Prepare full bounded Bug17 evaluation and preserve cost baselines

2026-10-20 20:57:58 +02:00
1 parent 86a02cb8c0
commit a3e1ea0429
@@ -0,0 +1,45 @@
+{
+  "format": "viano-trial-preparation",
+  "run": "bug17-bounded-full-20261020",
+  "date": "2026-10-20",
+  "code_commit": "86a02cb8c0d48690f31748ed831a2c297a902604",
+  "case_id": "BUG-000017",
+  "package_id": "trial-bounded-full-BUG-000017-20261020",
+  "account_eur_start": 13.01,
+  "billing_note": "Prior Bug20 settlement possibly still subject to a few delayed cents.",
+  "purpose": "Full run against already-fixed Bug17 input; assess unsupported-cause handling, bounded prompt stability, regular and corrected cost. Not a test of recovering the original pre-fix implementation defect.",
+  "dispatch_safety_limit": 1000,
+  "budget_and_iteration_limits_unchanged": true,
+  "inputs": [
+    {
+      "file": "BUG-000017-20261015-213913.tar.gz",
+      "sha256": "6fc61e0c54d18eb0673827aa69284f48807b80928c7d68643d2b920584cbcfde"
+    },
+    {
+      "file": "WOWSRC-BUG-000017-20261015-213934.tar.gz",
+      "sha256": "a189ef80672658466d30812fb095f88ab932870cdadc40d97665b73d31029561"
+    }
+  ],
+  "configuration_sha256": {
+    "config\\llm.early-review.local.toml": "ff3296f9a902e4e67861929e584d3629d76edd0d77898c3817ae7f44f50d7ef0",
+    "config\\project.local.toml": "235016a23be2d8aa7aed7f450fd77792ccbf0fb9b24c05b65d4771782249f5e3",
+    "config\\investigation.bounded.toml": "b3693a0eab479b67af1049dd0725e8d8e18b30d70eea176fa6c30a7bba723cf9"
+  },
+  "storage": {
+    "limit_bytes": 20000000000,
+    "measured_bytes": 2395792187,
+    "roots": {
+      "service-data\\trials": 48069916,
+      "service-data\\benchmarks": 498385,
+      "service-data\\test-archive": 1740768879,
+      "service-data\\inspection": 134752609,
+      "tests\\fixtures\\llm_rejections": 2268510,
+      "C:\\Users\\User\\AppData\\Local\\Temp\\pytest-of-User": 469433888
+    },
+    "archived_workspace_bytes_removed": 18296667356,
+    "final_results_and_descriptions_retained_under": "service-data/test-archive/",
+    "warning": "Reserve is finite; unusually large research payloads may still require storage observation during long execution."
+  },
+  "paid_api_calls_by_agent": 0,
+  "state": "VALIDATED"
+}
@@ -0,0 +1,14 @@
+{
+  "format": "viano-test-cost-update",
+  "recorded_date": "2026-10-20",
+  "run": "bug20-contract-v2-20261020",
+  "package_generation": 122,
+  "account_eur": {
+    "start": 12.83,
+    "intermediate": 12.93,
+    "latest_reported": 13.01,
+    "difference": 0.18,
+    "settlement": "updated_user_report; small further delayed charges not excluded"
+  },
+  "token_report": "bug20-contract-v2-20261020-g00000122.json"
+}
@@ -0,0 +1,58 @@
+{
+  "format": "viano-cost-projection",
+  "recorded_date": "2026-10-20",
+  "source_report": "bug20-contract-v2-20261020-g00000122.json",
+  "currency": "USD",
+  "pricing_snapshot": [
+    {
+      "id": "gemini-native",
+      "model": "gemini-3.8-flash",
+      "cost_currency": "USD",
+      "input_cost_per_million": 0.75,
+      "cached_input_cost_per_million": 0.075,
+      "output_cost_per_million": 3.75,
+      "cache_storage_cost_per_million_hour": 0.5
+    }
+  ],
+  "account_eur_settlement": "pending; no exchange-rate conversion assumed",
+  "assumptions": {
+    "hypotheses": 3,
+    "units_per_hypothesis": 100,
+    "cheapest_action_cost": 10,
+    "max_refund_fraction": 0.8,
+    "net_cost_after_full_refund": 2,
+    "maximum_actions_each": 46,
+    "total_research_actions": 138,
+    "startup_research_actions": 3,
+    "following_research_actions": 135,
+    "thin_call_average_usd": 0.0033548249999999996,
+    "consolidation_call_average_usd_excluding_retry": 0.007716150000000001,
+    "baseline_including_successful_handoff_usd": 0.14092312499999998,
+    "normal_observed_tool_queries": 5,
+    "normal_observed_thin_calls_including_recall_and_checkpoint_requests": 8,
+    "accepted_consolidations": 3
+  },
+  "scenarios": [
+    {
+      "name": "138 thin calls plus checkpoint overhead at three per eight following thin calls",
+      "following_thin_calls": 135,
+      "consolidations": 51,
+      "estimate_usd": 0.9873481500000001
+    },
+    {
+      "name": "Full research-action count with observed recall/checkpoint-request/consolidation overhead per five normal queries",
+      "following_thin_calls": 216,
+      "consolidations": 81,
+      "estimate_usd": 1.4905734750000001
+    }
+  ],
+  "limitations": [
+    "Small successful-case sample, not measured failed full-budget run.",
+    "No correction overhead included in scenarios. First regular rejected outputs remain in empirical averages where applicable.",
+    "Cache storage and variable corrections additional; late cache expiry/recreation can change costs.",
+    "Prices remain configured snapshot, not newly researched provider prices.",
+    "50 iterations per hypothesis may end actual run before 46 research actions when extra consolidation/recall iterations intervene. This is a cost scenario, not an executable guarantee of 138 actions.",
+    "Successful change-request generation retained in baseline as conservative allowance; failed run may omit it.",
+    "No fixed worst-case financial bound: reasoning intensity and failures may differ."
+  ]
+}