- Replace thread-based remote state sync with subprocess (sync_remote_state.py)
to prevent thread pool exhaustion hanging the API
- Fix pipeline showing 'waiting' when a real step is running alongside a gate
- Fix watcher scanner path for linux accounts mode
- Disable label-master semantic review (Step A.5 + §4.5) per user request
- Correct field names: use is_model_correct_dev for accuracy, origin_predict_dev
for model output (not cleaned_predict)
- Add prohibition against putting test set data in relabel_candidates
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix session resume: remove messages.length>1 guard so sessionStorage
ID is used as resumeSessionId on first message (prevents new session
creation when user sends "继续")
- Fix config_set tool schema: add missing `items: {}` to array type in
oneOf (Azure OpenAI strict validation rejects it otherwise)
- Metrics chart: use actual target set filename from trigger text
instead of generic "target_subset" key
- Add sub-agent skill call logging to agent_runtime.py (full
prompt/response, no truncation)
- Various metric enrichment and dedup fixes in server.py
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Auto-inject human-review gate when agent asks question but forgets gate entry
- Add complex_dev/complex_base field docs to program.md metric_diff table
- Fix submit_sft.sh minor issues
- jupyter_runtime improvements
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- submit_sft.sh: pure SFT submission, prints JobID and exits (no embedded watcher)
- submit_cml_eval.sh: pure CML eval, reads workflow_id/version from config.yaml
- jupyter_runtime write_text: rewrite to use Contents API instead of terminal websocket
- SKILL.md: restrict trigger to explicit UI click only
- program.md: update §5.2 docs to reflect two-script workflow
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
wuyang6