DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-codex-canvas

DeepSeek Harness tool plugin that generates images through Codex CLI and gpt-image-2.

UI & ProductivityDeveloper ToolsBrowser & WebRemote Execution

Install

Awaiting GitHub sync

Repository Intelligence

AI-assisted, source-grounded explanation based on the public repository snapshot. It does not replace compatibility or security verification.

source-grounded
dsh-codex-canvas adds an agent-facing `image_gen` tool to DeepSeek Harness. It invokes `codex exec` through the Harness subprocess interface, writes generated images to the session workspace, and defaults to background jobs for longer generations.

Key Capabilities

  • Registers `image_gen(prompt, file_name, run_in_background?)` for agents.
  • Uses Codex CLI with gpt-image-2 to generate images.
  • Runs generation through `ctx.subprocess` and can use background jobs via `ctx.jobs`.
  • Writes output under `images/<file_name>` in the session workspace.
  • Supports configuration of the Codex executable, foreground timeout, termination grace period, and child-process environment variables.
  • Attempts to recover a generated image when Codex writes it to its generated-images directory instead of the requested workspace path.

Useful For

  • Letting DeepSeek Harness Web UI agents create image assets from natural-language prompts.
  • Generating illustrations, icons, or other image files into a session workspace.
  • Running image generation asynchronously and collecting results with `job_output`.
  • Using a logged-in ChatGPT Codex CLI setup rather than configuring an OpenAI API key.

Who It Fits

  • DeepSeek Harness users running the Web UI.
  • Users with Codex CLI installed and authenticated through ChatGPT.
  • Agent workflows that need generated image files in their workspace.

Documented Limitations

  • Requires a machine-level installation of `@openai/codex` and a completed `codex login`.
  • Generation depends on Codex CLI and network access to OpenAI; proxy configuration may be required in restricted networks.
  • Background generation returns a job ID and requires collection through the standard `job_output` tool.
  • Git-based installation may require pnpm build authorization; a pre-built tarball is documented as an alternative.
  • The README documents Windows-specific Codex host installation issues.

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 0 runtime, 8 development, 0 peer, and 0 optional dependencies.

info
Prepare Script Detected

package.json declares a prepare lifecycle script that may run during relevant package installation workflows.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
License Not Declared

GitHub did not report an SPDX license for this repository snapshot.

low
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Traceable source and registry metadata for this entry, kept separate from runtime verification.

Source repository
mindcarver/dsh-codex-canvas
Registry source
Public GitHub repository
Source snapshot
ea9cf0cd2473
Artifact type
plugin
AI enrichment
gpt-5.6-terra · 2026-08-14
Prompt version
dsh-plugin-enrichment-v3

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.

Repository Activity

GitHub stars
0
Forks
0
Open issues
0
Last commit
2026-08-14
Last release