Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

Support transcripts from other coding agents (Codex, Cursor, Gemini CLI, opencode)

Open
  • Is something wrong?
#5 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
45/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Quiet
Tech stack
rust
Domain
cli

Research direction

Start in src/transcript.rs and read the existing Claude Code normalization and discovery logic. Choose one agent and inspect its session format before adding a parser, default discovery, and a hand-written fixture under tests/fixtures/. Done means that agent produces ToolCall and AssistantText values with ordering, while the existing downstream checks continue to work.

Written by the indexing model from the issue text.

Description

agent-support enhancement help wanted

backcheck reads Claude Code transcripts today. Nothing about the idea is Claude-specific —
every coding agent writes a session log containing what it said and what it ran, which is all
the analysis needs.

Widening this is the single highest-leverage change to the project: the verification engine,
the runner parsers, and the tamper detection are all agent-agnostic already.

The shape of the work

Only src/transcript.rs is Claude-specific. It normalises a
session file into three things the rest of the code consumes:

  • ToolCall { seq, name, input, result } — what ran, and what it printed
  • AssistantText { seq, text, is_last } — what the agent said
  • ordering, so a claim can be compared against evidence that preceded it

Everything downstream (claims, evidence, verify, tamper, report) already works purely
against those types. Adding an agent means writing a parser that produces them, plus discovery
of where that agent stores its sessions.

Agents worth supporting

  • OpenAI Codex CLI — ~/.codex/sessions/
  • Cursor — agent session storage
  • Gemini CLI — ~/.gemini/
  • opencode
  • Aider — .aider.chat.history.md (a different shape: prose plus diffs)
  • GitHub Copilot CLI / coding agent
  • Amp, Cline, Roo

Suggested approach

  1. Introduce a Source trait (or an enum) with parse(path) -> Transcript and a
    discover() for the agent's default session location.
  2. Move the current Claude Code logic behind it, unchanged.
  3. Auto-detect by path and file shape, with --agent <name> to force it.
  4. Add a small fixture per agent under tests/fixtures/ — hand-written, never a real
    transcript, since those contain real code and sometimes secrets.

Starting with one agent end-to-end is much more useful than a framework for all of them.
Comment here with which you're taking so two people don't write the same parser.

Worth knowing

Claude Code does not record exit codes, which is why outcomes are recovered from printed
output. If another agent does record them, that is strictly better evidence — the design
should let a source say "I know the exit code" rather than forcing everything through text
parsing.

Dominant language
Rust
Stars
0
Forks
2
No merged PRs in 30d

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from VectorInstitute/backcheck

All issues in VectorInstitute/backcheck

Similar issues

More Rust issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.