@agi-fans/oh-my-dsh 0.5.1 → 0.6.1

package/README.md

@@ -6,15 +6,15 @@
 
 **Into the Unknown**
 
-A focused, keyboard-first DeepSeek coding agent built on the plugin architecture of [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) and inspired by the interaction quality of [oh-my-pi](https://github.com/can1357/oh-my-pi).
+A focused, keyboard-first DeepSeek coding agent built on the plugin architecture of [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) and inspired by the interaction quality of [oh-my-pi](https://github.com/can1357/oh-my-pi) and the original [Pi](https://github.com/earendil-works/pi) agent harness.
 
-[![npm version](https://img.shields.io/npm/v/%40agi-fans%2Foh-my-dsh?style=flat-square&logo=npm)](https://www.npmjs.com/package/@agi-fans/oh-my-dsh) [![npm downloads](https://img.shields.io/npm/dm/%40agi-fans%2Foh-my-dsh?style=flat-square&logo=npm)](https://www.npmjs.com/package/@agi-fans/oh-my-dsh) [![Node.js ^22.19 or >=24](https://img.shields.io/badge/node-%5E22.19%20%7C%7C%20%3E%3D24-339933?style=flat-square&logo=node.js)](https://nodejs.org/) [![MIT License](https://img.shields.io/npm/l/%40agi-fans%2Foh-my-dsh?style=flat-square)](https://github.com/agi-fans/oh-my-dsh/blob/main/LICENSE)
+[![CI](https://github.com/agi-fans/oh-my-dsh/actions/workflows/ci.yml/badge.svg)](https://github.com/agi-fans/oh-my-dsh/actions/workflows/ci.yml) [![npm version](https://img.shields.io/npm/v/%40agi-fans%2Foh-my-dsh?style=flat-square&logo=npm)](https://www.npmjs.com/package/@agi-fans/oh-my-dsh) [![npm downloads](https://img.shields.io/npm/dm/%40agi-fans%2Foh-my-dsh?style=flat-square&logo=npm)](https://www.npmjs.com/package/@agi-fans/oh-my-dsh) [![Node.js ^22.19 or >=24](https://img.shields.io/badge/node-%5E22.19%20%7C%7C%20%3E%3D24-339933?style=flat-square&logo=node.js)](https://nodejs.org/) [![MIT License](https://img.shields.io/npm/l/%40agi-fans%2Foh-my-dsh?style=flat-square)](https://github.com/agi-fans/oh-my-dsh/blob/main/LICENSE)
 
 English · [简体中文](https://github.com/agi-fans/oh-my-dsh/blob/main/README.zh-CN.md)
 
 </div>
 
-![oh-my-dsh terminal interface](https://raw.githubusercontent.com/agi-fans/oh-my-dsh/main/docs/resources/screenshot.png)
+![oh-my-dsh terminal interface](https://raw.githubusercontent.com/agi-fans/oh-my-dsh/main/docs/resources/screenshot.webp)
 
 ## Quick start
 
@@ -32,14 +32,15 @@ Run `/login` once inside omdsh to validate and save your DeepSeek API key, then
 - **Durable conversations:** resume sessions, rewind to a human turn, retry, compact, and export complete transcripts as Markdown.
 - **Four real session controls:** choose a Harness Agent preset (Standard, PTC, Minimal, or Cordis), Workflow (Default or Plan), tool presentation (Native, Code, or Both), and Access (Read only, Workspace write, or Full access).
 - **Rich terminal input:** search project files with `@`, paste clipboard images, reuse persistent prompt history, edit multiline prompts externally, and retrieve queued follow-ups.
-- **Readable tool activity:** follow streaming calls, inspect distinct Input and Output sections, expand long results, and keep domain-specific presentation owned by tool plugins.
+- **Readable tool activity:** follow streaming calls and live subagent progress, open a child's transcript from the Agents roster, steer a continuable child from that view, inspect distinct Input and Output sections, expand long results, and keep domain-specific presentation owned by tool plugins.
 - **Live operational context:** see Agent, Workflow, Tools, Access, model, reasoning effort, workspace, Git state, context pressure, tokens, TTFT, throughput, cache, timings, turns, and steps without leaving the composer.
 - **Responsive by design:** retain settled transcript layout, coalesce scroll updates, emit row-level terminal diffs, and preserve correct display-cell alignment for CJK text and emoji.
 
 ## Learn
 
-- [Tutorials](https://github.com/agi-fans/oh-my-dsh/blob/main/docs/tutorials.md) — complete a first task, add precise context, guide queued work, recover long sessions, and customize the environment.
+- [Tutorials](https://github.com/agi-fans/oh-my-dsh/blob/main/docs/tutorials.md) — complete a first task, add precise context, guide queued work, recover long sessions, customize the environment, and write an installable plugin.
 - [Skills and MCP](https://github.com/agi-fans/oh-my-dsh/blob/main/docs/skills-and-mcp.md) — extend a project with reusable instructions and external tools.
+- [User plugins](https://github.com/agi-fans/oh-my-dsh/blob/main/docs/plugins.md) — install DSH bundles into the omdsh Profile with `omdsh plugin`.
 - [Architecture](https://github.com/agi-fans/oh-my-dsh/blob/main/docs/architecture.md) — understand the plugin boundaries and runtime data flow.
 - [Performance](https://github.com/agi-fans/oh-my-dsh/blob/main/docs/performance.md) — inspect the benchmarks, methodology, and rendering optimizations.
 
@@ -80,7 +81,7 @@ See the reproducible [TUI performance report](https://github.com/agi-fans/oh-my-
 
 ## Configuration
 
-Run `/login` to open the DeepSeek API Key dashboard, enter a key in a masked prompt, validate it, and save it through the Harness credential store. An interactively selected key takes priority over an inherited `DEEPSEEK_API_KEY` on subsequent requests and across restarts. `/logout` removes the omdsh-managed choice and falls back to the environment when available.
+Run `/login` to configure a provider API key. DeepSeek still opens the official key dashboard, validates the key, and prefers the stored credential over an inherited `DEEPSEEK_API_KEY`. The same command can also activate a catalog provider such as OpenAI or Anthropic, or add a custom provider with its own id, base URL, protocol, and model ids. `/model` then lists every live route. `/logout` removes an omdsh-managed choice and, for DeepSeek, falls back to the environment when available.
 
 Model settings can also come from `$DSH_HOME/settings.yaml`. Skills and MCP configuration are documented in [Skills and MCP](https://github.com/agi-fans/oh-my-dsh/blob/main/docs/skills-and-mcp.md).
 
@@ -98,7 +99,7 @@ pnpm smoke               # interactive PTY smoke test
 pnpm smoke:happy         # mock-LLM happy path
 ```
 
-The checkouts in `refs/deepseek-harness` and `refs/oh-my-pi` are read-only references. Do not use them as runtime dependencies or modify them while developing omdsh.
+The checkouts in `refs/deepseek-harness`, `refs/oh-my-pi`, and `refs/pi` are read-only references. Do not use them as runtime dependencies or modify them while developing omdsh.
 
 ## Changelog
 
@@ -106,12 +107,13 @@ User-visible changes and release history are tracked in [CHANGELOG.md](https://g
 
 ## Acknowledgements
 
-oh-my-dsh exists because of two projects:
+oh-my-dsh exists because of these projects:
 
 - [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) provides the runtime foundation, plugin architecture, and the conviction that agent capabilities should be composable rather than embedded in one application.
-- [oh-my-pi](https://github.com/can1357/oh-my-pi) demonstrates how thoughtful terminal interaction, compact information design, and careful keyboard workflows can make an agent feel fast and approachable.
+- [Pi](https://github.com/earendil-works/pi) is the original open agent harness whose terminal interaction, differential rendering, and compact coding-agent craft still set the standard this community builds on.
+- [oh-my-pi](https://github.com/can1357/oh-my-pi) continues that lineage and shows how thoughtful terminal interaction, compact information design, and careful keyboard workflows can make an agent feel fast and approachable.
 
-Thank you to both projects and their contributors. omdsh is an independent community project: it is built on DeepSeek Harness and learns from OMP, but is not an official distribution of either project.
+Thank you to these projects and their contributors. omdsh is an independent community project: it is built on DeepSeek Harness and learns from Pi and OMP, but is not an official distribution of any of them.
 
 ## License
 

package/config/cordis.yml

@@ -1,266 +1,274 @@
-# omdsh composition — the TUI coding agent over the DeepSeek Harness core
-# runtime. No Host, no HTTP, no browser layer: local executors, the
-# executor-less agent spine, the DeepSeek adapter, and the omdsh TUI seam
-# (provider + interactive runner).
+# omdsh product bundle — one insert over an empty Profile root.
+# TUI coding agent over the DeepSeek Harness core runtime. No Host, no HTTP, no
+# browser layer: local executors, the executor-less agent spine, the DeepSeek
+# adapter, and the omdsh TUI seam (provider + interactive runner).
 #
 # Model/provider rows read the CLI/environment overrides through the
 # harness's sanctioned dynamic-config mechanism (!!js under plugin config).
 
-- id: timer
-  name: '@deepseek-ai/cordis-plugin-timer'
-
-- id: llm
-  name: '@deepseek-ai/dsh-llm'
-
-- id: llm-deepseek
-  name: '@deepseek-ai/dsh-llm-deepseek'
-
-- id: session
-  name: '@deepseek-ai/dsh-session'
-
-- id: session-persistence
-  name: '@deepseek-ai/dsh-session-persistence-jsonl'
-  config:
-    root: !!js "(process.env.OMDSH_HOME || process.env.DSH_HOME || process.env.HOME + '/.dsh') + '/sessions'"
-
-- id: session-checkpoint
-  name: '@deepseek-ai/dsh-session-checkpoint-policy'
-
-- id: session-projection
-  name: '@deepseek-ai/dsh-session-projection'
-
-- id: session-title
-  name: '@deepseek-ai/dsh-session-title'
-  config:
-    fallbackMaxWords: 8
-    fallbackMaxBytes: 80
-    maxTitleBytes: 120
-
-- id: session-stats
-  name: '@deepseek-ai/dsh-session-stats'
-
-- id: attachments
-  name: '@deepseek-ai/dsh-attachment-local'
-  config:
-    dshHome: !!js process.env.OMDSH_HOME || process.env.DSH_HOME || undefined
-
-# User settings document ($DSH_HOME/settings.yaml) and credential sources
-# (inherited env, managed .credentials.yaml, project/user .env) — the same
-# rows the harness base mounts, so omdsh honors the user's existing model
-# route and API key setup out of the box.
-- id: settings
-  name: '@deepseek-ai/dsh-settings-file'
-  config:
-    dshHome: !!js process.env.OMDSH_HOME || process.env.DSH_HOME || undefined
-
-- id: credentials
-  name: '@deepseek-ai/dsh-credentials-local'
-  config:
-    dshHome: !!js process.env.OMDSH_HOME || process.env.DSH_HOME || undefined
-
-- id: agent
-  name: '@deepseek-ai/dsh-agent'
-
-- id: agent-default-model
-  name: '@deepseek-ai/dsh-agent-default-model'
-  config:
-    provider: !!js process.env.OMDSH_PROVIDER || 'deepseek-official'
-    model: !!js process.env.OMDSH_MODEL || 'deepseek-v4-flash'
-
-- id: agent-presets
-  name: '@deepseek-ai/dsh-agent-presets'
-  config:
-    default: standard
-    roots:
-      - path: !!js "process.getBuiltinModule('node:url').fileURLToPath(new URL('./agent-presets/', baseUrl))"
-        trust: system
-
-- id: commands
-  name: '@deepseek-ai/dsh-commands'
-
-- id: user-questions
-  name: '@deepseek-ai/dsh-user-questions'
-
-- id: approval
-  name: '@deepseek-ai/dsh-user-approval'
-  config:
-    policy: !!js "(process.env.OMDSH_PERMISSION_MODE || 'workspace-write') === 'danger-full-access' ? 'never' : 'ask'"
-
-# Every session starts with one explicit access preset. The environment is a
-# deployment override; the TUI switches it later through the /permission picker.
-- id: sandbox
-  name: '@deepseek-ai/dsh-sandbox-local'
-
-- id: sandbox-policy
-  name: '@deepseek-ai/dsh-sandbox-policy'
-  config:
-    mode: !!js process.env.OMDSH_PERMISSION_MODE || 'workspace-write'
-    workspaceRoot: !!js process.cwd()
-
-- id: fs
-  name: '@deepseek-ai/dsh-fs-local'
-
-- id: fs-observation-policy
-  name: '@deepseek-ai/dsh-fs-observation-policy'
-
-- id: subprocess
-  name: '@deepseek-ai/dsh-subprocess-local'
-
-- id: bash
-  name: '@deepseek-ai/dsh-bash-sandbox'
-
-- id: permission
-  name: '@deepseek-ai/dsh-permission-presets'
-  config:
-    presets:
-      read-only:
-        sandbox: read-only
-        approval: ask
-        name: Read only
-        description: Inspect the workspace without writing; escalation requires approval.
-      workspace-write:
-        sandbox: workspace-write
-        approval: ask
-        name: Workspace write
-        description: Write inside the workspace; wider access requires approval.
-      danger-full-access:
-        sandbox: danger-full-access
-        approval: never
-        name: Full access
-        description: Full filesystem access without approval prompts.
-
-- id: spine
-  name: '@deepseek-ai/dsh-agent-spine-demo'
-  config:
-    workspaceContext:
-      maxBytes: 65536
-    dshHome: !!js process.env.OMDSH_HOME || undefined
-    skills:
-      enabled: true
-    goals:
-      domain: {}
-      tool: {}
-    tools:
-      mode: native
-
-- id: code-runtime
-  name: '@deepseek-ai/dsh-code-runtime-worker-thread'
-
-- id: cordis-host-runner
-  name: '@deepseek-ai/dsh-cordis-host-runner'
-
-# Human and model workflow contributions. The TUI discovers human commands
-# from dsh-commands and renders unknown tools through its safe fallback.
-- id: command-goal
-  name: '@deepseek-ai/dsh-command-goal'
-
-- id: tool-ask-user
-  name: '@deepseek-ai/dsh-tool-ask-user'
-
-- id: plan-mode
-  name: '@deepseek-ai/dsh-plan-mode'
-  config:
-    section: |
-      You are in plan mode. Stay in plan mode until exit_plan_mode succeeds or the user switches the session mode. Imperative language to implement changes means plan the implementation, not execute it. A user's conversational agreement — including an answer confirming something you asked — approves nothing and does not end plan mode; fold the confirmed decision into the plan and submit it through exit_plan_mode.
-
-      Explore first. Use non-mutating reads, searches, static analysis, and checks to ground the plan in the actual repository. Do not edit or write files, change configuration, run formatters or code generation that rewrites tracked files, commit, or otherwise carry out the plan. Prefer existing functions and patterns over new machinery.
-
-      The tool catalog stays the same across modes for request-cache stability. These plan-mode rules override any later tool description or guidance that suggests using mutation tools; those tools remain listed to keep the tool catalog unchanged. Do not use todo_write to track this planning phase: it tracks implementation after an approved plan, while the plan itself belongs in exit_plan_mode.
-
-      Resolve discoverable facts by inspection. Use ask_user_question only for user-owned choices or material ambiguity that inspection cannot answer. Do not ask the user where code lives or how current behavior works when you can find out.
-
-      Make the plan decision-complete: state the goal and success criteria; group implementation changes by subsystem; identify public interface, schema, and data-flow changes; cover edge cases, failure modes, tests, acceptance criteria, and explicit assumptions. Keep it concise enough to review but detailed enough that another engineer can implement it without making design decisions.
-
-      When ready, call exit_plan_mode with the complete plan markdown, starting with a # title. Make exit_plan_mode the only and final tool call in that assistant response: it presents the plan for approval, and implementation begins only in a later step after approval. Do not paste the final plan as a plain reply or ask "should I proceed?" through prose or ask_user_question. If review rejects it, incorporate the feedback and present again. If the review channel is unavailable or aborted, stay in plan mode and ask the user to switch modes manually; do not proceed with implementation.
-
-- id: tool-fs
-  name: '@deepseek-ai/dsh-tool-fs'
-
-- id: tool-fs-search
-  name: '@deepseek-ai/dsh-tool-fs-search'
-  config:
-    sampleOverCapGlobResults: false
-
-- id: tool-todo
-  name: '@deepseek-ai/dsh-tool-todo'
-  config:
-    allowParallelInProgress: true
+- insert:
+  - id: timer
+    name: '@deepseek-ai/cordis-plugin-timer'
+
+  - id: llm
+    name: '@deepseek-ai/dsh-llm'
+
+  - id: llm-deepseek
+    name: '@deepseek-ai/dsh-llm-deepseek'
+
+  - id: session
+    name: '@deepseek-ai/dsh-session'
+
+  - id: session-persistence
+    name: '@deepseek-ai/dsh-session-persistence-jsonl'
+    config:
+      root: !!js "(process.env.OMDSH_HOME || process.env.DSH_HOME || process.env.HOME + '/.dsh') + '/sessions'"
+
+  - id: session-checkpoint
+    name: '@deepseek-ai/dsh-session-checkpoint-policy'
+
+  - id: session-projection
+    name: '@deepseek-ai/dsh-session-projection'
+
+  - id: session-title
+    name: '@deepseek-ai/dsh-session-title'
+    config:
+      fallbackMaxWords: 8
+      fallbackMaxBytes: 80
+      maxTitleBytes: 120
+
+  - id: session-stats
+    name: '@deepseek-ai/dsh-session-stats'
+
+  - id: attachments
+    name: '@deepseek-ai/dsh-attachment-local'
+    config:
+      dshHome: !!js process.env.OMDSH_HOME || process.env.DSH_HOME || undefined
+
+  # User settings document ($DSH_HOME/settings.yaml) and credential sources
+  # (inherited env, managed .credentials.yaml, project/user .env) — the same
+  # rows the harness base mounts, so omdsh honors the user's existing model
+  # route and API key setup out of the box.
+  - id: settings
+    name: '@deepseek-ai/dsh-settings-file'
+    config:
+      dshHome: !!js process.env.OMDSH_HOME || process.env.DSH_HOME || undefined
+
+  - id: credentials
+    name: '@deepseek-ai/dsh-credentials-local'
+    config:
+      dshHome: !!js process.env.OMDSH_HOME || process.env.DSH_HOME || undefined
+
+  # Dormant multi-provider twin: zero extra picker routes until a `llm-pi-ai:`
+  # settings section supplies profiles. /login writes those profiles; /model
+  # lists whatever routes become live. Keep llm-deepseek as the official
+  # DeepSeek identity — its route is `deepseek-official`, not catalog `deepseek`.
+  - id: llm-pi-ai
+    name: '@deepseek-ai/dsh-llm-pi-ai'
+
+  - id: agent
+    name: '@deepseek-ai/dsh-agent'
+
+  - id: agent-default-model
+    name: '@deepseek-ai/dsh-agent-default-model'
+    config:
+      provider: !!js process.env.OMDSH_PROVIDER || 'deepseek-official'
+      model: !!js process.env.OMDSH_MODEL || 'deepseek-v4-flash'
+
+  - id: agent-presets
+    name: '@deepseek-ai/dsh-agent-presets'
+    config:
+      default: standard
+      roots:
+        - path: !!js "process.getBuiltinModule('node:url').fileURLToPath(new URL('./agent-presets/', baseUrl))"
+          trust: system
+
+  - id: commands
+    name: '@deepseek-ai/dsh-commands'
+
+  - id: user-questions
+    name: '@deepseek-ai/dsh-user-questions'
+
+  - id: approval
+    name: '@deepseek-ai/dsh-user-approval'
+    config:
+      policy: !!js "(process.env.OMDSH_PERMISSION_MODE || 'workspace-write') === 'danger-full-access' ? 'never' : 'ask'"
+
+  # Every session starts with one explicit access preset. The environment is a
+  # deployment override; the TUI switches it later through the /permission picker.
+  - id: sandbox
+    name: '@deepseek-ai/dsh-sandbox-local'
+
+  - id: sandbox-policy
+    name: '@deepseek-ai/dsh-sandbox-policy'
+    config:
+      mode: !!js process.env.OMDSH_PERMISSION_MODE || 'workspace-write'
+      workspaceRoot: !!js process.cwd()
+
+  - id: fs
+    name: '@deepseek-ai/dsh-fs-local'
+
+  - id: fs-observation-policy
+    name: '@deepseek-ai/dsh-fs-observation-policy'
+
+  - id: subprocess
+    name: '@deepseek-ai/dsh-subprocess-local'
+
+  - id: bash
+    name: '@deepseek-ai/dsh-bash-sandbox'
+
+  - id: permission
+    name: '@deepseek-ai/dsh-permission-presets'
+    config:
+      presets:
+        read-only:
+          sandbox: read-only
+          approval: ask
+          name: Read only
+          description: Inspect the workspace without writing; escalation requires approval.
+        workspace-write:
+          sandbox: workspace-write
+          approval: ask
+          name: Workspace write
+          description: Write inside the workspace; wider access requires approval.
+        danger-full-access:
+          sandbox: danger-full-access
+          approval: never
+          name: Full access
+          description: Full filesystem access without approval prompts.
+
+  - id: spine
+    name: '@deepseek-ai/dsh-agent-spine-demo'
+    config:
+      workspaceContext:
+        maxBytes: 65536
+      dshHome: !!js process.env.OMDSH_HOME || undefined
+      skills:
+        enabled: true
+      goals:
+        domain: {}
+        tool: {}
+      tools:
+        mode: native
+
+  - id: code-runtime
+    name: '@deepseek-ai/dsh-code-runtime-worker-thread'
+
+  - id: cordis-host-runner
+    name: '@deepseek-ai/dsh-cordis-host-runner'
+
+  # Human and model workflow contributions. The TUI discovers human commands
+  # from dsh-commands and renders unknown tools through its safe fallback.
+  - id: command-goal
+    name: '@deepseek-ai/dsh-command-goal'
+
+  - id: tool-ask-user
+    name: '@deepseek-ai/dsh-tool-ask-user'
+
+  - id: plan-mode
+    name: '@deepseek-ai/dsh-plan-mode'
+    config:
+      section: |
+        You are in plan mode. Stay in plan mode until exit_plan_mode succeeds or the user switches the session mode. Imperative language to implement changes means plan the implementation, not execute it. A user's conversational agreement — including an answer confirming something you asked — approves nothing and does not end plan mode; fold the confirmed decision into the plan and submit it through exit_plan_mode.
+
+        Explore first. Use non-mutating reads, searches, static analysis, and checks to ground the plan in the actual repository. Do not edit or write files, change configuration, run formatters or code generation that rewrites tracked files, commit, or otherwise carry out the plan. Prefer existing functions and patterns over new machinery.
+
+        The tool catalog stays the same across modes for request-cache stability. These plan-mode rules override any later tool description or guidance that suggests using mutation tools; those tools remain listed to keep the tool catalog unchanged. Do not use todo_write to track this planning phase: it tracks implementation after an approved plan, while the plan itself belongs in exit_plan_mode.
+
+        Resolve discoverable facts by inspection. Use ask_user_question only for user-owned choices or material ambiguity that inspection cannot answer. Do not ask the user where code lives or how current behavior works when you can find out.
+
+        Make the plan decision-complete: state the goal and success criteria; group implementation changes by subsystem; identify public interface, schema, and data-flow changes; cover edge cases, failure modes, tests, acceptance criteria, and explicit assumptions. Keep it concise enough to review but detailed enough that another engineer can implement it without making design decisions.
+
+        When ready, call exit_plan_mode with the complete plan markdown, starting with a # title. Make exit_plan_mode the only and final tool call in that assistant response: it presents the plan for approval, and implementation begins only in a later step after approval. Do not paste the final plan as a plain reply or ask "should I proceed?" through prose or ask_user_question. If review rejects it, incorporate the feedback and present again. If the review channel is unavailable or aborted, stay in plan mode and ask the user to switch modes manually; do not proceed with implementation.
+
+  - id: tool-fs
+    name: '@deepseek-ai/dsh-tool-fs'
+
+  - id: tool-fs-search
+    name: '@deepseek-ai/dsh-tool-fs-search'
+    config:
+      sampleOverCapGlobResults: false
+
+  - id: tool-todo
+    name: '@deepseek-ai/dsh-tool-todo'
+    config:
+      allowParallelInProgress: true
 
-- id: tool-str-replace-editor
-  name: '@deepseek-ai/dsh-tool-str-replace-editor'
-  config:
-    maxOutputChars: 16000
+  - id: tool-str-replace-editor
+    name: '@deepseek-ai/dsh-tool-str-replace-editor'
+    config:
+      maxOutputChars: 16000
 
-- id: token-meter
-  name: '@deepseek-ai/dsh-token-meter'
+  - id: token-meter
+    name: '@deepseek-ai/dsh-token-meter'
 
-- id: compaction
-  name: '@deepseek-ai/dsh-compaction-basic'
+  - id: compaction
+    name: '@deepseek-ai/dsh-compaction-basic'
 
-- id: command-compact
-  name: '@deepseek-ai/dsh-command-compact'
+  - id: command-compact
+    name: '@deepseek-ai/dsh-command-compact'
 
-- id: subagent
-  name: '@deepseek-ai/dsh-subagent'
+  - id: subagent
+    name: '@deepseek-ai/dsh-subagent'
 
-- id: subagent-spawn
-  name: '@deepseek-ai/dsh-subagent-spawn-in-process'
-  config:
-    providerName: spawn
-
-- id: subagent-control
-  name: '@deepseek-ai/dsh-tool-subagent-control'
-
-- id: subagent-list
-  name: '@deepseek-ai/dsh-tool-subagent-control/list-agents'
+  - id: subagent-spawn
+    name: '@deepseek-ai/dsh-subagent-spawn-in-process'
+    config:
+      providerName: spawn
+
+  - id: subagent-control
+    name: '@deepseek-ai/dsh-tool-subagent-control'
+
+  - id: subagent-list
+    name: '@deepseek-ai/dsh-tool-subagent-control/list-agents'
 
-- id: tool-subagent
-  name: '@deepseek-ai/dsh-tool-subagent'
-  config:
-    provider: spawn
-    toolName: subagent
-    backgroundMode: continuable
+  - id: tool-subagent
+    name: '@deepseek-ai/dsh-tool-subagent'
+    config:
+      provider: spawn
+      toolName: subagent
+      backgroundMode: continuable
 
-- id: tui
-  name: '@agi-fans/dsh-tui'
-  config:
-    model: !!js process.env.OMDSH_MODEL || 'deepseek-v4-flash'
+  - id: tui
+    name: '@agi-fans/dsh-tui'
+    config:
+      model: !!js process.env.OMDSH_MODEL || 'deepseek-v4-flash'
 
-- id: tui-tool-presentation
-  name: '@agi-fans/dsh-tui/tool-presentation'
+  - id: tui-tool-presentation
+    name: '@agi-fans/dsh-tui/tool-presentation'
 
-- id: tui-session-runtime
-  name: '@agi-fans/dsh-tui/session-runtime'
+  - id: tui-session-runtime
+    name: '@agi-fans/dsh-tui/session-runtime'
 
-- id: tui-human-interaction
-  name: '@agi-fans/dsh-tui/human-interaction'
+  - id: tui-human-interaction
+    name: '@agi-fans/dsh-tui/human-interaction'
 
-- id: tui-command-session
-  name: '@agi-fans/dsh-tui/command-session'
+  - id: tui-command-session
+    name: '@agi-fans/dsh-tui/command-session'
 
-- id: tui-command-session-configuration
-  name: '@agi-fans/dsh-tui/command-session-configuration'
+  - id: tui-command-session-configuration
+    name: '@agi-fans/dsh-tui/command-session-configuration'
 
-- id: tui-command-steer
-  name: '@agi-fans/dsh-tui/command-steer'
+  - id: tui-command-steer
+    name: '@agi-fans/dsh-tui/command-steer'
 
-- id: tui-command-loop
-  name: '@agi-fans/dsh-tui/command-loop'
+  - id: tui-command-loop
+    name: '@agi-fans/dsh-tui/command-loop'
 
-- id: tui-command-model
-  name: '@agi-fans/dsh-tui/command-model'
+  - id: tui-command-model
+    name: '@agi-fans/dsh-tui/command-model'
 
-- id: tui-command-auth
-  name: '@agi-fans/dsh-tui/command-auth'
+  - id: tui-command-auth
+    name: '@agi-fans/dsh-tui/command-auth'
 
-- id: tui-command-export
-  name: '@agi-fans/dsh-tui/command-export'
+  - id: tui-command-export
+    name: '@agi-fans/dsh-tui/command-export'
 
-- id: tui-command-integrations
-  name: '@agi-fans/dsh-tui/command-integrations'
+  - id: tui-command-integrations
+    name: '@agi-fans/dsh-tui/command-integrations'
 
-- id: tui-startup-notices
-  name: '@agi-fans/dsh-tui/startup-notices'
+  - id: tui-startup-notices
+    name: '@agi-fans/dsh-tui/startup-notices'
 
-- id: runner
-  name: '@agi-fans/dsh-tui/runner'
+  - id: runner
+    name: '@agi-fans/dsh-tui/runner'

package/lib/args.d.ts

@@ -1,6 +1,6 @@
 /**
- * omdsh argument parsing: one optional prompt (positional words joined)
- * plus --model/--provider overrides, durable --resume, and help/version.
+ * omdsh argument parsing: one optional prompt, --model/--provider
+ * overrides, durable --resume, --dump-config, `omdsh plugin`, and help/version.
  * @module @agi-fans/oh-my-dsh
  */
 export interface OmdshInvocation {
@@ -12,6 +12,12 @@ export interface OmdshInvocation {
     provider: string | undefined;
     /** Durable session selected by --resume/-r. */
     resume: string | undefined;
+    /** Print the composed plugin tree and exit. */
+    dumpConfig: boolean;
+    /** `omdsh plugin` forwarded the remaining arguments to pnpm. */
+    plugin: boolean;
+    /** pnpm arguments after `omdsh plugin`. */
+    pluginArgs: string[];
     /** --help requested. */
     help: boolean;
 }