vibeostheog 0.22.16 → 0.22.21

package/src/vibeOS-lib/tests/reports/mode-calibration-2026-05-23T07-07-08Z.json

@@ -1,440 +0,0 @@
-{
-  "meta": {
-    "generated_at": "2026-05-22T07:46:33.046Z",
-    "version": "2.0",
-    "schema": "vibeos-mode-calibration-v2"
-  },
-  "active_models": {
-    "brain": "deepseek/deepseek-v4-pro",
-    "medium": "deepseek/deepseek-v4-flash",
-    "cheap": "deepseek/deepseek-chat"
-  },
-  "tier_collisions": [],
-  "pricing_estimates": {
-    "deepseek-v4-pro": {
-      "prompt": 1.25,
-      "completion": 8
-    },
-    "deepseek-v4-flash": {
-      "prompt": 0.25,
-      "completion": 1
-    },
-    "deepseek-chat": {
-      "prompt": 0.14,
-      "completion": 0.56
-    },
-    "deepseek-reasoner": {
-      "prompt": 0.55,
-      "completion": 2.19
-    },
-    "gpt-4o": {
-      "prompt": 2.5,
-      "completion": 10
-    },
-    "gpt-4o-mini": {
-      "prompt": 0.15,
-      "completion": 0.6
-    },
-    "claude-sonnet-4": {
-      "prompt": 3,
-      "completion": 15
-    },
-    "default": {
-      "prompt": 1,
-      "completion": 4
-    }
-  },
-  "mode_configs": {
-    "balanced": {
-      "tier": "auto",
-      "thinking": "auto",
-      "enforcement": "normal",
-      "flow": "normal",
-      "tdd": "normal",
-      "stress": 1,
-      "loop_threshold": 0.6,
-      "api_enrichment": true,
-      "outcome_detection": true,
-      "_empirical": {
-        "brain": {
-          "avg_latency_ms": 329,
-          "avg_tps": 7564,
-          "total_tok_out": 36892,
-          "total_cost": 0.295821,
-          "runs": 15
-        },
-        "medium": {
-          "avg_latency_ms": 308,
-          "avg_tps": 6686,
-          "total_tok_out": 29542,
-          "total_cost": 0.029679,
-          "runs": 15
-        },
-        "cheap": {
-          "avg_latency_ms": 391,
-          "avg_tps": 5344,
-          "total_tok_out": 13215,
-          "total_cost": 0.007441560000000001,
-          "runs": 8
-        }
-      }
-    },
-    "budget": {
-      "tier": "cheap",
-      "thinking": "off",
-      "enforcement": "relaxed",
-      "flow": "audit",
-      "tdd": "lazy",
-      "stress": 1,
-      "loop_threshold": 0.6,
-      "api_enrichment": false,
-      "outcome_detection": false,
-      "_empirical": {
-        "avg_latency_ms": 391,
-        "avg_tps": 5344,
-        "total_tok_out": 13215,
-        "total_cost": 0.007441560000000001,
-        "runs": 8
-      }
-    },
-    "quality": {
-      "tier": "brain",
-      "thinking": "full",
-      "enforcement": "strict",
-      "flow": "normal",
-      "tdd": "strict",
-      "stress": 1,
-      "loop_threshold": 0.4,
-      "api_enrichment": true,
-      "outcome_detection": true,
-      "_empirical": {
-        "avg_latency_ms": 329,
-        "avg_tps": 7564,
-        "total_tok_out": 36892,
-        "total_cost": 0.295821,
-        "runs": 15
-      }
-    },
-    "speed": {
-      "tier": "medium",
-      "thinking": "off",
-      "enforcement": "relaxed",
-      "flow": "audit",
-      "tdd": "lazy",
-      "stress": 1,
-      "loop_threshold": 0.7,
-      "api_enrichment": false,
-      "outcome_detection": false,
-      "_empirical": {
-        "avg_latency_ms": 308,
-        "avg_tps": 6686,
-        "total_tok_out": 29542,
-        "total_cost": 0.029679,
-        "runs": 15
-      }
-    },
-    "longrun": {
-      "tier": "brain",
-      "thinking": "brief",
-      "enforcement": "normal",
-      "flow": "normal",
-      "tdd": "normal",
-      "stress": 1,
-      "loop_threshold": 0.5,
-      "api_enrichment": true,
-      "outcome_detection": true,
-      "_empirical": {
-        "avg_latency_ms": 329,
-        "avg_tps": 7564,
-        "total_tok_out": 36892,
-        "total_cost": 0.295821,
-        "runs": 15
-      }
-    },
-    "forensic": {
-      "tier": "brain",
-      "thinking": "full",
-      "enforcement": "strict",
-      "flow": "strict",
-      "tdd": "strict",
-      "stress": 1.5,
-      "loop_threshold": 0.3,
-      "api_enrichment": true,
-      "outcome_detection": true,
-      "_empirical": {
-        "avg_latency_ms": 329,
-        "avg_tps": 7564,
-        "total_tok_out": 36892,
-        "total_cost": 0.295821,
-        "runs": 15,
-        "context7_urgency": "high",
-        "wbp_verbosity": "verbose",
-        "use_cases": [
-          "debugging",
-          "root cause analysis",
-          "security audit",
-          "bug investigation"
-        ],
-        "loop_protection": "aggressive"
-      }
-    },
-    "web-research": {
-      "tier": "medium",
-      "thinking": "full",
-      "enforcement": "audit",
-      "flow": "audit",
-      "tdd": "lazy",
-      "stress": 1,
-      "loop_threshold": 0.7,
-      "api_enrichment": true,
-      "outcome_detection": true,
-      "_empirical": {
-        "avg_latency_ms": 308,
-        "avg_tps": 6686,
-        "total_tok_out": 29542,
-        "total_cost": 0.029679,
-        "runs": 15,
-        "context7_urgency": "required",
-        "wbp_verbosity": "concise",
-        "use_cases": [
-          "web research",
-          "exploration",
-          "competitive analysis",
-          "documentation lookup"
-        ],
-        "loop_protection": "lenient"
-      }
-    }
-  },
-  "mode_breakdown": {
-    "balanced": {
-      "sessions": 5,
-      "cost": 0,
-      "deleg_savings": 0.11000000000000001,
-      "cache_savings": 0,
-      "warns": 12,
-      "tool_calls": 0,
-      "stress_sum": 0.68,
-      "stress_count": 5,
-      "scratchpad_hits": 0,
-      "total_session_ms": 0,
-      "context7_bypass": 0,
-      "ledger_entries": 0,
-      "task_calls": 0,
-      "task_success": 0,
-      "regime_changes": 0,
-      "cost_per_turn": 0,
-      "savings_ratio": 0,
-      "warn_per_session": 2.4,
-      "stress_avg": 0.14,
-      "cache_hit_rate": 0,
-      "cost_per_success": 0,
-      "thinking_roi": 0,
-      "speed_to_cost": 0,
-      "avg_cost_per_session": 0,
-      "est_prompt_tokens": 0,
-      "est_completion_tokens": 0,
-      "est_total_tokens": 0,
-      "est_tok_per_session": 0
-    },
-    "budget": {
-      "sessions": 0,
-      "cost": 0,
-      "deleg_savings": 0,
-      "cache_savings": 0,
-      "warns": 0,
-      "tool_calls": 0,
-      "stress_sum": 0,
-      "stress_count": 0,
-      "scratchpad_hits": 0,
-      "total_session_ms": 0,
-      "context7_bypass": 0,
-      "ledger_entries": 0,
-      "task_calls": 0,
-      "task_success": 0,
-      "regime_changes": 0,
-      "cost_per_turn": 0,
-      "savings_ratio": 0,
-      "warn_per_session": 0,
-      "stress_avg": 0,
-      "cache_hit_rate": 0,
-      "cost_per_success": 0,
-      "thinking_roi": 0,
-      "speed_to_cost": 0,
-      "avg_cost_per_session": 0,
-      "est_prompt_tokens": 0,
-      "est_completion_tokens": 0,
-      "est_total_tokens": 0,
-      "est_tok_per_session": 0
-    },
-    "quality": {
-      "sessions": 0,
-      "cost": 0,
-      "deleg_savings": 0,
-      "cache_savings": 0,
-      "warns": 0,
-      "tool_calls": 0,
-      "stress_sum": 0,
-      "stress_count": 0,
-      "scratchpad_hits": 0,
-      "total_session_ms": 0,
-      "context7_bypass": 0,
-      "ledger_entries": 0,
-      "task_calls": 0,
-      "task_success": 0,
-      "regime_changes": 0,
-      "cost_per_turn": 0,
-      "savings_ratio": 0,
-      "warn_per_session": 0,
-      "stress_avg": 0,
-      "cache_hit_rate": 0,
-      "cost_per_success": 0,
-      "thinking_roi": 0,
-      "speed_to_cost": 0,
-      "avg_cost_per_session": 0,
-      "est_prompt_tokens": 0,
-      "est_completion_tokens": 0,
-      "est_total_tokens": 0,
-      "est_tok_per_session": 0
-    },
-    "speed": {
-      "sessions": 0,
-      "cost": 0,
-      "deleg_savings": 0,
-      "cache_savings": 0,
-      "warns": 0,
-      "tool_calls": 0,
-      "stress_sum": 0,
-      "stress_count": 0,
-      "scratchpad_hits": 0,
-      "total_session_ms": 0,
-      "context7_bypass": 0,
-      "ledger_entries": 0,
-      "task_calls": 0,
-      "task_success": 0,
-      "regime_changes": 0,
-      "cost_per_turn": 0,
-      "savings_ratio": 0,
-      "warn_per_session": 0,
-      "stress_avg": 0,
-      "cache_hit_rate": 0,
-      "cost_per_success": 0,
-      "thinking_roi": 0,
-      "speed_to_cost": 0,
-      "avg_cost_per_session": 0,
-      "est_prompt_tokens": 0,
-      "est_completion_tokens": 0,
-      "est_total_tokens": 0,
-      "est_tok_per_session": 0
-    },
-    "longrun": {
-      "sessions": 0,
-      "cost": 0,
-      "deleg_savings": 0,
-      "cache_savings": 0,
-      "warns": 0,
-      "tool_calls": 0,
-      "stress_sum": 0,
-      "stress_count": 0,
-      "scratchpad_hits": 0,
-      "total_session_ms": 0,
-      "context7_bypass": 0,
-      "ledger_entries": 0,
-      "task_calls": 0,
-      "task_success": 0,
-      "regime_changes": 0,
-      "cost_per_turn": 0,
-      "savings_ratio": 0,
-      "warn_per_session": 0,
-      "stress_avg": 0,
-      "cache_hit_rate": 0,
-      "cost_per_success": 0,
-      "thinking_roi": 0,
-      "speed_to_cost": 0,
-      "avg_cost_per_session": 0,
-      "est_prompt_tokens": 0,
-      "est_completion_tokens": 0,
-      "est_total_tokens": 0,
-      "est_tok_per_session": 0
-    }
-  },
-  "regime_distribution": {
-    "UNKNOWN": 20
-  },
-  "regime_mode_map": {
-    "UNKNOWN": {
-      "balanced": 20
-    }
-  },
-  "learning_stats": {
-    "exploratory_words": 24,
-    "task_first_words": 122,
-    "ml_graph": "present",
-    "ml_cache": "present",
-    "cross_project_patterns": 58
-  },
-  "calibration_flags": [],
-  "expected_rankings": {
-    "cost_ranking": [
-      "balanced"
-    ],
-    "cost_valid": false,
-    "savings_ranking": [
-      "balanced"
-    ],
-    "warning_ranking": [
-      "balanced"
-    ]
-  },
-  "lifetime": {
-    "total_savings_usd": 0.366,
-    "cache_savings_usd": 0,
-    "missed_context7_usd": 0,
-    "scratchpad_hits": 0,
-    "warn_count": 22,
-    "session_count": 5,
-    "cost_sum": 0
-  },
-  "checklist": {
-    "speed_is_fastest_unverified": false,
-    "budget_is_cheapest_unverified": true,
-    "quality_best_output_unverified": true,
-    "longrun_appropriate_unverified": true,
-    "auto_mode_sensible_unverified": true,
-    "ttft_needs_live_bench": false,
-    "token_throughput_needs_live_bench": true,
-    "first_attempt_success_needs_live_bench": true,
-    "rework_cycles_needs_live_bench": true,
-    "compile_pass_rate_needs_live_bench": true,
-    "user_override_rate_needs_live_bench": true,
-    "balanced_empirically_verified": true,
-    "speed_latency_measured": "308ms avg",
-    "brain_latency_measured": "329ms avg",
-    "cheap_latency_measured": "391ms avg",
-    "tier_parity_confirmed": "brain ~= medium (within 8%)",
-    "forensic_mode_added": true,
-    "web_research_mode_added": true,
-    "calibration_date": "2026-05-23T07:07:08.679Z"
-  },
-  "verification": {
-    "tier_benchmark_completed": true,
-    "total_api_runs": 38,
-    "total_cost": 0.3329415600000001,
-    "human_flow_simulations": [
-      "delete-record-saving@72s",
-      "rename-sync-control@30s",
-      "fix-savings-field@95s"
-    ],
-    "modes_implemented": [
-      "balanced",
-      "budget",
-      "quality",
-      "speed",
-      "longrun",
-      "forensic",
-      "web-research"
-    ],
-    "auto_select_mode_fixed": true,
-    "compute_control_vector_active": true
-  }
-}

package/src/vibeOS-lib/tests/reports/mode-signal-analysis-2026-05-23T06-59-30Z.json

@@ -1,89 +0,0 @@
-{
-  "meta": {
-    "generated_at": "2026-05-23T06:59:30.473Z",
-    "type": "mode-signal-analysis",
-    "version": "1.0"
-  },
-  "mode_projections": [
-    {
-      "mode": "balanced",
-      "tier": "brain",
-      "thinking": "off",
-      "avg_lat_ms": 309,
-      "avg_tps": 8898,
-      "cost_per_run": 0.020487833333333334,
-      "tok_eff": 0.008016629711751664
-    },
-    {
-      "mode": "budget",
-      "tier": "cheap",
-      "thinking": "off",
-      "avg_lat_ms": 330,
-      "avg_tps": 1109,
-      "cost_per_run": 0.00022820000000000002,
-      "tok_eff": 0.000569077306733167
-    },
-    {
-      "mode": "quality",
-      "tier": "brain",
-      "thinking": "full",
-      "avg_lat_ms": 355,
-      "avg_tps": 7817,
-      "cost_per_run": 0.019018499999999997,
-      "tok_eff": 0.008017917369308599
-    },
-    {
-      "mode": "speed",
-      "tier": "medium",
-      "thinking": "off",
-      "avg_lat_ms": 283,
-      "avg_tps": 5442,
-      "cost_per_run": 0.0015545000000000001,
-      "tok_eff": 0.001005498059508409
-    },
-    {
-      "mode": "longrun",
-      "tier": "brain",
-      "thinking": "brief",
-      "avg_lat_ms": 332,
-      "avg_tps": 6040,
-      "cost_per_run": 0.017647833333333335,
-      "tok_eff": 0.008019312329597092
-    }
-  ],
-  "gaps_found": [
-    {
-      "id": "TURBO",
-      "priority": "low",
-      "description": "Cheap + off thinking, already covered by budget"
-    },
-    {
-      "id": "FORENSIC",
-      "priority": "high",
-      "description": "Brain + full thinking + strict flow — no existing mode covers debugging"
-    },
-    {
-      "id": "WEB_RESEARCH",
-      "priority": "high",
-      "description": "Medium + full thinking + context7 — fills exploration gap"
-    },
-    {
-      "id": "CODE_REVIEW",
-      "priority": "medium",
-      "description": "Brain + full thinking + strict TDD — partially covered by quality"
-    }
-  ],
-  "key_insights": [
-    "Brain and medium have nearly identical latency (~320ms avg) — medium is not meaningfully faster",
-    "Medium is 8x cheaper than brain for equivalent throughput",
-    "First cheap request is 2.6x slower than subsequent (cold start: 981ms vs ~370ms)",
-    "All modes except 'balanced' have 0 real sessions in calibration data",
-    "Calibration checklist marks all mode hypotheses as 'unverified'"
-  ],
-  "recommendations": [
-    "Add FORENSIC mode for debugging/sleuthing workflows",
-    "Add WEB_RESEARCH mode for exploration tasks",
-    "Recalibrate auto mode selection since brain=medium in latency",
-    "Run forced mode sessions to populate calibration data for non-balanced modes"
-  ]
-}