## Product Feedback Summary

Open
#4,047 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
35/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Active
Tech stack
github
Domain
ai, desktop

Research direction

Start by reproducing the identical delegated task calls described for GitHub Copilot App 1.1.22 on Windows, comparing the refusal, verified result, and fabricated result. Review the custom-agent tool configuration and the shipped human-pasted-output mitigation. Done means real and fabricated tool results can be distinguished through verifiable provenance or an equivalent user-visible trust signal.

Written by the indexing model from the issue text.

Description

Product Feedback Summary

Issue: Custom agents in the GitHub Copilot App can non-deterministically fabricate entire tool-call results, not just prose — and this can't be reliably prevented with prompt instructions alone.

What happened: A controller agent needed to fetch a real GitHub issue. It has no direct shell tool, so it delegated to a task subagent. Across identical prompts, that subagent: refused (claimed no bash access), then succeeded once (real data, verified), then later claimed success again and returned a fully-formed, plausible JSON blob describing rich issue content — which was completely fabricated (the real issue was empty).

Why it matters: We added explicit "don't fabricate" and "quote raw tool output as evidence" instructions. Both failed, because the subagent fabricated the evidence itself. This shows prompt-level anti-hallucination guardrails have a ceiling — they can't stop a model from inventing structured "proof" of a tool call that never happened.

Root cause: Declared tool capabilities (tools: frontmatter) didn't match actual runtime access — the controller never had real bash; only a subagent could reach it, and that subagent was inconsistent about its own tool availability across identical invocations.

Ask: Expose verifiable tool-call provenance (e.g., an ID/timestamp/platform-verified marker) so agents and users can distinguish a real tool result from a fabricated one — this can't be solved by better prompting alone.

Our mitigation (shipped in the plugin): Made human-pasted CLI output the default, trusted fetch path, and require explicit human confirmation before treating any subagent-fetched data as ground truth.


Field Value
App version 1.1.22
OS Windows 10.0.26200
Theme GitHub
Path /chat
Tenure Week 19
Dominant language
No language data
Stars
2.1k
Forks
157
PR merge metrics
No merged PRs in 30d

Contributor guide

Open the contributing guide

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 github/app

All issues in github/app

Similar issues

More AI Infra & Agents issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.