Rename workspace tool surface to project

AGENTS.md

@@ -13,15 +13,14 @@ primitives such as read, edit, write, grep, find, ls, and bash. DevSpace wraps
 those primitives behind a remote Streamable HTTP MCP interface, suitable for use
 through a Cloudflare Tunnel.
 
-The model-facing workflow is workspace based. MCP clients should call
-`open_workspace` once per local project directory or worktree, then reuse the
-returned `workspaceId` for subsequent tool calls in that same folder. Do not
-call `open_workspace` again for the same folder unless the `workspaceId` is
-rejected as unknown, the client switches folders/worktrees or checkout/worktree
-mode, or the user explicitly asks to reopen. `AGENTS.md` files are returned
-automatically by `open_workspace` and by later tool calls when the requested path
-enters a directory with instructions that have not been loaded for that
-workspace.
+The model-facing workflow is project based. MCP clients should call
+`open_project` once per local project directory or worktree, then reuse the
+returned `projectId` for subsequent tool calls in that same folder. Do not call
+`open_project` again for the same folder unless the `projectId` is rejected as
+unknown, the client switches folders/worktrees or checkout/worktree mode, or the
+user explicitly asks to reopen. `AGENTS.md` files are returned automatically by
+`open_project` and by later tool calls when the requested path enters a
+directory with instructions that have not been loaded for that project.
 
 Core constraints:
 

docs/agent-profile-schema.md

@@ -52,7 +52,7 @@ Use lowercase kebab-case names. If omitted, DevSpace uses the filename without
 
 ### `description`
 
-Required short purpose. This is exposed by `open_workspace` so the supervising
+Required short purpose. This is exposed by `open_project` so the supervising
 model can choose the right profile.
 
 ### `provider`
@@ -118,7 +118,7 @@ disabled: true
 ## Markdown body
 
 The body is the profile prompt prefix DevSpace prepends when launching that
-profile. It is not included in `open_workspace` by default.
+profile. It is not included in `open_project` by default.
 
 Recommended body content:
 
@@ -137,7 +137,7 @@ devspace agents run <profile-or-id> "<prompt>"
 devspace agents show <id>
 ```
 
-`open_workspace` exposes compact profile metadata:
+`open_project` exposes compact profile metadata:
 
 ```json
 {

docs/chatgpt-coding-workflow.md

@@ -4,22 +4,22 @@ DevSpace brings a Codex-style coding-agent loop to ChatGPT and other MCP hosts:
 inspect the repo, follow local instructions, make scoped edits, run
 verification, and show the user what changed.
 
-## Open One Workspace
+## Open One Project
 
-ChatGPT should call `open_workspace` once for a project folder:
+ChatGPT should call `open_project` once for a project folder:
 
 ```json
 {
   "path": "~/work/my-project"
 }
 ```
 
-The result includes a `workspaceId`. All later file, search, edit, show-changes,
-and shell calls should reuse that same `workspaceId`.
+The result includes a `projectId`. All later file, search, edit, show-changes,
+and shell calls should reuse that same `projectId`.
 
 Do not reopen the same folder unless:
 
-- the `workspaceId` is rejected as unknown
+- the `projectId` is rejected as unknown
 - the user switches to another folder
 - the user switches between checkout and worktree mode
 - the user explicitly asks to reopen
@@ -93,7 +93,7 @@ It also keeps compatibility with:
 
 When Subagents are enabled, DevSpace discovers agent profiles
 from `~/.devspace/agents/*.md` and project `.devspace/agents/*.md`.
-`open_workspace` exposes a compact catalog with profile names, descriptions,
+`open_project` exposes a compact catalog with profile names, descriptions,
 providers, and optional models/thinking levels so the model can choose a configured agent
 without seeing provider-specific launch details.
 
@@ -103,7 +103,7 @@ before use.
 
 Legacy project paths such as `.pi/skills` can be added through `DEVSPACE_SKILL_PATHS` when needed.
 
-When `open_workspace` returns matching skills, the model should read the
+When `open_project` returns matching skills, the model should read the
 advertised `SKILL.md` before following that skill.
 
 Skill paths may be outside the workspace. DevSpace only permits reading:
@@ -115,14 +115,14 @@ Set `DEVSPACE_SKILLS=0` to hide skills from workspace output. Set
 `DEVSPACE_SUBAGENTS=1` to expose the experimental subagent catalog and
 `subagent-delegation` skill. That skill teaches the minimal
 `devspace agents ls`, `devspace agents run`, and `devspace agents show`
-workflow. The catalog comes from `open_workspace`; `devspace agents ls` lists
+workflow. The catalog comes from `open_project`; `devspace agents ls` lists
 existing subagent sessions for that workspace.
 
 ## Tool Names
 
 DevSpace exposes these tool names:
 
-- `open_workspace`
+- `open_project`
 - `read`
 - `write`
 - `edit`
@@ -137,7 +137,7 @@ Use `DEVSPACE_TOOL_MODE=full` to restore dedicated search and directory tools.
 The experimental Codex-style surface is enabled with
 `DEVSPACE_TOOL_MODE=codex`. It exposes:
 
-- `open_workspace`
+- `open_project`
 - `read`
 - `apply_patch`
 - `exec_command`
@@ -160,7 +160,7 @@ to expose the aggregate show-changes flow.
 
 When `show_changes` is exposed, models should call it exactly once after the
 final file modification in any turn that changes files. The tool only requires
-the `workspaceId`; DevSpace automatically compares against the last shown
+the `projectId`; DevSpace automatically compares against the last shown
 checkpoint and advances that checkpoint after rendering the aggregate diff.
 
 ## Shell Use

docs/configuration.md

@@ -63,9 +63,9 @@ MCP clients discover metadata from:
 
 | Value | Behavior |
 | --- | --- |
-| `minimal` | Default. Exposes `open_workspace`, `read`, `write`, `edit`, and `bash`. Clients use `bash` with tools such as `rg`, `find`, and `ls` for inspection. |
+| `minimal` | Default. Exposes `open_project`, `read`, `write`, `edit`, and `bash`. Clients use `bash` with tools such as `rg`, `find`, and `ls` for inspection. |
 | `full` | Exposes the minimal tools plus dedicated `grep`, `glob`, and `ls` tools. |
-| `codex` | Experimental. Exposes `open_workspace`, `read`, `apply_patch`, `exec_command`, and `write_stdin`. Existing mutation and shell tools are hidden. |
+| `codex` | Experimental. Exposes `open_project`, `read`, `apply_patch`, `exec_command`, and `write_stdin`. Existing mutation and shell tools are hidden. |
 
 `DEVSPACE_MINIMAL_TOOLS` remains a backward-compatible alias when
 `DEVSPACE_TOOL_MODE` is unset: `1` selects `minimal` and `0` selects `full`.
@@ -84,7 +84,7 @@ sessions.
 | Value | Behavior |
 | --- | --- |
 | `full` | Default. Widget UI is attached to exposed workspace, file, edit, and shell tools. |
-| `changes` | Enables the aggregate `show_changes` tool and attaches widget UI to `open_workspace` and `show_changes`. |
+| `changes` | Enables the aggregate `show_changes` tool and attaches widget UI to `open_project` and `show_changes`. |
 | `off` | Disables widget UI. |
 
 ## Skills
@@ -114,7 +114,7 @@ from:
 - `~/.devspace/agents/*.md`
 - project `.devspace/agents/*.md`
 
-`open_workspace` returns a compact catalog containing profile names,
+`open_project` returns a compact catalog containing profile names,
 descriptions, providers, and optional models/thinking levels so the host model can choose an
 agent without reading provider-specific launch details. `devspace agents ls`
 lists existing subagent sessions for the current workspace, scoped by the

docs/gotchas.md

@@ -130,14 +130,14 @@ To regenerate setup:
 npx @waishnav/devspace init --force
 ```
 
-## Unknown `workspaceId`
+## Unknown `projectId`
 
-`workspaceId` values are session identifiers. If the server restarts and the
-client receives an unknown workspace error, call `open_workspace` again for that
+`projectId` values are opened-project identifiers. If the server restarts and the
+client receives an unknown project error, call `open_project` again for that
 project.
 
 Workspace session metadata is persisted, but clients should still treat
-`open_workspace` as the way to begin a fresh working session.
+`open_project` as the way to begin a fresh working session.
 
 ## Workspace Path Rejected
 
@@ -207,7 +207,7 @@ It also checks compatibility and custom paths:
 
 When `DEVSPACE_SUBAGENTS=1`, DevSpace loads agent profiles from
 `~/.devspace/agents/*.md` and project `.devspace/agents/*.md`, then exposes a
-compact profile catalog through `open_workspace`. The bundled
+compact profile catalog through `open_project`. The bundled
 `subagent-delegation` skill keeps the model-facing workflow to
 `devspace agents ls`, `devspace agents run`, and `devspace agents show`.
 `devspace agents ls` lists existing subagent sessions, not profile
@@ -218,7 +218,7 @@ Copy or adapt them into one of the active profile directories before use.
 
 Legacy project paths such as `.pi/skills` can be added through `DEVSPACE_SKILL_PATHS` when needed.
 
-If a skill appears in `open_workspace`, the model must read that skill's
+If a skill appears in `open_project`, the model must read that skill's
 `SKILL.md` before reading other files inside the skill directory.
 
 ## Review Card Does Not Appear

skills/subagent-delegation/SKILL.md

@@ -29,7 +29,7 @@ it automatically from the shell environment injected by the workspace tool.
 DevSpace agent id.
 
 `run <provider> "<prompt>"` starts a raw built-in provider when no configured
-profile is needed. Built-in providers are listed by `open_workspace`.
+profile is needed. Built-in providers are listed by `open_project`.
 
 `run <id> "<prompt>"` sends a follow-up to an existing agent.
 
@@ -44,9 +44,9 @@ DevSpace agent integration.
 ## Choosing a profile
 
 Choose profiles from the compact subagent profile catalog returned by
-`open_workspace`. Use the profile name with `devspace agents run`. If no
+`open_project`. Use the profile name with `devspace agents run`. If no
 profile fits and delegation is still appropriate, use a built-in provider name
-from `open_workspace`.
+from `open_project`.
 
 Profiles may declare a model and optional thinking level. To override the
 configured/default provider model or thinking level for a run, pass `--model`