Requested-command output is rendered by the inline pane whenever it is
expanded. Keep the backing terminal block hidden in both states so
collapsing the pane does not move the output to the bottom of the
conversation.
- Track user-initiated expansion state to avoid auto-collapse conflicts
- Invert inline action visibility so terminal block hides while inline pane owns the expanded body
- Add scrollable output rendering in requested command expanded view
- Simplify CLI monitor nudge message and extract to reusable method
- Show only latest user query and assistant text in monitor task transcript
- Add handle_ctrl_c_for_conversation to status bar for child agent cancellation
- Update rig_request tests for adjusted monitor nudge wording
Ensure parallel tool results finish before follow-ups, preserve warping
status across exchanges, clean up streams before crosscheck reviews, and
restore terminal focus when conversations complete. Remove temporary
debug
logging.
- Gate server requests on available credentials
- Run local child agents directly without a parent run ID
- Include command IDs in Bedrock context and recognize transfer tools
Add the 'Crosscheck Work' experiment to the Agents settings. When enabled,
a reviewer sub-agent is spawned after the main agent finishes a turn (with
no pending tool calls). The reviewer critiques the output using a dedicated
system prompt focused on correctness, simplicity, and code quality. If the
reviewer does not respond with 'LGTM!', its feedback is injected as a
synthetic user query back to the main agent, which must address it. This
loop continues until the reviewer approves or max iterations is reached.
Components:
- Feature flag: CrosscheckWork (enabled in DOGFOOD_FLAGS)
- Settings: agents.experiments.crosscheck_enabled,
agents.experiments.crosscheck_model_id,
agents.experiments.crosscheck_max_iterations
- Settings UI: new 'Experiments' subpage under Agents
- Crosscheck module: app/src/ai/crosscheck/ with prompt, reviewer model
- Controller integration: hooks into AfterStreamFinished when no actions
are queued, triggers reviewer, handles feedback injection
- Provider support: OpenAI-compatible and Bedrock direct invocation
- Safety: max iteration guard, error handling, reset on new user query
Ryan Ward
rkw6086