SILVER/NODEDC_1C
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Добавить post-repair validation в stage-loop

Browse Source
This commit is contained in:
dctouch
2026-05-09 12:47:04 +03:00
parent b4f50346cc
commit a3378a3d52
3 changed files with 139 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/orchestration/domain_scenario_loop_repo_adapter.md
+2
View File
@@ -157,6 +157,8 @@ python scripts/stage_agent_loop.py run-repair --manifest docs/orchestration/<sta
`--dry-run` writes `repair_coder.command.txt`, records `repair_execution_summary.json`, updates `stage_loop_summary.json`, and prints the exact non-interactive Codex command without changing code. Without `--dry-run`, it executes the coder command with the prepared `repair_prompt.md`, writes `repair_coder_result.json`, captures stdout/stderr, records `repair_execution_summary.json`, and updates the stage next action to rerun/ingest, inspect, or stop for a decision depending on the coder status. After a real coder patch, rerun the same semantic pack or GUI session and ingest the new `assistant-stage1-<id>`.
When the coder result is `patched`, the next `ingest-gui-run` is treated as post-repair validation for that repair iteration. `stage_loop_summary.json` records `latest_repair_validation` and `repair_validation_history`, including the validation run id, remaining P0/P1 findings, and whether the repair was actually accepted after replay. A patch without this rerun/ingest evidence is not a closed stage.
## Placeholder contract
Scenario questions can reference earlier step outputs with placeholders such as: