@muvon/octofs 0.20.5 → 0.22.0

package/README.md

@@ -130,10 +130,35 @@ cargo build --release
 
 ## Quick Start
 
+### Pair with Octocode
+
+The shared-ID workflow requires the next Octocode release or a build of the updated source. OctoFS’s existing line-ID format is unchanged.
+
+Use [Octocode](https://github.com/muvon/octocode) to find definitions, usages, and code relationships, then use OctoFS to read or edit the matching files. Octocode's MCP `structural_search` emits the same `N:hh|content` source line IDs that OctoFS accepts for `batch_edit`, using their shared Octolib utility. You do not need another `view` just to obtain IDs for lines already returned.
+
+Run both servers against the same checkout. IDs describe that source snapshot: changed targets are verified at edit time, and an error supplies current context rather than guessing where to write. Exact-name lookups return complete small definitions; previews of larger matches name the ranges you can read with OctoFS.
+
 ### 1. Configure Your AI Assistant
 
 The CLI uses a `mcp` subcommand — your config must pass `["mcp"]` as args.
 
+**Claude Code (CLI):**
+
+```bash
+claude mcp add octofs -- octofs mcp --path /path/to/your/project
+claude mcp add octocode -- octocode mcp --path /path/to/your/project
+```
+
+**Codex CLI:**
+
+```bash
+codex mcp add octofs -- octofs mcp --path /path/to/your/project
+codex mcp add octocode -- octocode mcp --path /path/to/your/project
+codex mcp list
+```
+
+The Octocode registration is optional. Install the servers you use and replace the paths with the same absolute checkout path. See the [official Codex MCP documentation](https://developers.openai.com/codex/mcp).
+
 **Cursor** (`~/.cursor/mcp.json`):
 ```json
 {
@@ -223,7 +248,7 @@ Ask your AI assistant to:
 ### Line Identifiers
 
 Every line is addressed by a composite id `N:hh` — its 1-indexed position plus a
-2-character hex hash (FNV-1a) of its content. `view` renders lines as `N:hh|content`:
+2-character hex hash (FNV-1a) of its content. Octocode structural-search source output uses the same shared utility and IDs. `view` renders lines as `N:hh|content`:
 
 ```
 1:a3|fn main() {
@@ -345,6 +370,10 @@ Do not re-read overlapping ranges or repeatedly narrow a range just to pick edit
 Re-read when the file may have changed, output was truncated, or prior context is unavailable.
 Empty files return `[empty file, 0 lines]` on an initial or forced full read.
 
+**Images:** a path with a `png`, `jpg`/`jpeg`, `gif` or `webp` extension returns the
+image itself as an MCP image block (up to 5 MB; the bytes must match the extension).
+`start`/`end` and `content` do not apply to it.
+
 **Delta views:** a whole-file view of a file the session already served returns
 only the hunks changed since — the same `...`/`-`/`+` style as edit results, with
 removed lines collapsed to their old id range — or
@@ -497,10 +526,11 @@ can retarget without a re-view. The result is a diff with fresh ids.
 }
 ```
 
-`from_end` is optional (omit to copy a single line). `from_start`, `from_end`, and
-`append_line` each accept a line number or a line id (`"12:a3"`, verified against
-the file). `append_line` positions the copy in the target: `0` = beginning,
-`-1` = end, `N` = after line N.
+`from_end` is optional (omit to copy a single line). `from_start` and `from_end`
+each accept a line number or a line id (`"12:a3"`, verified against the file).
+`append_line` positions the copy in the target: a line id to insert after
+(verified against the target), `0` = beginning, or `-1` = end. Like every edit
+target it takes no other plain line number.
 
 ---
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@muvon/octofs",
-  "version": "0.20.5",
+  "version": "0.22.0",
   "description": "Standalone MCP filesystem tools server \u2014 view, edit, shell, workdir.",
   "mcpName": "io.github.Muvon/octofs",
   "bin": {