   Compiling kremory v0.1.6 (/Users/jamessheen/Documents/Projects/Ideas/kremory/crates/kremory)
    Finished `test` profile [unoptimized + debuginfo] target(s) in 8.36s
     Running tests/label_precision_benchmark.rs (target/debug/deps/label_precision_benchmark-37564da61aef374d)

running 1 test
label_precision_benchmark: model=qwen2.5:14b
label_precision_benchmark: Engine::new receives Arc<Ollama> directly (NO ArcChatProvider wrapper). fn model() should return: 'qwen2.5:14b'
test label_precision_gte_0_75_on_mock_interview has been running for over 60 seconds
  extracted: 'Amazon Robotics' (id='amazon robotics') label='Entity'
  extracted: 'Amazon Robotics (Organisation)' (id='amazon robotics organisation') label='Entity'
  extracted: 'Boston' (id='boston') label='Entity'
  extracted: 'Boston Consulting Group' (id='boston consulting group') label='Entity'
  extracted: 'Boston Consulting Group (Organisation)' (id='boston consulting group organisation') label='Entity'
  extracted: 'Boston (Location)' (id='boston location') label='Entity'
  extracted: 'Morocco' (id='morocco') label='Entity'
  extracted: 'Morocco (Location)' (id='morocco location') label='Entity'
  extracted: 'Northeastern University' (id='northeastern university') label='Entity'
  extracted: 'Ria (implied from context, not directly quoted as a name but inferred to be the speaker's name in an interview setting based on typical job application process contexts.) - Since 'Ria' is mentioned as 'I'm Ria', it falls under Person type if we consider common conversational context for such introductions. However, without explicit context that this introduces her full name, we should treat her mention here more cautiously and strictly to direct quoted text alone which does not explicitly label her in a formal name capacity beyond self-identification as 'I'. If treating directly from given text, Ria would be Person if it's accepted she refers herself with a proper noun name in this context. Strictly speaking: ' (id='ria implied from context not directly quoted as a name but inferred to be the speakers name in an interview setting based on typical job application process contexts since ria is mentioned as im ria it falls under person type if we consider common conversational context for such introductions however without explicit context that this introduces her full name we should treat her mention here more cautiously and strictly to direct quoted text alone which does not explicitly label her in a formal name capacity beyond selfidentification as i if treating directly from given text ria would be person if its accepted she refers herself with a proper noun name in this context strictly speaking') label='Entity'
  extracted: 'Ria (implied from context, not directly quoted as a name but inferred to be the speaker's name in an interview setting based on typical job application process contexts.) - Since 'Ria' is mentioned as 'I'm Ria', it falls under Person type if we consider common conversational context for such introductions. However, without explicit context that this introduces her full name, we should treat her mention here more cautiously and strictly to direct quoted text alone which does not explicitly label her in a formal name capacity beyond self-identification as 'I'. If treating directly from given text, Ria would be Person if it's accepted she refers herself with a proper noun name in this context. Strictly speaking:  (Entity), Morocco (Location), Boston (Location), Northeastern University (Organisation), Amazon Robotics (Organisation), Boston Consulting Group (Organisation)' (id='ria implied from context not directly quoted as a name but inferred to be the speakers name in an interview setting based on typical job application process contexts since ria is mentioned as im ria it falls under person type if we consider common conversational context for such introductions however without explicit context that this introduces her full name we should treat her mention here more cautiously and strictly to direct quoted text alone which does not explicitly label her in a formal name capacity beyond selfidentification as i if treating directly from given text ria would be person if its accepted she refers herself with a proper noun name in this context strictly speaking entity morocco location boston location northeastern university organisation amazon robotics organisation boston consulting group organisation') label='Entity'
label_precision: 0.0% (0/10 ground-truth name+label pairs matched)
  11 non-canonical labels (TD-012 indicator)
  non-canonical entities: [("Amazon Robotics", "Entity"), ("Amazon Robotics (Organisation)", "Entity"), ("Boston", "Entity"), ("Boston Consulting Group", "Entity"), ("Boston Consulting Group (Organisation)", "Entity"), ("Boston (Location)", "Entity"), ("Morocco", "Entity"), ("Morocco (Location)", "Entity"), ("Northeastern University", "Entity"), ("Ria (implied from context, not directly quoted as a name but inferred to be the speaker's name in an interview setting based on typical job application process contexts.) - Since 'Ria' is mentioned as 'I'm Ria', it falls under Person type if we consider common conversational context for such introductions. However, without explicit context that this introduces her full name, we should treat her mention here more cautiously and strictly to direct quoted text alone which does not explicitly label her in a formal name capacity beyond self-identification as 'I'. If treating directly from given text, Ria would be Person if it's accepted she refers herself with a proper noun name in this context. Strictly speaking: ", "Entity"), ("Ria (implied from context, not directly quoted as a name but inferred to be the speaker's name in an interview setting based on typical job application process contexts.) - Since 'Ria' is mentioned as 'I'm Ria', it falls under Person type if we consider common conversational context for such introductions. However, without explicit context that this introduces her full name, we should treat her mention here more cautiously and strictly to direct quoted text alone which does not explicitly label her in a formal name capacity beyond self-identification as 'I'. If treating directly from given text, Ria would be Person if it's accepted she refers herself with a proper noun name in this context. Strictly speaking:  (Entity), Morocco (Location), Boston (Location), Northeastern University (Organisation), Amazon Robotics (Organisation), Boston Consulting Group (Organisation)", "Entity")]

── 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", "format_schema"), ("model", "qwen2.5:14b")] = 3
    rql.extraction.structured_call_success [("schema", "EntityListIntegerId"), ("arm", "format_schema")] = 3
    rql.extraction.stage_ms [("stage", "entities")] = 0
    rql.extraction.json_parse_ok [] = 9
    rql.extraction.structured_call_attempt [("schema", "RelTypeList"), ("arm", "format_schema"), ("model", "qwen2.5:14b")] = 3
    rql.extraction.structured_call_success [("schema", "RelTypeList"), ("arm", "format_schema")] = 3
    rql.extraction.stage_ms [("stage", "relations")] = 0
    rql.extraction.structured_call_attempt [("schema", "TripletList"), ("arm", "format_schema"), ("model", "qwen2.5:14b")] = 3
    rql.extraction.fallback_ladder_step [("schema", "TripletList"), ("from_arm", "format_schema"), ("to_arm", "llm_json_repair"), ("model", "qwen2.5:14b")] = 3
    rql.extraction.structured_call_attempt [("schema", "TripletList"), ("arm", "llm_json_repair"), ("model", "qwen2.5:14b")] = 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.db.insert_entity_with_group_ms [] = 0
    rql.db.set_entity_embedding_ms [] = 0
    rql.db.insert_episodic_edge_ms [] = 0
    rql.search.fts_facts_hits [] = 0
    rql.search.fts_facts_ms [] = 0
    rql.db.insert_fact_ms [] = 0
    rql.extraction.structured_call_attempt [("schema", "ContradictionVerdict"), ("arm", "format_schema"), ("model", "qwen2.5:14b")] = 1
    rql.extraction.structured_call_success [("schema", "ContradictionVerdict"), ("arm", "format_schema")] = 1
    rql.db.invalidate_fact_with_reason_ms [] = 0
    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
    rql.db.get_entity_ms [] = 0
── END DIAGNOSTIC ──


thread 'label_precision_gte_0_75_on_mock_interview' (9969692) 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%.
11 entities had non-canonical labels.
Check: StructuredCallBuilder FormatSchema arm is active for model 'qwen2.5:14b'.
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 406.77s

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