    Finished `test` profile [unoptimized + debuginfo] target(s) in 0.47s
     Running tests/label_precision_benchmark.rs (target/debug/deps/label_precision_benchmark-c64808f7653fac86)

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

── PHASE 1 EARLY-PANIC METRICS DUMP (ingest failed: extraction stage 'entities' failed: structured-output fallback exhausted for schema 'EntityList'; last response: LLM error: HTTP Error: error sending request for url (http://localhost:11434/api/chat)) ──
  rql.entity.label_rejected_total: NO REJECTIONS RECORDED before failure
  → meaning either (a) extraction failed before reaching L2,
    OR (b) all extracted labels passed L2 (entities are in graph).
  All rql.* counters in snapshot (first 30):
    rql.db.insert_episode_with_group_ms [] histogram[1 samples]
    rql.ingest.chunk_count [] histogram[1 samples]
    rql.ingest.registry_override_applied [persisted=true] counter=1
    rql.db.list_entities_count [] histogram[1 samples]
    rql.db.list_entities_ms [] histogram[1 samples]
    rql.extraction.structured_call_attempt [schema=EntityList,arm=format_schema,model=qwen2.5:14b] counter=1
    rql.extraction.fallback_ladder_step [schema=EntityList,from_arm=format_schema,to_arm=llm_json_repair,model=qwen2.5:14b] counter=1
    rql.extraction.structured_call_attempt [schema=EntityList,arm=llm_json_repair,model=qwen2.5:14b] counter=1
    rql.extraction.fallback_ladder_step [schema=EntityList,from_arm=llm_json_repair,to_arm=delimited_tuple,model=qwen2.5:14b] counter=1
    rql.extraction.structured_call_attempt [schema=EntityList,arm=delimited_tuple,model=qwen2.5:14b] counter=1
    rql.extraction.fallback_ladder_step [schema=EntityList,from_arm=delimited_tuple,to_arm=prompt_only,model=qwen2.5:14b] counter=1
    rql.extraction.structured_call_attempt [schema=EntityList,arm=prompt_only,model=qwen2.5:14b] counter=1
── END EARLY-PANIC DIAGNOSTIC ──


thread 'label_precision_gte_0_75_on_mock_interview' (8073753) panicked at crates/kremory/tests/label_precision_benchmark.rs:278:32:
ingest of mock_interview fixture must succeed: ExtractionStage { stage: "entities", detail: "structured-output fallback exhausted for schema 'EntityList'; last response: LLM error: HTTP Error: error sending request for url (http://localhost:11434/api/chat)" }
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; 4 filtered out; finished in 360.36s

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