Logan CusanoandClaude Sonnet 5
7189ba03e4
drb-correlation-review on the prior commit flagged two ways the per-scene transcript could silently fall back to the whole-call text: 1. _build_transcript_block numbered transmissions "1." while the prompt says "0-based indices" — a model echoing the labels it saw returned 1-based indices, shifting every scene's slice by one. Labels are now "0." to match the documented contract (also fixes the same latent skew in _build_scene_embed_text / #80). 2. An empty join (bad / out-of-range / non-int indices) hit `transcript or call_doc.get(...)` in _build_context and fell back to the whole-call transcript — re-opening the leak exactly when indices are wrong. The slice now falls back to this call's own whole transcript *before* _build_context sees it, so it is never "". Non-int and negative indices are rejected rather than raising. Slice logic extracted to `_scene_transcript_text` with a dedicated test file (4 cases: subset, corrected-wins, no-indices fallback, bad-indices fallback). Call-doc fallback kept (sweep / no-scene path) per the review. Also restored the `-> ` spacing lost in the prior commit's kwarg edit. Full c2-core suite green: 300 passed (sandboxed venv). Still DO NOT MERGE until the measurement window closes. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
41 lines
1.8 KiB
Python
41 lines
1.8 KiB
Python
"""
|
|
server-26#102 — a scene is correlated on its OWN transcript, not the whole call.
|
|
|
|
_scene_transcript_text slices the segments a scene owns. It must never return
|
|
"" (an empty slice would let incident_correlator._build_context fall back to
|
|
the call doc's whole-call transcript, re-opening the leak in exactly the case
|
|
— bad indices — where it matters).
|
|
"""
|
|
from app.internal.intelligence import _scene_transcript_text
|
|
|
|
SEGS = [
|
|
{"text": "structure fire, 12 Main"},
|
|
{"text": "engine 4 responding"},
|
|
{"text": "traffic stop, plate ABC"},
|
|
{"text": "one occupant"},
|
|
]
|
|
WHOLE = "structure fire, 12 Main engine 4 responding traffic stop, plate ABC one occupant"
|
|
|
|
|
|
def test_scene_owns_a_subset_of_segments():
|
|
assert _scene_transcript_text(WHOLE, SEGS, [0, 1], None) == "structure fire, 12 Main engine 4 responding"
|
|
assert _scene_transcript_text(WHOLE, SEGS, [2, 3], None) == "traffic stop, plate ABC one occupant"
|
|
|
|
|
|
def test_corrected_text_wins_when_present():
|
|
assert _scene_transcript_text(WHOLE, SEGS, [0], "cleaned up text") == "cleaned up text"
|
|
|
|
|
|
def test_no_segment_indices_falls_back_to_whole_call():
|
|
# single-segment calls are never numbered by _build_transcript_block → null indices
|
|
assert _scene_transcript_text(WHOLE, SEGS, None, None) == WHOLE
|
|
assert _scene_transcript_text(WHOLE, None, [0, 1], None) == WHOLE
|
|
|
|
|
|
def test_out_of_range_or_nonint_indices_fall_back_never_empty():
|
|
assert _scene_transcript_text(WHOLE, SEGS, [9, 10], None) == WHOLE # all out of range
|
|
assert _scene_transcript_text(WHOLE, SEGS, ["1", "2"], None) == WHOLE # 1-based strings, rejected
|
|
assert _scene_transcript_text(WHOLE, SEGS, [-1], None) == WHOLE # negative
|
|
# partial validity: keep what's in range
|
|
assert _scene_transcript_text(WHOLE, SEGS, [3, 99], None) == "one occupant"
|