Make EasyCom adjudication resumable

docs/easycom_event_review_tool.md

@@ -118,6 +118,30 @@ python3 adjudicate_easycom_eot_int_candidates.py \
   --allow-external-transcript-upload
 ```
 
+For SiliconFlow, keep the same API-key environment variable and select its
+OpenAI-compatible endpoint explicitly:
+
+```bash
+python3 adjudicate_easycom_eot_int_candidates.py \
+  --input reports/easycom_entry_int_sessions1_3_v14/easycom_eot_int_candidates.jsonl \
+  --output reports/easycom_entry_int_sessions1_3_v14/easycom_eot_int_deepseek.jsonl \
+  --base-url https://api.siliconflow.cn/v1 \
+  --model deepseek-ai/DeepSeek-V4-Flash \
+  --allow-external-transcript-upload
+```
+
+The default request batch remains 8. If a returned batch violates the strict
+label schema, the adjudicator isolates the bad record by recursively splitting
+8 to 4, 2, and 1. Each successful leaf batch is atomically recorded in
+`OUTPUT.checkpoint.json`; rerunning the identical command resumes from that
+checkpoint and does not request completed passes again. A singleton that still
+fails after `--max-retries` is written to `OUTPUT_STEM_pending.jsonl` for manual
+relabeling, while the remaining candidates continue. Provider/network failure
+does not create a semantic pending item: the command stops with its checkpoint
+intact and the identical command resumes later. Use `--checkpoint` or
+`--pending-output` to override the derived paths. `--overwrite` intentionally
+starts a fresh run instead of resuming.
+
 DeepSeek sees candidate source, structured timing, per-speaker activity, and
 transcript together. It returns one of `POSITIVE`, `HARD_NEGATIVE`, or
 `EXCLUDE`; positives additionally receive