dsh-codebase-chat 0.23.0 → 0.25.0

package/README.md

@@ -28,14 +28,15 @@
 npx dsh-codebase-chat-mcp setup
 ```
 
-The wizard detects **Claude, Cursor, Windsurf and VS Code**, writes the MCP config, done.
-No JSON to edit — and **no API key**: in `promptOnly` mode your host model does the thinking.
+The wizard detects **Claude, Cursor, Windsurf, VS Code, Zed, Gemini CLI, Kiro, Cline and Roo Code**, asks how you want answers (host model, API key, or offline local model), writes the MCP config, done.
+No JSON to edit — and **no API key**: in `promptOnly` mode your host model does the thinking,
+or go **fully offline** with the embedded local model (`localLlm`) — no key, no host, no cloud.
 
 Other paths — DeepSeek Harness plugin · CLI · from source · manual config: **[Reference](#reference)**.
 
 <p align="center">
-  <img src="docs/assets/demo.gif" alt="dsh-codebase-chat CLI demo" width="840"><br>
-  <em>Live terminal capture — <a href="docs/assets/demo-mcp.gif">MCP session</a> · <a href="docs/assets/demo-fr.gif">French mode</a></em>
+  <img src="docs/assets/demo-conv.gif" alt="dsh-codebase-chat real MCP session on a 422-file codebase" width="840"><br>
+  <em>Real MCP session on a real 422-file codebase — <code>codebase_health</code> finds 324 circular deps, <code>codebase_chat</code> answers with <code>[source: file:line]</code> receipts · <a href="docs/assets/demo-power.gif">PR review (--diff + --watch)</a> · <a href="docs/assets/demo.gif">CLI tour</a> · <a href="docs/assets/demo-mcp.gif">MCP stdio</a> · <a href="docs/assets/demo-fr.gif">French mode</a></em>
 </p>
 
 ## What a real session looks like
@@ -97,6 +98,7 @@ Every answer from `codebase_chat` arrives with `[source: file:line]` receipts yo
 | Code stays on your machine | ❌ | ❌ | ✅ |
 | Inside Claude / Cursor / Windsurf | ❌ | ~ | ✅ |
 | Deterministic health score, no LLM | ❌ | ❌ | ✅ |
+| Answers fully offline (embedded LLM) | ❌ | ❌ | ✅ |
 | Free — no API key, no account | ~ | ❌ | ✅ |
 
 ## How it works
@@ -107,7 +109,7 @@ Every answer from `codebase_chat` arrives with `[source: file:line]` receipts yo
 
 `/codebase-apply` writes safely — **dry-run** · **`.dsh-backups/`** before overwrite · **protected paths** · never outside the project.
 
-## The 12 tools
+## The 13 tools
 
 | Understand | Decide | Act | Explore |
 | --- | --- | --- | --- |
@@ -115,8 +117,9 @@ Every answer from `codebase_chat` arrives with `[source: file:line]` receipts yo
 | `codebase_search` | `codebase_audit` | `codebase_tasks` | `codebase_crea` |
 | `codebase_explain` | `codebase_report` | | |
 | `codebase_health` | `codebase_ceo` | | |
+| `codebase_impact` | | | |
 
-Same engine, three surfaces: **MCP tools** in your IDE, **slash commands** in DeepSeek Harness, **CLI flags** anywhere. Every tool takes `lang` (`fr`/`en`), `embed`, `promptOnly`, `maxTokens`.
+Same engine, three surfaces: **MCP tools** in your IDE, **slash commands** in DeepSeek Harness, **CLI flags** anywhere. Every tool takes `lang` (`fr`/`en`), `embed`, `promptOnly`, `localLlm`, `maxTokens`.
 
 ## Reference
 
@@ -139,6 +142,7 @@ npx dsh-codebase-chat --project C:\my-app --ask "how is auth handled?"
 npx dsh-codebase-chat --project C:\my-app --health   # offline, no LLM
 npx dsh-codebase-chat --project C:\my-app --health --diff main   # only what changed
 npx dsh-codebase-chat --project C:\my-app --watch    # index stays hot while you code
+npx dsh-codebase-chat --project C:\my-app --prompt intelligence   # same banner brief the IDE gets — pipe to any LLM
 ```
 
 **From source**
@@ -222,6 +226,7 @@ dsh --profile headless '/codebase-git --project C:\my-app'
 | `DEEPSEEK_API_KEY` / `OPENAI_API_KEY` | — | Direct-LLM mode only |
 | `DEEPSEEK_BASE_URL` / `OPENAI_BASE_URL` | `https://api.deepseek.com/v1` | Custom endpoint |
 | `CODEBASE_MODEL` | `deepseek-chat` | Model for direct-LLM mode |
+| `CODEBASE_LOCAL_LLM` | — | `1` enables the embedded local model (offline answers); `hf:owner/repo:QUANT` or a `.gguf` path picks another model |
 
 </details>
 
@@ -265,10 +270,10 @@ pnpm install && pnpm build && pnpm test && pnpm typecheck
 <br>
 
 **Does it send my code to the cloud?**
-No. Indexing, retrieval, and prompt building run on your machine. In prompt-only mode, nothing leaves it at all.
+Indexing, retrieval, and prompt building all run on your machine. In prompt-only mode the server makes no network calls itself — the assembled context is read by your host model (cloud or local, your choice). For zero-network answers end to end, enable the embedded local model (`localLlm`).
 
 **Do I need an API key?**
-Not for the MCP server — without a key it returns the built prompt to the host model. A key is only needed for direct LLM calls. Inside DeepSeek Harness, the plugin uses your configured model.
+No — three ways to get answers: the host model (`promptOnly`, best quality), a DeepSeek/OpenAI key, or the embedded local model (`localLlm`, fully offline). The local model is small — great for quick lookups, prefer a hosted model for full reports. Inside DeepSeek Harness, the plugin uses your configured model.
 
 **Which languages are supported?**
 French and English via `lang` on every tool. Source-side, AST covers JS/TS, Python, Go, Rust, Java, C#, PHP — the rest is indexed line by line.
@@ -290,7 +295,7 @@ Then restart `dsh --profile web`.
 
 | | |
 | --- | --- |
-| **Shipped** | tree-sitter AST (7 languages), deterministic health score, MCP setup wizard, `.codebase-chat.json`, `--diff` scoping, `--watch` mode |
+| **Shipped** | tree-sitter AST (7 languages), deterministic health score, MCP setup wizard, `.codebase-chat.json`, `--diff` scoping, `--watch` mode, embedded local LLM |
 | **Next** | GitHub Issues export from TASKS.md, prompt language packs (ES/DE/PT) |
 | **Planned** | VS Code extension, HTTP/SSE transport, PR review mode, report export |
 | **Exploring** | multi-repo workspaces, shared team index cache, CI bot |