From e2d092f1ce91021eb7c49dbc61ddff69296beeac Mon Sep 17 00:00:00 2001 From: Nitsu45 Date: Tue, 20 Oct 2026 20:22:20 +0200 Subject: [PATCH] Record bounded contract v2 regression metrics --- .../bug20-contract-v2-20261020-g00000077.json | 773 ++++++++++++++++++ 1 file changed, 773 insertions(+) create mode 100644 docs/test-results/token-usage/bug20-contract-v2-20261020-g00000077.json diff --git a/docs/test-results/token-usage/bug20-contract-v2-20261020-g00000077.json b/docs/test-results/token-usage/bug20-contract-v2-20261020-g00000077.json new file mode 100644 index 0000000..7a9cefa --- /dev/null +++ b/docs/test-results/token-usage/bug20-contract-v2-20261020-g00000077.json @@ -0,0 +1,773 @@ +{ + "format": "viano-token-usage-report", + "format_version": 1, + "recorded_date": "2026-10-20", + "run": "bug20-contract-v2-20261020", + "code_commit": "3a82a37ee688be35ba636f8659d0ba14fb27351e", + "case_id": "BUG-000020", + "package_id": "trial-contract-v2-BUG-000020-20261020", + "package_generation": 77, + "analysis_revision": 1, + "state": "INVESTIGATING_HYPOTHESES", + "routing": { + "destination": "cases", + "reason": null, + "retry_count": 0, + "retry_not_before": null + }, + "source_manifest_sha256": "5bae0f64a5452493edb67a79aea2f7b938e62ff748535c9fdb1911b8af482fdb", + "configuration_sha256": { + "config\\llm.early-review.local.toml": "ff3296f9a902e4e67861929e584d3629d76edd0d77898c3817ae7f44f50d7ef0", + "config\\project.local.toml": "235016a23be2d8aa7aed7f450fd77792ccbf0fb9b24c05b65d4771782249f5e3", + "config\\investigation.bounded.toml": "b3693a0eab479b67af1049dd0725e8d8e18b30d70eea176fa6c30a7bba723cf9" + }, + "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 + } + ], + "pricing_source": "Same configured USD rates as preceding report; not newly fetched market prices. Snapshot 2026-10-20.", + "account_eur": { + "start": 12.83, + "final": null, + "settlement": "pending" + }, + "scope": "12 dispatches; three startup hypotheses and joint review completed, three normal H1 queries; checkpoint response rejected for missing uncertainties, retry pending. Not a completed analysis.", + "notes": [ + "Output includes reasoning; do not add twice.", + "First regular calls retained in cleaned totals even if rejected. Only second H2 startup is correction overhead so far. No checkpoint correction has executed yet.", + "Missing cached values remain unknown; conservative estimate treats unknown input as uncached, lower bound as cached. Cache storage separate; USD estimate is not EUR billing.", + "Wire counts reconstruct configured stable-cache transport from retained requests, not token estimates.", + "No paid API requests made for evaluation." + ], + "totals_all": { + "call_count": 12, + "usage": { + "input_tokens": { + "known_sum": 87349, + "unknown_call_count": 0 + }, + "output_tokens_including_reasoning": { + "known_sum": 16566, + "unknown_call_count": 0 + }, + "reasoning_tokens": { + "known_sum": 10045, + "unknown_call_count": 2 + }, + "cached_input_tokens": { + "known_sum": 16005, + "unknown_call_count": 4 + } + }, + "api_elapsed_seconds_sum": 143.10700000000003, + "conservative_generation_estimate_usd": 0.11683087499999999, + "generation_lower_bound_usd": 0.073790175, + "estimated_cache_storage_usd": 0.00023658333333333333 + }, + "totals_cleaned": { + "call_count": 11, + "usage": { + "input_tokens": { + "known_sum": 84081, + "unknown_call_count": 0 + }, + "output_tokens_including_reasoning": { + "known_sum": 15834, + "unknown_call_count": 0 + }, + "reasoning_tokens": { + "known_sum": 9425, + "unknown_call_count": 2 + }, + "cached_input_tokens": { + "known_sum": 13970, + "unknown_call_count": 4 + } + }, + "api_elapsed_seconds_sum": 135.82600000000002, + "conservative_generation_estimate_usd": 0.11300849999999998, + "generation_lower_bound_usd": 0.0699678, + "estimated_cache_storage_usd": 0.00023658333333333333 + }, + "totals_correction_overhead": { + "call_count": 1, + "usage": { + "input_tokens": { + "known_sum": 3268, + "unknown_call_count": 0 + }, + "output_tokens_including_reasoning": { + "known_sum": 732, + "unknown_call_count": 0 + }, + "reasoning_tokens": { + "known_sum": 620, + "unknown_call_count": 0 + }, + "cached_input_tokens": { + "known_sum": 2035, + "unknown_call_count": 0 + } + }, + "api_elapsed_seconds_sum": 7.281, + "conservative_generation_estimate_usd": 0.003822375, + "generation_lower_bound_usd": 0.003822375, + "estimated_cache_storage_usd": 0 + }, + "phases": { + "entity_resolution_plan_v4": { + "all": { + "call_count": 1, + "usage": { + "input_tokens": { + "known_sum": 21008, + "unknown_call_count": 0 + }, + "output_tokens_including_reasoning": { + "known_sum": 194, + "unknown_call_count": 0 + }, + "reasoning_tokens": { + "known_sum": 0, + "unknown_call_count": 1 + }, + "cached_input_tokens": { + "known_sum": 0, + "unknown_call_count": 1 + } + }, + "api_elapsed_seconds_sum": 3.703, + "conservative_generation_estimate_usd": 0.0164835, + "generation_lower_bound_usd": 0.0023030999999999998, + "estimated_cache_storage_usd": 0 + }, + "cleaned": { + "call_count": 1, + "usage": { + "input_tokens": { + "known_sum": 21008, + "unknown_call_count": 0 + }, + "output_tokens_including_reasoning": { + "known_sum": 194, + "unknown_call_count": 0 + }, + "reasoning_tokens": { + "known_sum": 0, + "unknown_call_count": 1 + }, + "cached_input_tokens": { + "known_sum": 0, + "unknown_call_count": 1 + } + }, + "api_elapsed_seconds_sum": 3.703, + "conservative_generation_estimate_usd": 0.0164835, + "generation_lower_bound_usd": 0.0023030999999999998, + "estimated_cache_storage_usd": 0 + } + }, + "entity_resolution_assessment_v4": { + "all": { + "call_count": 1, + "usage": { + "input_tokens": { + "known_sum": 25795, + "unknown_call_count": 0 + }, + "output_tokens_including_reasoning": { + "known_sum": 526, + "unknown_call_count": 0 + }, + "reasoning_tokens": { + "known_sum": 0, + "unknown_call_count": 1 + }, + "cached_input_tokens": { + "known_sum": 0, + "unknown_call_count": 1 + } + }, + "api_elapsed_seconds_sum": 6.782, + "conservative_generation_estimate_usd": 0.02131875, + "generation_lower_bound_usd": 0.003907125, + "estimated_cache_storage_usd": 0 + }, + "cleaned": { + "call_count": 1, + "usage": { + "input_tokens": { + "known_sum": 25795, + "unknown_call_count": 0 + }, + "output_tokens_including_reasoning": { + "known_sum": 526, + "unknown_call_count": 0 + }, + "reasoning_tokens": { + "known_sum": 0, + "unknown_call_count": 1 + }, + "cached_input_tokens": { + "known_sum": 0, + "unknown_call_count": 1 + } + }, + "api_elapsed_seconds_sum": 6.782, + "conservative_generation_estimate_usd": 0.02131875, + "generation_lower_bound_usd": 0.003907125, + "estimated_cache_storage_usd": 0 + } + }, + "case_plan_v2": { + "all": { + "call_count": 1, + "usage": { + "input_tokens": { + "known_sum": 13944, + "unknown_call_count": 0 + }, + "output_tokens_including_reasoning": { + "known_sum": 6216, + "unknown_call_count": 0 + }, + "reasoning_tokens": { + "known_sum": 2300, + "unknown_call_count": 0 + }, + "cached_input_tokens": { + "known_sum": 0, + "unknown_call_count": 1 + } + }, + "api_elapsed_seconds_sum": 42.015, + "conservative_generation_estimate_usd": 0.033768, + "generation_lower_bound_usd": 0.0243558, + "estimated_cache_storage_usd": 0 + }, + "cleaned": { + "call_count": 1, + "usage": { + "input_tokens": { + "known_sum": 13944, + "unknown_call_count": 0 + }, + "output_tokens_including_reasoning": { + "known_sum": 6216, + "unknown_call_count": 0 + }, + "reasoning_tokens": { + "known_sum": 2300, + "unknown_call_count": 0 + }, + "cached_input_tokens": { + "known_sum": 0, + "unknown_call_count": 1 + } + }, + "api_elapsed_seconds_sum": 42.015, + "conservative_generation_estimate_usd": 0.033768, + "generation_lower_bound_usd": 0.0243558, + "estimated_cache_storage_usd": 0 + } + }, + "investigation_startup_v1": { + "all": { + "call_count": 4, + "usage": { + "input_tokens": { + "known_sum": 12388, + "unknown_call_count": 0 + }, + "output_tokens_including_reasoning": { + "known_sum": 2477, + "unknown_call_count": 0 + }, + "reasoning_tokens": { + "known_sum": 2117, + "unknown_call_count": 0 + }, + "cached_input_tokens": { + "known_sum": 8140, + "unknown_call_count": 0 + } + }, + "api_elapsed_seconds_sum": 26.139, + "conservative_generation_estimate_usd": 0.01308525, + "generation_lower_bound_usd": 0.01308525, + "estimated_cache_storage_usd": 8.479166666666666e-05 + }, + "cleaned": { + "call_count": 3, + "usage": { + "input_tokens": { + "known_sum": 9120, + "unknown_call_count": 0 + }, + "output_tokens_including_reasoning": { + "known_sum": 1745, + "unknown_call_count": 0 + }, + "reasoning_tokens": { + "known_sum": 1497, + "unknown_call_count": 0 + }, + "cached_input_tokens": { + "known_sum": 6105, + "unknown_call_count": 0 + } + }, + "api_elapsed_seconds_sum": 18.858, + "conservative_generation_estimate_usd": 0.009262875, + "generation_lower_bound_usd": 0.009262875, + "estimated_cache_storage_usd": 8.479166666666666e-05 + } + }, + "investigation_startup_review_v1": { + "all": { + "call_count": 1, + "usage": { + "input_tokens": { + "known_sum": 3017, + "unknown_call_count": 0 + }, + "output_tokens_including_reasoning": { + "known_sum": 2650, + "unknown_call_count": 0 + }, + "reasoning_tokens": { + "known_sum": 1985, + "unknown_call_count": 0 + }, + "cached_input_tokens": { + "known_sum": 0, + "unknown_call_count": 1 + } + }, + "api_elapsed_seconds_sum": 22.219, + "conservative_generation_estimate_usd": 0.01220025, + "generation_lower_bound_usd": 0.010163775, + "estimated_cache_storage_usd": 0 + }, + "cleaned": { + "call_count": 1, + "usage": { + "input_tokens": { + "known_sum": 3017, + "unknown_call_count": 0 + }, + "output_tokens_including_reasoning": { + "known_sum": 2650, + "unknown_call_count": 0 + }, + "reasoning_tokens": { + "known_sum": 1985, + "unknown_call_count": 0 + }, + "cached_input_tokens": { + "known_sum": 0, + "unknown_call_count": 1 + } + }, + "api_elapsed_seconds_sum": 22.219, + "conservative_generation_estimate_usd": 0.01220025, + "generation_lower_bound_usd": 0.010163775, + "estimated_cache_storage_usd": 0 + } + }, + "investigation_project_v20": { + "all": { + "call_count": 4, + "usage": { + "input_tokens": { + "known_sum": 11197, + "unknown_call_count": 0 + }, + "output_tokens_including_reasoning": { + "known_sum": 4503, + "unknown_call_count": 0 + }, + "reasoning_tokens": { + "known_sum": 3643, + "unknown_call_count": 0 + }, + "cached_input_tokens": { + "known_sum": 7865, + "unknown_call_count": 0 + } + }, + "api_elapsed_seconds_sum": 42.248999999999995, + "conservative_generation_estimate_usd": 0.019975125, + "generation_lower_bound_usd": 0.019975125, + "estimated_cache_storage_usd": 0.00015179166666666667 + }, + "cleaned": { + "call_count": 4, + "usage": { + "input_tokens": { + "known_sum": 11197, + "unknown_call_count": 0 + }, + "output_tokens_including_reasoning": { + "known_sum": 4503, + "unknown_call_count": 0 + }, + "reasoning_tokens": { + "known_sum": 3643, + "unknown_call_count": 0 + }, + "cached_input_tokens": { + "known_sum": 7865, + "unknown_call_count": 0 + } + }, + "api_elapsed_seconds_sum": 42.248999999999995, + "conservative_generation_estimate_usd": 0.019975125, + "generation_lower_bound_usd": 0.019975125, + "estimated_cache_storage_usd": 0.00015179166666666667 + } + } + }, + "calls": [ + { + "ref": "llm/operations/6c0a36f93bea41b87241a30769bd92bb6dc387869b46d3a013ec595cfc7e9548/round-0001.json", + "prompt_version": "entity_resolution_plan_v4", + "task": "entity_resolution_plan", + "hypothesis": null, + "model": "gemini-3.8-flash", + "config_hash": "249a08e844d8a62c6b202c0bf856d2fa67f9c77f7a1f03174e79f874bf24ac69", + "request_sha256": "993e4d9865e4e44ce59f3d6753713cac5fb009c217a14827b9a935c24be9a280", + "correction": false, + "gateway_status": "SUCCESS", + "controller_rejection": null, + "code": null, + "input_tokens": 21008, + "output_tokens_including_reasoning": 194, + "reasoning_tokens": null, + "cached_input_tokens": null, + "cache_status": "below_minimum", + "api_elapsed_seconds": 3.703, + "logical_wire_characters": null, + "estimated_generation_usd_conservative": 0.0164835, + "estimated_generation_usd_lower_bound": 0.0023030999999999998, + "estimated_cache_storage_usd": 0.0, + "normalization_rules": [] + }, + { + "ref": "llm/operations/88adb8b462df2c473b421f617b086dd65351532f28e81a7a1052e1f24da87dea/round-0001.json", + "prompt_version": "entity_resolution_assessment_v4", + "task": "entity_resolution_assessment", + "hypothesis": null, + "model": "gemini-3.8-flash", + "config_hash": "249a08e844d8a62c6b202c0bf856d2fa67f9c77f7a1f03174e79f874bf24ac69", + "request_sha256": "dc7bcd2f719f6b0c0e104e21868d74809c4aaaad9fc43a40b92b03d886e1706c", + "correction": false, + "gateway_status": "SUCCESS", + "controller_rejection": null, + "code": null, + "input_tokens": 25795, + "output_tokens_including_reasoning": 526, + "reasoning_tokens": null, + "cached_input_tokens": null, + "cache_status": "below_minimum", + "api_elapsed_seconds": 6.782, + "logical_wire_characters": null, + "estimated_generation_usd_conservative": 0.02131875, + "estimated_generation_usd_lower_bound": 0.003907125, + "estimated_cache_storage_usd": 0.0, + "normalization_rules": [] + }, + { + "ref": "llm/operations/572afccbd4034d9c5485045cb4bb28b61fdd40e48dc8a3fab67cfc17e997cd65/round-0001.json", + "prompt_version": "case_plan_v2", + "task": "interpret_and_propose", + "hypothesis": null, + "model": "gemini-3.8-flash", + "config_hash": "249a08e844d8a62c6b202c0bf856d2fa67f9c77f7a1f03174e79f874bf24ac69", + "request_sha256": "90d3e9354a928239039bc3cb3b4c0aad9e21a03c7e30e2c9fac37db66f25327f", + "correction": false, + "gateway_status": "SUCCESS", + "controller_rejection": null, + "code": null, + "input_tokens": 13944, + "output_tokens_including_reasoning": 6216, + "reasoning_tokens": 2300, + "cached_input_tokens": null, + "cache_status": "below_minimum", + "api_elapsed_seconds": 42.015, + "logical_wire_characters": null, + "estimated_generation_usd_conservative": 0.033768, + "estimated_generation_usd_lower_bound": 0.0243558, + "estimated_cache_storage_usd": 0.0, + "normalization_rules": [] + }, + { + "ref": "llm/operations/ca6cdff81de3cbae0492c26802daa287b11bf4fabefad477a9b64f1b6db30112/round-0001.json", + "prompt_version": "investigation_startup_v1", + "task": "startup_choose_query", + "hypothesis": "H1", + "model": "gemini-3.8-flash", + "config_hash": "249a08e844d8a62c6b202c0bf856d2fa67f9c77f7a1f03174e79f874bf24ac69", + "request_sha256": "4430ab1441295f8310c7f4d7f3db6679d1428d3ae2d659b12a88ee40d798f018", + "correction": false, + "gateway_status": "SUCCESS", + "controller_rejection": null, + "code": null, + "input_tokens": 2309, + "output_tokens_including_reasoning": 254, + "reasoning_tokens": 178, + "cached_input_tokens": 2035, + "cache_status": "created", + "api_elapsed_seconds": 5.109, + "logical_wire_characters": 8501, + "estimated_generation_usd_conservative": 0.001310625, + "estimated_generation_usd_lower_bound": 0.001310625, + "estimated_cache_storage_usd": 8.479166666666666e-05, + "normalization_rules": [] + }, + { + "ref": "llm/operations/54ef9b495e10fe49a2ffad5909c89efdbfe7ef7645b601865d12e5223b0651bc/round-0001.json", + "prompt_version": "investigation_startup_v1", + "task": "startup_choose_query", + "hypothesis": "H2", + "model": "gemini-3.8-flash", + "config_hash": "249a08e844d8a62c6b202c0bf856d2fa67f9c77f7a1f03174e79f874bf24ac69", + "request_sha256": "cbbefac0dbbeddacba3f779db8566e7b46f94014938cdab32c7d199fa17908c5", + "correction": false, + "gateway_status": "SUCCESS", + "controller_rejection": "PROJECT_DATABASE_COLUMN_UNKNOWN", + "code": null, + "input_tokens": 3255, + "output_tokens_including_reasoning": 890, + "reasoning_tokens": 779, + "cached_input_tokens": 2035, + "cache_status": "reused", + "api_elapsed_seconds": 7.234, + "logical_wire_characters": 11638, + "estimated_generation_usd_conservative": 0.004405125, + "estimated_generation_usd_lower_bound": 0.004405125, + "estimated_cache_storage_usd": 0.0, + "normalization_rules": [] + }, + { + "ref": "llm/operations/9d66012b57395476a4f69c72ffd0b6725da911ede849fc652d48568b73d28480/round-0001.json", + "prompt_version": "investigation_startup_v1", + "task": "startup_choose_query", + "hypothesis": "H2", + "model": "gemini-3.8-flash", + "config_hash": "249a08e844d8a62c6b202c0bf856d2fa67f9c77f7a1f03174e79f874bf24ac69", + "request_sha256": "9999501f1cb30251053a33f9c1938361c27ff980458c5bb94f993e43bfd8a97f", + "correction": true, + "gateway_status": "SUCCESS", + "controller_rejection": null, + "code": null, + "input_tokens": 3268, + "output_tokens_including_reasoning": 732, + "reasoning_tokens": 620, + "cached_input_tokens": 2035, + "cache_status": "reused", + "api_elapsed_seconds": 7.281, + "logical_wire_characters": 11693, + "estimated_generation_usd_conservative": 0.003822375, + "estimated_generation_usd_lower_bound": 0.003822375, + "estimated_cache_storage_usd": 0.0, + "normalization_rules": [] + }, + { + "ref": "llm/operations/71fd77c20b2af9bb2d842927c7a39cc8e1cf3e15541f387a26054fdb1047b6e4/round-0001.json", + "prompt_version": "investigation_startup_v1", + "task": "startup_choose_query", + "hypothesis": "H3", + "model": "gemini-3.8-flash", + "config_hash": "249a08e844d8a62c6b202c0bf856d2fa67f9c77f7a1f03174e79f874bf24ac69", + "request_sha256": "6b950849ec02eccfaaf16daa464a17454104532e38b6a4e77c343585f189adbf", + "correction": false, + "gateway_status": "SUCCESS", + "controller_rejection": null, + "code": null, + "input_tokens": 3556, + "output_tokens_including_reasoning": 601, + "reasoning_tokens": 540, + "cached_input_tokens": 2035, + "cache_status": "reused", + "api_elapsed_seconds": 6.515, + "logical_wire_characters": 12605, + "estimated_generation_usd_conservative": 0.003547125, + "estimated_generation_usd_lower_bound": 0.003547125, + "estimated_cache_storage_usd": 0.0, + "normalization_rules": [] + }, + { + "ref": "llm/operations/0270771b422d04af95c20c38558476ded170af96569985af436406482d8d043a/round-0001.json", + "prompt_version": "investigation_startup_review_v1", + "task": "review_initial_hypotheses", + "hypothesis": null, + "model": "gemini-3.8-flash", + "config_hash": "249a08e844d8a62c6b202c0bf856d2fa67f9c77f7a1f03174e79f874bf24ac69", + "request_sha256": "f6aba1d7fb8441d8e92b02164d2d3be522f756f43869b8ca8a9b83a37ce51a8d", + "correction": false, + "gateway_status": "SUCCESS", + "controller_rejection": null, + "code": null, + "input_tokens": 3017, + "output_tokens_including_reasoning": 2650, + "reasoning_tokens": 1985, + "cached_input_tokens": null, + "cache_status": "fallback", + "api_elapsed_seconds": 22.219, + "logical_wire_characters": 11012, + "estimated_generation_usd_conservative": 0.01220025, + "estimated_generation_usd_lower_bound": 0.010163775, + "estimated_cache_storage_usd": null, + "normalization_rules": [] + }, + { + "ref": "llm/operations/c619a7901de5674f54e8371759fba596a7746f67d62499b198780813912e5c31/round-0001.json", + "prompt_version": "investigation_project_v20", + "task": "investigate_one_step", + "hypothesis": "H1", + "model": "gemini-3.8-flash", + "config_hash": "249a08e844d8a62c6b202c0bf856d2fa67f9c77f7a1f03174e79f874bf24ac69", + "request_sha256": "8aab768fb27cb68e9c5cd8a90a2851fd6495b9bd1f7413bb0bb0be32269551a9", + "correction": false, + "gateway_status": "SUCCESS", + "controller_rejection": null, + "code": null, + "input_tokens": 2609, + "output_tokens_including_reasoning": 345, + "reasoning_tokens": 249, + "cached_input_tokens": 2111, + "cache_status": "created", + "api_elapsed_seconds": 6.781, + "logical_wire_characters": 9430, + "estimated_generation_usd_conservative": 0.001825575, + "estimated_generation_usd_lower_bound": 0.001825575, + "estimated_cache_storage_usd": 8.795833333333333e-05, + "normalization_rules": [] + }, + { + "ref": "llm/operations/b5de43dfa1122fa86decfa538047ee813621839eded8ed15356d341f3439e383/round-0001.json", + "prompt_version": "investigation_project_v20", + "task": "investigate_one_step", + "hypothesis": "H1", + "model": "gemini-3.8-flash", + "config_hash": "249a08e844d8a62c6b202c0bf856d2fa67f9c77f7a1f03174e79f874bf24ac69", + "request_sha256": "06f2bf0af9139e07d42f73f658b1c027ff450ee15dd67c38bc80158216323492", + "correction": false, + "gateway_status": "SUCCESS", + "controller_rejection": null, + "code": null, + "input_tokens": 2938, + "output_tokens_including_reasoning": 414, + "reasoning_tokens": 212, + "cached_input_tokens": 2111, + "cache_status": "reused", + "api_elapsed_seconds": 4.812, + "logical_wire_characters": 10486, + "estimated_generation_usd_conservative": 0.0023310749999999997, + "estimated_generation_usd_lower_bound": 0.0023310749999999997, + "estimated_cache_storage_usd": 0.0, + "normalization_rules": [] + }, + { + "ref": "llm/operations/6849c974442865e5ca3e8f146ef4520c275f2e37a25fb7caa498f17089ed6dc1/round-0001.json", + "prompt_version": "investigation_project_v20", + "task": "investigate_one_step", + "hypothesis": "H1", + "model": "gemini-3.8-flash", + "config_hash": "249a08e844d8a62c6b202c0bf856d2fa67f9c77f7a1f03174e79f874bf24ac69", + "request_sha256": "409b8272bc913ebb496e5bcf36cb029f119dfb6e0f593690884f4a11afe834c2", + "correction": false, + "gateway_status": "SUCCESS", + "controller_rejection": null, + "code": null, + "input_tokens": 3059, + "output_tokens_including_reasoning": 518, + "reasoning_tokens": 350, + "cached_input_tokens": 2111, + "cache_status": "reused", + "api_elapsed_seconds": 6.781, + "logical_wire_characters": 10814, + "estimated_generation_usd_conservative": 0.002811825, + "estimated_generation_usd_lower_bound": 0.002811825, + "estimated_cache_storage_usd": 0.0, + "normalization_rules": [] + }, + { + "ref": "llm/operations/475d5f458554c35131f24fc92fb2e762c69a8d9c6d4ab9d6426fbd72e6303af3/round-0001.json", + "prompt_version": "investigation_project_v20", + "task": "consolidate_investigation_session", + "hypothesis": "H1", + "model": "gemini-3.8-flash", + "config_hash": "249a08e844d8a62c6b202c0bf856d2fa67f9c77f7a1f03174e79f874bf24ac69", + "request_sha256": "bccdc72074422d53720daee19dbe30d7b0b547defa38274bfa5a10fb301972ea", + "correction": false, + "gateway_status": "ERROR", + "controller_rejection": "LLM_OUTPUT_SCHEMA", + "code": "LLM_OUTPUT_SCHEMA", + "input_tokens": 2591, + "output_tokens_including_reasoning": 3226, + "reasoning_tokens": 2832, + "cached_input_tokens": 1532, + "cache_status": "created", + "api_elapsed_seconds": 23.875, + "logical_wire_characters": 9156, + "estimated_generation_usd_conservative": 0.01300665, + "estimated_generation_usd_lower_bound": 0.01300665, + "estimated_cache_storage_usd": 6.383333333333333e-05, + "normalization_rules": [] + } + ], + "startup_done": true, + "hypotheses": { + "H1": { + "confidence": "strongly_supported", + "iterations": 5, + "invalid_responses": 1, + "disposition": "active" + }, + "H2": { + "confidence": "weakened", + "iterations": 1, + "invalid_responses": 0, + "disposition": "active" + }, + "H3": { + "confidence": "weakened", + "iterations": 1, + "invalid_responses": 0, + "disposition": "active" + } + }, + "package_valid": true, + "trial_process_elapsed_seconds": 248.332418, + "trial_process_elapsed_scope": "Telemetry process start to stop; excludes previous local import/preparation. Includes local processing.", + "assessment": { + "last_rejection": { + "code": "LLM_OUTPUT_SCHEMA", + "task": "consolidate_investigation_session", + "validation_path": "/", + "missing_required_fields": [ + "uncertainties" + ], + "retry_executed": false + }, + "startup_correction": { + "hypothesis": "H2", + "code": "PROJECT_DATABASE_COLUMN_UNKNOWN", + "unknown_column": "InhabitType", + "recovery": "Next LLM query removed the unknown column; valid query executed." + }, + "known_redundancy": "H1 repeats the creature_template name search already performed in H2 startup.", + "deterministic_choice_unwrap_exercised": false, + "entity_reference_catalog_exercised_by_source_context_query": false, + "caution": "No source.context query emitted; catalog presence alone is not a live proof of correct N reference usage. No deterministic choice-wrapper recovery observed." + } +}