround, or convention |
|
|
172
|
-
| `update_quirk` | Corrects a stored quirk that is outdated or wrong |
|
|
173
|
-
| `delete_quirk` | Removes a quirk that is fixed, obsolete, or no longer applies |
|
|
166
|
+
| **OpenCode plugin** | Day-to-day agent work with the full feature set (hotkeys, memory, Shell Guard, `/doc`, `/wiki`) | `opencode-rag setup`, then open OpenCode |
|
|
167
|
+
| **MCP server** | Claude Desktop, Cursor, and any other MCP-compatible client | `opencode-rag mcp` |
|
|
168
|
+
| **CLI** | Scripts, CI, and manual exploration | `opencode-rag <command>` |
|
|
174
169
|
|
|
175
170
|
### With OpenCode
|
|
176
171
|
|
|
177
|
-
**Discovery.** Workspace setup creates `.opencode/skills/opencode-rag/SKILL.md` (tool workflow) and `.opencode/skills/make-decision/SKILL.md` (decision-model guidance). Agents load them on demand, so idle sessions pay almost no token cost. When the index contains chunks, a brief tool list is also
|
|
172
|
+
- **Discovery.** Workspace setup creates `.opencode/skills/opencode-rag/SKILL.md` (tool workflow) and `.opencode/skills/make-decision/SKILL.md` (decision-model guidance). Agents load them on demand, so idle sessions pay almost no token cost. When the index contains chunks, a brief tool list is also added to the system prompt. It is skipped when nothing is indexed.
|
|
173
|
+
- **Hotkeys.** `Ctrl+Enter` appends a relevant file list to the prompt you are typing. `Ctrl+Alt+Enter` appends full code chunks. The query is taken from your typed text; if the prompt is empty, a toast reminds you to type first. Results land directly in the prompt as code blocks with file paths, line ranges, and relevance scores.
|
|
174
|
+
- **Read override.** A normal `read` can return the file plus supplementary RAG chunks relevant to the surrounding work.
|
|
175
|
+
- **Settings.** Models, retrieval options, and keybindings are configurable in the TUI settings panel (`Alt+S` or `/rag-settings`).
|
|
176
|
+
- **`AGENTS.md` directive.** Workspace setup merges a tool-usage directive into `AGENTS.md` using sentinel markers.
|
|
178
177
|
|
|
179
|
-
|
|
180
|
-
|
|
181
|
-
**Read override.** A normal `read` can return the file plus supplementary RAG chunks that are relevant to the surrounding work.
|
|
182
|
-
|
|
183
|
-
### With Other MCP Clients
|
|
184
|
-
|
|
185
|
-
<a id="mcp-server"></a>
|
|
178
|
+
### With other MCP clients
|
|
186
179
|
|
|
187
180
|
```bash
|
|
188
181
|
opencode-rag mcp
|
|
189
182
|
```
|
|
190
183
|
|
|
191
|
-
The MCP server is
|
|
184
|
+
The MCP server is only needed when an *external* client connects. Inside OpenCode the tools are registered in-process. The plugin auto-starts the server only when `mcp.enabled` is `true` (default `false`). Clients can also configure it manually, and workspace setup can register it for you.
|
|
192
185
|
|
|
193
186
|
### From the CLI
|
|
194
187
|
|
|
@@ -200,11 +193,26 @@ opencode-rag status # index health and coverage
|
|
|
200
193
|
opencode-rag ui # open the web dashboard
|
|
201
194
|
```
|
|
202
195
|
|
|
203
|
-
Further commands: `list`, `show <file>`, `dump`, `clear`, `describe-image`, `decide`, `mcp`, `update`, `clickhouse`, `quirk`, and the `eval:*` family. Run `opencode-rag --help` or see the [CLI reference](doc/cli.md)
|
|
196
|
+
Further commands: `list`, `show <file>`, `dump`, `clear`, `describe-image`, `decide`, `mcp`, `update`, `clickhouse`, `quirk`, and the `eval:*` family. Run `opencode-rag --help` or see the [CLI reference](doc/cli.md).
|
|
197
|
+
|
|
198
|
+
---
|
|
199
|
+
|
|
200
|
+
## Capabilities in detail
|
|
201
|
+
|
|
202
|
+
### 1. Semantic code search
|
|
203
|
+
|
|
204
|
+
The core of the project. It answers natural-language queries with the most relevant code.
|
|
204
205
|
|
|
205
|
-
|
|
206
|
+
- **Languages and formats.** AST chunking for 26 languages via tree-sitter, plus documents (Markdown, LaTeX, PDF, DOCX, Excel) and images.
|
|
207
|
+
- **Hybrid search.** Vector similarity combined with TF×IDF keyword matching. The keyword index is repaired from the store whenever it drifts behind, so the keyword half never covers only part of the corpus.
|
|
208
|
+
- **Context optimization.** Deduplication, per-file chunk limits, and adjacent-chunk merging.
|
|
209
|
+
- **Configurable parsers.** Remap file extensions to any parser via `chunking.parsers` (for example `.c` → `cpp`). The override applies to chunking, `get_file_skeleton`, and read labels ([docs](doc/chunking.md#parser-overrides-per-extension-chunkingparsers)).
|
|
210
|
+
- **Alternate providers.** Embeddings via Ollama, OpenAI-compatible endpoints, or Cohere. Descriptions and vision via Anthropic, Google Gemini, or OpenAI-compatible endpoints.
|
|
211
|
+
- **Scale.** Incremental indexing, a background watcher, and automatic rebuild on corruption. The optional ClickHouse backend provides one shared index across machines and workspaces, with HNSW ANN, epoch rebuilds, and state sync ([docs](doc/clickhouse.md)).
|
|
206
212
|
|
|
207
|
-
|
|
213
|
+
### 2. Quirk memory
|
|
214
|
+
|
|
215
|
+
Quirk memory gives the agent a **persistent, cross-session memory** of non-obvious facts: gotchas, preferences, decisions, and environment constraints. Quirks are embedded in the same vector store as your code and injected into the agent's context when their relevance clears a configurable threshold. The agent stops repeating the same mistake and accumulates project knowledge over time.
|
|
208
216
|
|
|
209
217
|
**Enabled by default.** Configure it in `opencode-rag.json`:
|
|
210
218
|
|
|
@@ -226,35 +234,36 @@ Quirk memory gives your agent a **persistent, cross-session memory** of non-obvi
|
|
|
226
234
|
}
|
|
227
235
|
```
|
|
228
236
|
|
|
229
|
-
**
|
|
237
|
+
**Three ways memory works**
|
|
230
238
|
|
|
231
|
-
|
|
239
|
+
| Mechanism | What happens |
|
|
240
|
+
|---|---|
|
|
241
|
+
| **Auto-injection** | On every user message, quirks related to the query and the agent's last response are injected if their vector similarity reaches `autoInjectMinScore` (0.75). Each quirk is injected at most once per session. A latency budget (`autoInjectLatencyBudgetMs`, 2000 ms) keeps a slow embedder from blocking messages. |
|
|
242
|
+
| **Learning from failures** | When a tool call fails, the plugin looks for a matching quirk and injects it into the next request (`injectOnToolError`). If none exists, it writes one from a deterministic template built from the tool name and error text, with no LLM involved (`autoCreateOnToolError`). These quirks are tagged `tool-error`, kept for *future* sessions, and excluded from generic auto-injection. Creation is limited to 2 per session, with a 10-minute cooldown per error, and is skipped if a quirk for the same tool and cause already exists. |
|
|
243
|
+
| **Prevention** | Known durable failure patterns are injected into the system prompt *before* the model picks a tool (`toolErrorProactiveInject`), scoped to the tools the session can actually call. Transient causes such as rate limits are never warned about in advance. The first occurrence of a failure is unavoidable; every later session is warned up front. |
|
|
232
244
|
|
|
233
|
-
**
|
|
245
|
+
**Safety.** Every `add_quirk` and every content-changing `update_quirk` passes an immutable trust monitor that rejects destructive patterns (`rm -rf`, `force push`, `bypass security`).
|
|
234
246
|
|
|
235
|
-
**
|
|
247
|
+
**Manual control from the CLI**
|
|
236
248
|
|
|
237
249
|
```bash
|
|
238
250
|
opencode-rag quirk add "npm needs --legacy-peer-deps" --type gotcha --tag installation
|
|
239
251
|
opencode-rag quirk list
|
|
240
252
|
opencode-rag quirk update <id> --content "..." --type decision
|
|
241
253
|
opencode-rag quirk rm <id>
|
|
242
|
-
opencode-rag quirk lint # flag low-confidence
|
|
254
|
+
opencode-rag quirk lint # flag low-confidence, stale, or duplicate quirks
|
|
243
255
|
opencode-rag quirk test "npm needs --legacy-peer-deps"
|
|
244
|
-
# ✓ Quirk has been appended:
|
|
245
|
-
# [gotcha] npm needs --legacy-peer-deps (installation)
|
|
246
|
-
# 99% confidence
|
|
247
256
|
```
|
|
248
257
|
|
|
249
|
-
See [
|
|
258
|
+
Manual `recall_quirks` calls use the looser `recallMinScore` (0.72). Raise it to 0.85 to keep unrelated quirks out of unrelated tasks. See the [plugin docs](doc/plugin.md#9-quirk-memory-experiential-memory) and the [CLI reference](doc/cli.md#quirk).
|
|
250
259
|
|
|
251
|
-
|
|
260
|
+
### 3. Decision model
|
|
252
261
|
|
|
253
|
-
|
|
262
|
+
A small local model answers fast **classification, routing, policy, and scoring questions**, so the agent does not spend its own tokens on them. OpenCodeRAG uses Together AI's [tev1](https://ollama.com/library/tev1) via Ollama's `/v1/systemone` endpoint. Unlike chat models, tev1 scores a short `state` against 1 to 64 named questions and returns the chosen option with probabilities, typically in **40 to 150 ms warm**.
|
|
254
263
|
|
|
255
264
|
| Question type | Use it for | Example |
|
|
256
265
|
|---|---|---|
|
|
257
|
-
| `choice` | Pick one of 2
|
|
266
|
+
| `choice` | Pick one of 2 to 24 options | "Which support intent is this?" → duplicate_charge / cancel / none |
|
|
258
267
|
| `noul` | True/false probability | "Does the customer explicitly ask for a refund?" |
|
|
259
268
|
| `score` | Place the input on a rubric | "How severe is this incident?" → cosmetic … critical |
|
|
260
269
|
|
|
@@ -271,21 +280,21 @@ One call, two questions:
|
|
|
271
280
|
}
|
|
272
281
|
```
|
|
273
282
|
|
|
274
|
-
```
|
|
275
|
-
|
|
283
|
+
```
|
|
284
|
+
Decision — ollama/tev1:0.8b
|
|
276
285
|
|
|
277
|
-
-
|
|
278
|
-
-
|
|
286
|
+
- intent = duplicate_charge (confidence 0.97)
|
|
287
|
+
- refund = true (p=0.96)
|
|
279
288
|
```
|
|
280
289
|
|
|
281
|
-
**
|
|
290
|
+
**Setup**
|
|
282
291
|
|
|
283
292
|
```bash
|
|
284
|
-
ollama pull tev1:0.8b # 812 MB, fast
|
|
285
|
-
ollama pull tev1:4b # 4.4 GB, more accurate
|
|
293
|
+
ollama pull tev1:0.8b # 812 MB, fast: good for quick labels and CI
|
|
294
|
+
ollama pull tev1:4b # 4.4 GB, more accurate: recommended for scoring
|
|
286
295
|
```
|
|
287
296
|
|
|
288
|
-
**Disabled by default
|
|
297
|
+
Requires Ollama ≥ 0.35. **Disabled by default.** Opt in via `decision.enabled`:
|
|
289
298
|
|
|
290
299
|
```json
|
|
291
300
|
{
|
|
@@ -299,15 +308,20 @@ ollama pull tev1:4b # 4.4 GB, more accurate — recommended when scoring
|
|
|
299
308
|
}
|
|
300
309
|
```
|
|
301
310
|
|
|
302
|
-
**Using it well
|
|
311
|
+
**Using it well**
|
|
303
312
|
|
|
304
|
-
|
|
313
|
+
- Always include a `none` / "cannot be determined" option.
|
|
314
|
+
- Keep `state` to the relevant excerpt (effective context is about 2k tokens).
|
|
315
|
+
- Treat `confidence < ~0.3` as undecided.
|
|
316
|
+
- Do not use it for factual recall, or as the only check for high-stakes decisions.
|
|
305
317
|
|
|
306
|
-
|
|
318
|
+
**Pre-ask routing (optional).** With `decision.routeBeforeAsking: true`, the agent is told to resolve option choices through `make_decision` before asking you. It proceeds on a confident answer and asks only when the model is undecided or the choice is a matter of preference. Off by default.
|
|
307
319
|
|
|
308
|
-
|
|
320
|
+
`opencode-rag decide` exposes the same engine from the CLI, and workspace setup creates a dedicated `make-decision` agent skill. See the [plugin docs](doc/plugin.md#make_decision) and the [configuration reference](doc/configuration.md#decision).
|
|
309
321
|
|
|
310
|
-
|
|
322
|
+
### 4. Shell Guard
|
|
323
|
+
|
|
324
|
+
The same decision model can vet **every shell command before it runs**. With `shellGuard.enabled: true`, each `shell` / `bash` call is classified for destructive and malicious intent. If `p(destructive)` or `p(malicious)` reaches the threshold, the command is escalated to OpenCode's confirmation prompt together with the full verdict (probabilities plus a risk category). Otherwise it runs unchanged.
|
|
311
325
|
|
|
312
326
|
```json
|
|
313
327
|
{
|
|
@@ -320,74 +334,64 @@ The same local decision model can vet **every shell command before it runs**. Wi
|
|
|
320
334
|
}
|
|
321
335
|
```
|
|
322
336
|
|
|
323
|
-
|
|
324
|
-
|
|
325
|
-
|
|
326
|
-
|
|
327
|
-
|
|
328
|
-
|
|
329
|
-
|
|
337
|
+
| Aspect | Behavior |
|
|
338
|
+
|---|---|
|
|
339
|
+
| **Default** | Off. Enabling it adds one local model call to every shell command. |
|
|
340
|
+
| **Speed** | A warm verdict takes about 200 to 230 ms. Example: `rm -rf ./dist` → 0.96 destructive; `ls -la src` → 0.23, allowed. |
|
|
341
|
+
| **On failure** | Fail-open by default (`onError: "allow"`): if the classifier is down or times out, the command runs and a warning is logged. Set `"ask"` to require confirmation instead. |
|
|
342
|
+
| **Cache** | Verdicts are cached for 10 minutes (256 entries). The key includes the provider and model, and cached probabilities are re-scored against the current threshold on every call. |
|
|
343
|
+
| **Scope** | Put the block in `~/.config/opencode/opencode-rag.json` to apply it to every workspace. A workspace config can still override or disable it. |
|
|
344
|
+
| **Live config** | Edits to `opencode-rag.json` apply without a restart. |
|
|
345
|
+
| **Backend** | Defaults to the `decision` section. Any `/v1/systemone` endpoint works, for example llama-swap with `"baseUrl": "http://localhost:11437", "model": "Clef-Flash"`. |
|
|
346
|
+
|
|
347
|
+
Every verdict is logged under `scope: shell.guard`, so you can tune the threshold against real commands. Shell Guard is a safety net, not a sandbox. See the [configuration reference](doc/configuration.md#shellguard) and the [plugin docs](doc/plugin.md#shell-guard-command-vetting).
|
|
330
348
|
|
|
331
|
-
|
|
349
|
+
### 5. Documentation and wiki modes
|
|
332
350
|
|
|
333
|
-
|
|
351
|
+
Two optional modes turn the agent into a documentation maintainer.
|
|
334
352
|
|
|
335
|
-
|
|
353
|
+
#### Documentation mode (`/doc`)
|
|
336
354
|
|
|
337
|
-
When `documentationMode.enabled` is `true`, the plugin
|
|
355
|
+
Off by default. When `documentationMode.enabled` is `true`, the plugin adds a `/doc` slash command that drives the agent to add JSDoc/TSDoc comments to undocumented source files. No agent tools are registered; it works entirely through the slash command and a documentation system prompt.
|
|
338
356
|
|
|
339
357
|
```json
|
|
340
|
-
{
|
|
341
|
-
"documentationMode": {
|
|
342
|
-
"enabled": true,
|
|
343
|
-
"batchSize": 5
|
|
344
|
-
}
|
|
345
|
-
}
|
|
358
|
+
{ "documentationMode": { "enabled": true, "batchSize": 5 } }
|
|
346
359
|
```
|
|
347
360
|
|
|
348
|
-
**Workflow
|
|
361
|
+
**Workflow**
|
|
349
362
|
|
|
350
|
-
|
|
363
|
+
1. Type `/doc` to list all undocumented files, grouped by subdirectory.
|
|
364
|
+
2. The agent picks a subdirectory and documents every public symbol, preserving existing comments and implementation code.
|
|
365
|
+
3. Type `/doc src/auth/` to mark that subdirectory complete.
|
|
351
366
|
|
|
352
|
-
|
|
367
|
+
Progress is saved in `.opencode/rag_db/doc-mode-progress.json`, so later sessions resume where you left off. See the [plugin docs](doc/plugin.md#5-documentation-mode--slash-command-doc).
|
|
353
368
|
|
|
354
|
-
|
|
369
|
+
#### Wiki mode (`/wiki`)
|
|
355
370
|
|
|
356
|
-
|
|
357
|
-
{
|
|
358
|
-
"wikiMode": {
|
|
359
|
-
"enabled": true
|
|
360
|
-
}
|
|
361
|
-
}
|
|
362
|
-
```
|
|
371
|
+
On by default. When `wikiMode.enabled` is `true`, the plugin injects a wiki-maintainer system prompt. The agent builds and maintains a persistent knowledge wiki in `.opencode/wiki/`: interlinked markdown pages that synthesize knowledge from the codebase, docs, and conversations.
|
|
363
372
|
|
|
364
373
|
| Command | Action |
|
|
365
374
|
|---|---|
|
|
366
|
-
| `/wiki` | Show wiki status (page count, subdirectories, index
|
|
375
|
+
| `/wiki` | Show wiki status (page count, subdirectories, index and log presence, latest log entry) |
|
|
367
376
|
| `/wiki seed` | Generate the initial wiki from the README, file structure, and code patterns |
|
|
368
|
-
| `/wiki lint` | Health-check for orphan pages, stale source
|
|
369
|
-
|
|
370
|
-
The agent maintains all wiki pages during normal coding sessions; you never write wiki pages yourself. The wiki is git-trackable in `.opencode/`, so every edit is a diff. See [Plugin documentation](doc/plugin.md#6-wiki-mode--slash-command-wiki) for the full protocol.
|
|
371
|
-
|
|
372
|
-
## Image Indexing
|
|
377
|
+
| `/wiki lint` | Health-check for orphan pages, stale source references, contradictions, and missing cross-links |
|
|
373
378
|
|
|
374
|
-
|
|
379
|
+
The agent maintains the pages during normal coding sessions; you do not write them yourself. The wiki lives in `.opencode/`, so it is git-trackable and every edit is a diff. See the [plugin docs](doc/plugin.md#6-wiki-mode--slash-command-wiki).
|
|
375
380
|
|
|
376
|
-
|
|
381
|
+
### 6. Image indexing
|
|
377
382
|
|
|
378
|
-
|
|
383
|
+
Image files (PNG, JPEG, WebP, and others) are sent to a vision-capable LLM, and the generated descriptions are stored as searchable chunks. Visual assets then become discoverable with natural-language queries such as "login screen screenshot" or "architecture diagram". The `describe_image` tool also lets an agent inspect an image on demand.
|
|
379
384
|
|
|
380
|
-
|
|
385
|
+
- **Providers:** Ollama, OpenAI, Anthropic, Google Gemini, and OpenCode Zen (`opencode` / `opencode-go`) compatible providers.
|
|
386
|
+
- **On by default.** Set `imageDescription.enabled: false` to skip image files entirely. This is recommended if you have no vision model or no GPU.
|
|
381
387
|
|
|
382
|
-
|
|
388
|
+
### 7. Web UI, evaluation, and calibration
|
|
383
389
|
|
|
384
|
-
|
|
390
|
+
**Web UI.** A browser dashboard for exploring the vector database: browse, visualize, and inspect chunks, and evaluate OpenCode sessions by retrieved chunks and consumed tokens. Launch it with `opencode-rag ui`. See the [Web UI docs](doc/webui.md).
|
|
385
391
|
|
|
386
|
-
|
|
392
|
+
[](doc/assets/webui-3d.png)
|
|
387
393
|
|
|
388
|
-
|
|
389
|
-
|
|
390
|
-
OpenCodeRAG tracks token usage, RAG injection overhead, and costs across sessions, so you can measure whether semantic retrieval actually saves tokens.
|
|
394
|
+
**Does it actually save tokens?** Session-level analysis compares RAG-on against RAG-off, using tiktoken BPE (`cl100k_base`) for code tokenization:
|
|
391
395
|
|
|
392
396
|
```bash
|
|
393
397
|
opencode-rag eval:sessions # list sessions
|
|
@@ -395,17 +399,69 @@ opencode-rag eval:analyze <id> # detailed breakdown
|
|
|
395
399
|
opencode-rag eval:compare <A> <B> # side-by-side comparison
|
|
396
400
|
```
|
|
397
401
|
|
|
398
|
-
|
|
402
|
+
**Is retrieval good enough?** A separate harness measures quality:
|
|
403
|
+
|
|
404
|
+
| Command | Purpose |
|
|
405
|
+
|---|---|
|
|
406
|
+
| `opencode-rag eval:gate` | Runs the labelled golden set and fails when Hit@5, MRR, or nDCG@10 drop below the documented floors |
|
|
407
|
+
| `opencode-rag eval:decide` | Measures the decision model's accuracy, ECE, and Brier score on a labelled calibration set |
|
|
408
|
+
| `opencode-rag eval:tune` | Sweeps the retrieval fusion weights against the golden set and reports the best configuration for your setup |
|
|
409
|
+
|
|
410
|
+
The shipped `keywordWeight=0.4` is a default, not an optimum (on a code embedder it costs about 8 Hit@5 points), so measure instead of guessing. See the [evaluation docs](doc/evaluation.md).
|
|
411
|
+
|
|
412
|
+
---
|
|
413
|
+
|
|
414
|
+
## Tool reference
|
|
415
|
+
|
|
416
|
+
### MCP tools (plugin and MCP server)
|
|
417
|
+
|
|
418
|
+
Inside OpenCode the plugin registers these in-process. Over MCP they are served by `opencode-rag mcp`.
|
|
419
|
+
|
|
420
|
+
| Tool | What it does | When the agent uses it |
|
|
421
|
+
|---|---|---|
|
|
422
|
+
| `search_semantic` | Hybrid vector and keyword search over the indexed code | Before a code task, instead of reading whole files |
|
|
423
|
+
| `get_file_skeleton` | AST outline of a file (functions, classes, methods) | To orient in a large file before reading it |
|
|
424
|
+
| `find_usages` | Every reference to a symbol | Before editing a function, class, or variable |
|
|
425
|
+
| `describe_image` | Describes an image with the configured vision model | When the task involves a screenshot, diagram, or other asset |
|
|
426
|
+
| `make_decision` | Classifies, routes, or scores short text (needs `decision.enabled`) | When the answer reduces to a choice, a yes/no check, or a rubric score |
|
|
427
|
+
|
|
428
|
+
### Plugin-only tools (OpenCode)
|
|
399
429
|
|
|
400
|
-
|
|
430
|
+
Registered by the OpenCode plugin, not served over MCP.
|
|
401
431
|
|
|
402
|
-
|
|
403
|
-
|
|
404
|
-
|
|
432
|
+
| Tool | What it does |
|
|
433
|
+
|---|---|
|
|
434
|
+
| `recall_quirks` | Recalls stored gotchas, preferences, and decisions from past sessions |
|
|
435
|
+
| `add_quirk` | Stores a new non-obvious fact, workaround, or convention |
|
|
436
|
+
| `update_quirk` | Corrects a stored quirk that is outdated or wrong |
|
|
437
|
+
| `delete_quirk` | Removes a quirk that is fixed, obsolete, or no longer applies |
|
|
438
|
+
|
|
439
|
+
### Slash commands and hotkeys (OpenCode)
|
|
440
|
+
|
|
441
|
+
Default hotkeys and slash commands:
|
|
442
|
+
|
|
443
|
+
| Input | Action |
|
|
444
|
+
|---|---|
|
|
445
|
+
| `Ctrl+Enter` | Append a relevant file list to the prompt |
|
|
446
|
+
| `Ctrl+Alt+Enter` | Append full code chunks to the prompt |
|
|
447
|
+
| `/rag-settings` or `Alt+S` | Open the settings panel |
|
|
448
|
+
| `/doc` | Documentation mode (if enabled) |
|
|
449
|
+
| `/wiki`, `/wiki seed`, `/wiki lint` | Wiki mode |
|
|
450
|
+
|
|
451
|
+
Hotkeys can be changed via /rag-settings.
|
|
452
|
+
|
|
453
|
+
---
|
|
405
454
|
|
|
406
455
|
## Configuration
|
|
407
456
|
|
|
408
|
-
Settings
|
|
457
|
+
Settings are stored as JSON (no comments).
|
|
458
|
+
|
|
459
|
+
| File | Purpose |
|
|
460
|
+
|---|---|
|
|
461
|
+
| `.opencode/opencode-rag.json` | Workspace config (canonical) |
|
|
462
|
+
| `~/.config/opencode/opencode-rag.json` | Machine-wide settings (Shell Guard, provider choices) inherited by every workspace |
|
|
463
|
+
|
|
464
|
+
Shipped defaults:
|
|
409
465
|
|
|
410
466
|
```json
|
|
411
467
|
{
|
|
@@ -420,49 +476,59 @@ Settings live in JSON (no comments). The workspace file `.opencode/opencode-rag.
|
|
|
420
476
|
}
|
|
421
477
|
```
|
|
422
478
|
|
|
423
|
-
The [
|
|
479
|
+
The [configuration reference](doc/configuration.md) documents every option (embedding, indexing, retrieval, description, image description, decision, Shell Guard, plugin) and how the global and workspace layers merge.
|
|
480
|
+
|
|
481
|
+
---
|
|
482
|
+
|
|
483
|
+
## Privacy and security
|
|
484
|
+
|
|
485
|
+
- **100% local by default.** Embeddings are generated locally via Ollama, and the vector database stays in your project directory. No source code or embeddings leave your machine unless you explicitly configure a third-party API.
|
|
486
|
+
- **Shell Guard** sends command text only to the decision-model endpoint you configure (local Ollama or a local proxy).
|
|
487
|
+
- **Decision model** is only asked about short excerpts that you or the agent pass in.
|
|
488
|
+
- **Quirk memory** writes pass an immutable trust monitor that rejects destructive patterns.
|
|
489
|
+
|
|
490
|
+
---
|
|
491
|
+
|
|
492
|
+
## Limitations
|
|
493
|
+
|
|
494
|
+
- **Retrieval quality depends on the embedding model.** Small CPU-friendly models trade accuracy for speed. Measure with `eval:gate` and `eval:tune` rather than assuming a default.
|
|
495
|
+
- **Image descriptions need a vision model.** This is a feature that meaningfully wants a GPU to be pleasant. Disable it with `imageDescription.enabled: false` if you have none.
|
|
496
|
+
- **Shell Guard costs one model call per shell command** (about 200 ms warm) and fails open by default. It is a safety net, not a sandbox.
|
|
497
|
+
- **The decision model supports only Ollama's `/v1/systemone` endpoint** for now.
|
|
498
|
+
- **ClickHouse is opt-in** and needs a running server. LanceDB is the default and needs no separate installation.
|
|
424
499
|
|
|
425
|
-
|
|
500
|
+
---
|
|
501
|
+
|
|
502
|
+
## Documentation index
|
|
503
|
+
|
|
504
|
+
This README is the entry point. Deep dives live in [`doc/`](doc).
|
|
426
505
|
|
|
427
506
|
| Document | Contents |
|
|
428
507
|
|---|---|
|
|
429
508
|
| [Architecture](doc/architecture.md) | Module design, data flow, tech stack |
|
|
430
509
|
| [Installation](doc/installation.md) | Full install guide, global setup, uninstall |
|
|
431
|
-
| [Configuration](doc/configuration.md) | All options
|
|
510
|
+
| [Configuration](doc/configuration.md) | All options |
|
|
432
511
|
| [Chunking](doc/chunking.md) | Language matrix, adding new chunkers, custom chunkers |
|
|
433
512
|
| [Embedding](doc/embedding.md) | Providers, model recommendations, proxy, dimension probing |
|
|
434
|
-
| [ClickHouse store](doc/clickhouse.md) | Central vector store
|
|
513
|
+
| [ClickHouse store](doc/clickhouse.md) | Central vector store: setup, epochs, ANN, multi-machine sync |
|
|
435
514
|
| [Retrieval](doc/retrieval.md) | Pipeline, hybrid search, score fusion, caching |
|
|
436
515
|
| [Plugin](doc/plugin.md) | OpenCode integration, tools, hooks, TUI, troubleshooting |
|
|
437
|
-
| [CLI
|
|
516
|
+
| [CLI reference](doc/cli.md) | All commands, options, examples |
|
|
438
517
|
| [Web UI](doc/webui.md) | Dashboard, chunk browser, file explorer, compare view |
|
|
439
518
|
| [Evaluation](doc/evaluation.md) | Token analysis, session logging, benchmark runner, accuracy guide |
|
|
440
519
|
| [Development](doc/development.md) | Setup, testing, conventions, adding providers |
|
|
441
520
|
| [Troubleshooting](doc/troubleshooting.md) | Common issues, logging, debugging |
|
|
442
|
-
| [Roadmap](doc/roadmap.md) | Completed items, short
|
|
443
|
-
|
|
444
|
-
## Privacy and Security
|
|
445
|
-
|
|
446
|
-
**100% local by default.** Embeddings are generated locally via Ollama, and the vector database stays in your project directory. **No source code or embeddings leave your machine** unless you explicitly configure a third-party API. The optional [Shell Guard](#shell-guard-optional) likewise sends command text only to the decision-model endpoint you configure (local Ollama or a local proxy).
|
|
447
|
-
|
|
448
|
-
Every quirk written to memory passes an immutable trust monitor that rejects destructive patterns, and the decision model is only ever asked about short excerpts you (or the agent) pass in.
|
|
449
|
-
|
|
450
|
-
## Limitations and Non-Goals
|
|
521
|
+
| [Roadmap](doc/roadmap.md) | Completed items, short-, mid-, and long-term plans |
|
|
451
522
|
|
|
452
|
-
|
|
453
|
-
- **Retrieval quality depends on the embedding model.** Small CPU-friendly models trade accuracy for speed; measure with `eval:gate` and `eval:tune` rather than assuming a default.
|
|
454
|
-
- **Image descriptions need a vision model.** They are on by default; set `imageDescription.enabled: false` if you have none — it is the one feature that meaningfully wants a GPU to be pleasant.
|
|
455
|
-
- **Shell Guard costs one model call per shell command** (~200 ms warm) and fails open by default; it is a safety net, not a sandbox.
|
|
456
|
-
- **The decision model currently supports Ollama's `/v1/systemone` endpoint only.**
|
|
457
|
-
- **The ClickHouse backend is opt-in** and requires a running ClickHouse server; LanceDB is the default and needs no server.
|
|
523
|
+
---
|
|
458
524
|
|
|
459
|
-
## Contributing and
|
|
525
|
+
## Contributing and support
|
|
460
526
|
|
|
461
|
-
- **Development setup, conventions,
|
|
527
|
+
- **Development setup, conventions, testing:** [doc/development.md](doc/development.md)
|
|
462
528
|
- **Troubleshooting and logging:** [doc/troubleshooting.md](doc/troubleshooting.md)
|
|
463
|
-
- **
|
|
529
|
+
- **Bugs and feature requests:** [GitHub Issues](https://github.com/MrDoe/OpenCodeRAG/issues)
|
|
464
530
|
- **Roadmap:** [doc/roadmap.md](doc/roadmap.md)
|
|
465
531
|
|
|
466
532
|
## License
|
|
467
533
|
|
|
468
|
-
MIT
|
|
534
|
+
[MIT](LICENSE)
|