Spaces:
Running
Running
Commit History
-
add
a6fc11c -
add
aed2e81
-
add
a469640 -
add
e20ad3b
-
π§ Fix character ranges for all window KG files
bd9612e
-
π¬ Complete replay support for all algorithm samples (14 & 16)
fa963b0 -
π¬ Add replay support for algorithm_sample_0 & algorithm_sample_3
8bc258a -
π― Redesign window KGs as independent processing stages
1bd7dcc -
π§ Fix window KG entity reference - remove invalid rel_009 from window_0
2c3bb26 -
π¬ Add temporal replay support for algorithm_sample_1 with 3 progressive window KGs
d3559e7 -
π§Ή Clean up demo data and rebuild frontendβ
- Remove window_replay_demo sample and associated KG files - Clean up samples_config.json structure - Rebuild frontend with latest changes - Prepare for production deploymente0a5339 -
add
6961471 -
π§Ή Clean up temporary analytics enhancement script
f3d9d2c -
π Add Comprehensive Trace Analytics to Sample Dataβ
MAJOR ENHANCEMENT: Sample traces now show real statistics instead of N/A π PROBLEM: Sample traces lacked schema_analytics metadata π οΈ SOLUTION: Added realistic analytics to all 6 sample traces π ANALYTICS: Tokens, prompts, execution time, success rate, call stack depth π― OUTCOME: Better demo experience matching production tracesd0b86b6 -
π§ Fix Failure and Optimization Type Field Namesβ
CRITICAL FIX: Corrected field names causing failures and optimizations to display as 'OTHER' type in AgentGraph UI π¨ ROOT CAUSE: Wrong field names in knowledge graphs - Failures used 'type' instead of 'risk_type' - Optimizations used 'type' instead of 'recommendation_type' π§ FIXES APPLIED: 1. β Failure Field Names: BEFORE: "type": "EXECUTION_ERROR" (wrong) AFTER: "risk_type": "EXECUTION_ERROR" (correct) 2. β Optimization Field Names: BEFORE: "type": "TOOL_ENHANCEMENT" (wrong) AFTER: "recommendation_type": "TOOL_ENHANCEMENT" (correct) 3. π§Ή Cleanup Extra Fields: - Removed 'severity' from failures (not in model) - Removed 'priority' from optimizations (not in model) π AFFECTED FILES & COUNTS: - kg_algorithm_sample_1.json: 2 failures + 3 optimizations β - kg_algorithm_sample_3.json: 2 failures + 3 optimizations β - kg_algorithm_sample_14.json: 2 failures + 3 optimizations β - kg_algorithm_sample_16.json: 2 failures + 3 optimizations β β VALIDATION RESULTS: - β¦6464c11 -
π§ Fix Critical Computer Terminal Entity Type Errorβ
MAJOR CONCEPTUAL FIX: Corrected Computer Terminal from Agent to Tool type based on actual behavioral analysis π§ ROOT CAUSE ANALYSIS: - Analyzed original algorithm-generated.jsonl data - Computer Terminal behavior: 'There is no code from the last 1 message for me to execute' - Function: Passive code execution environment, not autonomous agent - Role: Computational tool used by other agents π¨ MODELING ERRORS FIXED: 1. β Entity Type Misclassification: BEFORE: Computer Terminal (Agent) - incorrect AFTER: Computer Terminal (Tool) - correct 2. β Relationship Logic Errors: BEFORE: Agent(Computer Terminal) PERFORMS Task - illogical AFTER: Tool(Computer Terminal) REQUIRED_BY Task - logical Agent USES Tool(Computer Terminal) - logical π IMPACT ON ALL 5 KNOWLEDGE GRAPHS: - kg_algorithm_sample_0.json: β Fixed - kg_algorithm_sample_1.json: β Fixed - kg_algorithm_sample_3.json: β Fixed - kg_algorithm_sample_14.json: β Fixed - kg_algorithm_sample_16.json: β Fixed β Vβ¦66a2a90 -
π§ Fix All Knowledge Graph Relationship Rule Violationsβ
CRITICAL FIXES: Corrected relationship types and directions to comply with AgentGraph rules from task_prompts.py and reference_based/ π¨ VIOLATIONS FIXED: 1. β USES Relationships (Agent β Task) β Fixed to PERFORMS (Agent β Task) in: - kg_algorithm_sample_3.json (rel_009) - kg_algorithm_sample_14.json (rel_009) - kg_algorithm_sample_16.json (rel_009) - kg_algorithm_sample_1.json (rel_009) 2. β DELIVERS_TO Relationship (Output β Agent) β Fixed to DELIVERS_TO (Output β Human) in: - kg_algorithm_sample_0.json (relation_005) - Added human_001 (Park Visitor) entity 3. β Field Name Errors β Fixed in kg_algorithm_sample_1.json: - 'source_id' β 'source' - 'target_id' β 'target' π VALIDATION RESULTS: - β 47 total relationships across 6 knowledge graphs - β 0 violations remaining - β All relationship directions now comply with strict rules: - CONSUMED_BY: Input β Agent - PERFORMS: Agent β Task - USES: Agent β Tool - DELIVERS_TO: Output β Human - Alβ¦c0a875b -
π§ Fix Knowledge Graph Relationship Field Namesβ
CRITICAL FIX: Relationships were not connecting in visualization due to incorrect field names: β BEFORE (broken): - 'source_id' and 'target_id' fields - Relationships appeared as disconnected nodes β AFTER (fixed): - 'source' and 'target' fields (correct format) - Relationships now properly connect in graph visualization π AFFECTED FILES: - kg_algorithm_sample_3.json (Probability Game Theory) - kg_algorithm_sample_14.json (Academic Literature) - kg_algorithm_sample_16.json (Wildlife Data Analysis) π― RESULT: All 9 relationships per knowledge graph now render correctly with proper entity connections46af2b7 -
π― Add 3 Diverse Multi-Agent System Examples from Algorithm Datasetβ
π¬ NEW SAMPLES ADDED: 1. π² Probability Game Theory Analysis System (Sample 3) - Cross-disciplinary: Probability Expert + Theoretical Chemistry Expert - Complex riddle scenarios with game theory and chemical modeling - Simulation implementation failures and interdisciplinary coordination - 10 entities, 9 relations, 2 failures, 3 optimizations 2. π Academic Literature Research System (Sample 14) - Scholarly research: Literary Analysis + Norse Mythology expertise - Emily Midkiff article investigation with mythological references - Academic database retrieval errors and validation challenges - 10 entities, 9 relations, 2 failures, 3 optimizations 3. π Wildlife Data Analysis & Ecological Monitoring (Sample 16) - Data science: Statistical Analysis + Government Dataset Processing - Florida invasive crocodile population analysis (2000-2020) - USGS data retrieval failures and format compatibility issues - 10 entities, 9 relations, 2 failures, 3 optimizaβ¦fb42428 -
π½οΈ Add Complex Location-Based Restaurant Discovery Sampleβ
- Add algorithm_sample_1: sophisticated location-based services example - Features 4 specialized agents: Location-Based Services Expert, Eateries Expert, Data Verification Expert, Computer Terminal - Complex workflow: geographic proximity analysis β restaurant data collection β operating hours validation - Real failure scenarios: execution errors in data verification, API limitations - Multiple optimization opportunities: tool enhancement, workflow simplification, prompt refinement - Demonstrates real-world constraints: time-based filtering, multi-source validation, API integration challenges - Complexity level: expert (more advanced than simple arithmetic example) - 10 entities, 9 relations, 2 failures, 3 optimizationsa7c5051 -
π Add real AI knowledge graph integration (API keys redacted)
5aa050e -
add
286c429