3.2 KiB
RX watcher usage
Start
On the RX laptop, pull video-development and double-click:
tools\start_rx_watcher.cmd
The watcher stays in a visible console and polls origin/video-development every 30 seconds. It does not start ChatGPT, Codex or another agent.
Idle
While no new TASK_ID exists, the watcher performs only git fetch, reads the remote task file and compares IDs with .local/rx_agent_state.json. There is no model execution or token use.
New task
The console shows:
NEW TASK DETECTED
TASK ID =
TITLE =
SAFETY LEVEL =
HARDWARE ACCESS =
RF RX =
RF TX =
Choose [A] Approve, [D] Defer or [S] Stop watcher. RF TX also requires the exact phrase AUTHORIZE RF TX. Another RED action requires AUTHORIZE <TASK_ID>.
Approve and execute
After approval, open:
.local\rx_agent_outbox\<TASK_ID>\TASK.md
Transfer that prepared task to the chosen executor. The watcher records last_approved_task_id, which is required for result publication. Preparing the outbox is not evidence that the hardware task ran.
When the task is actually complete, run:
python -B tools/rx_agent_watcher.py --mark-completed <TASK_ID>
Publish READY
For RF001A_OTA_CAPTURE_003, first complete RF_HANDOFF_CHANNEL_TEST_001. Then create the strict READY JSON outside Git only after CLKIN is detected, the capture child is alive and the file is growing. Run:
python -B tools/rx_agent_watcher.py --publish-result <ready-json-path> --result-branch rx-node
On success, the watcher prints RX RESULT PUBLISH = PUBLISHED or UNCHANGED, the result commit, the independently confirmed RX RESULT REMOTE HEAD, and RF TX = 0. Report RX READY FOR TX = YES only after the remote HEAD equals the result commit.
The command fails if:
- the task was not approved locally;
- the TASK_ID differs;
- source_head differs from the checkout HEAD;
- origin/rx-node does not exist;
- the schema is invalid;
- Git commit or push fails.
A failed publication is not READY evidence and cannot authorize TX.
Model-free channel test
Before hardware access, while the MAIN watcher is running, execute:
python -B tools/rf_handoff_smoke.py --hold-seconds 7
It publishes synthetic READY and COMPLETE results through the real origin. Require the MAIN watcher to observe both and require COMPLETE as the final remote state. Failure blocks the hardware capture. REAL RX remains NOT_RUN and RF TX remains 0.
Publish COMPLETE
After capture completion, build the strict final JSON with state CAPTURE_COMPLETE and publish it with the same command:
python -B tools/rx_agent_watcher.py --publish-result <final-json-path> --result-branch rx-node
Only the two fixed result files are committed. Raw IQ, video, waveform, stdout, stderr and large logs stay outside Git.
Stop
Double-click:
tools\stop_rx_watcher.cmd
The script creates a local stop request and waits for the watcher PID to clear. A successful stop prints WATCHER STOPPED.
Dry run
From the repository root:
python -B tools/rx_agent_watcher.py --dry-run --once --approval approve --task-file tests/fixtures/watcher_test_task.md
The fake task is written under .local/rx_agent_outbox/WATCHER_TEST_001/. No Git fetch, SDR access, agent call, RF RX, RF TX, commit or push occurs.