aws / aws/amazon-q-developer-cli

Feature Request: Add /tangent compact command to summarize tangent conversation before returning to main session

Open
#3,079 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Rust
Stars
2k
Forks
439
PR merge metrics
No merged PRs in 30d

Description

### Checks

- [x] I have searched [github.com/aws/amazon-q-developer-cli/issues](https://github.com/aws/amazon-q-developer-cli/issues?q=) and there are no duplicates of my issue
- [x] I have run `q doctor` in the affected terminal session
- [x] I have run `q restart` and replicated the issue again

### Operating system

macOS 15.6.1 (24G90)

### Expected behaviour

When in tangent mode with a long-running conversation, I should be able to use /tangent compact to:
1. Automatically summarize the entire tangent conversation (similar to how /compact works in main
sessions)
2. Return to the main session with the summary added to context
3. Preserve the key insights from the tangent without bringing back the full conversation history

This would be similar to /tangent tail but instead of only preserving the last Q&A pair, it would
intelligently summarize the entire tangent conversation.

### Actual behaviour

Currently, tangent mode only offers two exit options:
• /tangent - Returns to main session, discarding all tangent conversation
• /tangent tail - Returns to main session, preserving only the last question and answer

For long tangent conversations with multiple valuable insights, neither option is ideal:
• Plain /tangent loses all the information
• /tangent tail only captures the final exchange, missing earlier important context

### Steps to reproduce

1. Enable tangent mode: /experiment and select tangent mode
2. Enter tangent mode: /tangent
3. Have a multi-turn conversation (e.g., 5-10 exchanges exploring a complex topic)
4. Try to return to main session with a summary of the tangent
5. Realize only /tangent (discard all) or /tangent tail (keep last Q&A only) are available

### Environment

```yaml
[q-details]
version = "1.17.1"
hash = "52301a3b0f81abff5ecde04a02481734c5c7ecc4"
date = "2025-09-30T22:25:33.521557Z (2d ago)"
variant = "full"

[system-info]
os = "macOS 15.6.1 (24G90)"
chip = "Apple M1 Pro"
total-cores = 10
memory = "32.00 GB"

[environment]
cwd = "/Users/"
cli-path = "/Users/"
os = "Mac"
shell-path = "/bin/zsh"
shell-version = "5.9"
terminal = "iTerm 2"
install-method = "unknown"

[env-vars]
PATH = "/Users//bin:/Users//.asdf/shims:/Users//.asdf/bin:/Users//.rbenv/shims:/Users//bin:/Users//.rbenv/shims:/Users//.toolbox/bin:/opt/homebrew/opt/ruby/bin:/opt/homebrew/bin:/opt/homebrew/sbin:/usr/local/bin:/System/Cryptexes/App/usr/bin:/usr/bin:/bin:/usr/sbin:/sbin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/local/bin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/bin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/appleinternal/bin:/Library/Apple/usr/bin:/Users//.cargo/bin:/Applications/iTerm.app/Contents/Resources/utilities:/Users//.local/bin:/Users//Library/Application Support/JetBrains/Toolbox/scripts"
QTERM_SESSION_ID = ""
Q_SET_PARENT_CHECK = "1"
Q_TERM = "1.17.0"
SHELL = "/bin/zsh"
TERM = "xterm-256color"
__CFBundleIdentifier = "com.googlecode.iterm2"
```

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.