{"reportId":"c7c60faa-caf5-4133-86d3-fc61111515a5","traceId":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","status":"success","stage":"completed","henanGroupAssemblySummary":null,"requestedHenanGroupBucketTargets":null,"henanGroupTargetSummary":null,"currentStep":"report.state.completed","lastFailedStep":null,"stepCount":13,"steps":[{"seq":1,"spanId":"span_4c0523ab-1459-49f4-8d26-c715b9593aa7","parentSpanId":null,"layer":"service","stepCode":"report.record.created","stepName":"Create report record","status":"success","startedAt":"2026-05-18T16:13:56.409+00:00","endedAt":"2026-05-18T16:13:56.426+00:00","durationMs":17,"errorCode":null,"errorMessage":null,"inputSummary":{"formMode":null,"province":"山东","subjectType":"物理、化学、地理"},"outputSummary":{"stage":"created","reportId":"c7c60faa-caf5-4133-86d3-fc61111515a5"},"raw":{"id":34,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","span_id":"span_4c0523ab-1459-49f4-8d26-c715b9593aa7","parent_span_id":null,"seq":1,"layer":"service","step_code":"report.record.created","step_name":"Create report record","status":"success","input_summary":{"formMode":null,"province":"山东","subjectType":"物理、化学、地理"},"output_summary":{"stage":"created","reportId":"c7c60faa-caf5-4133-86d3-fc61111515a5"},"error_code":null,"error_message":null,"started_at":"2026-05-18T16:13:56.409+00:00","ended_at":"2026-05-18T16:13:56.426+00:00","duration_ms":17,"created_at":"2026-05-19T00:13:56+00:00","updated_at":"2026-05-19T00:13:56+00:00"}},{"seq":2,"spanId":"span_9ed1b6d1-c355-4b65-8ae6-16c0c6b535ac","parentSpanId":null,"layer":"service","stepCode":"report.state.queued","stepName":"Queue report generation","status":"success","startedAt":"2026-05-18T16:13:56.427+00:00","endedAt":"2026-05-18T16:13:56.428+00:00","durationMs":1,"errorCode":null,"errorMessage":null,"inputSummary":{"reportId":"c7c60faa-caf5-4133-86d3-fc61111515a5"},"outputSummary":{"stage":"queued","status":"pending"},"raw":{"id":35,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","span_id":"span_9ed1b6d1-c355-4b65-8ae6-16c0c6b535ac","parent_span_id":null,"seq":2,"layer":"service","step_code":"report.state.queued","step_name":"Queue report generation","status":"success","input_summary":{"reportId":"c7c60faa-caf5-4133-86d3-fc61111515a5"},"output_summary":{"stage":"queued","status":"pending"},"error_code":null,"error_message":null,"started_at":"2026-05-18T16:13:56.427+00:00","ended_at":"2026-05-18T16:13:56.428+00:00","duration_ms":1,"created_at":"2026-05-19T00:13:56+00:00","updated_at":"2026-05-19T00:13:56+00:00"}},{"seq":3,"spanId":"span_d63a6536-4cb3-47a4-afce-bd655cde9d33","parentSpanId":null,"layer":"service","stepCode":"report.generation.run","stepName":"Run report generation pipeline","status":"success","startedAt":"2026-05-18T16:13:56.439+00:00","endedAt":"2026-05-18T16:25:56.864+00:00","durationMs":720425,"errorCode":null,"errorMessage":null,"inputSummary":{"source":"after_response"},"outputSummary":{"stage":"completed","source":"after_response","status":"success"},"raw":{"id":36,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","span_id":"span_d63a6536-4cb3-47a4-afce-bd655cde9d33","parent_span_id":null,"seq":3,"layer":"service","step_code":"report.generation.run","step_name":"Run report generation pipeline","status":"success","input_summary":{"source":"after_response"},"output_summary":{"stage":"completed","source":"after_response","status":"success"},"error_code":null,"error_message":null,"started_at":"2026-05-18T16:13:56.439+00:00","ended_at":"2026-05-18T16:25:56.864+00:00","duration_ms":720425,"created_at":"2026-05-19T00:13:56+00:00","updated_at":"2026-05-19T00:25:56+00:00"}},{"seq":4,"spanId":"span_88b12376-140e-42b2-808a-94286bf9c703","parentSpanId":"span_d63a6536-4cb3-47a4-afce-bd655cde9d33","layer":"service","stepCode":"report.state.generating","stepName":"Set report state generating","status":"success","startedAt":"2026-05-18T16:13:56.439+00:00","endedAt":"2026-05-18T16:13:56.44+00:00","durationMs":1,"errorCode":null,"errorMessage":null,"inputSummary":null,"outputSummary":{"stage":"generating","status":"pending"},"raw":{"id":37,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","span_id":"span_88b12376-140e-42b2-808a-94286bf9c703","parent_span_id":"span_d63a6536-4cb3-47a4-afce-bd655cde9d33","seq":4,"layer":"service","step_code":"report.state.generating","step_name":"Set report state generating","status":"success","input_summary":null,"output_summary":{"stage":"generating","status":"pending"},"error_code":null,"error_message":null,"started_at":"2026-05-18T16:13:56.439+00:00","ended_at":"2026-05-18T16:13:56.44+00:00","duration_ms":1,"created_at":"2026-05-19T00:13:56+00:00","updated_at":"2026-05-19T00:13:56+00:00"}},{"seq":5,"spanId":"span_de7db260-8cfe-40c8-8a1c-be42eb7c9d38","parentSpanId":"span_d63a6536-4cb3-47a4-afce-bd655cde9d33","layer":"service","stepCode":"report.generation.execute","stepName":"Generate report content","status":"success","startedAt":"2026-05-18T16:13:56.441+00:00","endedAt":"2026-05-18T16:25:56.86+00:00","durationMs":720419,"errorCode":null,"errorMessage":null,"inputSummary":{"source":"after_response"},"outputSummary":{"hasContent":true,"contentType":"object"},"raw":{"id":38,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","span_id":"span_de7db260-8cfe-40c8-8a1c-be42eb7c9d38","parent_span_id":"span_d63a6536-4cb3-47a4-afce-bd655cde9d33","seq":5,"layer":"service","step_code":"report.generation.execute","step_name":"Generate report content","status":"success","input_summary":{"source":"after_response"},"output_summary":{"hasContent":true,"contentType":"object"},"error_code":null,"error_message":null,"started_at":"2026-05-18T16:13:56.441+00:00","ended_at":"2026-05-18T16:25:56.86+00:00","duration_ms":720419,"created_at":"2026-05-19T00:13:56+00:00","updated_at":"2026-05-19T00:25:56+00:00"}},{"seq":6,"spanId":"span_9c805b38-ac89-4ca3-a735-ae5c21db847f","parentSpanId":"span_de7db260-8cfe-40c8-8a1c-be42eb7c9d38","layer":"ai","stepCode":"report.guided_grounding.run","stepName":"Prepare guided local evidence package","status":"success","startedAt":"2026-05-18T16:13:56.442+00:00","endedAt":"2026-05-18T16:21:10.966+00:00","durationMs":434524,"errorCode":null,"errorMessage":null,"inputSummary":{"hasRank":true,"province":"山东","hasAdmissionsProvider":true},"outputSummary":{"status":"ready","bucketPipelines":{"safe_pool":{"round1":{"kept":26,"excluded":0,"downranked":0,"topDownrankReasons":[],"topExclusionReasons":[]},"round2":{"eligible":26,"highRisk":0,"topHighRiskReasons":[],"topExclusionReasons":[],"excludedByConstraints":0},"round3":{"rankedCount":26,"excludedByRound3":0},"round4":{"candidateCards":26,"excludedByRound4":0,"enrichmentMatchedCount":0}},"match_pool":{"round1":{"kept":50,"excluded":0,"downranked":0,"topDownrankReasons":[],"topExclusionReasons":[]},"round2":{"eligible":50,"highRisk":0,"topHighRiskReasons":[],"topExclusionReasons":[],"excludedByConstraints":0},"round3":{"rankedCount":50,"excludedByRound3":0},"round4":{"candidateCards":50,"excludedByRound4":0,"enrichmentMatchedCount":0}},"reach_pool":{"round1":{"kept":20,"excluded":0,"downranked":0,"topDownrankReasons":[],"topExclusionReasons":[]},"round2":{"eligible":20,"highRisk":0,"topHighRiskReasons":[],"topExclusionReasons":[],"excludedByConstraints":0},"round3":{"rankedCount":20,"excludedByRound3":0},"round4":{"candidateCards":20,"excludedByRound4":0,"enrichmentMatchedCount":0}}},"reviewedBatches":1,"finalEvidenceCount":96,"reviewedCandidates":96,"enrichmentMatchedCount":96},"raw":{"id":39,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","span_id":"span_9c805b38-ac89-4ca3-a735-ae5c21db847f","parent_span_id":"span_de7db260-8cfe-40c8-8a1c-be42eb7c9d38","seq":6,"layer":"ai","step_code":"report.guided_grounding.run","step_name":"Prepare guided local evidence package","status":"success","input_summary":{"hasRank":true,"province":"山东","hasAdmissionsProvider":true},"output_summary":{"status":"ready","bucketPipelines":{"safe_pool":{"round1":{"kept":26,"excluded":0,"downranked":0,"topDownrankReasons":[],"topExclusionReasons":[]},"round2":{"eligible":26,"highRisk":0,"topHighRiskReasons":[],"topExclusionReasons":[],"excludedByConstraints":0},"round3":{"rankedCount":26,"excludedByRound3":0},"round4":{"candidateCards":26,"excludedByRound4":0,"enrichmentMatchedCount":0}},"match_pool":{"round1":{"kept":50,"excluded":0,"downranked":0,"topDownrankReasons":[],"topExclusionReasons":[]},"round2":{"eligible":50,"highRisk":0,"topHighRiskReasons":[],"topExclusionReasons":[],"excludedByConstraints":0},"round3":{"rankedCount":50,"excludedByRound3":0},"round4":{"candidateCards":50,"excludedByRound4":0,"enrichmentMatchedCount":0}},"reach_pool":{"round1":{"kept":20,"excluded":0,"downranked":0,"topDownrankReasons":[],"topExclusionReasons":[]},"round2":{"eligible":20,"highRisk":0,"topHighRiskReasons":[],"topExclusionReasons":[],"excludedByConstraints":0},"round3":{"rankedCount":20,"excludedByRound3":0},"round4":{"candidateCards":20,"excludedByRound4":0,"enrichmentMatchedCount":0}}},"reviewedBatches":1,"finalEvidenceCount":96,"reviewedCandidates":96,"enrichmentMatchedCount":96},"error_code":null,"error_message":null,"started_at":"2026-05-18T16:13:56.442+00:00","ended_at":"2026-05-18T16:21:10.966+00:00","duration_ms":434524,"created_at":"2026-05-19T00:13:56+00:00","updated_at":"2026-05-19T00:21:10+00:00"}},{"seq":7,"spanId":"span_fb0192cf-d9b4-4beb-9126-67645aafc850","parentSpanId":"span_9c805b38-ac89-4ca3-a735-ae5c21db847f","layer":"ai","stepCode":"report.guided_grounding.semantic_query_plan","stepName":"Build semantic query plan","status":"success","startedAt":"2026-05-18T16:14:08.496+00:00","endedAt":"2026-05-18T16:14:11.723+00:00","durationMs":3227,"errorCode":null,"errorMessage":null,"inputSummary":{"hasRank":true,"province":"山东"},"outputSummary":{"rankWindow":"normal","provinceScope":"national","softAvoidCount":0,"hardExcludeCount":0,"preferredKeywordCount":15},"raw":{"id":40,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","span_id":"span_fb0192cf-d9b4-4beb-9126-67645aafc850","parent_span_id":"span_9c805b38-ac89-4ca3-a735-ae5c21db847f","seq":7,"layer":"ai","step_code":"report.guided_grounding.semantic_query_plan","step_name":"Build semantic query plan","status":"success","input_summary":{"hasRank":true,"province":"山东"},"output_summary":{"rankWindow":"normal","provinceScope":"national","softAvoidCount":0,"hardExcludeCount":0,"preferredKeywordCount":15},"error_code":null,"error_message":null,"started_at":"2026-05-18T16:14:08.496+00:00","ended_at":"2026-05-18T16:14:11.723+00:00","duration_ms":3227,"created_at":"2026-05-19T00:14:08+00:00","updated_at":"2026-05-19T00:14:11+00:00"}},{"seq":8,"spanId":"span_67e28b70-17f4-46c6-a531-7eb1dab5641d","parentSpanId":"span_9c805b38-ac89-4ca3-a735-ae5c21db847f","layer":"ai","stepCode":"report.guided_grounding.stage3_single_dimension_slicer","stepName":"Run guided stage3 single-dimension slicer","status":"success","startedAt":"2026-05-18T16:14:11.725+00:00","endedAt":"2026-05-18T16:21:10.936+00:00","durationMs":419211,"errorCode":null,"errorMessage":null,"inputSummary":{"referencePoolCounts":{"safe_pool":692,"match_pool":377,"reach_pool":316}},"outputSummary":{"rounds":4,"finalCounts":{"safe_pool":26,"match_pool":50,"reach_pool":20}},"raw":{"id":41,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","span_id":"span_67e28b70-17f4-46c6-a531-7eb1dab5641d","parent_span_id":"span_9c805b38-ac89-4ca3-a735-ae5c21db847f","seq":8,"layer":"ai","step_code":"report.guided_grounding.stage3_single_dimension_slicer","step_name":"Run guided stage3 single-dimension slicer","status":"success","input_summary":{"referencePoolCounts":{"safe_pool":692,"match_pool":377,"reach_pool":316}},"output_summary":{"rounds":4,"finalCounts":{"safe_pool":26,"match_pool":50,"reach_pool":20}},"error_code":null,"error_message":null,"started_at":"2026-05-18T16:14:11.725+00:00","ended_at":"2026-05-18T16:21:10.936+00:00","duration_ms":419211,"created_at":"2026-05-19T00:14:11+00:00","updated_at":"2026-05-19T00:21:10+00:00"}},{"seq":9,"spanId":"span_8168185a-836e-4e39-9e44-2c8b4c6e6c8e","parentSpanId":"span_9c805b38-ac89-4ca3-a735-ae5c21db847f","layer":"service","stepCode":"report.guided_grounding.final_assembly","stepName":"Assemble three bucket pipelines","status":"success","startedAt":"2026-05-18T16:21:10.939+00:00","endedAt":"2026-05-18T16:21:10.942+00:00","durationMs":3,"errorCode":null,"errorMessage":null,"inputSummary":{"bucketPipelines":{"safe_pool":26,"match_pool":50,"reach_pool":20}},"outputSummary":{"safePoolCount":26,"matchPoolCount":50,"reachPoolCount":20},"raw":{"id":42,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","span_id":"span_8168185a-836e-4e39-9e44-2c8b4c6e6c8e","parent_span_id":"span_9c805b38-ac89-4ca3-a735-ae5c21db847f","seq":9,"layer":"service","step_code":"report.guided_grounding.final_assembly","step_name":"Assemble three bucket pipelines","status":"success","input_summary":{"bucketPipelines":{"safe_pool":26,"match_pool":50,"reach_pool":20}},"output_summary":{"safePoolCount":26,"matchPoolCount":50,"reachPoolCount":20},"error_code":null,"error_message":null,"started_at":"2026-05-18T16:21:10.939+00:00","ended_at":"2026-05-18T16:21:10.942+00:00","duration_ms":3,"created_at":"2026-05-19T00:21:10+00:00","updated_at":"2026-05-19T00:21:10+00:00"}},{"seq":10,"spanId":"span_6165cb58-e144-4351-b034-25423e526ce3","parentSpanId":"span_9c805b38-ac89-4ca3-a735-ae5c21db847f","layer":"data","stepCode":"report.guided_grounding.enrichment_lookup","stepName":"Attach admission enrichment to ranked candidates","status":"success","startedAt":"2026-05-18T16:21:10.943+00:00","endedAt":"2026-05-18T16:21:10.964+00:00","durationMs":21,"errorCode":null,"errorMessage":null,"inputSummary":{"province":"山东","candidateCount":96},"outputSummary":{"candidateCount":96,"enrichmentMatchedCount":96},"raw":{"id":43,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","span_id":"span_6165cb58-e144-4351-b034-25423e526ce3","parent_span_id":"span_9c805b38-ac89-4ca3-a735-ae5c21db847f","seq":10,"layer":"data","step_code":"report.guided_grounding.enrichment_lookup","step_name":"Attach admission enrichment to ranked candidates","status":"success","input_summary":{"province":"山东","candidateCount":96},"output_summary":{"candidateCount":96,"enrichmentMatchedCount":96},"error_code":null,"error_message":null,"started_at":"2026-05-18T16:21:10.943+00:00","ended_at":"2026-05-18T16:21:10.964+00:00","duration_ms":21,"created_at":"2026-05-19T00:21:10+00:00","updated_at":"2026-05-19T00:21:10+00:00"}},{"seq":11,"spanId":"span_335f9cee-e3cd-458b-9933-66473e68d45a","parentSpanId":"span_d63a6536-4cb3-47a4-afce-bd655cde9d33","layer":"service","stepCode":"report.state.post_processing","stepName":"Set report state post processing","status":"success","startedAt":"2026-05-18T16:25:56.86+00:00","endedAt":"2026-05-18T16:25:56.861+00:00","durationMs":1,"errorCode":null,"errorMessage":null,"inputSummary":null,"outputSummary":{"stage":"post_processing","status":"pending"},"raw":{"id":44,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","span_id":"span_335f9cee-e3cd-458b-9933-66473e68d45a","parent_span_id":"span_d63a6536-4cb3-47a4-afce-bd655cde9d33","seq":11,"layer":"service","step_code":"report.state.post_processing","step_name":"Set report state post processing","status":"success","input_summary":null,"output_summary":{"stage":"post_processing","status":"pending"},"error_code":null,"error_message":null,"started_at":"2026-05-18T16:25:56.86+00:00","ended_at":"2026-05-18T16:25:56.861+00:00","duration_ms":1,"created_at":"2026-05-19T00:25:56+00:00","updated_at":"2026-05-19T00:25:56+00:00"}},{"seq":12,"spanId":"span_150dd53a-8706-4852-b16e-0614233284a1","parentSpanId":"span_d63a6536-4cb3-47a4-afce-bd655cde9d33","layer":"service","stepCode":"report.content.saved","stepName":"Persist report content","status":"success","startedAt":"2026-05-18T16:25:56.861+00:00","endedAt":"2026-05-18T16:25:56.863+00:00","durationMs":2,"errorCode":null,"errorMessage":null,"inputSummary":null,"outputSummary":{"hasContent":true},"raw":{"id":45,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","span_id":"span_150dd53a-8706-4852-b16e-0614233284a1","parent_span_id":"span_d63a6536-4cb3-47a4-afce-bd655cde9d33","seq":12,"layer":"service","step_code":"report.content.saved","step_name":"Persist report content","status":"success","input_summary":null,"output_summary":{"hasContent":true},"error_code":null,"error_message":null,"started_at":"2026-05-18T16:25:56.861+00:00","ended_at":"2026-05-18T16:25:56.863+00:00","duration_ms":2,"created_at":"2026-05-19T00:25:56+00:00","updated_at":"2026-05-19T00:25:56+00:00"}},{"seq":13,"spanId":"span_2a72dc11-ccb7-400c-96ff-f8aaa734de07","parentSpanId":"span_d63a6536-4cb3-47a4-afce-bd655cde9d33","layer":"service","stepCode":"report.state.completed","stepName":"Set report state completed","status":"success","startedAt":"2026-05-18T16:25:56.863+00:00","endedAt":"2026-05-18T16:25:56.864+00:00","durationMs":1,"errorCode":null,"errorMessage":null,"inputSummary":null,"outputSummary":{"stage":"completed","status":"success"},"raw":{"id":46,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","span_id":"span_2a72dc11-ccb7-400c-96ff-f8aaa734de07","parent_span_id":"span_d63a6536-4cb3-47a4-afce-bd655cde9d33","seq":13,"layer":"service","step_code":"report.state.completed","step_name":"Set report state completed","status":"success","input_summary":null,"output_summary":{"stage":"completed","status":"success"},"error_code":null,"error_message":null,"started_at":"2026-05-18T16:25:56.863+00:00","ended_at":"2026-05-18T16:25:56.864+00:00","duration_ms":1,"created_at":"2026-05-19T00:25:56+00:00","updated_at":"2026-05-19T00:25:56+00:00"}}],"eventCount":9,"aiCallCount":9,"promptRecordCount":9,"latestPromptRecord":{"id":18,"run_key":"c7c60faa-caf5-4133-86d3-fc61111515a5:b20c514c-07bb-45ba-b63a-071708eda229","report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","generation_attempt_no":1,"generation_source":"after_response:safe_pool","run_origin":"after_response","prompt_version":"report-v2-rank-first+report-guided-grounding-v1+bucket-v1","request_kind":"guided_safe_pool_report_generate","target_provider":"DeepSeek","target_model":"deepseek-chat","provider_order_json":["DeepSeek"],"form_data_json":{"rank":"25000","score":"500","gender":"男","province":"山东","student_name":"测试02","subject_type":"物理、化学、地理","path_priority":["考公 / 考编","国企 / 央企","考研深造","本科直接就业","市场化高薪"],"planning_mode":"full","decision_maker":"学生","accept_intensive":true,"willing_graduate":true,"accept_adjustment":null,"adjustment_policy":"not_applicable","school_preference":["211","双一流","公办优先"],"selected_subjects":["物理","化学","地理"],"accept_out_province":true,"prefer_home_province":"unsure"},"system_prompt":"slot_rating is the authoritative Stage3 structured field for safe_pool.\nRead the dynamic slot axis from the bucket package before making any structural explanation.\n- For every candidate you mention, echo candidate_id, source_bucket, and slot_rating exactly as provided.\n- You may not create candidates, remove candidate_id, or move a candidate between reach_pool, match_pool, and safe_pool.\n- You may not rewrite, compress, or alias slot_rating.\n- Your score, keep_priority, or ranking is only a within-slot soft signal; if uncertain, add risk_flags or uncertainty_reason instead of guessing.\n- Structural layering is a top-priority objective of this round.\n- Structural layering remains the highest-priority objective whenever it conflicts with weak or ambiguous preference signals.\n- slot_rating is a precomputed, read-only structural position label inside the candidate's own bucket.\n- Smaller slot numbers mean the candidate is closer to the upper edge of that bucket.\n- Larger slot numbers mean the candidate is closer to the buffer edge of that bucket.\n- slot_rating is not a school quality score, not a major value score, and not a final recommendation strength score.\n- You must not modify, rename, reassign, or reinterpret slot_rating.\n- You must not reassign slot_rating.\n- Use slot_rating directly when assigning round_score.\n- round_score is the only scoring field in this round and must be an integer from 0 to 100.\n- round_score must already reflect both round-specific fit and structural usefulness under the existing slot_rating.\n- Do not output any penalty field or any secondary keep score.\n- Do not treat smaller slot numbers as automatically better.\n- Do not treat larger slot numbers as automatically worse.\n- If head slots are structurally overcrowded, lower round_score directly instead of using a separate penalty field.\n- If a middle or buffer candidate remains viable and helps preserve bucket layering, raise round_score directly.\n- round_score is a final integrated evaluation score, not a single-factor enthusiasm score.\n- First judge whether the candidate is supported by the main factor of this round.\n- Then check whether the candidate's slot_rating is already overcrowded inside its own bucket.\n- If many candidates are already concentrated in the same slot_rating, even a good candidate should be actively downscored.\n- If the slot_rating is relatively sparse and the candidate is still reasonable under this round's main factor, it should be actively upscored.\n- The final round_score must reflect both round-specific fit and the candidate's contribution to slot_rating structure dispersion.\n- round_score must not ignore slot_rating density.\n- It is invalid if most candidates sharing the same slot_rating still receive similarly high scores without any structural separation.\n- It is also invalid if slot_rating scarcity or overcrowding has no visible effect on the final round_score.\n- reasons[0] must explain why the candidate should receive this round_score under its existing slot_rating.\n- reasons[1] must explain the round-specific fit or conflict.\n- Invalid output warning: if most viable candidates fall into adjacent middle scores, if score gaps are only cosmetic, or if slot_rating no longer meaningfully affects the final round_score, the output is invalid.\n- Missing or weak user signal should produce cautious and mostly stable scoring, not random churn.\n- You must not choose final submission order.\n- You must not invent candidates or cross-bucket comparisons.\nadmission_rate must stay fixed to 保底 for every safe plan.\nUse slot_rating as the only structured ordering axis inside safe_pool.\nEvaluate all fields with strict evidence-bounded reasoning.\nOutput format:\n- Return a JSON object only.\n- Use exactly these fixed fields and do not add, remove, rename, or merge any fields:\n- civil_service_friendly\n- soe_fit\n- grad_boost\n- reason\n- risk\n- alternative\n- undergrad_employment\n- grad_employment\n- All field values must be written in Chinese.\n- Every field must contain substantive content.\nEvidence boundary:\n- Use only these evidence sources: bucket-package evidence, expert_enrichment, history, risk_flags, and stated student preferences.\n- Do not use unsupported assumptions, school fame, city popularity, or generic praise as evidence.\n- If the evidence is weak, incomplete, or indirect, stay conservative and say so explicitly.\n- If the evidence does not support a strong claim, state what is missing or uncertain.\nField separation:\n- Each evaluative field must answer a different question.\n- Do not reuse the same praise, prestige signal, or generic employment language across multiple fields unless the evidence truly supports different conclusions.\n- Do not let school prestige, city heat, or vague “good employment” claims fill every field.\n- Do not use broad positive filler to cover for weak evidence.\nField definitions:\n- civil_service_friendly: Judge only civil-service and public-institution friendliness, including compatibility with 考公、考编、选调、事业单位、公共治理类岗位.\n- Focus on major eligibility, breadth of matching岗位, exam-route compatibility, and whether the program helps entry into public-sector tracks.\n- Do not substitute general stability, school prestige, or overall employment quality.\n- soe_fit: Judge only compatibility with SOE / central-enterprise / infrastructure / energy / grid / transport / telecom / manufacturing / other regulated-industry employment paths.\n- Focus on major relevance, industry linkage, and downstream job coverage.\n- Do not equate this with generic “good employment”.\n- grad_boost: Judge only the value of this option for 考研、保研、继续深造、research-platform upgrade, and credential upside.\n- Focus on discipline continuity, platform resources, research atmosphere, and post-graduate path uplift.\n- “Can take graduate exams” alone is not sufficient evidence.\n- reason: Answer \"why this school-major should enter the volunteer list, and how the user should use it\".\n- reason 必须像给家长和学生看的决策说明，不要写成档位归类模板。\n- This field must clearly cover all four of the following information roles:\n- 1. 院校看点: explain the school itself, such as school level, regional recognition, industry links, city resources, discipline strengths, or employment influence when evidence exists.\n- 2. 专业价值: explain why the major fits the student path, including civil-service, SOE, banking, audit, finance, graduate-study, technical, or transferable career paths when relevant.\n- 3. 录取判断: explain the score/rank fit, historical boundary, plan count, subject or group constraints, and popularity volatility that support this bucket position.\n- 4. 填报动作: give a practical placement or pairing suggestion, such as 冲刺区前段/中段/后段、稳妥区主体、保底区承接, or what kind of lower-risk option should accompany it.\n- Start from the school itself when evidence is available; the user should learn what this school is worth considering for, not only why it belongs to a bucket.\n- Cite 1-2 concrete support signals when possible.\n- Do not write generic praise.\n- Do not use empty phrases such as “就业面广”, “学校层次高”, “值得冲一冲”, or “录取概率较高” unless immediately supported by concrete school, major, admission, or placement evidence.\n- Do not simply repeat visible label-style conclusions such as “冲/稳/保”, “true”, or similar tags.\n- Write it as a short natural recommendation explanation, not as a checklist.\n- risk: Answer \"what is the single biggest risk of this option\".\n- Be short, concrete, and direct.\n- Prioritize the most important uncertainty or cost first, such as tight rank margin, major heat volatility, plan changes, city acceptance, or path uncertainty.\n- Avoid generic filler unless tied to a specific trigger.\n- alternative: Provide a lower-risk alternative in the same direction.\n- Reduce risk through one clear dimension change, such as lower city competition, lower school tier, lower major heat, safer program-group, or stronger historical margin.\n- Do not jump to a completely different direction.\n- undergrad_employment: Describe the likely direct employment exits if the student stops at the undergraduate level.\n- Focus on “本科阶段直接出口”: which industries,岗位 types, employer scenarios, or regional job markets are most likely after undergraduate graduation.\n- grad_employment: Describe the likely upgraded employment exits after graduate study or further academic progression.\n- Focus on “深造后的升级出口”: which higher-end, research-oriented, platform-oriented, or stronger career paths become more accessible after graduate study.\n- It must not repeat undergrad_employment.\nField writing requirements:\n- civil_service_friendly, soe_fit, and grad_boost must follow their own definitions strictly.\n- If civil_service_friendly, soe_fit, or grad_boost is weak, explicitly explain why it is weak instead of using vague positive language.\n- reason should be concise, specific, evidence-bounded, and ideally 3-5 sentences.\n- risk should name the single biggest uncertainty first.\n- alternative must remain in the same direction and become safer through one clear change.\n- undergrad_employment and grad_employment must be clearly differentiated and non-redundant.\nQuality bar:\n- Every field must be specific, non-redundant, and traceable to evidence.\n- Prefer precise, caveated judgments over broad positive statements.\n- If evidence is limited, it is better to be conservative than to overclaim.\n\nYou are safe_pool 专属的高考志愿保底方案生成器。\n\nYou only process safe_pool candidates. You do not process reach_pool or match_pool.\nYour task is to select, sort, and generate up to 26 truly safe plans from the provided safe_pool package; if local candidates are fewer than 26, do not invent or pad.\nYou are not allowed to invent new candidates outside the provided safe_pool package.\n\n一、核心目标\nYou must keep only candidates that satisfy all three conditions:\n1. 更稳: they have stronger downside protection than match-tier options, not merely lower school prestige or lower score threshold.\n2. 可接受: the student and family can still realistically accept the city, school level, major path, and future direction.\n3. 可解释: every plan can clearly explain its safety basis, acceptance basis, and main risk.\n\nThe priority order for safe_pool is:\nadmission feasibility > no hard-constraint conflict > student/family acceptability > clear professional path > within-bucket ranking.\n\n二、硬性禁止\nYou must exclude any candidate with:\n- missing or incomplete school / major / program-group / key admissions information\n- placeholder content such as 待确认, 待核实, 专业待确认, 院校待确认, 某大学, 某专业, ???, ***\n- clearly insufficient evidence to explain why it is safer\n- explicit conflict with student hard constraints\n- fake-safe reasoning that only depends on lower school tier, weaker city, or colder major\n- high likelihood that the student/family would not actually accept it\n- obvious conflict with path_priority and no valid explanation\n- candidates that do not belong to safe_pool\n\n三、判定流程\nFor every candidate, reason internally in this exact order:\n1. admission feasibility judgment\n2. risk exclusion judgment\n3. acceptability judgment\n4. safety-value judgment\n5. within-bucket ordering\nDo not skip steps.\n\n四、优先保留\nPrefer candidates with:\n- clearer safety margin than match bucket\n- explicit evidence from rank / score / plan / major-group / history\n- complete major naming and clear training direction\n- relatively stable direct-undergrad employment path\n- acceptable graduate-study extension\n- no conflict with path_priority\n- city, school level, and institution type inside realistic family acceptance range\n- a clear but tolerable downside\n\n五、降权或排除\nDownrank or exclude candidates that:\n- prove safety only by lower score threshold\n- have unclear employment exit\n- obviously miss city preference\n- fall below school-level acceptance floor\n- clearly mismatch interests / strong subjects / path priorities\n- cannot support a concrete risk sentence\n- cannot offer a same-layer alternative\n\n六、输出要求\nReturn JSON only.\nTarget up to 26 plans; if candidate_table is undersized, output only the actual local candidates and mention local_candidate_shortage in bucket_summary.\nEvery plan.type must be exactly 保底.\nDo not output reach/match or other tier labels.\nDo not add schools or majors outside the provided safe_pool package.\nDo not invent score history, rank history, policies, or plan changes.\nIf evidence is insufficient, stay conservative and explicit about uncertainty.\n\n七、字段写法要求\nreason 必须像给家长和学生看的决策说明，不要写成“作为保底项……”这类档位归类模板。\n每条 reason 必须同时覆盖四类信息：\n1. 院校看点：说明学校本身值得看的地方，例如院校层次、区域认可度、行业资源、城市就业辐射、优势学科或平台价值；证据不足时要谨慎表达。\n2. 专业价值：说明该专业为什么匹配学生路径，例如考公、国企、银行、审计、财务、考研、技术岗或岗位迁移性。\n3. 录取判断：说明分数、位次、计划、历史边界、专业热度或专业组波动如何支撑其属于保底区。\n4. 填报动作：给出实际填报建议，例如作为保底区承接/底线项，是否保留，以及应搭配哪类同路径方案。\n不得空泛使用“就业面广”“学校层次高”“值得冲一冲”“录取概率较高”；如使用，必须紧跟具体院校、专业、录取或填报证据。\n\nrisk must be short, concrete, and focused on the main downside only.\nUse risk types such as:\n- 学校层次相对一般\n- 城市机会相对有限\n- 专业热度或行业弹性一般\n- 非目标城市\n- 非最优路径但可接受\n- 后续需复核招生计划或专业组变化\n\nalternative must stay near the same layer.\nIt should point to a similar school-level / city-range / professional-path / safety-profile alternative.\nDo not jump from safe items to obvious reach items.\n\n八、输出前自检\n- no more than 26 plans; fewer only when local candidates are insufficient or disqualified\n- every plan.type is exactly 保底\n- all plans come from safe_pool\n- no placeholders, no 待确认, no 待核实, no malformed major names\n- every plan explains why it is safer\n- every plan explains why it is still acceptable\n- every risk is concrete and non-generic\n- no fake-safe candidate justified only by lower score\n- no clear hard-constraint violation\n\nReturn strict JSON only.\n\nRequired JSON shape:\n{\n  \"bucket_summary\": \"string\",\n  \"plans\": [\n    {\n      \"type\": \"保底\",\n      \"school\": \"string\",\n      \"major\": \"string\",\n      \"admission_rate\": \"保底\",\n      \"civil_service_friendly\": \"string\",\n      \"soe_fit\": \"string\",\n      \"grad_boost\": \"string\",\n      \"reason\": \"string\",\n      \"risk\": \"string\",\n      \"alternative\": \"string\",\n      \"undergrad_employment\": \"string\",\n      \"grad_employment\": \"string\"\n    }\n  ]\n}","user_prompt":"请基于以下输入，只从 safe_pool 候选中生成 safe 桶志愿方案。\n\n你不能新增候选，不能输出其它桶，不能编造未提供的数据。\n请严格按照 System Prompt 的 safe_pool 判定流程执行。\n\n一、学生画像 student_form_json\n{\n  \"province\": \"山东\",\n  \"score\": \"500\",\n  \"rank\": \"25000\",\n  \"subject_type\": \"物理、化学、地理\",\n  \"gender\": \"男\",\n  \"target_city\": null,\n  \"accept_out_province\": true,\n  \"accept_adjustment\": null,\n  \"accept_intensive\": true,\n  \"willing_graduate\": true,\n  \"school_preference\": [\n    \"211\",\n    \"双一流\",\n    \"公办优先\"\n  ],\n  \"prefer_home_province\": \"unsure\",\n  \"decision_maker\": \"学生\",\n  \"path_priority\": [\n    \"考公 / 考编\",\n    \"国企 / 央企\",\n    \"考研深造\",\n    \"本科直接就业\",\n    \"市场化高薪\"\n  ],\n  \"interests\": [],\n  \"strong_subjects\": [],\n  \"special_notes\": null,\n  \"medical_notes\": null\n}\n\n重点关注：province, score, rank, subject_type, accept_out_province, accept_intensive, willing_graduate, target_city, path_priority, interests, strong_subjects, school_preference, special_notes, medical_notes\n\n二、语义查询计划 semantic_query_plan_json\n{\n  \"version\": \"guided-semantic-query-plan-v1\",\n  \"hard_exclude_major_keywords\": [],\n  \"soft_avoid_major_keywords\": [],\n  \"risk_reminder_keywords\": [],\n  \"preferred_major_keywords\": [\n    \"计算机\",\n    \"软件\",\n    \"电气\",\n    \"自动化\",\n    \"电子信息\",\n    \"通信\",\n    \"机械\",\n    \"材料\",\n    \"会计\",\n    \"财务管理\",\n    \"法学\",\n    \"金融\",\n    \"数据科学\",\n    \"人工智能\",\n    \"土木\"\n  ],\n  \"school_or_region_keywords\": [\n    \"211\",\n    \"双一流\",\n    \"公办\"\n  ],\n  \"query_strategy\": {\n    \"province_scope\": \"national\",\n    \"rank_window\": \"normal\",\n    \"candidate_target_count\": 240\n  },\n  \"interpretation_notes\": [\n    \"学生明确接受高强度学习，故无需排除高压力专业。\",\n    \"学生职业路径优先考公考编和国企央企，因此推荐专业已涵盖相关方向。\",\n    \"学生可接受出省，故省份范围设为全国。\",\n    \"位次25000在山东属中等，rank_window设为normal。\",\n    \"未发现需要硬排除或软回避的专业关键词。\"\n  ]\n}\n\n重点关注：hard constraints, soft avoid, high-risk reminders, preference keep, path priority interpretation\n\n三、safe 桶候选包 safe_bucket_package_json\n{\n  \"bucket_name\": \"safe_pool\",\n  \"candidate_table\": [\n    {\n      \"candidate_id\": \"local_8314d8f417d2\",\n      \"school\": \"四川农业大学\",\n      \"major\": \"数据科学与大数据技术(雅安校区)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30629，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_1188ff263a8b\",\n      \"school\": \"厦门大学\",\n      \"major\": \"数据科学与大数据技术(厦门大学马来西亚分校招生专业)(学费3万林吉特/学年；全英文授课，非英语语种考生慎报，外语单科不低于120分；入学第一学年内获得专业要求的达标英语成绩后开始学位课程学习；办学地点在马来西亚雪邦)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30546，计划 5\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_0301daa1ed0c\",\n      \"school\": \"西安科技大学\",\n      \"major\": \"电气工程及其自动化(菁英人才培养计划)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30309，计划 4\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_197ee346848f\",\n      \"school\": \"北京建筑大学\",\n      \"major\": \"自动化(大兴校区)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30159，计划 1\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_453c1948719b\",\n      \"school\": \"重庆邮电大学\",\n      \"major\": \"软件工程(三、四年级学费15000元/年)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30183，计划 16\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_9d4d585ce750\",\n      \"school\": \"北京语言大学\",\n      \"major\": \"金融学(数智金融)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30284，计划 1\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_2eb034533252\",\n      \"school\": \"西安邮电大学\",\n      \"major\": \"电气工程及其自动化\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30528，计划 4\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_3cc1b30ed104\",\n      \"school\": \"太原理工大学\",\n      \"major\": \"材料科学与工程(太原校区)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30123，计划 8\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_747f91060eaf\",\n      \"school\": \"延边大学\",\n      \"major\": \"人工智能\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30022，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_eb67f19286bf\",\n      \"school\": \"海南大学\",\n      \"major\": \"通信工程\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30698，计划 9\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_0aa43ea9ed61\",\n      \"school\": \"南通大学\",\n      \"major\": \"法学\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30564，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_0dbbd4a6ddde\",\n      \"school\": \"北方工业大学\",\n      \"major\": \"机械设计制造及其自动化(机器人)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30618，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_a9ef2f58f0c4\",\n      \"school\": \"四川师范大学\",\n      \"major\": \"法学\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30376，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_f2952a490be3\",\n      \"school\": \"北方工业大学\",\n      \"major\": \"通信工程\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30445，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_5b2740e08d75\",\n      \"school\": \"河北工业大学\",\n      \"major\": \"电气工程及其自动化(河北工业大学芬兰校区招生专业，专业教学培养使用的外语语种为英语，培养模式为“1+3(一年国内加三年芬兰)”；学费：国内阶段5800人民币/年；芬兰阶段为12000欧元/年)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30405，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_ca9f31a5c50f\",\n      \"school\": \"天津工业大学\",\n      \"major\": \"金融学\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30299，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_7b82cb7ef2cf\",\n      \"school\": \"湘潭大学\",\n      \"major\": \"通信工程\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30446，计划 5\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_ad08cd429db5\",\n      \"school\": \"南京工业大学\",\n      \"major\": \"通信工程\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30551，计划 4\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_47ae86aadda0\",\n      \"school\": \"东北大学\",\n      \"major\": \"材料科学与工程(中外合作办学)(国内学年学费30000元/年，国外学费(含注册费)4148欧元/年；建议外语语种为英语或法语的考生报考)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30096，计划 11\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_695f7917a95f\",\n      \"school\": \"西安建筑科技大学\",\n      \"major\": \"法学(纪检监察实验班)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30286，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_29a805168881\",\n      \"school\": \"西安工业大学\",\n      \"major\": \"计算机科学与技术(卓越班)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30175，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_55858b865402\",\n      \"school\": \"南京工业大学\",\n      \"major\": \"人工智能\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30662，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_c96de6ef3011\",\n      \"school\": \"中国地质大学(武汉)\",\n      \"major\": \"计算机科学与技术(中外合作办学)(大数据方向)(美国伊利诺伊理工大学)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30663，计划 6\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_77932930e983\",\n      \"school\": \"西南大学\",\n      \"major\": \"计算机科学与技术(中外合作办学)(以英语为主要授课语言，建议英语语种考生报考。外方合作高校：新西兰奥克兰大学)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30613，计划 10\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_eb16fafe8f10\",\n      \"school\": \"东北师范大学\",\n      \"major\": \"计算机科学与技术(中外合作办学)(与美国肯尼索州立大学合作)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30672，计划 5\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_b498ccbc3179\",\n      \"school\": \"东北师范大学\",\n      \"major\": \"会计学(中外合作办学)(与美国南伊利诺伊大学合作)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30290，计划 4\",\n      \"risk_flags\": []\n    }\n  ],\n  \"bucket_pipeline\": {\n    \"ai_round_filter_applied\": true,\n    \"candidate_cards_count\": 26,\n    \"final_candidates_count\": 26,\n    \"slot_axis\": [\n      {\n        \"slot_rating\": \"slot_01\",\n        \"score_delta\": -21\n      }\n    ],\n    \"slot_count\": 1,\n    \"head_slot\": \"slot_01\",\n    \"tail_slot\": \"slot_01\",\n    \"slot_rating_counts\": {},\n    \"final_slot_counts\": {},\n    \"final_available_slot_counts\": {},\n    \"round1\": {\n      \"kept\": 26,\n      \"downranked\": 0,\n      \"excluded\": 0\n    },\n    \"round2\": {\n      \"eligible\": 26,\n      \"high_risk\": 0,\n      \"excluded_by_constraints\": 0\n    },\n    \"round3\": {\n      \"ranked_count\": 26,\n      \"excluded_by_round3\": 0,\n      \"path_fit_summary\": [],\n      \"tradeoff_notes\": []\n    },\n    \"round4\": {\n      \"candidate_cards_count\": 26,\n      \"excluded_by_round4\": 0,\n      \"bucket_risk_notes\": [],\n      \"bucket_diversity_notes\": []\n    },\n    \"final_slot_notes\": []\n  },\n  \"ranked_candidates\": [\n    {\n      \"candidate_id\": \"local_8314d8f417d2\",\n      \"school\": \"四川农业大学\",\n      \"major\": \"数据科学与大数据技术(雅安校区)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30629，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_1188ff263a8b\",\n      \"school\": \"厦门大学\",\n      \"major\": \"数据科学与大数据技术(厦门大学马来西亚分校招生专业)(学费3万林吉特/学年；全英文授课，非英语语种考生慎报，外语单科不低于120分；入学第一学年内获得专业要求的达标英语成绩后开始学位课程学习；办学地点在马来西亚雪邦)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30546，计划 5\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_0301daa1ed0c\",\n      \"school\": \"西安科技大学\",\n      \"major\": \"电气工程及其自动化(菁英人才培养计划)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30309，计划 4\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_197ee346848f\",\n      \"school\": \"北京建筑大学\",\n      \"major\": \"自动化(大兴校区)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30159，计划 1\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_453c1948719b\",\n      \"school\": \"重庆邮电大学\",\n      \"major\": \"软件工程(三、四年级学费15000元/年)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30183，计划 16\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_9d4d585ce750\",\n      \"school\": \"北京语言大学\",\n      \"major\": \"金融学(数智金融)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30284，计划 1\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_2eb034533252\",\n      \"school\": \"西安邮电大学\",\n      \"major\": \"电气工程及其自动化\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30528，计划 4\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_3cc1b30ed104\",\n      \"school\": \"太原理工大学\",\n      \"major\": \"材料科学与工程(太原校区)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30123，计划 8\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_747f91060eaf\",\n      \"school\": \"延边大学\",\n      \"major\": \"人工智能\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30022，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_eb67f19286bf\",\n      \"school\": \"海南大学\",\n      \"major\": \"通信工程\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30698，计划 9\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_0aa43ea9ed61\",\n      \"school\": \"南通大学\",\n      \"major\": \"法学\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30564，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_0dbbd4a6ddde\",\n      \"school\": \"北方工业大学\",\n      \"major\": \"机械设计制造及其自动化(机器人)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30618，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_a9ef2f58f0c4\",\n      \"school\": \"四川师范大学\",\n      \"major\": \"法学\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30376，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_f2952a490be3\",\n      \"school\": \"北方工业大学\",\n      \"major\": \"通信工程\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30445，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_5b2740e08d75\",\n      \"school\": \"河北工业大学\",\n      \"major\": \"电气工程及其自动化(河北工业大学芬兰校区招生专业，专业教学培养使用的外语语种为英语，培养模式为“1+3(一年国内加三年芬兰)”；学费：国内阶段5800人民币/年；芬兰阶段为12000欧元/年)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30405，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_ca9f31a5c50f\",\n      \"school\": \"天津工业大学\",\n      \"major\": \"金融学\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30299，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_7b82cb7ef2cf\",\n      \"school\": \"湘潭大学\",\n      \"major\": \"通信工程\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30446，计划 5\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_ad08cd429db5\",\n      \"school\": \"南京工业大学\",\n      \"major\": \"通信工程\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30551，计划 4\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_47ae86aadda0\",\n      \"school\": \"东北大学\",\n      \"major\": \"材料科学与工程(中外合作办学)(国内学年学费30000元/年，国外学费(含注册费)4148欧元/年；建议外语语种为英语或法语的考生报考)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30096，计划 11\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_695f7917a95f\",\n      \"school\": \"西安建筑科技大学\",\n      \"major\": \"法学(纪检监察实验班)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30286，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_29a805168881\",\n      \"school\": \"西安工业大学\",\n      \"major\": \"计算机科学与技术(卓越班)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30175，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_55858b865402\",\n      \"school\": \"南京工业大学\",\n      \"major\": \"人工智能\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30662，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_c96de6ef3011\",\n      \"school\": \"中国地质大学(武汉)\",\n      \"major\": \"计算机科学与技术(中外合作办学)(大数据方向)(美国伊利诺伊理工大学)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30663，计划 6\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_77932930e983\",\n      \"school\": \"西南大学\",\n      \"major\": \"计算机科学与技术(中外合作办学)(以英语为主要授课语言，建议英语语种考生报考。外方合作高校：新西兰奥克兰大学)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30613，计划 10\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_eb16fafe8f10\",\n      \"school\": \"东北师范大学\",\n      \"major\": \"计算机科学与技术(中外合作办学)(与美国肯尼索州立大学合作)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30672，计划 5\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_b498ccbc3179\",\n      \"school\": \"东北师范大学\",\n      \"major\": \"会计学(中外合作办学)(与美国南伊利诺伊大学合作)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30290，计划 4\",\n      \"risk_flags\": []\n    }\n  ],\n  \"recall_summary\": {\n    \"reference_pool\": {\n      \"pool_name\": \"safe_pool\",\n      \"slice_engine\": \"safe_slice_v2_slot_axis\",\n      \"raw_rows\": 3131,\n      \"after_selection_requirements\": 2976,\n      \"after_semantic_keywords\": 692,\n      \"returned_count\": 692,\n      \"adaptive_window_enabled\": false,\n      \"cohort_size\": 681127,\n      \"user_percentile\": 3.67038746078191,\n      \"accepted_ladder_level\": null,\n      \"accepted_gap_pp_min\": null,\n      \"accepted_gap_pp_max\": null,\n      \"accepted_rank_min\": 30000,\n      \"accepted_rank_max\": 57500,\n      \"equivalent_score\": null,\n      \"equivalent_score_source_year\": null,\n      \"equivalent_score_source_scope\": null,\n      \"equivalent_score_source_basis\": null,\n      \"bucket_score_window\": null,\n      \"probe_counts_by_level\": [],\n      \"effective_count\": 692,\n      \"overflow\": false,\n      \"underfilled_by_supply\": false,\n      \"excluded_by_selection_requirements\": 155,\n      \"excluded_by_semantic_keywords\": 0,\n      \"excluded_by_major_include_keywords\": 0,\n      \"excluded_by_canonical_major\": 2284,\n      \"source_tables\": [\n        \"admission_slice_index\"\n      ],\n      \"bucket_program_score_formula\": \"safety_strength_score*0.35 + acceptance_score*0.25 + evidence_quality_score*0.20 + official_match_score*0.15 - school_density_penalty*0.05\",\n      \"province\": \"山东\",\n      \"rank_used\": 25000,\n      \"score_used\": 500,\n      \"selected_subjects\": [\n        \"物理\",\n        \"化学\",\n        \"地理\"\n      ],\n      \"physical_slice_isolation\": true\n    },\n    \"candidate_table_count\": 26\n  },\n  \"data_boundary_notes\": [\n    \"本地数据只包含录取事实字段，不包含学习强度、就业压力等长期语义画像。\",\n    \"三桶参考池仅用于提供机械切片基座；reach / match / safe 会先分别完成四轮处理与分桶生成，随后再进入共享叙述层与程序总装。\",\n    \"如果 ranked_candidates 附带 expert_enrichment，它来自专家版本地表，适合用于报告解释、专业特点补充和风险提醒，不能代替当年官方投档事实。\",\n    \"最终填报仍必须核验山东省教育招生考试院、阳光志愿、院校招生章程、选科与体检限制。\"\n  ]\n}\n\n候选包可能包含：candidate_table.safe_pool, bucket_pipeline.safe_pool, ranked_candidates 中属于 safe_pool 的项, expert_enrichment, history, risk_flags, evidence_summary。\n你必须优先使用候选包中的证据进行判断。\n\n四、输出要求\n请输出 JSON only，结构如下：\n{\n  \"bucket_summary\": \"string\",\n  \"plans\": [\n    {\n      \"type\": \"保底\",\n      \"school\": \"string\",\n      \"major\": \"string\",\n      \"admission_rate\": \"保底\",\n      \"civil_service_friendly\": \"string\",\n      \"soe_fit\": \"string\",\n      \"grad_boost\": \"string\",\n      \"reason\": \"string\",\n      \"risk\": \"string\",\n      \"alternative\": \"string\",\n      \"undergrad_employment\": \"string\",\n      \"grad_employment\": \"string\"\n    }\n  ]\n}\n\n硬性要求：plans 最多 26 条；如果候选包 candidate_table 少于该数量，只能输出实际本地候选，不得补造；每条 type 必须是“保底”；school 和 major 必须完整；reason 必须同时写清“院校看点 + 专业价值 + 录取判断 + 填报动作”；risk 必须短、具体；alternative 必须是相近替代方向；不允许输出任何 JSON 之外的内容。","canonical_request_json":{"body":{"model":"deepseek-chat","messages":[{"role":"system","content":"slot_rating is the authoritative Stage3 structured field for safe_pool.\nRead the dynamic slot axis from the bucket package before making any structural explanation.\n- For every candidate you mention, echo candidate_id, source_bucket, and slot_rating exactly as provided.\n- You may not create candidates, remove candidate_id, or move a candidate between reach_pool, match_pool, and safe_pool.\n- You may not rewrite, compress, or alias slot_rating.\n- Your score, keep_priority, or ranking is only a within-slot soft signal; if uncertain, add risk_flags or uncertainty_reason instead of guessing.\n- Structural layering is a top-priority objective of this round.\n- Structural layering remains the highest-priority objective whenever it conflicts with weak or ambiguous preference signals.\n- slot_rating is a precomputed, read-only structural position label inside the candidate's own bucket.\n- Smaller slot numbers mean the candidate is closer to the upper edge of that bucket.\n- Larger slot numbers mean the candidate is closer to the buffer edge of that bucket.\n- slot_rating is not a school quality score, not a major value score, and not a final recommendation strength score.\n- You must not modify, rename, reassign, or reinterpret slot_rating.\n- You must not reassign slot_rating.\n- Use slot_rating directly when assigning round_score.\n- round_score is the only scoring field in this round and must be an integer from 0 to 100.\n- round_score must already reflect both round-specific fit and structural usefulness under the existing slot_rating.\n- Do not output any penalty field or any secondary keep score.\n- Do not treat smaller slot numbers as automatically better.\n- Do not treat larger slot numbers as automatically worse.\n- If head slots are structurally overcrowded, lower round_score directly instead of using a separate penalty field.\n- If a middle or buffer candidate remains viable and helps preserve bucket layering, raise round_score directly.\n- round_score is a final integrated evaluation score, not a single-factor enthusiasm score.\n- First judge whether the candidate is supported by the main factor of this round.\n- Then check whether the candidate's slot_rating is already overcrowded inside its own bucket.\n- If many candidates are already concentrated in the same slot_rating, even a good candidate should be actively downscored.\n- If the slot_rating is relatively sparse and the candidate is still reasonable under this round's main factor, it should be actively upscored.\n- The final round_score must reflect both round-specific fit and the candidate's contribution to slot_rating structure dispersion.\n- round_score must not ignore slot_rating density.\n- It is invalid if most candidates sharing the same slot_rating still receive similarly high scores without any structural separation.\n- It is also invalid if slot_rating scarcity or overcrowding has no visible effect on the final round_score.\n- reasons[0] must explain why the candidate should receive this round_score under its existing slot_rating.\n- reasons[1] must explain the round-specific fit or conflict.\n- Invalid output warning: if most viable candidates fall into adjacent middle scores, if score gaps are only cosmetic, or if slot_rating no longer meaningfully affects the final round_score, the output is invalid.\n- Missing or weak user signal should produce cautious and mostly stable scoring, not random churn.\n- You must not choose final submission order.\n- You must not invent candidates or cross-bucket comparisons.\nadmission_rate must stay fixed to 保底 for every safe plan.\nUse slot_rating as the only structured ordering axis inside safe_pool.\nEvaluate all fields with strict evidence-bounded reasoning.\nOutput format:\n- Return a JSON object only.\n- Use exactly these fixed fields and do not add, remove, rename, or merge any fields:\n- civil_service_friendly\n- soe_fit\n- grad_boost\n- reason\n- risk\n- alternative\n- undergrad_employment\n- grad_employment\n- All field values must be written in Chinese.\n- Every field must contain substantive content.\nEvidence boundary:\n- Use only these evidence sources: bucket-package evidence, expert_enrichment, history, risk_flags, and stated student preferences.\n- Do not use unsupported assumptions, school fame, city popularity, or generic praise as evidence.\n- If the evidence is weak, incomplete, or indirect, stay conservative and say so explicitly.\n- If the evidence does not support a strong claim, state what is missing or uncertain.\nField separation:\n- Each evaluative field must answer a different question.\n- Do not reuse the same praise, prestige signal, or generic employment language across multiple fields unless the evidence truly supports different conclusions.\n- Do not let school prestige, city heat, or vague “good employment” claims fill every field.\n- Do not use broad positive filler to cover for weak evidence.\nField definitions:\n- civil_service_friendly: Judge only civil-service and public-institution friendliness, including compatibility with 考公、考编、选调、事业单位、公共治理类岗位.\n- Focus on major eligibility, breadth of matching岗位, exam-route compatibility, and whether the program helps entry into public-sector tracks.\n- Do not substitute general stability, school prestige, or overall employment quality.\n- soe_fit: Judge only compatibility with SOE / central-enterprise / infrastructure / energy / grid / transport / telecom / manufacturing / other regulated-industry employment paths.\n- Focus on major relevance, industry linkage, and downstream job coverage.\n- Do not equate this with generic “good employment”.\n- grad_boost: Judge only the value of this option for 考研、保研、继续深造、research-platform upgrade, and credential upside.\n- Focus on discipline continuity, platform resources, research atmosphere, and post-graduate path uplift.\n- “Can take graduate exams” alone is not sufficient evidence.\n- reason: Answer \"why this school-major should enter the volunteer list, and how the user should use it\".\n- reason 必须像给家长和学生看的决策说明，不要写成档位归类模板。\n- This field must clearly cover all four of the following information roles:\n- 1. 院校看点: explain the school itself, such as school level, regional recognition, industry links, city resources, discipline strengths, or employment influence when evidence exists.\n- 2. 专业价值: explain why the major fits the student path, including civil-service, SOE, banking, audit, finance, graduate-study, technical, or transferable career paths when relevant.\n- 3. 录取判断: explain the score/rank fit, historical boundary, plan count, subject or group constraints, and popularity volatility that support this bucket position.\n- 4. 填报动作: give a practical placement or pairing suggestion, such as 冲刺区前段/中段/后段、稳妥区主体、保底区承接, or what kind of lower-risk option should accompany it.\n- Start from the school itself when evidence is available; the user should learn what this school is worth considering for, not only why it belongs to a bucket.\n- Cite 1-2 concrete support signals when possible.\n- Do not write generic praise.\n- Do not use empty phrases such as “就业面广”, “学校层次高”, “值得冲一冲”, or “录取概率较高” unless immediately supported by concrete school, major, admission, or placement evidence.\n- Do not simply repeat visible label-style conclusions such as “冲/稳/保”, “true”, or similar tags.\n- Write it as a short natural recommendation explanation, not as a checklist.\n- risk: Answer \"what is the single biggest risk of this option\".\n- Be short, concrete, and direct.\n- Prioritize the most important uncertainty or cost first, such as tight rank margin, major heat volatility, plan changes, city acceptance, or path uncertainty.\n- Avoid generic filler unless tied to a specific trigger.\n- alternative: Provide a lower-risk alternative in the same direction.\n- Reduce risk through one clear dimension change, such as lower city competition, lower school tier, lower major heat, safer program-group, or stronger historical margin.\n- Do not jump to a completely different direction.\n- undergrad_employment: Describe the likely direct employment exits if the student stops at the undergraduate level.\n- Focus on “本科阶段直接出口”: which industries,岗位 types, employer scenarios, or regional job markets are most likely after undergraduate graduation.\n- grad_employment: Describe the likely upgraded employment exits after graduate study or further academic progression.\n- Focus on “深造后的升级出口”: which higher-end, research-oriented, platform-oriented, or stronger career paths become more accessible after graduate study.\n- It must not repeat undergrad_employment.\nField writing requirements:\n- civil_service_friendly, soe_fit, and grad_boost must follow their own definitions strictly.\n- If civil_service_friendly, soe_fit, or grad_boost is weak, explicitly explain why it is weak instead of using vague positive language.\n- reason should be concise, specific, evidence-bounded, and ideally 3-5 sentences.\n- risk should name the single biggest uncertainty first.\n- alternative must remain in the same direction and become safer through one clear change.\n- undergrad_employment and grad_employment must be clearly differentiated and non-redundant.\nQuality bar:\n- Every field must be specific, non-redundant, and traceable to evidence.\n- Prefer precise, caveated judgments over broad positive statements.\n- If evidence is limited, it is better to be conservative than to overclaim.\n\nYou are safe_pool 专属的高考志愿保底方案生成器。\n\nYou only process safe_pool candidates. You do not process reach_pool or match_pool.\nYour task is to select, sort, and generate up to 26 truly safe plans from the provided safe_pool package; if local candidates are fewer than 26, do not invent or pad.\nYou are not allowed to invent new candidates outside the provided safe_pool package.\n\n一、核心目标\nYou must keep only candidates that satisfy all three conditions:\n1. 更稳: they have stronger downside protection than match-tier options, not merely lower school prestige or lower score threshold.\n2. 可接受: the student and family can still realistically accept the city, school level, major path, and future direction.\n3. 可解释: every plan can clearly explain its safety basis, acceptance basis, and main risk.\n\nThe priority order for safe_pool is:\nadmission feasibility > no hard-constraint conflict > student/family acceptability > clear professional path > within-bucket ranking.\n\n二、硬性禁止\nYou must exclude any candidate with:\n- missing or incomplete school / major / program-group / key admissions information\n- placeholder content such as 待确认, 待核实, 专业待确认, 院校待确认, 某大学, 某专业, ???, ***\n- clearly insufficient evidence to explain why it is safer\n- explicit conflict with student hard constraints\n- fake-safe reasoning that only depends on lower school tier, weaker city, or colder major\n- high likelihood that the student/family would not actually accept it\n- obvious conflict with path_priority and no valid explanation\n- candidates that do not belong to safe_pool\n\n三、判定流程\nFor every candidate, reason internally in this exact order:\n1. admission feasibility judgment\n2. risk exclusion judgment\n3. acceptability judgment\n4. safety-value judgment\n5. within-bucket ordering\nDo not skip steps.\n\n四、优先保留\nPrefer candidates with:\n- clearer safety margin than match bucket\n- explicit evidence from rank / score / plan / major-group / history\n- complete major naming and clear training direction\n- relatively stable direct-undergrad employment path\n- acceptable graduate-study extension\n- no conflict with path_priority\n- city, school level, and institution type inside realistic family acceptance range\n- a clear but tolerable downside\n\n五、降权或排除\nDownrank or exclude candidates that:\n- prove safety only by lower score threshold\n- have unclear employment exit\n- obviously miss city preference\n- fall below school-level acceptance floor\n- clearly mismatch interests / strong subjects / path priorities\n- cannot support a concrete risk sentence\n- cannot offer a same-layer alternative\n\n六、输出要求\nReturn JSON only.\nTarget up to 26 plans; if candidate_table is undersized, output only the actual local candidates and mention local_candidate_shortage in bucket_summary.\nEvery plan.type must be exactly 保底.\nDo not output reach/match or other tier labels.\nDo not add schools or majors outside the provided safe_pool package.\nDo not invent score history, rank history, policies, or plan changes.\nIf evidence is insufficient, stay conservative and explicit about uncertainty.\n\n七、字段写法要求\nreason 必须像给家长和学生看的决策说明，不要写成“作为保底项……”这类档位归类模板。\n每条 reason 必须同时覆盖四类信息：\n1. 院校看点：说明学校本身值得看的地方，例如院校层次、区域认可度、行业资源、城市就业辐射、优势学科或平台价值；证据不足时要谨慎表达。\n2. 专业价值：说明该专业为什么匹配学生路径，例如考公、国企、银行、审计、财务、考研、技术岗或岗位迁移性。\n3. 录取判断：说明分数、位次、计划、历史边界、专业热度或专业组波动如何支撑其属于保底区。\n4. 填报动作：给出实际填报建议，例如作为保底区承接/底线项，是否保留，以及应搭配哪类同路径方案。\n不得空泛使用“就业面广”“学校层次高”“值得冲一冲”“录取概率较高”；如使用，必须紧跟具体院校、专业、录取或填报证据。\n\nrisk must be short, concrete, and focused on the main downside only.\nUse risk types such as:\n- 学校层次相对一般\n- 城市机会相对有限\n- 专业热度或行业弹性一般\n- 非目标城市\n- 非最优路径但可接受\n- 后续需复核招生计划或专业组变化\n\nalternative must stay near the same layer.\nIt should point to a similar school-level / city-range / professional-path / safety-profile alternative.\nDo not jump from safe items to obvious reach items.\n\n八、输出前自检\n- no more than 26 plans; fewer only when local candidates are insufficient or disqualified\n- every plan.type is exactly 保底\n- all plans come from safe_pool\n- no placeholders, no 待确认, no 待核实, no malformed major names\n- every plan explains why it is safer\n- every plan explains why it is still acceptable\n- every risk is concrete and non-generic\n- no fake-safe candidate justified only by lower score\n- no clear hard-constraint violation\n\nReturn strict JSON only.\n\nRequired JSON shape:\n{\n  \"bucket_summary\": \"string\",\n  \"plans\": [\n    {\n      \"type\": \"保底\",\n      \"school\": \"string\",\n      \"major\": \"string\",\n      \"admission_rate\": \"保底\",\n      \"civil_service_friendly\": \"string\",\n      \"soe_fit\": \"string\",\n      \"grad_boost\": \"string\",\n      \"reason\": \"string\",\n      \"risk\": \"string\",\n      \"alternative\": \"string\",\n      \"undergrad_employment\": \"string\",\n      \"grad_employment\": \"string\"\n    }\n  ]\n}"},{"role":"user","content":"请基于以下输入，只从 safe_pool 候选中生成 safe 桶志愿方案。\n\n你不能新增候选，不能输出其它桶，不能编造未提供的数据。\n请严格按照 System Prompt 的 safe_pool 判定流程执行。\n\n一、学生画像 student_form_json\n{\n  \"province\": \"山东\",\n  \"score\": \"500\",\n  \"rank\": \"25000\",\n  \"subject_type\": \"物理、化学、地理\",\n  \"gender\": \"男\",\n  \"target_city\": null,\n  \"accept_out_province\": true,\n  \"accept_adjustment\": null,\n  \"accept_intensive\": true,\n  \"willing_graduate\": true,\n  \"school_preference\": [\n    \"211\",\n    \"双一流\",\n    \"公办优先\"\n  ],\n  \"prefer_home_province\": \"unsure\",\n  \"decision_maker\": \"学生\",\n  \"path_priority\": [\n    \"考公 / 考编\",\n    \"国企 / 央企\",\n    \"考研深造\",\n    \"本科直接就业\",\n    \"市场化高薪\"\n  ],\n  \"interests\": [],\n  \"strong_subjects\": [],\n  \"special_notes\": null,\n  \"medical_notes\": null\n}\n\n重点关注：province, score, rank, subject_type, accept_out_province, accept_intensive, willing_graduate, target_city, path_priority, interests, strong_subjects, school_preference, special_notes, medical_notes\n\n二、语义查询计划 semantic_query_plan_json\n{\n  \"version\": \"guided-semantic-query-plan-v1\",\n  \"hard_exclude_major_keywords\": [],\n  \"soft_avoid_major_keywords\": [],\n  \"risk_reminder_keywords\": [],\n  \"preferred_major_keywords\": [\n    \"计算机\",\n    \"软件\",\n    \"电气\",\n    \"自动化\",\n    \"电子信息\",\n    \"通信\",\n    \"机械\",\n    \"材料\",\n    \"会计\",\n    \"财务管理\",\n    \"法学\",\n    \"金融\",\n    \"数据科学\",\n    \"人工智能\",\n    \"土木\"\n  ],\n  \"school_or_region_keywords\": [\n    \"211\",\n    \"双一流\",\n    \"公办\"\n  ],\n  \"query_strategy\": {\n    \"province_scope\": \"national\",\n    \"rank_window\": \"normal\",\n    \"candidate_target_count\": 240\n  },\n  \"interpretation_notes\": [\n    \"学生明确接受高强度学习，故无需排除高压力专业。\",\n    \"学生职业路径优先考公考编和国企央企，因此推荐专业已涵盖相关方向。\",\n    \"学生可接受出省，故省份范围设为全国。\",\n    \"位次25000在山东属中等，rank_window设为normal。\",\n    \"未发现需要硬排除或软回避的专业关键词。\"\n  ]\n}\n\n重点关注：hard constraints, soft avoid, high-risk reminders, preference keep, path priority interpretation\n\n三、safe 桶候选包 safe_bucket_package_json\n{\n  \"bucket_name\": \"safe_pool\",\n  \"candidate_table\": [\n    {\n      \"candidate_id\": \"local_8314d8f417d2\",\n      \"school\": \"四川农业大学\",\n      \"major\": \"数据科学与大数据技术(雅安校区)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30629，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_1188ff263a8b\",\n      \"school\": \"厦门大学\",\n      \"major\": \"数据科学与大数据技术(厦门大学马来西亚分校招生专业)(学费3万林吉特/学年；全英文授课，非英语语种考生慎报，外语单科不低于120分；入学第一学年内获得专业要求的达标英语成绩后开始学位课程学习；办学地点在马来西亚雪邦)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30546，计划 5\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_0301daa1ed0c\",\n      \"school\": \"西安科技大学\",\n      \"major\": \"电气工程及其自动化(菁英人才培养计划)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30309，计划 4\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_197ee346848f\",\n      \"school\": \"北京建筑大学\",\n      \"major\": \"自动化(大兴校区)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30159，计划 1\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_453c1948719b\",\n      \"school\": \"重庆邮电大学\",\n      \"major\": \"软件工程(三、四年级学费15000元/年)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30183，计划 16\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_9d4d585ce750\",\n      \"school\": \"北京语言大学\",\n      \"major\": \"金融学(数智金融)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30284，计划 1\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_2eb034533252\",\n      \"school\": \"西安邮电大学\",\n      \"major\": \"电气工程及其自动化\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30528，计划 4\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_3cc1b30ed104\",\n      \"school\": \"太原理工大学\",\n      \"major\": \"材料科学与工程(太原校区)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30123，计划 8\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_747f91060eaf\",\n      \"school\": \"延边大学\",\n      \"major\": \"人工智能\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30022，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_eb67f19286bf\",\n      \"school\": \"海南大学\",\n      \"major\": \"通信工程\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30698，计划 9\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_0aa43ea9ed61\",\n      \"school\": \"南通大学\",\n      \"major\": \"法学\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30564，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_0dbbd4a6ddde\",\n      \"school\": \"北方工业大学\",\n      \"major\": \"机械设计制造及其自动化(机器人)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30618，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_a9ef2f58f0c4\",\n      \"school\": \"四川师范大学\",\n      \"major\": \"法学\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30376，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_f2952a490be3\",\n      \"school\": \"北方工业大学\",\n      \"major\": \"通信工程\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30445，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_5b2740e08d75\",\n      \"school\": \"河北工业大学\",\n      \"major\": \"电气工程及其自动化(河北工业大学芬兰校区招生专业，专业教学培养使用的外语语种为英语，培养模式为“1+3(一年国内加三年芬兰)”；学费：国内阶段5800人民币/年；芬兰阶段为12000欧元/年)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30405，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_ca9f31a5c50f\",\n      \"school\": \"天津工业大学\",\n      \"major\": \"金融学\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30299，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_7b82cb7ef2cf\",\n      \"school\": \"湘潭大学\",\n      \"major\": \"通信工程\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30446，计划 5\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_ad08cd429db5\",\n      \"school\": \"南京工业大学\",\n      \"major\": \"通信工程\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30551，计划 4\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_47ae86aadda0\",\n      \"school\": \"东北大学\",\n      \"major\": \"材料科学与工程(中外合作办学)(国内学年学费30000元/年，国外学费(含注册费)4148欧元/年；建议外语语种为英语或法语的考生报考)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30096，计划 11\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_695f7917a95f\",\n      \"school\": \"西安建筑科技大学\",\n      \"major\": \"法学(纪检监察实验班)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30286，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_29a805168881\",\n      \"school\": \"西安工业大学\",\n      \"major\": \"计算机科学与技术(卓越班)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30175，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_55858b865402\",\n      \"school\": \"南京工业大学\",\n      \"major\": \"人工智能\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30662，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_c96de6ef3011\",\n      \"school\": \"中国地质大学(武汉)\",\n      \"major\": \"计算机科学与技术(中外合作办学)(大数据方向)(美国伊利诺伊理工大学)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30663，计划 6\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_77932930e983\",\n      \"school\": \"西南大学\",\n      \"major\": \"计算机科学与技术(中外合作办学)(以英语为主要授课语言，建议英语语种考生报考。外方合作高校：新西兰奥克兰大学)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30613，计划 10\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_eb16fafe8f10\",\n      \"school\": \"东北师范大学\",\n      \"major\": \"计算机科学与技术(中外合作办学)(与美国肯尼索州立大学合作)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30672，计划 5\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_b498ccbc3179\",\n      \"school\": \"东北师范大学\",\n      \"major\": \"会计学(中外合作办学)(与美国南伊利诺伊大学合作)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30290，计划 4\",\n      \"risk_flags\": []\n    }\n  ],\n  \"bucket_pipeline\": {\n    \"ai_round_filter_applied\": true,\n    \"candidate_cards_count\": 26,\n    \"final_candidates_count\": 26,\n    \"slot_axis\": [\n      {\n        \"slot_rating\": \"slot_01\",\n        \"score_delta\": -21\n      }\n    ],\n    \"slot_count\": 1,\n    \"head_slot\": \"slot_01\",\n    \"tail_slot\": \"slot_01\",\n    \"slot_rating_counts\": {},\n    \"final_slot_counts\": {},\n    \"final_available_slot_counts\": {},\n    \"round1\": {\n      \"kept\": 26,\n      \"downranked\": 0,\n      \"excluded\": 0\n    },\n    \"round2\": {\n      \"eligible\": 26,\n      \"high_risk\": 0,\n      \"excluded_by_constraints\": 0\n    },\n    \"round3\": {\n      \"ranked_count\": 26,\n      \"excluded_by_round3\": 0,\n      \"path_fit_summary\": [],\n      \"tradeoff_notes\": []\n    },\n    \"round4\": {\n      \"candidate_cards_count\": 26,\n      \"excluded_by_round4\": 0,\n      \"bucket_risk_notes\": [],\n      \"bucket_diversity_notes\": []\n    },\n    \"final_slot_notes\": []\n  },\n  \"ranked_candidates\": [\n    {\n      \"candidate_id\": \"local_8314d8f417d2\",\n      \"school\": \"四川农业大学\",\n      \"major\": \"数据科学与大数据技术(雅安校区)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30629，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_1188ff263a8b\",\n      \"school\": \"厦门大学\",\n      \"major\": \"数据科学与大数据技术(厦门大学马来西亚分校招生专业)(学费3万林吉特/学年；全英文授课，非英语语种考生慎报，外语单科不低于120分；入学第一学年内获得专业要求的达标英语成绩后开始学位课程学习；办学地点在马来西亚雪邦)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30546，计划 5\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_0301daa1ed0c\",\n      \"school\": \"西安科技大学\",\n      \"major\": \"电气工程及其自动化(菁英人才培养计划)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30309，计划 4\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_197ee346848f\",\n      \"school\": \"北京建筑大学\",\n      \"major\": \"自动化(大兴校区)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30159，计划 1\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_453c1948719b\",\n      \"school\": \"重庆邮电大学\",\n      \"major\": \"软件工程(三、四年级学费15000元/年)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30183，计划 16\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_9d4d585ce750\",\n      \"school\": \"北京语言大学\",\n      \"major\": \"金融学(数智金融)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30284，计划 1\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_2eb034533252\",\n      \"school\": \"西安邮电大学\",\n      \"major\": \"电气工程及其自动化\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30528，计划 4\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_3cc1b30ed104\",\n      \"school\": \"太原理工大学\",\n      \"major\": \"材料科学与工程(太原校区)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30123，计划 8\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_747f91060eaf\",\n      \"school\": \"延边大学\",\n      \"major\": \"人工智能\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30022，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_eb67f19286bf\",\n      \"school\": \"海南大学\",\n      \"major\": \"通信工程\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30698，计划 9\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_0aa43ea9ed61\",\n      \"school\": \"南通大学\",\n      \"major\": \"法学\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30564，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_0dbbd4a6ddde\",\n      \"school\": \"北方工业大学\",\n      \"major\": \"机械设计制造及其自动化(机器人)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30618，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_a9ef2f58f0c4\",\n      \"school\": \"四川师范大学\",\n      \"major\": \"法学\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30376，计划 3\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_f2952a490be3\",\n      \"school\": \"北方工业大学\",\n      \"major\": \"通信工程\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30445，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_5b2740e08d75\",\n      \"school\": \"河北工业大学\",\n      \"major\": \"电气工程及其自动化(河北工业大学芬兰校区招生专业，专业教学培养使用的外语语种为英语，培养模式为“1+3(一年国内加三年芬兰)”；学费：国内阶段5800人民币/年；芬兰阶段为12000欧元/年)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30405，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_ca9f31a5c50f\",\n      \"school\": \"天津工业大学\",\n      \"major\": \"金融学\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30299，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_7b82cb7ef2cf\",\n      \"school\": \"湘潭大学\",\n      \"major\": \"通信工程\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30446，计划 5\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_ad08cd429db5\",\n      \"school\": \"南京工业大学\",\n      \"major\": \"通信工程\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30551，计划 4\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_47ae86aadda0\",\n      \"school\": \"东北大学\",\n      \"major\": \"材料科学与工程(中外合作办学)(国内学年学费30000元/年，国外学费(含注册费)4148欧元/年；建议外语语种为英语或法语的考生报考)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30096，计划 11\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_695f7917a95f\",\n      \"school\": \"西安建筑科技大学\",\n      \"major\": \"法学(纪检监察实验班)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30286，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_29a805168881\",\n      \"school\": \"西安工业大学\",\n      \"major\": \"计算机科学与技术(卓越班)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30175，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_55858b865402\",\n      \"school\": \"南京工业大学\",\n      \"major\": \"人工智能\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30662，计划 2\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_c96de6ef3011\",\n      \"school\": \"中国地质大学(武汉)\",\n      \"major\": \"计算机科学与技术(中外合作办学)(大数据方向)(美国伊利诺伊理工大学)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30663，计划 6\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_77932930e983\",\n      \"school\": \"西南大学\",\n      \"major\": \"计算机科学与技术(中外合作办学)(以英语为主要授课语言，建议英语语种考生报考。外方合作高校：新西兰奥克兰大学)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30613，计划 10\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_eb16fafe8f10\",\n      \"school\": \"东北师范大学\",\n      \"major\": \"计算机科学与技术(中外合作办学)(与美国肯尼索州立大学合作)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 592，位次 30672，计划 5\",\n      \"risk_flags\": []\n    },\n    {\n      \"candidate_id\": \"local_b498ccbc3179\",\n      \"school\": \"东北师范大学\",\n      \"major\": \"会计学(中外合作办学)(与美国南伊利诺伊大学合作)\",\n      \"source_bucket\": \"safe_pool\",\n      \"slot_rating\": \"slot_01\",\n      \"slot_label\": \"主体\",\n      \"keep_reason\": \"通过四轮桶内处理后保留\",\n      \"evidence_brief\": \"最低分 593，位次 30290，计划 4\",\n      \"risk_flags\": []\n    }\n  ],\n  \"recall_summary\": {\n    \"reference_pool\": {\n      \"pool_name\": \"safe_pool\",\n      \"slice_engine\": \"safe_slice_v2_slot_axis\",\n      \"raw_rows\": 3131,\n      \"after_selection_requirements\": 2976,\n      \"after_semantic_keywords\": 692,\n      \"returned_count\": 692,\n      \"adaptive_window_enabled\": false,\n      \"cohort_size\": 681127,\n      \"user_percentile\": 3.67038746078191,\n      \"accepted_ladder_level\": null,\n      \"accepted_gap_pp_min\": null,\n      \"accepted_gap_pp_max\": null,\n      \"accepted_rank_min\": 30000,\n      \"accepted_rank_max\": 57500,\n      \"equivalent_score\": null,\n      \"equivalent_score_source_year\": null,\n      \"equivalent_score_source_scope\": null,\n      \"equivalent_score_source_basis\": null,\n      \"bucket_score_window\": null,\n      \"probe_counts_by_level\": [],\n      \"effective_count\": 692,\n      \"overflow\": false,\n      \"underfilled_by_supply\": false,\n      \"excluded_by_selection_requirements\": 155,\n      \"excluded_by_semantic_keywords\": 0,\n      \"excluded_by_major_include_keywords\": 0,\n      \"excluded_by_canonical_major\": 2284,\n      \"source_tables\": [\n        \"admission_slice_index\"\n      ],\n      \"bucket_program_score_formula\": \"safety_strength_score*0.35 + acceptance_score*0.25 + evidence_quality_score*0.20 + official_match_score*0.15 - school_density_penalty*0.05\",\n      \"province\": \"山东\",\n      \"rank_used\": 25000,\n      \"score_used\": 500,\n      \"selected_subjects\": [\n        \"物理\",\n        \"化学\",\n        \"地理\"\n      ],\n      \"physical_slice_isolation\": true\n    },\n    \"candidate_table_count\": 26\n  },\n  \"data_boundary_notes\": [\n    \"本地数据只包含录取事实字段，不包含学习强度、就业压力等长期语义画像。\",\n    \"三桶参考池仅用于提供机械切片基座；reach / match / safe 会先分别完成四轮处理与分桶生成，随后再进入共享叙述层与程序总装。\",\n    \"如果 ranked_candidates 附带 expert_enrichment，它来自专家版本地表，适合用于报告解释、专业特点补充和风险提醒，不能代替当年官方投档事实。\",\n    \"最终填报仍必须核验山东省教育招生考试院、阳光志愿、院校招生章程、选科与体检限制。\"\n  ]\n}\n\n候选包可能包含：candidate_table.safe_pool, bucket_pipeline.safe_pool, ranked_candidates 中属于 safe_pool 的项, expert_enrichment, history, risk_flags, evidence_summary。\n你必须优先使用候选包中的证据进行判断。\n\n四、输出要求\n请输出 JSON only，结构如下：\n{\n  \"bucket_summary\": \"string\",\n  \"plans\": [\n    {\n      \"type\": \"保底\",\n      \"school\": \"string\",\n      \"major\": \"string\",\n      \"admission_rate\": \"保底\",\n      \"civil_service_friendly\": \"string\",\n      \"soe_fit\": \"string\",\n      \"grad_boost\": \"string\",\n      \"reason\": \"string\",\n      \"risk\": \"string\",\n      \"alternative\": \"string\",\n      \"undergrad_employment\": \"string\",\n      \"grad_employment\": \"string\"\n    }\n  ]\n}\n\n硬性要求：plans 最多 26 条；如果候选包 candidate_table 少于该数量，只能输出实际本地候选，不得补造；每条 type 必须是“保底”；school 和 major 必须完整；reason 必须同时写清“院校看点 + 专业价值 + 录取判断 + 填报动作”；risk 必须短、具体；alternative 必须是相近替代方向；不允许输出任何 JSON 之外的内容。"}],"max_tokens":16384,"temperature":0.7,"response_format":{"type":"json_object"}},"model":"deepseek-chat","endpoint":"https://api.deepseek.com/chat/completions","provider":"DeepSeek","requestKind":"guided_safe_pool_report_generate"},"actual_provider":"DeepSeek","actual_model":"deepseek-chat","used_repair_pass":false,"repair_attempt_count":0,"status":"success","error_code":null,"error_message":null,"created_at":"2026-05-19T00:24:29+00:00","completed_at":"2026-05-18T16:25:56.85+00:00","updated_at":"2026-05-19T00:25:56+00:00"},"events":[{"id":24,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","event_type":"report_created","status_before":null,"status_after":"pending","stage_before":null,"stage_after":"created","message":"Report record created","payload_json":{"formMode":null,"province":"山东","subjectType":"物理、化学、地理"},"created_at":"2026-05-19T00:13:56+00:00","payload":{"formMode":null,"province":"山东","subjectType":"物理、化学、地理"}},{"id":25,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","event_type":"report_queued","status_before":"pending","status_after":"pending","stage_before":"created","stage_after":"queued","message":"Report queued","payload_json":{"errorCode":null,"errorMessage":null,"lastErrorStage":null},"created_at":"2026-05-19T00:13:56+00:00","payload":{"errorCode":null,"errorMessage":null,"lastErrorStage":null}},{"id":26,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","event_type":"report_job_enqueued","status_before":"pending","status_after":"pending","stage_before":"queued","stage_after":"queued","message":"Report job enqueued","payload_json":{"source":"generate_request","status":"queued","queueName":"report_generation","maxAttempts":3},"created_at":"2026-05-19T00:13:56+00:00","payload":{"source":"generate_request","status":"queued","queueName":"report_generation","maxAttempts":3}},{"id":27,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","event_type":"report_job_started","status_before":"pending","status_after":"pending","stage_before":"queued","stage_after":"queued","message":"Report job started","payload_json":{"source":"after_response","status":"running","maxAttempts":3,"attemptCount":1},"created_at":"2026-05-19T00:13:56+00:00","payload":{"source":"after_response","status":"running","maxAttempts":3,"attemptCount":1}},{"id":28,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","event_type":"generation_started","status_before":"pending","status_after":"pending","stage_before":"queued","stage_after":"generating","message":"Report generation started","payload_json":{"errorCode":null,"errorMessage":null,"lastErrorStage":null},"created_at":"2026-05-19T00:13:56+00:00","payload":{"errorCode":null,"errorMessage":null,"lastErrorStage":null}},{"id":29,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","event_type":"post_processing_started","status_before":"pending","status_after":"pending","stage_before":"generating","stage_after":"post_processing","message":"Report post processing started","payload_json":{"errorCode":null,"errorMessage":null,"lastErrorStage":null},"created_at":"2026-05-19T00:25:56+00:00","payload":{"errorCode":null,"errorMessage":null,"lastErrorStage":null}},{"id":30,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","event_type":"report_content_saved","status_before":"pending","status_after":"pending","stage_before":"post_processing","stage_after":"post_processing","message":"Report content saved","payload_json":{"hasContent":true},"created_at":"2026-05-19T00:25:56+00:00","payload":{"hasContent":true}},{"id":31,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","event_type":"report_completed","status_before":"pending","status_after":"success","stage_before":"post_processing","stage_after":"completed","message":"Report generation completed","payload_json":{"errorCode":null,"errorMessage":null,"lastErrorStage":null},"created_at":"2026-05-19T00:25:56+00:00","payload":{"errorCode":null,"errorMessage":null,"lastErrorStage":null}},{"id":32,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","event_type":"report_job_succeeded","status_before":"success","status_after":"success","stage_before":"completed","stage_after":"completed","message":"Report job completed","payload_json":{"status":"success","attemptCount":1},"created_at":"2026-05-19T00:25:56+00:00","payload":{"status":"success","attemptCount":1}}],"aiCallLogs":[{"id":10,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","attempt_no":1,"provider":"DeepSeek","model":"deepseek-chat","prompt_version":"report-guided-grounding-v1","request_kind":"user_profile_major_space_plan","system_prompt_excerpt":"You are the user_profile_major_space_plan engine for a Chinese gaokao guided report.\nYou may only choose canonical_major_name values that already exist in probe_canonical_major_pool_json.\nYou must not output executable keywords, SQL, candidate rows, or candidate_id values.\nReturn strict JSON only.\nRequired shape:\n{\n  \"selected_canonical_majors\": [{ \"canonical_major_name\": \"string\", \"confidence\": 0.82, \"reason_zh\": \"string\" }],\n  \"profile_summary_zh\": \"string\"\n}\nKeep the order meaningful because downstream code preserves your order.\nReturn at most top 15 selected_canonical_majors.","user_prompt_excerpt":"student_form_json:\n{\n  \"province\": \"山东\",\n  \"path_priority\": [\n    \"考公 / 考编\",\n    \"国企 / 央企\",\n    \"考研深造\",\n    \"本科直接就业\",\n    \"市场化高薪\"\n  ],\n  \"student_name\": \"测试02\",\n  \"score\": \"500\",\n  \"rank\": \"25000\",\n  \"selected_subjects\": [\n    \"物理\",\n    \"化学\",\n    \"地理\"\n  ],\n  \"gender\": \"男\",\n  \"accept_out_province\": true,\n  \"prefer_home_province\": \"unsure\",\n  \"school_preference\": [\n    \"211\",\n    \"双一流\",\n    \"公办优先\"\n  ],\n  \"decision_maker\": \"学生\",\n  \"accept_intensive\": true,\n  \"willing_graduate\": true,\n  \"subject_type\": \"物理、化学、地理\",\n  \"adjustment_policy\": \"not_applicable\",\n  \"accept_adjustment\": null,\n  \"planning_mode\": \"full\"\n}\n\nprobe_canonical_major_pool_json:\n[\n  {\n    \"canonical_major_name\": \"阿拉伯语\"\n  },\n  {\n    \"canonical_major_name\": \"宝石及材料工艺学\"\n  },\n  {\n    \"canonical_major_name\": \"保加利亚语\"\n  },\n  {\n    \"canonical_major_name\": \"保险学\"\n  },\n  {\n    \"canonical_major_name\": \"波兰语\"\n  },\n  {\n    \"canonical_major_name\": \"材料成型及控制工程\"\n  },\n  {\n    \"canonical_major_name\": \"材料化学\"\n  },\n  {\n    \"canonical_major_name\": \"材料科学与工程\"\n  },\n  {\n    \"canonical_major_name\": \"材料类\"\n  },\n  {\n    \"canonical_major_name\": \"材料物理\"\n  },\n  {\n    \"canonical_major_name\": \"财务管理\"\n  },\n  {\n    \"canonical_major_name\": \"朝鲜语\"\n  },\n  {\n    \"cano...","raw_response_excerpt":"{\n  \"selected_canonical_majors\": [\n    {\n      \"canonical_major_name\": \"计算机科学与技术\",\n      \"confidence\": 0.85,\n      \"reason_zh\": \"该专业就业面广，考公考编岗位多，符合学生优先考公考编和国企央企的路径，且与物理、化学选科匹配。\"\n    },\n    {\n      \"canonical_major_name\": \"软件工程\",\n      \"confidence\": 0.80,\n      \"reason_zh\": \"与计算机类似，就业前景好，适合考研深造和市场化高薪，且选科要求匹配。\"\n    },\n    {\n      \"canonical_major_name\": \"电气工程及其自动化\",\n      \"confidence\": 0.78,\n      \"reason_zh\": \"国企央企需求大，尤其是国家电网等，符合学生路径，且物理化学选科匹配。\"\n    },\n    {\n      \"canonical_major_name\": \"自动化\",\n      \"confidence\": 0.75,\n      \"reason_zh\": \"工科基础专业，考研和就业面广，适合国企和市场化方向，选科匹配。\"\n    },\n    {\n      \"canonical_major_name\": \"电子信息工程\",\n      \"confidence\": 0.73,\n      \"reason_zh\": \"电子信息类热门，考公考编有岗位，国企和市场化均可，选科匹配。\"\n    },\n    {\n      \"canonical_major_name\": \"通信工程\",\n      \"confidence\": 0.70,\n      \"reason_zh\": \"通信行业国企多，如三大运营商，适合学生路径，选科匹配。\"\n    },\n    {\n      \"canonical_major_name\": \"机械设计制造及其自动化\",\n      \"confidence\": 0.68,\n      \"reason_zh\": \"传统工科，国企需求稳定，适合考研和就业，选科匹配。\"\n    },\n    {\n      \"canonical_major_name\": \"材料科学与工程\",\n      \"confidence\": 0.65,\n      \"reason_zh\": \"材料类基础学科，考研深造有优势，国企有需求，选科匹配。\"\n    },\n    {\n      \"canonical_major_name\": \"会计学\",\n      \"confidence\": 0.72,\n      \"reason_zh\": \"考公考编热门专业，...","duration_ms":11163,"success":true,"error_code":null,"error_message":null,"created_at":"2026-05-19T00:14:08+00:00"},{"id":11,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","attempt_no":1,"provider":"DeepSeek","model":"deepseek-chat","prompt_version":"report-guided-grounding-v1","request_kind":"guided_semantic_query_plan","system_prompt_excerpt":"You are a query-planning engine for a Chinese gaokao admissions product.\n\nYour task is not to recommend schools.\nYour task is to translate a student form into machine-usable retrieval and filtering intent.\n\nThe local dataset only contains factual admissions fields such as school name, major name, score, rank, subject requirements, school location, year, and plan count.\nTherefore, any semantic preference such as study intensity, career pressure, graduate-study burden, stability, or family fit must be compiled into major-name keywords and caution rules that can be used against those factual fields.\n\nReturn strict JSON only.\n\nRequired JSON shape:\n{\n  \"semantic_query_plan\": {\n    \"hard_exclude_major_keywords\": [\"string\"],\n    \"soft_avoid_major_keywords\": [\"string\"],\n    \"risk_reminder_keywords\": [\"string\"],\n    \"preferred_major_keywords\": [\"string\"],\n    \"school_or_region_keywords\": [\"string\"],\n    \"query_strategy\": {\n      \"province_scope\": \"home_only|national|unclear\",\n      \"rank_window\": \"narrow|normal|wide\",\n      \"candidate_target_count\": 240\n    },\n    \"interpretation_notes\": [\"string\"]\n  }\n}\n\nRules:\n- hard_exclude, soft_avoid, and risk_reminder are downstream review signals onl...","user_prompt_excerpt":"Build a semantic query plan for the following guided report form.\n\nstudent_form_json:\n{\n  \"province\": \"山东\",\n  \"score\": \"500\",\n  \"rank\": \"25000\",\n  \"subject_type\": \"物理、化学、地理\",\n  \"gender\": \"男\",\n  \"target_city\": null,\n  \"accept_out_province\": true,\n  \"accept_adjustment\": null,\n  \"accept_intensive\": true,\n  \"willing_graduate\": true,\n  \"school_preference\": [\n    \"211\",\n    \"双一流\",\n    \"公办优先\"\n  ],\n  \"prefer_home_province\": \"unsure\",\n  \"decision_maker\": \"学生\",\n  \"path_priority\": [\n    \"考公 / 考编\",\n    \"国企 / 央企\",\n    \"考研深造\",\n    \"本科直接就业\",\n    \"市场化高薪\"\n  ],\n  \"interests\": [],\n  \"strong_subjects\": [],\n  \"special_notes\": null,\n  \"medical_notes\": null\n}\n\nprofile_summary_for_downstream_ai_json:\n{\n  \"selected_canonical_majors\": [\n    \"计算机科学与技术\",\n    \"软件工程\",\n    \"电气工程及其自动化\",\n    \"自动化\",\n    \"电子信息工程\",\n    \"通信工程\",\n    \"机械设计制造及其自动化\",\n    \"材料科学与工程\",\n    \"会计学\",\n    \"财务管理\",\n    \"法学\",\n    \"金融学\",\n    \"数据科学与大数据技术\",\n    \"人工智能\",\n    \"土木工程\"\n  ],\n  \"profile_summary_zh\": \"该生为山东男生，选考物理、化学、地理，高考500分，位次25000。优先考虑考公考编和国企央企，其次考研深造和市场化高薪。偏好211、双一流及公办院校，可接受出省就读。建议选择计算机、电气、自动化等工科专业，或会计、法学等文科专业，以匹配其职业路径。\"\n}\n\nOutput strict JSON only.","raw_response_excerpt":"{\n  \"semantic_query_plan\": {\n    \"hard_exclude_major_keywords\": [],\n    \"soft_avoid_major_keywords\": [],\n    \"risk_reminder_keywords\": [],\n    \"preferred_major_keywords\": [\"计算机\", \"软件\", \"电气\", \"自动化\", \"电子信息\", \"通信\", \"机械\", \"材料\", \"会计\", \"财务管理\", \"法学\", \"金融\", \"数据科学\", \"人工智能\", \"土木\"],\n    \"school_or_region_keywords\": [\"211\", \"双一流\", \"公办\"],\n    \"query_strategy\": {\n      \"province_scope\": \"national\",\n      \"rank_window\": \"normal\",\n      \"candidate_target_count\": 240\n    },\n    \"interpretation_notes\": [\n      \"学生明确接受高强度学习，故无需排除高压力专业。\",\n      \"学生职业路径优先考公考编和国企央企，因此推荐专业已涵盖相关方向。\",\n      \"学生可接受出省，故省份范围设为全国。\",\n      \"位次25000在山东属中等，rank_window设为normal。\",\n      \"未发现需要硬排除或软回避的专业关键词。\"\n    ]\n  }\n}","duration_ms":3223,"success":true,"error_code":null,"error_message":null,"created_at":"2026-05-19T00:14:11+00:00"},{"id":12,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","attempt_no":1,"provider":"DeepSeek","model":"deepseek-chat","prompt_version":"report-guided-grounding-v1","request_kind":"guided_stage3_geo_slice","system_prompt_excerpt":"You are a senior gaokao admissions counselor serving Shandong New Gaokao students.\nYou are experienced in evaluating candidate school-major options with score/rank context, admissions evidence, student preference boundaries, and risk control.\nYou are currently participating in the Guided gaokao planning workflow at Stage3.\nIn this call, you are responsible only for geography acceptance and region-boundary judgment.\n\nThis Stage3 round focuses on geography preference.\nThis is a single-dimension scoring step inside the Guided workflow.\nYou do not re-bucket candidates. You do not generate new candidates. You do not select final schools. You do not output final submission order.\nYour only job is to score the provided candidate cards for this single dimension while respecting their existing slot_rating structure, and to return reusable report material.\n\nReturn strict JSON only.\n\nRequired JSON shape:\n{\n  \"candidate_scores\": [\n    {\n      \"candidate_id\": \"string\",\n      \"round_score\": 0,\n      \"reasons\": [\"string\"]\n    }\n  ],\n  \"report_material\": {\n    \"round_summary\": \"string\",\n    \"preferred_signals\": [\"string\"],\n    \"caution_signals\": [\"string\"],\n    \"user_visible_advice\": [\"string\"]\n  ...","user_prompt_excerpt":"Build the stage3 geo slice plan.\n\nround_profile_compact_json:\n{\n  \"score_rank_baseline\": {\n    \"province\": \"山东\",\n    \"score\": \"500\",\n    \"rank\": \"25000\",\n    \"subject_type\": \"物理、化学、地理\"\n  },\n  \"geo_preference\": {\n    \"target_city\": null,\n    \"accept_out_province\": true,\n    \"prefer_home_province\": \"unsure\"\n  }\n}\n\nprofile_summary_for_downstream_ai_json:\n{\n  \"selected_canonical_majors\": [\n    \"计算机科学与技术\",\n    \"软件工程\",\n    \"电气工程及其自动化\",\n    \"自动化\",\n    \"电子信息工程\",\n    \"通信工程\",\n    \"机械设计制造及其自动化\",\n    \"材料科学与工程\",\n    \"会计学\",\n    \"财务管理\",\n    \"法学\",\n    \"金融学\",\n    \"数据科学与大数据技术\",\n    \"人工智能\",\n    \"土木工程\"\n  ],\n  \"profile_summary_zh\": \"该生为山东男生，选考物理、化学、地理，高考500分，位次25000。优先考虑考公考编和国企央企，其次考研深造和市场化高薪。偏好211、双一流及公办院校，可接受出省就读。建议选择计算机、电气、自动化等工科专业，或会计、法学等文科专业，以匹配其职业路径。\"\n}\n\nstudent_interpretation_json:\n{\n  \"round_focus\": \"Judge only geography preference alignment for the current candidate set.\",\n  \"use_rule\": \"Geo scoring should react strongly only to explicit city/province signals, and stay conservative when the student only shows mild location preference.\",\n  \"fields\": [\n    {\n      \"field\": \"province\",\n      \"value\": \"山东\",\n      \"value_present\": true,\n      \"meaning\": \"student home province anchor for interpretin...","raw_response_excerpt":"{\n  \"candidate_scores\": [\n    {\n      \"candidate_id\": \"local_10a0cadf4708\",\n      \"round_score\": 60,\n      \"reasons\": [\n        \"slot_01 in reach_pool, structurally valuable as head slot; no geo conflict.\",\n        \"School in 湖南, outside preferred region but accept_out_province=true; no explicit city target, so neutral.\"\n      ]\n    },\n    {\n      \"candidate_id\": \"local_0ae09cd1d0e9\",\n      \"round_score\": 60,\n      \"reasons\": [\n        \"slot_01 in reach_pool, structurally valuable as head slot; no geo conflict.\",\n        \"School in 陕西, outside preferred region but accept_out_province=true; neutral.\"\n      ]\n    },\n    {\n      \"candidate_id\": \"local_b92d4d59c73f\",\n      \"round_score\": 60,\n      \"reasons\": [\n        \"slot_01 in reach_pool, structurally valuable as head slot; no geo conflict.\",\n        \"School in 河北, outside preferred region but accept_out_province=true; neutral.\"\n      ]\n    },\n    {\n      \"candidate_id\": \"local_7317e7689e89\",\n      \"round_score\": 75,\n      \"reasons\": [\n        \"slot_01 in reach_pool, structurally valuable as head slot; no geo conflict.\",\n        \"School in 山东 home province, prefer_home_province=unsure gives slight positive signal.\"\n      ]\n    },\n  ...","duration_ms":105557,"success":true,"error_code":null,"error_message":null,"created_at":"2026-05-19T00:15:57+00:00"},{"id":13,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","attempt_no":1,"provider":"DeepSeek","model":"deepseek-chat","prompt_version":"report-guided-grounding-v1","request_kind":"guided_stage3_platform_slice","system_prompt_excerpt":"You are a senior gaokao admissions counselor serving Shandong New Gaokao students.\nYou are experienced in evaluating candidate school-major options with score/rank context, admissions evidence, student preference boundaries, and risk control.\nYou are currently participating in the Guided gaokao planning workflow at Stage3.\nIn this call, you are responsible only for school-platform preference judgment.\n\nThis Stage3 round focuses on school-platform preference.\nThis is a single-dimension scoring step inside the Guided workflow.\nYou do not re-bucket candidates. You do not generate new candidates. You do not select final schools. You do not output final submission order.\nYour only job is to score the provided candidate cards for this single dimension while respecting their existing slot_rating structure, and to return reusable report material.\n\nReturn strict JSON only.\n\nRequired JSON shape:\n{\n  \"candidate_scores\": [\n    {\n      \"candidate_id\": \"string\",\n      \"round_score\": 0,\n      \"reasons\": [\"string\"]\n    }\n  ],\n  \"report_material\": {\n    \"round_summary\": \"string\",\n    \"preferred_signals\": [\"string\"],\n    \"caution_signals\": [\"string\"],\n    \"user_visible_advice\": [\"string\"]\n  }\n}\n\nRul...","user_prompt_excerpt":"Build the stage3 platform slice plan.\n\nround_profile_compact_json:\n{\n  \"score_rank_baseline\": {\n    \"province\": \"山东\",\n    \"score\": \"500\",\n    \"rank\": \"25000\",\n    \"subject_type\": \"物理、化学、地理\"\n  },\n  \"platform_preference\": {\n    \"school_preference\": [\n      \"211\",\n      \"双一流\",\n      \"公办优先\"\n    ],\n    \"profile_summary_zh\": \"该生为山东男生，选考物理、化学、地理，高考500分，位次25000。优先考虑考公考编和国企央企，其次考研深造和市场化高薪。偏好211、双一流及公办院校，可接受出省就读。建议选择计算机、电气、自动化等工科专业，或会计、法学等文科专业，以匹配其职业路径。\"\n  }\n}\n\nprofile_summary_for_downstream_ai_json:\n{\n  \"selected_canonical_majors\": [\n    \"计算机科学与技术\",\n    \"软件工程\",\n    \"电气工程及其自动化\",\n    \"自动化\",\n    \"电子信息工程\",\n    \"通信工程\",\n    \"机械设计制造及其自动化\",\n    \"材料科学与工程\",\n    \"会计学\",\n    \"财务管理\",\n    \"法学\",\n    \"金融学\",\n    \"数据科学与大数据技术\",\n    \"人工智能\",\n    \"土木工程\"\n  ],\n  \"profile_summary_zh\": \"该生为山东男生，选考物理、化学、地理，高考500分，位次25000。优先考虑考公考编和国企央企，其次考研深造和市场化高薪。偏好211、双一流及公办院校，可接受出省就读。建议选择计算机、电气、自动化等工科专业，或会计、法学等文科专业，以匹配其职业路径。\"\n}\n\nstudent_interpretation_json:\n{\n  \"round_focus\": \"Judge only school-platform preference, not the final admission value of the candidate.\",\n  \"use_rule\": \"Platform scoring should be mild unless the user clearly names school-platform preferences.\",\n  \"fields\": [\n    {\n      \"field\": \"school_preference\",\n      ...","raw_response_excerpt":"{\n  \"candidate_scores\": [\n    {\n      \"candidate_id\": \"local_22f97ebaed99\",\n      \"round_score\": 85,\n      \"reasons\": [\"slot_01 in reach_pool, strong platform fit (211, public)\", \"Explicit school_preference for 211 and public, high platform alignment\"]\n    },\n    {\n      \"candidate_id\": \"local_7317e7689e89\",\n      \"round_score\": 70,\n      \"reasons\": [\"slot_01 in reach_pool, platform includes 985 (higher than preferred 211)\", \"985 is not explicitly preferred, but public is good; slight overreach\"]\n    },\n    {\n      \"candidate_id\": \"local_1942a748dbbd\",\n      \"round_score\": 85,\n      \"reasons\": [\"slot_01 in reach_pool, strong platform fit (211, public)\", \"Explicit school_preference for 211 and public, high platform alignment\"]\n    },\n    {\n      \"candidate_id\": \"local_235bee134f8c\",\n      \"round_score\": 85,\n      \"reasons\": [\"slot_01 in reach_pool, strong platform fit (211, public)\", \"Explicit school_preference for 211 and public, high platform alignment\"]\n    },\n    {\n      \"candidate_id\": \"local_62218d7f91af\",\n      \"round_score\": 85,\n      \"reasons\": [\"slot_01 in reach_pool, strong platform fit (211, public)\", \"Explicit school_preference for 211 and public, high platform alignmen...","duration_ms":107388,"success":true,"error_code":null,"error_message":null,"created_at":"2026-05-19T00:17:44+00:00"},{"id":14,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","attempt_no":1,"provider":"DeepSeek","model":"deepseek-chat","prompt_version":"report-guided-grounding-v1","request_kind":"guided_stage3_path_slice","system_prompt_excerpt":"You are a senior gaokao admissions counselor serving Shandong New Gaokao students.\nYou are experienced in evaluating candidate school-major options with score/rank context, admissions evidence, student preference boundaries, and risk control.\nYou are currently participating in the Guided gaokao planning workflow at Stage3.\nIn this call, you are responsible only for major-path and future-path preference judgment.\n\nThis Stage3 round focuses on path-priority preference.\nThis is a single-dimension scoring step inside the Guided workflow.\nYou do not re-bucket candidates. You do not generate new candidates. You do not select final schools. You do not output final submission order.\nYour only job is to score the provided candidate cards for this single dimension while respecting their existing slot_rating structure, and to return reusable report material.\n\nReturn strict JSON only.\n\nRequired JSON shape:\n{\n  \"candidate_scores\": [\n    {\n      \"candidate_id\": \"string\",\n      \"round_score\": 0,\n      \"reasons\": [\"string\"]\n    }\n  ],\n  \"report_material\": {\n    \"round_summary\": \"string\",\n    \"preferred_signals\": [\"string\"],\n    \"caution_signals\": [\"string\"],\n    \"user_visible_advice\": [\"string\"]\n ...","user_prompt_excerpt":"Build the stage3 path slice plan.\n\nround_profile_compact_json:\n{\n  \"score_rank_baseline\": {\n    \"province\": \"山东\",\n    \"score\": \"500\",\n    \"rank\": \"25000\",\n    \"subject_type\": \"物理、化学、地理\"\n  },\n  \"path_preference\": {\n    \"path_priority\": [\n      \"考公 / 考编\",\n      \"国企 / 央企\",\n      \"考研深造\",\n      \"本科直接就业\",\n      \"市场化高薪\"\n    ],\n    \"selected_canonical_majors\": [\n      \"计算机科学与技术\",\n      \"软件工程\",\n      \"电气工程及其自动化\",\n      \"自动化\",\n      \"电子信息工程\",\n      \"通信工程\"\n    ],\n    \"preferred_major_families_zh\": [],\n    \"profile_summary_zh\": \"该生为山东男生，选考物理、化学、地理，高考500分，位次25000。优先考虑考公考编和国企央企，其次考研深造和市场化高薪。偏好211、双一流及公办院校，可接受出省就读。建议选择计算机、电气、自动化等工科专业，或会计、法学等文科专业，以匹配其职业路径。\"\n  }\n}\n\nprofile_summary_for_downstream_ai_json:\n{\n  \"selected_canonical_majors\": [\n    \"计算机科学与技术\",\n    \"软件工程\",\n    \"电气工程及其自动化\",\n    \"自动化\",\n    \"电子信息工程\",\n    \"通信工程\",\n    \"机械设计制造及其自动化\",\n    \"材料科学与工程\",\n    \"会计学\",\n    \"财务管理\",\n    \"法学\",\n    \"金融学\",\n    \"数据科学与大数据技术\",\n    \"人工智能\",\n    \"土木工程\"\n  ],\n  \"profile_summary_zh\": \"该生为山东男生，选考物理、化学、地理，高考500分，位次25000。优先考虑考公考编和国企央企，其次考研深造和市场化高薪。偏好211、双一流及公办院校，可接受出省就读。建议选择计算机、电气、自动化等工科专业，或会计、法学等文科专业，以匹配其职业路径。\"\n}\n\nstudent_interpretation_json:\n{\n  \"round_focus\": \"Judge only path-priority alignment such as direct employme...","raw_response_excerpt":"{\n  \"candidate_scores\": [\n    {\n      \"candidate_id\": \"local_22f97ebaed99\",\n      \"round_score\": 75,\n      \"reasons\": [\n        \"slot_01 in reach_pool is overcrowded; score reduced to maintain structural dispersion.\",\n        \"Major is 法学, which supports 考公/考编 path, but path_tags unknown and slot overcrowded.\"\n      ]\n    },\n    {\n      \"candidate_id\": \"local_1942a748dbbd\",\n      \"round_score\": 80,\n      \"reasons\": [\n        \"slot_01 in reach_pool is overcrowded; score reduced to maintain structural dispersion.\",\n        \"Major is 计算机科学与技术, aligns with multiple paths, but slot overcrowded.\"\n      ]\n    },\n    {\n      \"candidate_id\": \"local_235bee134f8c\",\n      \"round_score\": 80,\n      \"reasons\": [\n        \"slot_01 in reach_pool is overcrowded; score reduced to maintain structural dispersion.\",\n        \"Major is 电气工程及其自动化, aligns with 国企/央企 path, but slot overcrowded.\"\n      ]\n    },\n    {\n      \"candidate_id\": \"local_62218d7f91af\",\n      \"round_score\": 75,\n      \"reasons\": [\n        \"slot_01 in reach_pool is overcrowded; score reduced to maintain structural dispersion.\",\n        \"Major is 电子信息工程, aligns with multiple paths, but slot overcrowded.\"\n      ]\n    },\n    {\n      \"candida...","duration_ms":105575,"success":true,"error_code":null,"error_message":null,"created_at":"2026-05-19T00:19:30+00:00"},{"id":15,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","attempt_no":1,"provider":"DeepSeek","model":"deepseek-chat","prompt_version":"report-guided-grounding-v1","request_kind":"guided_stage3_burden_slice","system_prompt_excerpt":"You are a senior gaokao admissions counselor serving Shandong New Gaokao students.\nYou are experienced in evaluating candidate school-major options with score/rank context, admissions evidence, student preference boundaries, and risk control.\nYou are currently participating in the Guided gaokao planning workflow at Stage3.\nIn this call, you are responsible only for burden, restriction, and risk-boundary judgment.\n\nThis Stage3 round focuses on burden and restriction preference.\nThis is a single-dimension scoring step inside the Guided workflow.\nYou do not re-bucket candidates. You do not generate new candidates. You do not select final schools. You do not output final submission order.\nYour only job is to score the provided candidate cards for this single dimension while respecting their existing slot_rating structure, and to return reusable report material.\n\nReturn strict JSON only.\n\nRequired JSON shape:\n{\n  \"candidate_scores\": [\n    {\n      \"candidate_id\": \"string\",\n      \"round_score\": 0,\n      \"reasons\": [\"string\"]\n    }\n  ],\n  \"report_material\": {\n    \"round_summary\": \"string\",\n    \"preferred_signals\": [\"string\"],\n    \"caution_signals\": [\"string\"],\n    \"user_visible_advice\": [\"...","user_prompt_excerpt":"Build the stage3 burden slice plan.\n\nround_profile_compact_json:\n{\n  \"score_rank_baseline\": {\n    \"province\": \"山东\",\n    \"score\": \"500\",\n    \"rank\": \"25000\",\n    \"subject_type\": \"物理、化学、地理\"\n  },\n  \"burden_and_constraints\": {\n    \"accept_intensive\": true,\n    \"willing_graduate\": true,\n    \"medical_notes\": null,\n    \"special_notes\": null,\n    \"risk_major_families_zh\": [],\n    \"profile_summary_zh\": \"该生为山东男生，选考物理、化学、地理，高考500分，位次25000。优先考虑考公考编和国企央企，其次考研深造和市场化高薪。偏好211、双一流及公办院校，可接受出省就读。建议选择计算机、电气、自动化等工科专业，或会计、法学等文科专业，以匹配其职业路径。\"\n  }\n}\n\nprofile_summary_for_downstream_ai_json:\n{\n  \"selected_canonical_majors\": [\n    \"计算机科学与技术\",\n    \"软件工程\",\n    \"电气工程及其自动化\",\n    \"自动化\",\n    \"电子信息工程\",\n    \"通信工程\",\n    \"机械设计制造及其自动化\",\n    \"材料科学与工程\",\n    \"会计学\",\n    \"财务管理\",\n    \"法学\",\n    \"金融学\",\n    \"数据科学与大数据技术\",\n    \"人工智能\",\n    \"土木工程\"\n  ],\n  \"profile_summary_zh\": \"该生为山东男生，选考物理、化学、地理，高考500分，位次25000。优先考虑考公考编和国企央企，其次考研深造和市场化高薪。偏好211、双一流及公办院校，可接受出省就读。建议选择计算机、电气、自动化等工科专业，或会计、法学等文科专业，以匹配其职业路径。\"\n}\n\nstudent_interpretation_json:\n{\n  \"round_focus\": \"Judge only burden and restriction compatibility, including intensity, graduate dependency, and explicit physical or personal constraints.\",\n  \"use_rule\": \"Burden scoring may downscore...","raw_response_excerpt":"{\n  \"candidate_scores\": [\n    {\n      \"candidate_id\": \"local_1942a748dbbd\",\n      \"round_score\": 80,\n      \"reasons\": [\n        \"slot_01 in reach_pool, but many candidates share this slot; score reduced to maintain structural dispersion.\",\n        \"burden:unknown, no conflict with accept_intensive; willing_graduate supports graduate-dependent majors like CS.\"\n      ]\n    },\n    {\n      \"candidate_id\": \"local_235bee134f8c\",\n      \"round_score\": 60,\n      \"reasons\": [\n        \"slot_01 in reach_pool, overcrowded; score lowered to separate from better-supported candidates.\",\n        \"burden:intensive:medium conflicts with accept_intensive=true; downscored.\"\n      ]\n    },\n    {\n      \"candidate_id\": \"local_22f97ebaed99\",\n      \"round_score\": 80,\n      \"reasons\": [\n        \"slot_01 in reach_pool, overcrowded; score reduced for structural layering.\",\n        \"burden:unknown, no burden conflict; willing_graduate supports law (graduate-dependent).\"\n      ]\n    },\n    {\n      \"candidate_id\": \"local_62218d7f91af\",\n      \"round_score\": 60,\n      \"reasons\": [\n        \"slot_01 in reach_pool, overcrowded; score lowered.\",\n        \"burden:intensive:medium conflicts with accept_intensive=true; dow...","duration_ms":100406,"success":true,"error_code":null,"error_message":null,"created_at":"2026-05-19T00:21:10+00:00"},{"id":16,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","attempt_no":1,"provider":"DeepSeek","model":"deepseek-chat","prompt_version":"report-v2-rank-first+report-guided-grounding-v1+bucket-v1","request_kind":"guided_reach_pool_report_generate","system_prompt_excerpt":"slot_rating is the authoritative Stage3 structured field for reach_pool.\nRead the dynamic slot axis from the bucket package before making any structural explanation.\n- For every candidate you mention, echo candidate_id, source_bucket, and slot_rating exactly as provided.\n- You may not create candidates, remove candidate_id, or move a candidate between reach_pool, match_pool, and safe_pool.\n- You may not rewrite, compress, or alias slot_rating.\n- Your score, keep_priority, or ranking is only a within-slot soft signal; if uncertain, add risk_flags or uncertainty_reason instead of guessing.\n- Structural layering is a top-priority objective of this round.\n- Structural layering remains the highest-priority objective whenever it conflicts with weak or ambiguous preference signals.\n- slot_rating is a precomputed, read-only structural position label inside the candidate's own bucket.\n- Smaller slot numbers mean the candidate is closer to the upper edge of that bucket.\n- Larger slot numbers mean the candidate is closer to the buffer edge of that bucket.\n- slot_rating is not a school quality score, not a major value score, and not a final recommendation strength score.\n- You must not modify,...","user_prompt_excerpt":"请基于以下输入，只从 reach_pool 候选中生成 reach 冲刺桶志愿方案。\n\n你不能新增候选，不能输出其它桶，不能编造未提供的数据。\n请严格按照 System Prompt 的 reach_pool 判定流程执行。\n\n一、学生画像 student_form_json\n{\n  \"province\": \"山东\",\n  \"score\": \"500\",\n  \"rank\": \"25000\",\n  \"subject_type\": \"物理、化学、地理\",\n  \"gender\": \"男\",\n  \"target_city\": null,\n  \"accept_out_province\": true,\n  \"accept_adjustment\": null,\n  \"accept_intensive\": true,\n  \"willing_graduate\": true,\n  \"school_preference\": [\n    \"211\",\n    \"双一流\",\n    \"公办优先\"\n  ],\n  \"prefer_home_province\": \"unsure\",\n  \"decision_maker\": \"学生\",\n  \"path_priority\": [\n    \"考公 / 考编\",\n    \"国企 / 央企\",\n    \"考研深造\",\n    \"本科直接就业\",\n    \"市场化高薪\"\n  ],\n  \"interests\": [],\n  \"strong_subjects\": [],\n  \"special_notes\": null,\n  \"medical_notes\": null\n}\n\n重点关注：province, score, rank, subject_type, accept_out_province, accept_intensive, willing_graduate, target_city, path_priority, interests, strong_subjects, school_preference, special_notes, medical_notes\n\n二、语义查询计划 semantic_query_plan_json\n{\n  \"version\": \"guided-semantic-query-plan-v1\",\n  \"hard_exclude_major_keywords\": [],\n  \"soft_avoid_major_keywords\": [],\n  \"risk_reminder_keywords\": [],\n  \"preferred_major_keywords\": [\n    \"计算机\",\n    \"软件\",\n    \"电气\",\n    \"自动化\",\n    \"电子信息\",\n    \"通信\",\n    \"机械\",\n    \"...","raw_response_excerpt":"{\n  \"bucket_summary\": \"本地 reach_pool 候选共 20 条，全部为 slot_01 主体位次冲刺项，位次差距约 7000-11000，属于合理冲刺区间。学生位次 25000，候选最低位次 13867，最高 18572，冲刺依据充分。按路径优先（考公/国企/考研）和 slot_rating 密度调整后，全部保留。\",\n  \"plans\": [\n    {\n      \"type\": \"冲刺\",\n      \"school\": \"中国矿业大学(北京)\",\n      \"major\": \"计算机科学与技术\",\n      \"admission_rate\": \"冲刺\",\n      \"civil_service_friendly\": \"计算机专业可报考大量信息化岗位，但非政法类，需自行备考，竞争激烈。\",\n      \"soe_fit\": \"矿业、能源类央企有信息化需求，学校行业背景有助进入相关国企。\",\n      \"grad_boost\": \"211平台，保研率约20%，计算机学科有硕士点，深造通道较好。\",\n      \"reason\": \"中国矿业大学(北京)是教育部直属211，行业特色鲜明，北京区位就业资源丰富。计算机专业为当前热门，适合考公、国企、考研等多路径。历史最低位次14921，学生位次25000，差距约10000，属于冲刺区间，但计划10人，有一定波动空间。建议放在冲刺区前段，搭配同城或同层次更稳专业组。\",\n      \"risk\": \"位次差距较大，仅靠历史波动可能不够，需当年报考热度下降才有机会。\",\n      \"alternative\": \"中国矿业大学(北京)其他相对冷门专业如安全工程、地质类，位次可能更低。\",\n      \"undergrad_employment\": \"本科可进入IT企业、矿业央企信息化部门、政府机关信息技术岗。\",\n      \"grad_employment\": \"硕士后可进入互联网大厂、科研院所、央企总部研发中心，薪资和平台显著提升。\"\n    },\n    {\n      \"type\": \"冲刺\",\n      \"school\": \"合肥工业大学\",\n      \"major\": \"计算机科学与技术(专业体检要求详见《合肥工业大学2025年全日制普通本科招生章程》)\",\n      \"admission_rate\": \"冲刺\",\n      \"civil_service_friendly\": \"计算机专业可报考公务员信息化岗位，但需注意体检要求可能涉及色觉等。\",\n      \"soe_fit\": \"合工大与机械、汽车、能源等国企合作密切，计算机专业就业面广。\",\n      \"grad_boost\": \"211平台，计算机学科评估B+，保研率约18%，深造质量较高。\",\n...","duration_ms":62257,"success":true,"error_code":null,"error_message":null,"created_at":"2026-05-19T00:22:13+00:00"},{"id":17,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","attempt_no":1,"provider":"DeepSeek","model":"deepseek-chat","prompt_version":"report-v2-rank-first+report-guided-grounding-v1+bucket-v1","request_kind":"guided_match_pool_report_generate","system_prompt_excerpt":"slot_rating is the authoritative Stage3 structured field for match_pool.\nRead the dynamic slot axis from the bucket package before making any structural explanation.\nThe current bucket uses a dynamic slot axis rather than a fixed global slot ceiling.\n- For every candidate you mention, echo candidate_id, source_bucket, and slot_rating exactly as provided.\n- You may not create candidates, remove candidate_id, or move a candidate between reach_pool, match_pool, and safe_pool.\n- You may not rewrite, compress, or alias slot_rating.\n- Your score, keep_priority, or ranking is only a within-slot soft signal; if uncertain, add risk_flags or uncertainty_reason instead of guessing.\n- Structural layering is a top-priority objective of this round.\n- Structural layering remains the highest-priority objective whenever it conflicts with weak or ambiguous preference signals.\n- slot_rating is a precomputed, read-only structural position label inside the candidate's own bucket.\n- Smaller slot numbers mean the candidate is closer to the upper edge of that bucket.\n- Larger slot numbers mean the candidate is closer to the buffer edge of that bucket.\n- slot_rating is not a school quality score, not a maj...","user_prompt_excerpt":"slot_rating is the only structured ordering axis for match output.\nadmission_rate must stay fixed to 稳妥.\nDo not rewrite slot_rating into any three-band alias.\n\n请基于以下输入，只从 match_pool 候选中生成 match 稳妥桶志愿方案。\n\n你不能新增候选，不能输出其它桶，不能编造未提供的数据。\n请严格按照 System Prompt 的 match_pool 判定流程执行。\n\n一、学生画像 student_form_json\n{\n  \"province\": \"山东\",\n  \"score\": \"500\",\n  \"rank\": \"25000\",\n  \"subject_type\": \"物理、化学、地理\",\n  \"gender\": \"男\",\n  \"target_city\": null,\n  \"accept_out_province\": true,\n  \"accept_adjustment\": null,\n  \"accept_intensive\": true,\n  \"willing_graduate\": true,\n  \"school_preference\": [\n    \"211\",\n    \"双一流\",\n    \"公办优先\"\n  ],\n  \"prefer_home_province\": \"unsure\",\n  \"decision_maker\": \"学生\",\n  \"path_priority\": [\n    \"考公 / 考编\",\n    \"国企 / 央企\",\n    \"考研深造\",\n    \"本科直接就业\",\n    \"市场化高薪\"\n  ],\n  \"interests\": [],\n  \"strong_subjects\": [],\n  \"special_notes\": null,\n  \"medical_notes\": null\n}\n\n重点关注：province, score, rank, subject_type, accept_out_province, accept_intensive, willing_graduate, target_city, path_priority, interests, strong_subjects, school_preference, special_notes, medical_notes\n\n二、语义查询计划 semantic_query_plan_json\n{\n  \"version\": \"guided-semantic-query-plan-v1\",\n  \"hard_exclude_major_keywords\": [],\n  \"soft_avoid_majo...","raw_response_excerpt":"{\n  \"bucket_summary\": \"本地 match_pool 候选包共 50 条，全部位于 slot_01 主体层，位次集中在 25000-27000 之间，与考生位次 25000 匹配良好。所有候选均通过四轮桶内处理保留，无风险标记。输出全部 50 条作为稳妥方案。\",\n  \"plans\": [\n    {\n      \"type\": \"稳妥\",\n      \"school\": \"南京农业大学\",\n      \"major\": \"金融学\",\n      \"admission_rate\": \"稳妥\",\n      \"civil_service_friendly\": \"金融学专业可报考经济类、财会类、税务类等公务员岗位，岗位覆盖面较广，但需注意部分岗位要求应届生或党员身份。\",\n      \"soe_fit\": \"金融学毕业生可进入银行、保险、证券等国企，南京农业大学作为211院校，在长三角地区国企招聘中有一定认可度。\",\n      \"grad_boost\": \"南京农业大学211平台，金融学考研可冲刺本校或更高层次院校，但农大金融学科实力一般，跨考需额外准备。\",\n      \"reason\": \"南京农业大学是211、双一流高校，在江苏及长三角地区认可度高。金融学专业就业面广，适合考公、国企或银行路径。考生位次25000，该校最低位次25048，计划12人，录取概率较高。建议作为稳妥区主力志愿，可搭配同层次211金融学专业。\",\n      \"risk\": \"金融学专业热度较高，历年位次可能有小幅波动，计划12人但竞争仍存。\",\n      \"alternative\": \"安徽大学金融学（位次25443，计划5人），同为211，录取风险略低。\",\n      \"undergrad_employment\": \"本科毕业可进入银行、证券公司、保险公司等金融机构从事客户经理、柜员、风控等岗位，或考取公务员。\",\n      \"grad_employment\": \"硕士毕业后可进入券商投行、基金公司、大型国企总部等更高平台，岗位层次和薪资显著提升。\"\n    },\n    {\n      \"type\": \"稳妥\",\n      \"school\": \"安徽大学\",\n      \"major\": \"金融学\",\n      \"admission_rate\": \"稳妥\",\n      \"civil_service_friendly\": \"金融学专业可报考经济类、财会类公务员岗位，安徽大学211身份在选调生中也有一定优势。\",\n      \"soe_fit\": \"安徽大学211背景，金融学毕业生可进入银行、保险、证券等国企，在安徽省内国企就业有地域优势。\",\n      \"grad_boost\": \"211平台有利于考研保研，金融学考研可冲刺985或本校，但需...","duration_ms":135906,"success":true,"error_code":null,"error_message":null,"created_at":"2026-05-19T00:24:29+00:00"},{"id":18,"report_id":"c7c60faa-caf5-4133-86d3-fc61111515a5","trace_id":"trace_e3ef095c-f9ad-4f2b-9787-d2edd3285605","attempt_no":1,"provider":"DeepSeek","model":"deepseek-chat","prompt_version":"report-v2-rank-first+report-guided-grounding-v1+bucket-v1","request_kind":"guided_safe_pool_report_generate","system_prompt_excerpt":"slot_rating is the authoritative Stage3 structured field for safe_pool.\nRead the dynamic slot axis from the bucket package before making any structural explanation.\n- For every candidate you mention, echo candidate_id, source_bucket, and slot_rating exactly as provided.\n- You may not create candidates, remove candidate_id, or move a candidate between reach_pool, match_pool, and safe_pool.\n- You may not rewrite, compress, or alias slot_rating.\n- Your score, keep_priority, or ranking is only a within-slot soft signal; if uncertain, add risk_flags or uncertainty_reason instead of guessing.\n- Structural layering is a top-priority objective of this round.\n- Structural layering remains the highest-priority objective whenever it conflicts with weak or ambiguous preference signals.\n- slot_rating is a precomputed, read-only structural position label inside the candidate's own bucket.\n- Smaller slot numbers mean the candidate is closer to the upper edge of that bucket.\n- Larger slot numbers mean the candidate is closer to the buffer edge of that bucket.\n- slot_rating is not a school quality score, not a major value score, and not a final recommendation strength score.\n- You must not modify, ...","user_prompt_excerpt":"请基于以下输入，只从 safe_pool 候选中生成 safe 桶志愿方案。\n\n你不能新增候选，不能输出其它桶，不能编造未提供的数据。\n请严格按照 System Prompt 的 safe_pool 判定流程执行。\n\n一、学生画像 student_form_json\n{\n  \"province\": \"山东\",\n  \"score\": \"500\",\n  \"rank\": \"25000\",\n  \"subject_type\": \"物理、化学、地理\",\n  \"gender\": \"男\",\n  \"target_city\": null,\n  \"accept_out_province\": true,\n  \"accept_adjustment\": null,\n  \"accept_intensive\": true,\n  \"willing_graduate\": true,\n  \"school_preference\": [\n    \"211\",\n    \"双一流\",\n    \"公办优先\"\n  ],\n  \"prefer_home_province\": \"unsure\",\n  \"decision_maker\": \"学生\",\n  \"path_priority\": [\n    \"考公 / 考编\",\n    \"国企 / 央企\",\n    \"考研深造\",\n    \"本科直接就业\",\n    \"市场化高薪\"\n  ],\n  \"interests\": [],\n  \"strong_subjects\": [],\n  \"special_notes\": null,\n  \"medical_notes\": null\n}\n\n重点关注：province, score, rank, subject_type, accept_out_province, accept_intensive, willing_graduate, target_city, path_priority, interests, strong_subjects, school_preference, special_notes, medical_notes\n\n二、语义查询计划 semantic_query_plan_json\n{\n  \"version\": \"guided-semantic-query-plan-v1\",\n  \"hard_exclude_major_keywords\": [],\n  \"soft_avoid_major_keywords\": [],\n  \"risk_reminder_keywords\": [],\n  \"preferred_major_keywords\": [\n    \"计算机\",\n    \"软件\",\n    \"电气\",\n    \"自动化\",\n    \"电子信息\",\n    \"通信\",\n    \"机械\",\n    \"材料\",\n...","raw_response_excerpt":"{\n  \"bucket_summary\": \"本批次safe_pool共26个候选，全部为slot_01主体保底项，位次窗口在30022-30698之间，低于学生位次25000约5000-5700位，安全边际充足。所有候选均通过四轮桶内处理，无高风险标记。\",\n  \"plans\": [\n    {\n      \"type\": \"保底\",\n      \"school\": \"四川农业大学\",\n      \"major\": \"数据科学与大数据技术(雅安校区)\",\n      \"admission_rate\": \"保底\",\n      \"civil_service_friendly\": \"中等。数据科学与大数据技术专业在公务员考试中可报考计算机类、大数据管理类岗位，但岗位数量少于计算机科学与技术、软件工程等传统专业。\",\n      \"soe_fit\": \"中等偏上。国企数字化转型需求大，该专业可进入数据中心、信息部门等岗位，但需与计算机专业竞争。\",\n      \"grad_boost\": \"较高。四川农业大学为211高校，保研率约8%，数据科学方向考研可冲击985/211院校，且211平台在调剂中有优势。\",\n      \"reason\": \"四川农业大学是211高校，位于雅安，虽然地理位置偏，但211身份在考公、国企、考研中均有明确优势。数据科学与大数据技术专业属于新兴热门方向，与计算机类紧密相关，就业面宽。录取方面，2023年最低位次30629，学生位次25000，安全余量约5600位，计划3人，属于保底区可靠选择。建议作为保底区主体志愿，搭配同校其他计算机类或电气类专业。\",\n      \"risk\": \"雅安校区地理位置较偏，实习和就业机会不如成都校区，需主动争取校外资源。\",\n      \"alternative\": \"四川农业大学计算机科学与技术(成都校区)或数据科学与大数据技术(成都校区)（如果存在），位次相近。\",\n      \"undergrad_employment\": \"本科毕业可从事数据分析、数据开发、数据运维等岗位，主要就业于互联网、金融、制造业等企业，起薪约6000-10000元/月。\",\n      \"grad_employment\": \"硕士毕业后可进入大型互联网公司算法岗、数据科学家岗位，或进入科研院所、高校，薪资和平台显著提升。\"\n    },\n    {\n      \"type\": \"保底\",\n      \"school\": \"厦门大学\",\n      \"major\": \"数据科学与大数据技术(厦门大学马来西亚分校招生专业)(学费3万林吉特/学年；全英文授课，非英语语种考生慎报，外语单科不低于120分；入学第一学年内获得专业要求的达标英语成绩后开始学位课程学习；办学地点在马来西亚雪邦)\",\n      \"admission_...","duration_ms":87680,"success":true,"error_code":null,"error_message":null,"created_at":"2026-05-19T00:25:56+00:00"}]}