Skip to content
Back to search

dsh-codex-connect

Use openai-codex models and image generation via ChatGPT OAuth for DeepSeek Harness.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/franksong2702/dsh-codex-connect with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/franksong2702/dsh-codex-connect'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/franksong2702--dsh-codex-connect/badge.svg)](/listings/franksong2702--dsh-codex-connect)

HTML

<a href="/listings/franksong2702--dsh-codex-connect"><img src="/api/listings/franksong2702--dsh-codex-connect/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

This guide describes the published pairing below. Check `dsh --version` first and use `doctor --json` for local diagnostics; the CLI version alone does not prove which model-runtime packages are installed, and missing metadata is reported as unknown. For other versions, use [Installation and upgrades](INSTALL.md). A moving npm tag such as `alpha` is not a compatibility guarantee.

| Requirement | Verified pairing | |---|---| | Codex Connect | `0.2.0-alpha.2` | | DeepSeek Harness | `0.1.7-rc.1`, `0.1.7-rc.2`, `0.2.0-rc.1`, `0.2.0-rc.2` or `0.2.1-alpha.1` (consistent package set) | | Node.js | `^22.19.0 \|\| >=24.0.0` | | Account | ChatGPT OAuth with access to the requested Codex model; availability is decided by OpenAI |

[`0.2.0-alpha.2`](docs/release-notes/0.2.0-alpha.2.md) publishes exact DSH `0.2.1-alpha.1` compatibility and the cross-route image selection handle repair. The earlier `0.2.0-alpha.1` artifact remains unchanged and rejects that host. Existing supported hosts do not require an upgrade.

As of 2026-10-04, npm `alpha` points to `0.2.0-alpha.2`, while `latest` remains `0.2.0-alpha.1`. Default installation still selects the earlier Alpha; the `latest` tag does not make it a stable release. Use the exact version below for these DSH pairings; a moving npm tag is not a compatibility guarantee for other hosts.

[`0.2.0-alpha.1`](docs/release-notes/0.2.0-alpha.1.md) adds `gpt-6.1-sol` through a model-catalog fallback and begins the shorter independent plugin numbering. The four supported DSH versions are unchanged; no host upgrade is required.

It retains Alpha 4.54's handling of initial system instructions and tool definitions on DSH 0.2.0-rc.2, diagnostics for differing host/plugin provider libraries, and Canary's normal-request checks, along with Alpha 4.53's core maintenance changes, existing-task recovery and safety, and 4.52's [opt-in local request metrics](docs/request-metrics.md). Collection stays off until a private directory is configured; unknown usage is not zero. No Task reopening or model-library/OAuth upgrade is included.

The package passed keyless installation/runtime regression on all five exact DSH versions above. Task controls remain paused: activation is rejected and existing current-host browser regressions show no controls in fresh Sessions. These checks do not establish live OAuth, real-account image editing, authenticated browser acceptance on the new host, or full user acceptance; migration of earlier Task grants across a Harness upgrade is not verified. Older supported pairings and their task behavior are documented in [Installation and upgrades](INSTALL.md).

1. Install

dsh plugin --profile web add dsh-codex-connect@0.2.0-alpha.2
dsh web

Replace `web` with your existing profile name; use that same profile when starting Harness. From a DSH source checkout, prefix commands with `pnpm`. See [INSTALL.md](INSTALL.md) for other profiles and installation checks.

2. Authorize and select a model

Open **Settings → Models → Openai-Codex → Authorize**, then complete approval yourself in the browser. If an embedded window is blocked, select **Open ChatGPT sign-in page**. Choose an `openai-codex` model in the normal Harness model picker.

Never paste an authorization URL, code, token, or account identifier into an issue, log, chat, or configuration file. For a browser on another device, the optional manual callback form can complete the pending login without forwarding the localhost callback port; follow [Remote browser authorization](docs/reference.md#remote-browser-authorization).

3. Check the installation

dsh plugin --profile web exec dsh-codex-connect status --json
dsh plugin --profile web exec dsh-codex-connect doctor --json

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 153 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Codex Connect
  2. Use your ChatGPT subscription as an `openai-codex` model provider in DeepSeek Harness. Codex Connect is a community Alpha plugin.
  3. English | [中文](docs/README.zh.md)
  4. ## Quick start
  5. ### 1. Install
  6. Run `dsh --version` first. For DSH `0.2.2-rc.1`, install into your Web profile:
  7. ```sh
  8. dsh plugin --profile web add dsh-codex-connect@0.2.0-alpha.15
  9. dsh web
  10. ```
  11. | Requirement | Verified default pairing |
  12. | --- | --- |
  13. | DeepSeek Harness | `0.2.2-rc.1` (DSH npm `latest` on 2026-11-17, with a consistent host package set) |
  14. | Codex Connect | `0.2.0-alpha.15` (npm `latest` and `alpha` on 2026-11-17) |
  15. | Node.js | `^22.19.0 \|\| >=24.0.0` |
  16. | Account | ChatGPT OAuth with access to the selected Codex model |
  17. On this exact DSH version, `dsh-codex-connect@latest` resolved to Alpha 15 and passed isolated installation and keyless startup checks. For reproducible installs, use the exact version above. Check the full table before installing on another DSH version or in Desktop. [Installation and upgrades](INSTALL.md) · [Alpha 15 release and promotion record](docs/release-notes/0.2.0-alpha.15.md#latest-promotion-on-2026-11-17)
  18. Replace `web` with your existing profile name and start Harness with that same profile. From a DSH source checkout, prefix the commands with `pnpm`.
  19. ### 2. Authorize and select a model
  20. Open **Settings → Models → Openai-Codex → Authorize**, then complete approval yourself in the browser. If an embedded window is blocked, select **Open ChatGPT sign-in page**. Choose an `openai-codex` model in the normal Harness model picker.
  21. Never paste an authorization URL, code, token, or account identifier into an issue, log, chat, or configuration file. For a browser on another device, the optional manual callback form can complete the pending login without forwarding the localhost callback port; follow [Remote browser authorization](docs/reference.md#remote-browser-authorization).
  22. ### 3. Check the installation
  23. For a package-manager-free diagnostic, run the already installed bin directly (replace these independently identified paths):
  24. ```sh
  25. node /absolute/profile/node_modules/dsh-codex-connect/lib/bin.js doctor --json \
  26. --install-anchor /absolute/dsh/node_modules/@deepseek-ai/dsh/package.json
  27. ```
  28. `doctor --json` reports local installation metadata without a network request or raw credentials; an anchor does not prove that installation is running. Wrappers such as `dsh plugin exec` may reconcile dependencies. See [runtime identity and direct diagnostics](docs/runtime-identity.md), including Desktop/ASAR limitations. Development builds containing that change also distinguish page, Host-loaded and installed plugin versions in settings. A passing diagnostic is not proof of model access; an actual request requires separate authorization.
  29. <p align="center">
  30. <img src="https://raw.githubusercontent.com/franksong2702/dsh-codex-connect/main/docs/assets/en/hero.jpg" alt="Codex Connect — ChatGPT OAuth for DeepSeek Harness" width="100%">
  31. </p>
  32. ## Core capabilities
  33. Codex Connect supplies the provider. Harness manages tools, permissions, approvals, attachments, sessions, compaction and recovery. Installing the plugin preserves your default model and search route. The plugin is independent of OpenAI and DeepSeek, and uses ChatGPT OAuth rather than an OpenAI Platform API key.
  34. - **Accounts:** save up to 16 accounts on the DSH host and manually select the active account for subsequent requests. Account selection is not a per-session binding. Requests keep their captured account; the plugin does not rotate accounts or silently fail over.
  35. - **Models and Astra support:** the currently verified DSH and plugin combination supports `gpt-6-astra`. The plugin supplies its missing model definition with Low, Medium, High, Xhigh, and Max reasoning levels; Default preserves the provider default. Saved Off/Minimal selections require an [explicit update](MIGRATION.md#astra-reasoning-selections). When the installed dependency catalog includes Astra, the plugin preserves its native metadata while retaining these five calibrated reasoning choices. A model appearing in the list does not mean the current account has permission to use it; overall compatibility with new dependency versions still requires separate verification.
  36. - **Fast Mode:** request priority service for one conversation, off by default. Optional, separate profile settings can enable it for newly started top-level or subagent conversations without changing existing conversations. Actual speed and quota consumption depend on the service; no fixed speed multiplier is guaranteed.
  37. - **Quota:** show the server-returned `5h` and `7d` windows and reset times, normally refreshed every 60 seconds while signed in and the tab is visible; failures back off. Missing windows are not invented; Spark uses its separate quota bucket.
  38. - **Plugin updates:** check for newer Codex Connect releases without installing anything or recommending changes to DSH. Host compatibility is available through explicit local diagnostics.
  39. <p align="center">
  40. <img src="https://raw.githubusercontent.com/franksong2702/dsh-codex-connect/main/docs/assets/composer-capabilities.jpg" alt="Fast Mode and quota controls in the DeepSeek Harness Composer" width="820">
  41. </p>
  42. ## Optional capabilities
  43. Development now follows the [core maintenance scope](docs/maintenance-scope.md): maintain connection, compatibility, diagnostics and recovery; freeze Task orchestration and unproven optimization work. Existing published options are not removed or remotely disabled by this decision.
  44. Alpha 4.40 also supplies `gpt-6-sol` and `gpt-6-luna` when older provider catalogs omit them, retaining native metadata when present. Both expose Low through Max (including Xhigh); Default omits an explicit effort. Codex Sol's Ultra orchestration mode is not implemented. New task grants can explicitly include these models, but existing grants and GPT-5.6 Sol/Medium startup remain unchanged; Luna Reserve has subsequently been removed. A catalog entry is not proof of account access. See [compatibility scope and validation](docs/experiments/gpt6-sol-luna-compatibility.md).
  45. All options below are off on a fresh installation. Edit them in **Settings → Plugins → Plugin configuration → Codex Connect** or **Settings → Models → Openai-Codex → More settings**, then select **Save changes**. A conflict or failed save preserves your draft.
  46. | Capability | Enable with | Important behavior |
  47. |---|---|---|
  48. | Proxy | `enableProxy` | Credential-free HTTP(S), scoped to this plugin's traffic, including compressed OAuth and quota responses. Unrelated Fetch calls retain the host's original transport. A failed proxy request does not silently retry directly. |
  49. | Codex Search | `enableSearch` | Selects Codex for the entire profile's search route; disabling restores the previously active route. |
  50. | Image viewing | `enableImageTool` | Adds `view_image` to vision-capable models for local files and validated public HTTP(S) images. |
  51. | GPT Image generation and editing | `enableImageGeneration` | Generate from a prompt or edit selected conversation images with ordered references. Availability, dimensions, and quota remain account- and service-controlled. Also gates the cross-route image handle bridge, which persists the Codex Connect image selection handles into image tool results on non-Codex routes so image editing works there too; the `openai-codex` route is skipped because its adapter already injects the same handles per request. Optional `imageHandleBridgeTools` restricts the bridge to specific tools. |
  52. | Auto-review | `enableAutoReview` | Sends bounded approval context, tool arguments, working directory, and the planned action to `chatgpt.com`, with confirmation on first enablement. Failures return to human approval. |
  53. **Luna Reserve has been removed.** Legacy `enableReserveFallback` settings are ignored; no Reserve negotiation or automatic model switching remains. Select an ordinary model explicitly for an old `gpt-reserve` conversation. If the Host cannot change that conversation’s model, preserve it and start a new conversation with the model you choose. Old return files are not read, migrated or deleted. Account quota UI and the read-only quota tool retain ordinary 60-second caching and failure cooldowns, with no background polling. See [migration guidance](docs/reference.md#luna-reserve-fallback).
  54. Use the image generation capability included with your current GPT subscription. Successful images appear below the conversation answer without opening its processing details; the original tool card remains available there. Generated originals are stored separately from attachment previews; disabling the capability or uninstalling the plugin does not delete them. See [Configuration and recovery](docs/reference.md#search-and-image-tools) for storage and access rules.
  55. Auto-review operates after Harness policy requires approval; it does not bypass that policy. See [Auto-review behavior](docs/auto-review.md) before enabling it.
  56. **Optional model quota observation:** profile composition can set `enableQuotaTool: true` and reload the plugin to expose the read-only `codex_connect_quota` tool. It is off by default and has no custom settings-card toggle. It reports shared Codex window percentages, reset times and freshness, excluding balances and account identifiers. See [quota observation](docs/quota-tool.md) and the optional [skill example](docs/skills/codex-quota-awareness/SKILL.md). Percentages are not task budgets; resource limits never justify dropping requirements, tests or safety checks.
  57. ## FAQ and important limits
  58. ### Where are my credentials stored?
  59. OAuth credentials are stored on the host running DSH and used there to authenticate and send requests to OpenAI. Normal browser account responses return account summaries, not raw tokens. A remote browser device is not necessarily the DSH host.
  60. ### Does uninstalling sign me out?
  61. No. OAuth state is stored separately at `$DSH_HOME/.openai-codex-auth.json` (`~/.dsh` by default). The plugin does not copy or modify `~/.codex/auth.json`. Use **Sign out all accounts**, or `logout` before uninstalling, only when deleting credentials is intentional.
  62. ### Can I switch accounts for different conversations?
  63. Subsequent Codex requests use the selected active account; conversations do not bind their own accounts. Fast Mode is conversation-scoped. Cancelling a new authorization preserves existing accounts; an explicit revoked-refresh response asks for reauthorization, while temporary failures preserve the account for retry. See [Account behavior](docs/reference.md#accounts-models-and-quota).
  64. ### Why does a listed model fail?
  65. Model HTTP/SSE failures include bounded, request-local diagnostic metadata after the existing error message. An `overloaded` message alone does not establish an account block. See [persistent-error diagnostics](docs/experiments/issue-219-diagnostics.md) for scope and reproduction.
  66. Account permissions, plugin/host compatibility, and network conditions all affect availability. Access on another client does not guarantee this integration will work. OpenAI controls model access, quota, context capacity, and service behavior; catalog entries are not proof of entitlement.
  67. ### Does changing client headers prevent persistent authorization failures?
  68. No such guarantee is established. Codex Connect is a third-party integration; it does not impersonate Codex Desktop or fabricate installation/attestation headers. The pi-ai model/OAuth route and auxiliary routes currently identify themselves differently. OpenAI's [App Server documentation](https://developers.openai.com/codex/app-server/) asks integrations to identify their own client with `clientInfo`; it does not establish acceptance rules for this plugin's direct backend calls. An `overloaded` message is not proof of a block. Capture the bounded error metadata and compare successful and failed windows before attributing the cause; share request IDs privately, never tokens or full session archives.
  69. ### Can I keep the original `dsh-codex` plugin installed?
  70. Not in the same effective configuration: both register `openai-codex`. Follow [MIGRATION.md](MIGRATION.md); remove only the confirmed conflicting entry, not credentials or unrelated providers.
  71. ### What do diagnostics prove?
  72. `doctor` is local. Capability and reviewer probes may make network requests and consume quota when their preconditions are met. `auto-review-probe` checks only the reviewer route and structured response, not the full Harness approval integration or execution of the reviewed action. Commands, limits, and exit codes are in the [diagnostics reference](docs/reference.md#capability-probes).
  73. A missing entry in [verified-compatibility.json](verified-compatibility.json) means a DSH/plugin combination is unverified, not known to be broken. Do not infer support for newer hosts from an older pairing.
  74. ## Documentation and development
  75. - [Installation and upgrades](INSTALL.md)
  76. - [Release history](docs/release-notes/README.md)
  77. - [Configuration, diagnostics, and recovery](docs/reference.md)
  78. - [Local request metrics: enable, report, and disable](docs/request-metrics.md)
  79. - [Explicit, bounded bili preflight activity (source change; default off)](docs/preflight-activity.md)
  80. - [Migration from `dsh-codex`](MIGRATION.md)
  81. - [Architecture and security details](docs/design.md)
  82. - [Auto-review behavior](docs/auto-review.md)
  83. - [Release runbook](RELEASING.md), [Contributing](CONTRIBUTING.md), and [Security policy](SECURITY.md)
  84. ```sh
  85. pnpm install --frozen-lockfile
  86. pnpm run check
  87. pnpm run test:browser
  88. pnpm run check:dsh-install
  89. ```
  90. `check` covers static checks, unit tests, build, compatibility, and packaging. `lint:metadata` checks package and release rules; `lint:source` checks host and browser TypeScript for unhandled or misused promises, invalid awaits, duplicate cases, and unreachable code. Browser regression and isolated DSH installation are separate commands. These checks use no real OAuth authorization and do not replace real-account acceptance.
  91. ## License and acknowledgements
  92. Copyright 2026 Frank Song for Codex Connect modifications and additional work. This project contains software derived from [Yan-Zero/dsh-codex](https://github.com/Yan-Zero/dsh-codex); Copyright 2026 Yan-Zero is retained for upstream material. Both are distributed under Apache-2.0; see [NOTICE](NOTICE).
  93. Published `0.2.0-alpha.1` adds `gpt-6.1-sol` to the manual model catalog and configuration selector. It exposes Low, Medium, High, Xhigh and Max; Default omits effort, and Ultra orchestration is unsupported. At that release, the Codex fallback was 272,000 tokens with an optional 872,000 local ceiling, not the API product window or proof of account access. See [metadata and validation](docs/agent-notes/gpt61-sol-support.md). No Adaptive Task grants are expanded.
  94. Alpha 5 capability calibration: the [source comparison](docs/agent-notes/gpt61-capability-calibration.md) distinguishes the pinned 272k fallback/872k local ceiling, official Work/Codex product text advertising 500k surfaced in search results, and separate API limits. That historical change refreshed only Sol61's policy-source pin; then-current defaults, native-provider metadata precedence and Fast/effort behavior were unchanged. No account/endpoint capacity was verified.
  95. Published base-default follow-up for #338: Sol61 now uses a dedicated **500,000-token** base default for its missing entry and known old bundled-static metadata, following the official Work/Codex product default. Explicit provider metadata and user overrides keep precedence; other models, output limits and the 872,000 local override ceiling are unchanged. [Scope and evidence](docs/agent-notes/sol61-context-default.md) distinguish the calibrated default from measured route capacity.
  96. Published in Alpha 11: `gpt-6.1-terra` is available through the manual catalog and configuration selector, with text/image input and existing Responses tools. Its official Codex fallback is 500,000 tokens with an optional 872,000 local ceiling and 128,000 output limit; native provider metadata wins, with the same effort mask as Sol61. Low, Medium, High, Xhigh and Max are exposed; Default omits effort. API `none` is not advertised by the pinned OAuth catalog, and Ultra orchestration is unsupported. This does not add a desktop Computer Use executor or expand Ultrafast eligibility. [Sources, scope and synthetic validation](docs/agent-notes/gpt61-terra-support.md); real-account access remains unverified.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.