r3b_chunk_regex_strip
Per-chunk regex meant to strip citation tags from the stream (ineffective: tags span chunks)
Guard successfull suite successchange categories: code, imports3 checks run, impact analysis 0.2 s
Guard, live
Live runs are turned off on this public site. The results below are recorded; live runs happen on the owner's runner.
Checks: targeted selection vs full suite
Recorded in RQ3 (2026-10-06). Its perf-gate figures predate the gate's warmup fix; see the corrections; the re-measured numbers are in the repair timeline below.
| check | selected by Guard | result | s | detail |
|---|---|---|---|---|
| unit:tests/test_retriever.py | no: exercises nothing this change touches | pass | 1.4 | 2 passed in 0.34s |
| unit:tests/test_prompts.py | no: exercises nothing this change touches | pass | 1.6 | 2 passed in 0.59s |
| check:citation_required | yes | pass | 10.3 | citation contract met in 0/34 answers on the PR vs 0/34 on base (-0.0 pts; budget -5 pts; p=1.00); via full answer path (incl. post-processing) |
| judge:ungrounded_answer | yes | skip | 0.0 | no judge model key configured (BYOK); judge not run |
| check:prompt_prefix_stable | no: exercises nothing this change touches | pass | 4.6 | requests share 3954 leading characters (base 3954, need 3558) |
| check:context_budget | no: exercises nothing this change touches | pass | 7.8 | largest prompt 980 tokens (base 980) against a budget of 3840; median 964 vs 964 |
| security:approval_gate | yes | pass | 1.5 | 1 approval test(s) (generated from the base revision): 1 passed in 0.31s |
| bench:chat_perf_gate | no: exercises workflow:app/main.py::POST /chat, but the change (code, imports) is not one it detects | pass | 45.6 | median p95 TTFT 243.4 -> 200.6 ms (-17.6%, pass; 3 runs each, runs overlap); prefix-cache hit 98% -> 98% |
Check run as posted to GitHub (markdown)
# No regressions in 3 targeted checks conclusion: success **Ran 3 of 8 suite items** selected from the behavior-to-code graph. Change categories: code, imports. ### Quality | check | result | detail | |---|---|---| | `check:citation_required` | **PASS** | citation contract met in 0/34 answers on the PR vs 0/34 on base (-0.0 pts; budget -5 pts; p=1.00); via full answer path (incl. post-processing) | | `judge:ungrounded_answer` | **SKIP** | no judge model key configured (BYOK); judge not run | ### Security | check | result | detail | |---|---|---| | `security:approval_gate` | **PASS** | 1 approval test(s) (generated from the base revision): 1 passed in 0.31s | <details><summary>Not run for this change</summary> - `unit:tests/test_retriever.py`: exercises nothing this change touches - `unit:tests/test_prompts.py`: exercises nothing this change touches - `check:prompt_prefix_stable`: exercises nothing this change touches - `check:context_budget`: exercises nothing this change touches - `bench:chat_perf_gate`: exercises workflow:app/main.py::POST /chat, but the change (code, imports) is not one it detects </details> ### What changed in the graph