8a4d464a - Surface the vendor's actual review output from a lane run - #37
Closed
Danswar wants to merge 2 commits into
Closed
8a4d464a - Surface the vendor's actual review output from a lane run#37Danswar wants to merge 2 commits into
Danswar wants to merge 2 commits into
Conversation
agent lane run invokes grok/codex for real and captures the full output, but the CLI only ever printed a one-line STATUS/rc summary and discarded result.stdout — by the time launch() returns, the tmux pane it came from is already killed, so nothing downstream (gate record --evidence, a human watching the run) could ever see what the vendor actually found.
The --no-tmux runner captures raw vendor subprocess output (unlike the tmux path, whose capture-pane already drops escape sequences), so an ESC-led control sequence from a misbehaving vendor process could reach the terminal verbatim once printed. Strip C0/DEL control bytes (keeping tab/newline/CR) before printing either stream. Also add a stdout-content assertion for the `agent run` one-step-chain call site (tests/test_run.py) — only the `agent lane run` call site had one before, even though both were fixed.
Collaborator
Author
|
EN: DE: |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
EN:
`agent lane run` genuinely invokes grok/codex against a real diff, but the CLI only ever printed a one-line STATUS/rc summary and threw away the vendor's actual output. By the time `launch()` returns, the tmux pane it was captured from is already killed, so nothing downstream — `gate record --evidence`, a human watching the run — could ever see what the vendor found. Fixed both call sites (`agent lane run` and the `agent run` one-step chain) to print `result.stdout`/`result.stderr` before the summary line.
DE:
`agent lane run` ruft grok/codex tatsächlich mit einem echten Diff auf, aber die CLI hat bisher nur eine einzeilige STATUS/rc-Zusammenfassung ausgegeben und die eigentliche Vendor-Ausgabe verworfen. Sobald `launch()` zurückkehrt, ist die tmux-Pane, aus der sie stammt, bereits beendet — nichts Nachgelagertes (`gate record --evidence`, ein Mensch, der zusieht) konnte je sehen, was der Vendor gefunden hat. Beide Aufrufstellen (`agent lane run` und die `agent run`-Ein-Schritt-Kette) geben jetzt `result.stdout`/`result.stderr` vor der Zusammenfassungszeile aus.
Details
Found while manually driving a diagnostic `review` task against `RealUnitCH/web#27`'s real diff through Jonny Luca's dfxai instance: the grok quality lane ran for real (`STATUS=complete`) but produced no retrievable findings anywhere. Traced to `cmd_lane`/`cmd_run` in `main.py` never touching `result.stdout`.
Full local suite green: 423 passed, 1 skipped (agent-core integration test, needs that package importable).