icassp2027-experiment/test_adjudicate_easycom_eot_int_candidates.py

"""Tests for wearer-entry/INT DeepSeek suggestion validation without network calls."""

from __future__ import annotations

import unittest
from pathlib import Path
import json
import tempfile

from adjudicate_easycom_eot_int_candidates import (
    PROMPT_VERSION, SYSTEM_PROMPT, _progress_line, _transport_rows, build_user_prompt,
    exclude_reason_group, read_candidates,
    requires_semantic_adjudication, validate_decisions,
)


class EntryINTAdjudicationTests(unittest.TestCase):
    def test_progress_line_reports_items_percent_pass_and_elapsed_time(self) -> None:
        line = _progress_line(25, 100, label="pass 1/2 · batch 4/13", elapsed_seconds=65)
        self.assertIn("25/100 ( 25.0%)", line)
        self.assertIn("pass 1/2 · batch 4/13", line)
        self.assertTrue(line.endswith("01:05"))

    def test_prompt_contains_task_and_context(self) -> None:
        prompt = build_user_prompt(
            [{"uid": "u1", "candidate_source": "WEARER_ONSET", "task": "wearer_entry",
              "temporal_evidence": {"wearer_duration": 2.0},
              "context": [{"transcription": "Yes."}]}],
            0,
        )
        self.assertIn("WEARER_ONSET", prompt)
        self.assertIn("wearer_duration", prompt)
        self.assertIn("Yes.", prompt)

    def test_system_prompt_treats_laughter_as_nonlexical_floor_feedback(self) -> None:
        self.assertEqual(PROMPT_VERSION, "easycom-wearer-boundary-semantic-prelabel-v15")
        self.assertIn("opportunity_options", SYSTEM_PROMPT)
        self.assertIn("t_w < t_o < t_y never proves takeover", SYSTEM_PROMPT)
        self.assertIn("Every supplied WEARER_ONSET and WEARER_OFFSET is a raw observed", SYSTEM_PROMPT)
        self.assertIn("a transcription consisting of [L] denotes laughter-only vocalization", SYSTEM_PROMPT)
        self.assertIn("ENTRY_WEARER_BACKCHANNEL", SYSTEM_PROMPT)
        self.assertIn("INT_OTHER_BACKCHANNEL", SYSTEM_PROMPT)
        self.assertIn("Subtype precedence", SYSTEM_PROMPT)
        self.assertIn("same non-wearer resumes", SYSTEM_PROMPT)
        self.assertIn("different non-wearer takes", SYSTEM_PROMPT)
        self.assertIn("This is not an uncertainty fallback", SYSTEM_PROMPT)
        self.assertIn("Apply this adjacency-pair rule before using brevity", SYSTEM_PROMPT)
        self.assertIn("Floor entry here means making the committed conversational response", SYSTEM_PROMPT)
        self.assertIn("does not answer a question, accept or reject a proposal", SYSTEM_PROMPT)
        self.assertIn('the wearer answers "Nope." at 54.15 s', SYSTEM_PROMPT)
        self.assertIn("participant 3 later speaks again", SYSTEM_PROMPT)
        self.assertIn("does not require a preceding non-wearer release", SYSTEM_PROMPT)
        self.assertIn("duration alone never determines floor function", SYSTEM_PROMPT)
        self.assertIn("normal wearer completion", SYSTEM_PROMPT)
        self.assertIn("relevant non-wearer actually takes", SYSTEM_PROMPT)
        self.assertIn("must not retroactively invalidate the preceding INT_YIELD", SYSTEM_PROMPT)
        self.assertIn("do not infer that a visible smile occurred", SYSTEM_PROMPT)
        self.assertIn("POSITIVE / INT_YIELD: subtype=null; exclude_reason=null", SYSTEM_PROMPT)
        self.assertIn("OUT_OF_SCOPE_WITHIN_TURN_CONTINUATION", SYSTEM_PROMPT)
        self.assertIn("DATA_TIMESTAMP_CORRUPTION", SYSTEM_PROMPT)
        self.assertNotIn("NOT_APPLICABLE", SYSTEM_PROMPT)
        self.assertNotIn("UNSURE", SYSTEM_PROMPT)
        self.assertNotIn('"needs_human_review"', SYSTEM_PROMPT)

    def test_decisions_require_exact_uid_and_vocabulary(self) -> None:
        payload = {
            "items": [
                {
                    "uid": "u1",
                    "verdict": "HARD_NEGATIVE",
                    "event_type": None,
                    "subtype": "INT_OTHER_BACKCHANNEL",
                    "confidence": 0.91,
                    "reason": "Brief feedback while the wearer continues.",
                    "needs_human_review": False,
                }
            ]
        }
        decisions = validate_decisions(payload, ["u1"])
        self.assertEqual(decisions[0]["subtype"], "INT_OTHER_BACKCHANNEL")
        self.assertTrue(decisions[0]["needs_human_review"])
        with self.assertRaisesRegex(ValueError, "mismatch"):
            validate_decisions({"items": []}, ["u1"])

    def test_model_needs_human_review_type_drift_is_ignored(self) -> None:
        payload = {
            "items": [{
                "uid": "u1", "verdict": "EXCLUDE", "event_type": None,
                "subtype": None, "exclude_reason": "INSUFFICIENT_EVIDENCE",
                "confidence": 0.4, "reason": "Ambiguous context.",
                "needs_human_review": "true",
            }]
        }
        decision = validate_decisions(payload, ["u1"])[0]
        self.assertTrue(decision["needs_human_review"])

    def test_removed_fallback_verdicts_are_rejected(self) -> None:
        for verdict in ("UNSURE", "NOT_APPLICABLE"):
            payload = {"items": [{
                "uid": "u1", "verdict": verdict, "event_type": None,
                "subtype": None, "confidence": 0.4, "reason": "Ambiguous context.",
            }]}
            with self.subTest(verdict=verdict), self.assertRaisesRegex(ValueError, "Invalid verdict"):
                validate_decisions(payload, ["u1"])

    def test_entry_positive_may_select_only_a_supplied_release(self) -> None:
        item = {
            "uid": "u1", "verdict": "POSITIVE", "event_type": "WEARER_ENTRY",
            "subtype": None, "selected_opportunity_uid": "release-2",
            "confidence": 0.9, "reason": "The wearer answers the second release.",
        }
        decision = validate_decisions(
            {"items": [item]}, ["u1"], {"u1": {"release-1", "release-2"}}
        )[0]
        self.assertEqual(decision["selected_opportunity_uid"], "release-2")
        with self.assertRaisesRegex(ValueError, "only a supplied opportunity"):
            validate_decisions(
                {"items": [{**item, "selected_opportunity_uid": "invented"}]},
                ["u1"],
                {"u1": {"release-1", "release-2"}},
            )
        optional = validate_decisions(
            {"items": [{**item, "selected_opportunity_uid": None}]},
            ["u1"], {"u1": {"release-1", "release-2"}},
        )[0]
        self.assertIsNone(optional["selected_opportunity_uid"])

    def test_irrelevant_selected_opportunity_is_cleared_without_retrying_label(self) -> None:
        for verdict, event_type, subtype in (
            ("POSITIVE", "INT_YIELD", None),
            ("HARD_NEGATIVE", None, "INT_OTHER_BACKCHANNEL"),
            ("EXCLUDE", None, None),
        ):
            with self.subTest(verdict=verdict):
                item = {
                    "uid": "u1",
                    "verdict": verdict,
                    "event_type": event_type,
                    "subtype": subtype,
                    "exclude_reason": (
                        "INSUFFICIENT_EVIDENCE" if verdict == "EXCLUDE" else None
                    ),
                    "selected_opportunity_uid": "copied-release",
                    "confidence": 0.8,
                    "reason": "Evidence-based decision.",
                }
                decision = validate_decisions(
                    {"items": [item]}, ["u1"],
                    {"u1": {"copied-release"}},
                    {"u1": "INT"},
                )[0]
                self.assertIsNone(decision["selected_opportunity_uid"])

    def test_exclude_reason_taxonomy_separates_scope_evidence_and_data(self) -> None:
        self.assertEqual(
            exclude_reason_group("OUT_OF_SCOPE_NORMAL_COMPLETION"), "OUT_OF_SCOPE"
        )
        self.assertEqual(
            exclude_reason_group("INSUFFICIENT_EVIDENCE"), "INSUFFICIENT_EVIDENCE"
        )
        self.assertEqual(
            exclude_reason_group("DATA_ANNOTATION_ERROR"), "DATA_QUALITY"
        )
        base = {
            "uid": "u1", "verdict": "EXCLUDE", "event_type": None,
            "subtype": None, "selected_opportunity_uid": None,
            "confidence": 0.4, "reason": "Not a scored event.",
        }
        with self.assertRaisesRegex(ValueError, "valid exclude_reason"):
            validate_decisions({"items": [base]}, ["u1"])
        with self.assertRaisesRegex(ValueError, "valid exclude_reason"):
            validate_decisions(
                {"items": [{**base, "exclude_reason": "ANNOTATION_ERROR"}]}, ["u1"]
            )

    def test_event_and_hard_negative_subtypes_match_candidate_family(self) -> None:
        positive = {
            "uid": "u1", "verdict": "POSITIVE", "event_type": "INT_YIELD",
            "subtype": None, "selected_opportunity_uid": None,
            "confidence": 0.8, "reason": "Wrong family.",
        }
        with self.assertRaisesRegex(ValueError, "ENTRY candidate requires WEARER_ENTRY"):
            validate_decisions(
                {"items": [positive]}, ["u1"], expected_families={"u1": "ENTRY"}
            )
        hard_negative = {
            "uid": "u1", "verdict": "HARD_NEGATIVE", "event_type": None,
            "subtype": "ENTRY_OTHER_MIDTURN_PAUSE", "selected_opportunity_uid": None,
            "confidence": 0.8, "reason": "Wrong family.",
        }
        with self.assertRaisesRegex(ValueError, "INT candidate requires an INT_"):
            validate_decisions(
                {"items": [hard_negative]}, ["u1"], expected_families={"u1": "INT"}
            )

    def test_markdown_escaped_uid_is_normalized_but_still_unique(self) -> None:
        item = {
            "uid": "Session\\_4/wearer\\_onset/00000024",
            "verdict": "POSITIVE",
            "event_type": "WEARER_ENTRY",
            "subtype": None,
            "confidence": 0.9,
            "reason": "Sustained wearer response after the other speaker stops.",
            "needs_human_review": False,
        }
        expected = "Session_4/wearer_onset/00000024"
        decision = validate_decisions({"items": [item]}, [expected])[0]
        self.assertEqual(decision["uid"], expected)
        with self.assertRaisesRegex(ValueError, "duplicate"):
            validate_decisions({"items": [item, {**item, "uid": expected}]}, [expected])

    def test_duplicate_rule_uids_are_disambiguated_with_provenance(self) -> None:
        with tempfile.TemporaryDirectory() as temporary:
            path = Path(temporary) / "candidates.jsonl"
            base = {"uid": "Session_4/other_to_other/00003600", "task": "wearer_entry"}
            rows = [
                {**base, "previous_other_participant_ids": [6], "incoming_other_participant_ids": [4]},
                {**base, "previous_other_participant_ids": [3], "incoming_other_participant_ids": [6]},
            ]
            path.write_text("".join(json.dumps(row) + "\n" for row in rows), encoding="utf-8")
            loaded = read_candidates(path)
            self.assertEqual(len({row["uid"] for row in loaded}), 2)
            self.assertTrue(all(row["uid_disambiguated_from"] == base["uid"] for row in loaded))

    def test_transport_ids_are_short_unique_and_reversible(self) -> None:
        rows = [{"uid": "Session_4/other_to_other/00003600/a"},
                {"uid": "Session_4/other_to_other/00003600/b"}]
        transported, mapping = _transport_rows(rows)
        self.assertEqual([row["uid"] for row in transported], ["item-0000", "item-0001"])
        self.assertEqual(mapping["item-0001"], rows[1]["uid"])

    def test_every_current_wearer_offset_is_sent_for_adjudication(self) -> None:
        control = {
            "candidate_source": "WEARER_OFFSET",
            "temporal_evidence": {
                "active_other_ids_before_offset": [],
                "active_other_ids_after_offset": [],
            },
        }
        crossing = {
            "candidate_source": "WEARER_OFFSET",
            "temporal_evidence": {
                "active_other_ids_before_offset": [4],
                "active_other_ids_after_offset": [4],
            },
        }
        speaker_change = {
            "candidate_source": "WEARER_OFFSET",
            "temporal_evidence": {
                "active_other_ids_before_offset": [3],
                "active_other_ids_after_offset": [4],
            },
        }
        self.assertTrue(requires_semantic_adjudication(control))
        self.assertTrue(requires_semantic_adjudication(crossing))
        self.assertTrue(requires_semantic_adjudication(speaker_change))
        self.assertFalse(requires_semantic_adjudication({"candidate_source": "WEARER_OFFSET_CONTROL"}))
        self.assertFalse(requires_semantic_adjudication({"candidate_source": "WEARER_ONSET_CONTROL"}))
        self.assertFalse(requires_semantic_adjudication({"candidate_source": "WEARER_RESUME"}))


if __name__ == "__main__":
    unittest.main()