    Finished `test` profile [unoptimized + debuginfo] target(s) in 0.20s
     Running tests/label_precision_benchmark.rs (target/debug/deps/label_precision_benchmark-37564da61aef374d)

running 1 test
label_precision_benchmark: model=gemma4-e2b
label_precision_benchmark: Engine::new receives Arc<Ollama> directly (NO ArcChatProvider wrapper). fn model() should return: 'gemma4-e2b'
[KREMORY_DEBUG] parse_entities_integer raw input (len=4):
null
[KREMORY_DEBUG end]
warn: failed to parse integer-id entity JSON after repair: invalid type: null, expected a sequence at line 1 column 4
[KREMORY_DEBUG] parse_entities_integer raw input (len=2):
{}
[KREMORY_DEBUG end]
[KREMORY_DEBUG] parse_entities_integer raw input (len=4):
null
[KREMORY_DEBUG end]
warn: failed to parse integer-id entity JSON after repair: invalid type: null, expected a sequence at line 1 column 4
label_precision: 0.0% (0/10 ground-truth name+label pairs matched)
  0 non-canonical labels (TD-012 indicator)

── PHASE 1 DIAGNOSTIC: Metrics snapshot ──
  rql.entity.label_rejected_total: NO REJECTIONS RECORDED
  Other rql.* counters in snapshot:
    rql.entity_types.default_seed_applied [("group_id", "default")] = 1
    rql.db.insert_episode_with_group_ms [] = 0
    rql.ingest.chunk_count [] = 0
    rql.db.list_entities_count [] = 0
    rql.db.list_entities_ms [] = 0
    rql.extraction.structured_call_attempt [("schema", "EntityListIntegerId"), ("arm", "llm_json_repair"), ("model", "gemma4-e2b")] = 3
    rql.extraction.repair_attempt [("schema", "unknown"), ("arm", "llm_json")] = 2
    rql.extraction.structured_call_success [("schema", "EntityListIntegerId"), ("arm", "llm_json_repair")] = 3
    rql.extraction.stage_ms [("stage", "entities")] = 0
    rql.extraction.json_parse_fail [] = 2
    rql.extraction.structured_call_attempt [("schema", "RelTypeList"), ("arm", "llm_json_repair"), ("model", "gemma4-e2b")] = 3
    rql.extraction.structured_call_success [("schema", "RelTypeList"), ("arm", "llm_json_repair")] = 3
    rql.extraction.stage_ms [("stage", "relations")] = 0
    rql.extraction.json_parse_ok [] = 6
    rql.extraction.structured_call_attempt [("schema", "TripletList"), ("arm", "llm_json_repair"), ("model", "gemma4-e2b")] = 3
    rql.extraction.structured_call_success [("schema", "TripletList"), ("arm", "llm_json_repair")] = 3
    rql.extraction.stage_ms [("stage", "triplets")] = 0
    rql.extraction.entity_count [] = 0
    rql.extraction.fact_count [] = 0
    rql.extraction.json_parse_ok [("path", "wrapped")] = 1
    rql.ingest.total_ms [] = 0
    rql.ingest.entity_count [] = 0
    rql.ingest.fact_count [] = 0
    rql.ingest.merge_count [] = 0
    rql.ingest.contradiction_count [] = 0
── END DIAGNOSTIC ──


thread 'label_precision_gte_0_75_on_mock_interview' (10264994) panicked at crates/kremory/tests/label_precision_benchmark.rs:382:5:
label_precision 0.0% (0/10) is below the 65% R1 threshold.
Pre-Phase-4 (TD-012 broken state) produces ≈ 0%. Post-L1+L2+L3 target >= 65%.
0 entities had non-canonical labels.
Check: StructuredCallBuilder FormatSchema arm is active for model 'gemma4-e2b'.
note: run with `RUST_BACKTRACE=1` environment variable to display a backtrace
test label_precision_gte_0_75_on_mock_interview ... FAILED

failures:

failures:
    label_precision_gte_0_75_on_mock_interview

test result: FAILED. 0 passed; 1 failed; 0 ignored; 0 measured; 5 filtered out; finished in 17.51s

error: test failed, to rerun pass `-p kremory --test label_precision_benchmark`
