hotheat/dsh-claude-codex-mode ↗★ 0

dsh-claude-codex-mode

Discussion stays read-only, and every repository code edit goes to Codex. The discussion runs on the DSH model or through the Claude Code CLI.

パッケージ
dsh-claude-codex-mode
互換性
未検証
Harness ピア範囲
>=0.2.1-rc.2 <0.3.0
バージョン
0.7.1
ライセンス
MIT
最終更新
2026/11/06

インストール

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hotheat/dsh-claude-codex-mode

ドキュメント

README 全文を読む ↗

dsh-claude-codex-mode

English | 简体中文

Discuss / Execute Split is a DeepSeek Harness (DSH) bundle that splits the work in two: discussion stays read-only, and every repository code edit goes to Codex.

  • Discussion covers requirements, plans, architecture, docs, reading code, and judging whether a fix is worth making. The DSH model does this itself, or forwards it to the Claude Code CLI. The bundle is designed with Claude in mind, so in api mode pick a Claude model as the DSH default.
  • Edits to code or config inside a Git repository go to the Codex CLI through in-process host tools backed by DSH background jobs. They happen only after you say so ("开始吧 / 做吧 / 执行", that is, "go ahead"). DSH then reviews git status, git diff, and the test results itself before reporting back.

A write guard enforces this split. If the model tries to write a repository code file with a structured edit tool, the guard blocks it and tells the model how to hand the edit to Codex.

Modes

You choose the mode in this plugin's form on the DSH Plugins page. Switching takes effect without restarting DSH.

ModeWho discussesWho editsMCP servers mounted
api (default)The DSH model itself. You configure an Anthropic provider (API key) on the Models page and pick ClaudeCodex host toolsNone
claude-code-cliThe DSH model forwards discussion to the Claude Code CLI in read-only discuss/review modes, using your Claude subscription login (no API key)Codex host tools, called by the DSH modelclaude-code

In claude-code-cli mode, Claude Code cannot see the DSH session. The routing prompt therefore tells the DSH model to:

  • send your words and any needed context in each mcp__claude-code__claude_code_run call;
  • continue a topic with resumeSessionId;
  • relay Claude Code's conclusions faithfully.

Claude Code run modes

claude_code_run supports three modes:

ModeBehavior
discuss (default)Read-only discussion of requirements, plans, architecture, docs and code; plans and designs state their assumptions, trade-offs and failure conditions.
reviewRead-only code or change review, reporting findings with file paths and line numbers, ordered by severity.
taskRequires an explicit permissionMode; permissions and tool access follow the caller's configuration.

discuss and review share --permission-mode plan --safe-mode --strict-mcp-config --tools Read,Glob,Grep, with different prompt preambles for discussion and findings. Both modes ignore caller overrides for permissionMode, allowedTools, allowedCommands, disallowedTools, mcpConfigFile and strictMcpConfig. Repository code edits still go to Codex through the routing rules below.

outputFormat defaults to "json", which returns output when the process finishes. Set outputFormat: "stream" explicitly when progress is needed; this passes --output-format stream-json --verbose to Claude Code. Stdout events flow through the runner to the background worker, which updates the job's event count, latest assistant tool name and last activity time, with activity reports throttled to once per second. The final result, cost, duration, session and model usage come from the last result event.

Set stallAfterMs (minimum 1000) to terminate the process group after that many milliseconds without stdout or stderr data. The outcome reports status: "failed", stalled: true and timedOut: false, preserving stderr. This idle limit is optional and separate from timeoutMs, the total execution deadline.

Codex execution

The host registers codex_cli_setup, codex_cli_run and codex_cli_review directly, sharing schemas and the runner with the bundled standalone MCP fallback. codex_cli_setup probes the executable and login asynchronously. Runs stream JSONL events through the host into ctx.jobs, so the session header's Background jobs panel shows live output, progress, duration and a stop button.

Foreground calls are jobs too: they wait up to timeoutMs (four minutes by default), return the canonical Codex result on settlement and remove the collected row. If that wait expires, the process continues and the call returns a jobId; the row stays available after completion. Set background: true for an immediate handle; timeoutMs above 240000 also selects background execution and remains the process deadline. Use DSH job_output to read/wait, job_list to list and job_kill to stop a job; continue Codex with resumeSessionId. Caller abort kills and collects a foreground job before throwing; stopping from the panel terminates the whole Codex process group.

The task panel requires @deepseek-ai/dsh-jobs-local and @deepseek-ai/dsh-tool-jobs in the composition. Without the registry, foreground calls run directly with a timeout and background calls fail with a mount hint. If registration is refused because the session has no job controller or has reached its job cap, the host logs a warning and runs foreground calls directly; background calls report the admission error.

Codex output

In the plugin's Discussion mode form, Codex output controls where runs appear:

  • jobs (default): use dsh-better-sidebar's built-in Background jobs drawer; the Codex tab is not registered.
  • tab: register a dedicated Codex sidebar page; requires dsh-better-sidebar.

Changing this option saves immediately, without preflight checks or a page reload. With tab selected, open the right sidebar's + menu and pick Codex to list this session's Codex runs and stream the selected run's output live. The tab also supports copying output and stopping a running job with a second confirmation click. The tab option remains selectable when the sidebar plugin is absent, and the form shows an installation hint.

Preflight checks

When the form opens, it checks the current mode and shows the result:

  • If the current mode passes, the form says so and lists any warnings.
  • If it fails, the form lists each failed check with a fix hint and also checks the other mode. If the other mode passes, its card says it can be switched to.
  • Clicking the card of the other mode checks that mode right away and shows the result. The click only selects the mode; it does not save it.
  • The mode never changes automatically.

When the API card is selected, the form also shows the Anthropic provider settings DSH is using:

  • the base URL;
  • the name of the key variable, and where the key comes from (saved in DSH, the environment, or missing);
  • the configured models and the default model.

These are read-only here. To change them, open Settings → Models. A plugin form cannot open that page for you.

Test connection asks the provider for its model list (GET /v1/models) with the current key, so it uses no tokens.

  • The result tells apart a rejected key, an unreachable address, a timeout, and configured models missing from the list.
  • Some relays don't offer a model list. Then the test can't tell whether the key works, and it shows a warning instead of a failure.
  • The test runs only when you click the button.
  • Redirects are refused, so the key is never sent to a second address.

Clicking Check and save runs a preflight check for the target mode first. If any blocking check fails, the save is refused, the current mode stays, and the form lists each failed check with a fix hint.

ScopeCheckLevel
All modesNode.js ≥ 20Blocking
All modescodex --version succeedsBlocking
All modescodex login status reports logged inBlocking
All modesBundled standalone MCP fallback mcp/codex-cli/server.mjs existsBlocking
apillm-pi-ai has an anthropic provider with at least one modelBlocking
apiThe credential its apiKeyEnv points to exists (checked for presence only)Blocking
apiThe default model is not ClaudeWarning
claude-code-cliclaude --version succeedsBlocking
claude-code-cliclaude auth status reports loggedIn: trueBlocking
claude-code-cliBundled mcp/claude-code/server.mjs existsBlocking

About these checks:

  • Every external command has a timeout.
  • The output reports only whether a check passed. It never shows command output or credential values.
  • The same checks run when DSH starts. At startup a failure only logs a warning.
  • The same checks are available from the command line (see Diagnostics).

Requirements

  • DSH `>=0.2.1-rc.2 models: - id: claude-sonnet-5-5 - id: claude-opus-5-5

- Save the key on the Models page, or put it in the environment or in `~/.dsh/.env`. The patch should name only the environment variable, never the key itself.
- Pick Claude in the model selector and save it as the default model. The bundle cannot set the default model for you, because the profile's `agent-default-model` row is applied after bundles.
- Existing sessions keep their model. Switch them with `/model`.

## Write guard

The guard checks the path arguments of four structured file-writing tools: `write`, `edit`, `str_replace_editor`, and `apply_patch`.

- `str_replace_editor` with `command: "view"` is read-only and always allowed.
- `apply_patch` is listed for forward compatibility. DSH 0.2.1-rc.2 has no such tool.
- `bash` / `pwsh` are not checked. The routing prompt tells the model not to use `sed -i`, heredocs, or redirection to get around the guard, but nothing enforces that.

How each write is decided:

1. Read the tool's path argument.
2. Resolve it against the session's current working directory.
3. Find the nearest Git root and check for the bypass marker.
4. Allow the write, or deny it with Codex instructions.

Relative paths with no known session directory are denied, and the model is asked to use an absolute path.

The guard allows these writes directly:

- Files ending in `.md`, `.mdx`, `.markdown`, `.txt`, `.canvas`, `.base`, or `.rst` (case-insensitive). The exceptions are `requirements*.txt`, `constraints*.txt`, and `CMakeLists.txt`, which count as config.
- Anything under `~/.claude`.
- Files outside any Git repository.
- Repositories that contain `.claude/direct-edit` at their root.
- Every write, when DSH is started with `DSH_DIRECT_EDIT=1` or `CLAUDE_DIRECT_EDIT=1`.

If the Codex tools fail to come online, the guard stays active, and its deny message says that Codex is unavailable.

## Diagnostics

From a clone of this repository:

```bash
npm install
npm run doctor
npm run doctor -- --mode claude-code-cli --profile web
  • doctor runs the same preflight checks offline and exits non-zero if a blocking check fails.
  • In api mode it reads the selected profile's cordis.patch.yml without evaluating !!js expressions.
  • It looks for the credential in the DSH credential store, the process environment, the project .env, and ~/.dsh/.env.

Codex runs use the process-local DSH job registry. Claude Code MCP job state is stored under /claude-codex-mode/claude-code/.

Development

npm test
node --test mcp/*/tests/*.test.mjs

npm test covers:

  • the policy tests;
  • table-driven preflight tests with injected command results;
  • the doctor and form tests;
  • shared schema validation and incremental Codex event rendering;
  • host tools with a real local DSH job registry and fake CLI subprocesses, including timeout promotion, live output, cancellation and admission fallback;
  • a real Cordis load test that switches modes both ways, keeps Codex host tools registered and mounts/unmounts only the Claude MCP server.

The load test finds Cordis through DSH_CORDIS_PATH, and failing that through a global @deepseek-ai/dsh install (npm root -g). If neither is found, it is skipped with a message.

Attribution and license

The bundled MCP servers in mcp/codex-cli and mcp/claude-code come from the author's own earlier plugins. See ATTRIBUTION.md for where each part comes from.

MIT © 2026 Jiaoguo