You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
[FEATURE]: Add /dump-context command for inspecting inference context #14674
I have verified this feature I'm about to request hasn't been suggested before.
Describe the enhancement you want to request
When debugging agent behavior or prompt engineering, there's no way to see the full context that gets sent to the provider — the assembled system prompt, message history, and provider options. You have to read the source code and mentally trace LLM.stream() to understand what the model actually receives.
A /dump-context slash command that writes the full inference context to a file would help. Two variants:
/dump-context — human-readable text with sections for system prompt, messages, and provider options
/dump-context-json — structured JSON for programmatic use
Output goes to .opencode/dumps/ in the project directory. Gated behind experimental.dump_context config flag, disabled by default.
Why would you possibly want this on your workflow?
Prompt debugging: see exactly what system prompt the model receives after all layers are assembled
Provider comparison: dump context, switch providers, compare what each one gets
Understanding compaction: see what the context looks like after compaction has run
Bug reports: attach the actual context when reporting unexpected model behavior
Reacted by GarrettGu, Tamás Táncos, Rico, cos3345678, Nick Cellino, Tefa, Bo Jiang, Jari Pennanen, Jamison, Faisal Hakim and 10 more
If your request is meaningfully distinct from those, feel free to clarify the differences.
Those issues request debug log lines, runtime telemetry metrics, or compaction diagnostics. This is different — it's a one-shot file dump of the full assembled inference payload (system prompt + messages + provider options) so you can inspect exactly what the model receives at any point.
Activity
github-actions commentedon Feb 22, 2026
This issue might be a duplicate of or closely related to existing issues. Please check:
If your request is meaningfully distinct from those, feel free to clarify the differences.
ualtinok commentedon Feb 22, 2026
Those issues request debug log lines, runtime telemetry metrics, or compaction diagnostics. This is different — it's a one-shot file dump of the full assembled inference payload (system prompt + messages + provider options) so you can inspect exactly what the model receives at any point.
VictorTaelin commentedon Mar 2, 2026
this is a very important feature
alesspalma commentedon Mar 16, 2026
any update on this?
katsar0v commentedon Mar 29, 2026
I also want this
Cold-sand commentedon Apr 1, 2026
This feature is very importan for me
jepachecoam commentedon Apr 6, 2026
This feature is very importan for me X2
tomasz-grz commentedon Apr 17, 2026
+1
ualtinok commentedon Apr 23, 2026
Closing the issue as I published new plugin that does this in a better way:
https://github.com/cortexkit/opencode-interceptor