OpenCode Content Review

Local OpenCode review-note tooling for model and release evaluations.

What It Does

• Adds a TUI slash command: /note.
• Lets the reviewer choose how many prompt/response pairs to capture.
• Lets the reviewer select or create a tag before saving.
• Saves each note as structured local JSONL under .opencode/reviews/<tag>/.
• Captures exact prompt text, model/version fields when available, reasoning effort, request IDs, tool inputs/outputs, and trace parts.
• Generates a minimal, academic-style HTML or PDF report.

Install From npm

Add the TUI plugin to .opencode/tui.json in the project where you want to review models:

{
  "$schema": "https://opencode.ai/tui.json",
  "plugin": [
    ["ryanvogel-opencode-note-review", {
      "defaultPairs": 1,
      "defaultTag": "General",
      "outputDir": ".opencode/reviews",
      "maxTextChars": 12000,
      "includeToolOutputs": true
    }]
  ]
}

Restart OpenCode after editing tui.json.

Install the report CLI globally if you want the opencode-review command available outside OpenCode:

npm install -g ryanvogel-opencode-note-review

You can also run the report CLI with npm exec:

npx ryanvogel-opencode-note-review report --help

Run the report command without arguments for an interactive setup flow:

opencode-review report

It asks for report name, notes input, output format, output path, and optional tag filter while showing defaults. The default notes input is .opencode/reviews, and the default output filename includes the report name and current date.

Install For Local Development

Build the package:

bun install
bun run build

For local development, point .opencode/tui.json at the built file:

{
  "$schema": "https://opencode.ai/tui.json",
  "plugin": [
    ["/Users/ryanvogel/dev/opencode-content-review/dist/tui.js", {
      "defaultPairs": 1,
      "defaultTag": "General",
      "outputDir": ".opencode/reviews",
      "maxTextChars": 12000,
      "includeToolOutputs": true
    }]
  ]
}

Restart OpenCode after editing tui.json.

Usage

In an OpenCode session, run:

/note

The plugin asks for the number of prompt/response pairs to capture, then asks you to select or create a tag, then opens a note prompt. It writes notes under the selected tag:

.opencode/reviews/<tag>/tag.json
.opencode/reviews/<tag>/notes.jsonl
.opencode/reviews/<tag>/notes/<note-id>.json

Each note is self-contained. For each captured pair, it stores the exact prompt, assistant output, model/provider IDs, request IDs when OpenCode exposes them, reasoning effort when available, token/cost metadata, tool inputs and outputs, raw message metadata, and trace parts such as reasoning, snapshots, patches, retries, and step markers.

Generate Report HTML

opencode-review report \
  --input .opencode/reviews \
  --out .opencode/reviews/reports/model-review.html \
  --title "GPT-5.5 Model Review"

Or after building:

opencode-review report --out .opencode/reviews/reports/model-review.html

If --title is omitted in an interactive terminal, the CLI asks for a report name. Default output filenames include the report name and current date, for example .opencode/reviews/reports/frontier-model-review-2026-05-13.pdf.

--input can be a single .jsonl file, a single note .json file, or a folder. Folder inputs are scanned recursively for .jsonl files and note_*.json notes, then deduped by note ID. This lets multiple reviewers send you their .opencode/reviews/<tag>/notes/*.json files or whole review folders.

Example combined folder workflow:

combined-notes/
  alice/note_20260511_120000_a1b2c3d4.json
  ben/notes.jsonl
  casey/reviews/notes/note_20260511_130000_e5f6g7h8.json

opencode-review report \
  --input combined-notes \
  --out reports/combined-model-review.pdf \
  --title "Combined Model Review"

Filter by tag:

opencode-review report \
  --input combined-notes \
  --tag gpt-5-5 \
  --out reports/gpt-5-5-review.pdf

Generate Report PDF

The CLI can render the report directly to PDF with headless Chrome. On macOS it automatically checks /Applications/Google Chrome.app/Contents/MacOS/Google Chrome; on other systems it checks common Chrome/Chromium executable names in PATH.

opencode-review report \
  --input .opencode/reviews \
  --pdf .opencode/reviews/reports/model-review.pdf \
  --title "GPT-5.5 Model Review"

You can also use a .pdf output path:

opencode-review report --out .opencode/reviews/reports/model-review.pdf

Useful PDF options:

• --html <path> writes the intermediate HTML used for PDF rendering.
• --keep-html writes a sidecar HTML file next to the PDF.
• --chrome-path <path> uses a specific Chrome or Chromium executable.
• --title <text> skips the interactive report-name prompt.
• --tag <name> filters by tag name or tag folder ID.

Notes

• Tool inputs and outputs are captured by default for technical review evidence. Set includeToolOutputs to false if notes get too large.
• maxTextChars limits each prompt and response body to prevent accidental giant reports.
• Use defaultPairs: "all" only for short review sessions.
• Use defaultTag to change the default tag shown in the tag picker.