@ictechgy/context-guard 0.4.9 → 0.4.11

package/docs/benchmark-fixtures/token-savings-12task.tasks.example.json

@@ -0,0 +1,182 @@
+[
+  {
+    "id": "token_savings_01_bugfix",
+    "prompt": "Fixture-only synthetic token-savings roadmap task (bugfix). Fix a null-check regression in a sanitized request parser while preserving exact stack-frame evidence. This validates benchmark shape only; real claims require provider-measured tokens/costs for matched successful tasks, failure-rate guardrail, human corrections, and shifted-cost accounting.",
+    "model": "sonnet",
+    "effort": "medium",
+    "max_turns": 3,
+    "max_budget_usd": 1.0,
+    "allowed_tools": [],
+    "success_command": "python3 -c \"raise SystemExit('fixture-only placeholder: replace success_command before real benchmark runs')\"",
+    "success_cwd": ".",
+    "variant_prompt_files": {
+      "baseline_full_context_fixture": "token-savings-12task-baseline.prompt.example.md",
+      "fixture_only_contextguard_advisory_foundations": "token-savings-12task-contextguard.prompt.example.md"
+    }
+  },
+  {
+    "id": "token_savings_02_exploration",
+    "prompt": "Fixture-only synthetic token-savings roadmap task (exploration). Explore a small sanitized repository and identify the next file to inspect without loading unrelated logs. This validates benchmark shape only; real claims require provider-measured tokens/costs for matched successful tasks, failure-rate guardrail, human corrections, and shifted-cost accounting.",
+    "model": "sonnet",
+    "effort": "medium",
+    "max_turns": 3,
+    "max_budget_usd": 1.0,
+    "allowed_tools": [],
+    "success_command": "python3 -c \"raise SystemExit('fixture-only placeholder: replace success_command before real benchmark runs')\"",
+    "success_cwd": ".",
+    "variant_prompt_files": {
+      "baseline_full_context_fixture": "token-savings-12task-baseline.prompt.example.md",
+      "fixture_only_contextguard_advisory_foundations": "token-savings-12task-contextguard.prompt.example.md"
+    }
+  },
+  {
+    "id": "token_savings_03_code_review",
+    "prompt": "Fixture-only synthetic token-savings roadmap task (code_review). Review a focused diff and identify one correctness risk plus one test gap. This validates benchmark shape only; real claims require provider-measured tokens/costs for matched successful tasks, failure-rate guardrail, human corrections, and shifted-cost accounting.",
+    "model": "sonnet",
+    "effort": "medium",
+    "max_turns": 3,
+    "max_budget_usd": 1.0,
+    "allowed_tools": [],
+    "success_command": "python3 -c \"raise SystemExit('fixture-only placeholder: replace success_command before real benchmark runs')\"",
+    "success_cwd": ".",
+    "variant_prompt_files": {
+      "baseline_full_context_fixture": "token-savings-12task-baseline.prompt.example.md",
+      "fixture_only_contextguard_advisory_foundations": "token-savings-12task-contextguard.prompt.example.md"
+    }
+  },
+  {
+    "id": "token_savings_04_long_log_analysis",
+    "prompt": "Fixture-only synthetic token-savings roadmap task (long_log_analysis). Analyze a long sanitized CI log and cite the failing command, preserving artifact receipt fallback. This validates benchmark shape only; real claims require provider-measured tokens/costs for matched successful tasks, failure-rate guardrail, human corrections, and shifted-cost accounting.",
+    "model": "sonnet",
+    "effort": "medium",
+    "max_turns": 3,
+    "max_budget_usd": 1.0,
+    "allowed_tools": [],
+    "success_command": "python3 -c \"raise SystemExit('fixture-only placeholder: replace success_command before real benchmark runs')\"",
+    "success_cwd": ".",
+    "variant_prompt_files": {
+      "baseline_full_context_fixture": "token-savings-12task-baseline.prompt.example.md",
+      "fixture_only_contextguard_advisory_foundations": "token-savings-12task-contextguard.prompt.example.md"
+    }
+  },
+  {
+    "id": "token_savings_05_migration",
+    "prompt": "Fixture-only synthetic token-savings roadmap task (migration). Plan a safe migration of a deprecated CLI flag to a new option while keeping backwards compatibility. This validates benchmark shape only; real claims require provider-measured tokens/costs for matched successful tasks, failure-rate guardrail, human corrections, and shifted-cost accounting.",
+    "model": "sonnet",
+    "effort": "medium",
+    "max_turns": 3,
+    "max_budget_usd": 1.0,
+    "allowed_tools": [],
+    "success_command": "python3 -c \"raise SystemExit('fixture-only placeholder: replace success_command before real benchmark runs')\"",
+    "success_cwd": ".",
+    "variant_prompt_files": {
+      "baseline_full_context_fixture": "token-savings-12task-baseline.prompt.example.md",
+      "fixture_only_contextguard_advisory_foundations": "token-savings-12task-contextguard.prompt.example.md"
+    }
+  },
+  {
+    "id": "token_savings_06_docs",
+    "prompt": "Fixture-only synthetic token-savings roadmap task (docs). Update user-facing docs to clarify provider-measured matched successful task requirements. This validates benchmark shape only; real claims require provider-measured tokens/costs for matched successful tasks, failure-rate guardrail, human corrections, and shifted-cost accounting.",
+    "model": "sonnet",
+    "effort": "medium",
+    "max_turns": 3,
+    "max_budget_usd": 1.0,
+    "allowed_tools": [],
+    "success_command": "python3 -c \"raise SystemExit('fixture-only placeholder: replace success_command before real benchmark runs')\"",
+    "success_cwd": ".",
+    "variant_prompt_files": {
+      "baseline_full_context_fixture": "token-savings-12task-baseline.prompt.example.md",
+      "fixture_only_contextguard_advisory_foundations": "token-savings-12task-contextguard.prompt.example.md"
+    }
+  },
+  {
+    "id": "token_savings_07_refactor",
+    "prompt": "Fixture-only synthetic token-savings roadmap task (refactor). Refactor duplicated helper parsing into a shared function without changing public output schema. This validates benchmark shape only; real claims require provider-measured tokens/costs for matched successful tasks, failure-rate guardrail, human corrections, and shifted-cost accounting.",
+    "model": "sonnet",
+    "effort": "medium",
+    "max_turns": 3,
+    "max_budget_usd": 1.0,
+    "allowed_tools": [],
+    "success_command": "python3 -c \"raise SystemExit('fixture-only placeholder: replace success_command before real benchmark runs')\"",
+    "success_cwd": ".",
+    "variant_prompt_files": {
+      "baseline_full_context_fixture": "token-savings-12task-baseline.prompt.example.md",
+      "fixture_only_contextguard_advisory_foundations": "token-savings-12task-contextguard.prompt.example.md"
+    }
+  },
+  {
+    "id": "token_savings_08_performance",
+    "prompt": "Fixture-only synthetic token-savings roadmap task (performance). Find a deterministic hot path in a local-only helper and propose a bounded optimization. This validates benchmark shape only; real claims require provider-measured tokens/costs for matched successful tasks, failure-rate guardrail, human corrections, and shifted-cost accounting.",
+    "model": "sonnet",
+    "effort": "medium",
+    "max_turns": 3,
+    "max_budget_usd": 1.0,
+    "allowed_tools": [],
+    "success_command": "python3 -c \"raise SystemExit('fixture-only placeholder: replace success_command before real benchmark runs')\"",
+    "success_cwd": ".",
+    "variant_prompt_files": {
+      "baseline_full_context_fixture": "token-savings-12task-baseline.prompt.example.md",
+      "fixture_only_contextguard_advisory_foundations": "token-savings-12task-contextguard.prompt.example.md"
+    }
+  },
+  {
+    "id": "token_savings_09_telemetry",
+    "prompt": "Fixture-only synthetic token-savings roadmap task (telemetry). Add claim-safe telemetry fields for shifted local work without hosted cost-savings claims. This validates benchmark shape only; real claims require provider-measured tokens/costs for matched successful tasks, failure-rate guardrail, human corrections, and shifted-cost accounting.",
+    "model": "sonnet",
+    "effort": "medium",
+    "max_turns": 3,
+    "max_budget_usd": 1.0,
+    "allowed_tools": [],
+    "success_command": "python3 -c \"raise SystemExit('fixture-only placeholder: replace success_command before real benchmark runs')\"",
+    "success_cwd": ".",
+    "variant_prompt_files": {
+      "baseline_full_context_fixture": "token-savings-12task-baseline.prompt.example.md",
+      "fixture_only_contextguard_advisory_foundations": "token-savings-12task-contextguard.prompt.example.md"
+    }
+  },
+  {
+    "id": "token_savings_10_cache_layout",
+    "prompt": "Fixture-only synthetic token-savings roadmap task (cache_layout). Inspect a prompt layout and identify stable prefix versus dynamic suffix placement. This validates benchmark shape only; real claims require provider-measured tokens/costs for matched successful tasks, failure-rate guardrail, human corrections, and shifted-cost accounting.",
+    "model": "sonnet",
+    "effort": "medium",
+    "max_turns": 3,
+    "max_budget_usd": 1.0,
+    "allowed_tools": [],
+    "success_command": "python3 -c \"raise SystemExit('fixture-only placeholder: replace success_command before real benchmark runs')\"",
+    "success_cwd": ".",
+    "variant_prompt_files": {
+      "baseline_full_context_fixture": "token-savings-12task-baseline.prompt.example.md",
+      "fixture_only_contextguard_advisory_foundations": "token-savings-12task-contextguard.prompt.example.md"
+    }
+  },
+  {
+    "id": "token_savings_11_tool_schema",
+    "prompt": "Fixture-only synthetic token-savings roadmap task (tool_schema). Select a small core tool set from a sanitized MCP catalog and defer the rest by receipt. This validates benchmark shape only; real claims require provider-measured tokens/costs for matched successful tasks, failure-rate guardrail, human corrections, and shifted-cost accounting.",
+    "model": "sonnet",
+    "effort": "medium",
+    "max_turns": 3,
+    "max_budget_usd": 1.0,
+    "allowed_tools": [],
+    "success_command": "python3 -c \"raise SystemExit('fixture-only placeholder: replace success_command before real benchmark runs')\"",
+    "success_cwd": ".",
+    "variant_prompt_files": {
+      "baseline_full_context_fixture": "token-savings-12task-baseline.prompt.example.md",
+      "fixture_only_contextguard_advisory_foundations": "token-savings-12task-contextguard.prompt.example.md"
+    }
+  },
+  {
+    "id": "token_savings_12_artifact_receipt",
+    "prompt": "Fixture-only synthetic token-savings roadmap task (artifact_receipt). Verify that a digest plus receipt can re-expand omitted sanitized output exactly when needed. This validates benchmark shape only; real claims require provider-measured tokens/costs for matched successful tasks, failure-rate guardrail, human corrections, and shifted-cost accounting.",
+    "model": "sonnet",
+    "effort": "medium",
+    "max_turns": 3,
+    "max_budget_usd": 1.0,
+    "allowed_tools": [],
+    "success_command": "python3 -c \"raise SystemExit('fixture-only placeholder: replace success_command before real benchmark runs')\"",
+    "success_cwd": ".",
+    "variant_prompt_files": {
+      "baseline_full_context_fixture": "token-savings-12task-baseline.prompt.example.md",
+      "fixture_only_contextguard_advisory_foundations": "token-savings-12task-contextguard.prompt.example.md"
+    }
+  }
+]

package/docs/benchmark-fixtures/token-savings-12task.variants.example.json

@@ -0,0 +1,10 @@
+[
+  {
+    "name": "baseline_full_context_fixture",
+    "extra_args": []
+  },
+  {
+    "name": "fixture_only_contextguard_advisory_foundations",
+    "extra_args": []
+  }
+]

package/docs/benchmark-workflow-examples.md

@@ -26,6 +26,7 @@ Use them to decide what evidence a workflow has and what it does **not** prove:
 3. Treat `comparisons[].quality_gate != "pass"` as a warning to inspect failures, correction burden, and unmatched tasks before discussing savings.
 4. Keep byte-proxy, provider-cache, wall-time, and shifted-cost evidence in separate language from provider-measured token/cost claims. Provider-cache telemetry is not independent savings proof.
 5. Keep self-hosted local/model-server latency, memory, and quality metrics in the run-evidence ledger sidecar; do not fold them into hosted API token/cost savings claims unless provider-measured matched-task evidence separately supports that claim.
+6. For deterministic local replay, add `--evidence-jsonl ... --dashboard-md ...`. Synthetic/manual replay evidence regenerates CSV/report/dashboard artifacts, but the report is marked `replay_only_not_public_claim` or `unknown_mixed_csv` unless every report row has complete provider-export provenance. Public hosted savings claims must additionally have `public_claim_readiness.claim_allowed=true`, which requires matched successful tasks, provider-measured token/cost, quality non-inferiority, shifted-cost accounting, explicit confidence/failure notes, and complete provider-export provenance.
 
 ## Safe wording
 
@@ -42,3 +43,5 @@ The `.example.json` fixtures intentionally use full `context-guard-bench-report-
 The self-hosted metrics example is a JSONL run-evidence sidecar, not a full report shape. Its fields are additive ledger evidence only: `latency_ms`, `peak_memory_mb`, and normalized `quality_score` describe local/model-server behavior and leave hosted API report calculations unchanged. Use `context-guard experiments plan self-hosted-metrics-ledger --json ...` only as a dry-run ledger-preview checker for explicit metrics; it does not write the benchmark ledger.
 
 For task/variant starter fixtures rather than full report-shape examples, see [`experimental-benchmark-fixtures.md`](experimental-benchmark-fixtures.md). Those files are fixture-only and synthetic dry-run-only starters until users replace the placeholder prompts and success checks; they are not shipped OCR, visual-token, learned-compression, or output-transform benchmark results, and real claims still require provider-measured matched successful tasks plus failure-rate, correction, and shifted-cost guardrails.
+
+The token-savings 12-task starter also includes [`benchmark-fixtures/token-savings-12task.evidence.example.jsonl`](benchmark-fixtures/token-savings-12task.evidence.example.jsonl) for `context-guard-bench --evidence-jsonl` replay. That file is synthetic local replay evidence, not provider-measured savings proof; use it to validate dashboards and claim-boundary handling before collecting real provider exports.

package/docs/benchmark-workflows/context-pack-byte-proxy.example.json

@@ -1,169 +1,310 @@
 {
-  "schema": "context-guard-bench-report-v1",
   "baseline_variant": "baseline",
+  "caveat": "Proxy byte reductions are reported separately from matched-task token/cost metrics; shifted cost savings require measured primary cost and measured external cost when external tokens are present. Wall time and provider cached-token fields are diagnostic telemetry, not proof of ContextGuard-caused token or cost savings; provider-cache discounts must stay separate from token-reduction claims. Public hosted savings claims must use public_claim_readiness.claim_allowed; unsupported claims are forbidden.",
+  "claim_status": "insufficient_paired_data",
+  "comparisons": [
+    {
+      "baseline_corrections_per_successful_task": 0.0,
+      "baseline_failure_rate": 0.0,
+      "baseline_successful_task_count": 1,
+      "baseline_variant": "baseline",
+      "corrections_delta_per_successful_task": 0.0,
+      "cost_savings_pct_with_shift": null,
+      "failure_rate_delta_pp": 0.0,
+      "matched_successful_task_count": 1,
+      "missing_baseline_success_tasks": [],
+      "paired_corrections_task_count": 1,
+      "paired_cost_task_count": 0,
+      "paired_token_task_count": 0,
+      "paired_wall_time_task_count": 1,
+      "quality_gate": "pass",
+      "token_savings_pct": null,
+      "variant": "context_pack_auto",
+      "variant_corrections_per_successful_task": 0.0,
+      "variant_failure_rate": 0.0,
+      "wall_time_change_pct": -8.333333333333332,
+      "wall_time_delta_seconds_per_successful_task": -1.0
+    }
+  ],
+  "public_claim_readiness": {
+    "blocking_gate_ids": [
+      "matched_successful_tasks",
+      "provider_measured_token_cost",
+      "shifted_cost_accounting",
+      "confidence_failure_notes",
+      "provider_export_provenance"
+    ],
+    "claim_allowed": false,
+    "claim_boundary": {
+      "claim_allowed_field": "public_claim_readiness.claim_allowed",
+      "fixed_percent_savings_claim_without_matched_provider_report_forbidden": true,
+      "hosted_api_cost_savings_claim_without_claim_allowed_forbidden": true,
+      "hosted_api_token_savings_claim_without_claim_allowed_forbidden": true,
+      "id": "public_claim_readiness_authoritative_release_gate",
+      "reason": "Public hosted token/cost savings claims are forbidden unless every readiness gate passes and public_claim_readiness.claim_allowed is true.",
+      "reporting_only": true,
+      "requires_confidence_and_failure_notes": true,
+      "requires_matched_successful_tasks": true,
+      "requires_provider_export_provenance": true,
+      "requires_provider_measured_tokens_and_cost": true,
+      "requires_quality_non_inferiority": true,
+      "requires_shifted_cost_accounting": true,
+      "unsupported_claims_forbidden": true
+    },
+    "gates": [
+      {
+        "evidence": {
+          "comparison_count": 1,
+          "matched_pair_count": 0,
+          "min_matched_successful_task_count": 1.0,
+          "missing_baseline_success_task_count": 0,
+          "variants": [
+            "context_pack_auto"
+          ]
+        },
+        "id": "matched_successful_tasks",
+        "label": "Matched successful tasks",
+        "passed": false,
+        "reason": "missing_or_regressed_matched_successful_tasks",
+        "required": true,
+        "status": "fail"
+      },
+      {
+        "evidence": {
+          "matched_pair_count": 0,
+          "required_fields": [
+            "matched_pair_evidence[*].measurements.baseline.primary_tokens.measured",
+            "matched_pair_evidence[*].measurements.variant.primary_tokens.measured",
+            "matched_pair_evidence[*].measurements.baseline.primary_cost_usd.measured",
+            "matched_pair_evidence[*].measurements.variant.primary_cost_usd.measured"
+          ]
+        },
+        "id": "provider_measured_token_cost",
+        "label": "Provider-measured token and primary cost",
+        "passed": false,
+        "reason": "missing_provider_measured_primary_tokens_or_cost",
+        "required": true,
+        "status": "fail"
+      },
+      {
+        "evidence": {
+          "max_corrections_delta_per_successful_task": 0.0,
+          "max_failure_rate_delta_pp": 0.0,
+          "quality_gates": [
+            "pass"
+          ]
+        },
+        "id": "quality_non_inferiority",
+        "label": "Quality non-inferiority",
+        "passed": true,
+        "reason": "all_quality_gates_pass",
+        "required": true,
+        "status": "pass"
+      },
+      {
+        "evidence": {
+          "matched_pair_count": 0,
+          "required_fields": [
+            "matched_pair_evidence[*].claim_boundary.shifted_cost_claim_allowed",
+            "matched_pair_evidence[*].measurements.baseline.total_cost_with_shift_usd.measured",
+            "matched_pair_evidence[*].measurements.variant.total_cost_with_shift_usd.measured"
+          ]
+        },
+        "id": "shifted_cost_accounting",
+        "label": "Shifted-cost accounting",
+        "passed": false,
+        "reason": "missing_shifted_cost_claim_accounting",
+        "required": true,
+        "status": "fail"
+      },
+      {
+        "evidence": {
+          "comparison_failure_fields_present": true,
+          "explicit_note_count": 0,
+          "failed_row_count": 0,
+          "failed_rows_with_notes": 0,
+          "replay_row_count": 0
+        },
+        "id": "confidence_failure_notes",
+        "label": "Confidence and failure notes",
+        "passed": false,
+        "reason": "missing_explicit_replay_notes_or_failure_evidence",
+        "required": true,
+        "status": "unknown"
+      },
+      {
+        "evidence": {
+          "mixed_csv": false,
+          "provider_names": [],
+          "replay_row_count": 0,
+          "report_row_count": 2,
+          "same_run_complete": false,
+          "source_types": []
+        },
+        "id": "provider_export_provenance",
+        "label": "Provider-export provenance",
+        "passed": false,
+        "reason": "missing_or_mixed_provider_export_provenance",
+        "required": true,
+        "status": "unknown"
+      }
+    ],
+    "generated_from": "matched_pair_evidence_and_replay_provenance",
+    "passed_required_gate_count": 1,
+    "public_claim_eligible_observed": null,
+    "public_claim_status_observed": "csv_provenance_unknown_requires_original_evidence_or_trusted_ledger",
+    "raw_metric_claim_status_observed": "insufficient_paired_data",
+    "reason": "replay_evidence_required_for_public_claim",
+    "required_gate_count": 6,
+    "required_gate_ids": [
+      "matched_successful_tasks",
+      "provider_measured_token_cost",
+      "quality_non_inferiority",
+      "shifted_cost_accounting",
+      "confidence_failure_notes",
+      "provider_export_provenance"
+    ],
+    "schema_version": "contextguard.bench.public-claim-readiness.v1",
+    "status": "csv_provenance_unknown_requires_original_evidence_or_trusted_ledger"
+  },
   "row_count": 2,
+  "schema": "context-guard-bench-report-v1",
   "summary_by_variant": {
     "baseline": {
-      "runs": 1,
-      "successful_runs": 1,
+      "artifacts_used_per_successful_task": 0.0,
+      "artifacts_used_successful": 0,
+      "byte_reduction_ratio": 1.0,
+      "byte_savings_pct": 0.0,
+      "bytes_after_successful": 24000,
+      "bytes_before_successful": 24000,
+      "bytes_saved_per_successful_task": 0.0,
+      "bytes_saved_successful": 0,
+      "compression_strategy": "baseline",
+      "corrections_per_successful_task": 0.0,
+      "corrections_successful": 0,
+      "external_cost_successful_usd": 0.0,
+      "external_cost_unknown_successful": 1,
+      "external_tokens_measured_successful": 0,
+      "external_tokens_per_successful_task": null,
+      "external_tokens_successful": 0,
       "failed_runs": 0,
-      "total_tokens_all_runs": 0,
-      "primary_tokens_measured_runs": 0,
+      "failure_rate": 0.0,
+      "hook_triggers_successful": 0,
+      "is_baseline_strategy": true,
+      "observed_telemetry": {
+        "byte_savings": "observed",
+        "external_tokens": "unavailable",
+        "primary_cost": "unavailable",
+        "provider_cache": "unavailable",
+        "token_proxy": "inferred",
+        "tokens": "unavailable",
+        "wall_time": "observed"
+      },
       "primary_cost_all_runs_usd": 0.0,
       "primary_cost_measured_runs": 0,
-      "wall_time_seconds_all_runs": 12.0,
-      "wall_time_seconds_measured_runs": 1,
+      "primary_cost_measured_successful": 0,
+      "primary_cost_per_successful_task_usd": null,
+      "primary_cost_per_task_including_failures_usd": null,
+      "primary_cost_successful_usd": 0.0,
+      "primary_tokens_measured_runs": 0,
+      "primary_tokens_measured_successful": 0,
       "provider_cached_tokens_all_runs": 0,
       "provider_cached_tokens_measured_runs": 0,
+      "provider_cached_tokens_measured_successful": 0,
+      "provider_cached_tokens_per_successful_task": 0.0,
+      "provider_cached_tokens_per_task_including_failures": 0.0,
+      "provider_cached_tokens_successful": 0,
+      "runs": 1,
+      "successful_runs": 1,
+      "successful_task_count": 1,
+      "task_count": 1,
+      "token_proxy_saved_per_successful_task": 0.0,
+      "token_proxy_saved_successful": 0,
+      "tokens_per_successful_task": null,
+      "tokens_per_task_including_failures": null,
       "total_cost_with_shift_all_runs_usd": 0.0,
       "total_cost_with_shift_measured_runs": 0,
+      "total_cost_with_shift_measured_successful": 0,
+      "total_cost_with_shift_per_successful_task_usd": null,
+      "total_cost_with_shift_per_task_including_failures_usd": null,
+      "total_cost_with_shift_successful_usd": 0.0,
+      "total_tokens_all_runs": 0,
       "total_tokens_successful": 0,
-      "primary_tokens_measured_successful": 0,
-      "primary_cost_successful_usd": 0.0,
-      "primary_cost_measured_successful": 0,
-      "wall_time_seconds_successful": 12.0,
+      "turns_successful": 0,
+      "wall_time_seconds_all_runs": 12.0,
+      "wall_time_seconds_measured_runs": 1,
       "wall_time_seconds_measured_successful": 1,
-      "provider_cached_tokens_successful": 0,
-      "provider_cached_tokens_measured_successful": 0,
+      "wall_time_seconds_per_successful_task": 12.0,
+      "wall_time_seconds_per_task_including_failures": 12.0,
+      "wall_time_seconds_successful": 12.0
+    },
+    "context_pack_auto": {
+      "artifacts_used_per_successful_task": 0.0,
+      "artifacts_used_successful": 0,
+      "byte_reduction_ratio": 0.25,
+      "byte_savings_pct": 75.0,
+      "bytes_after_successful": 6000,
+      "bytes_before_successful": 24000,
+      "bytes_saved_per_successful_task": 18000.0,
+      "bytes_saved_successful": 18000,
+      "compression_strategy": "context_pack_auto",
+      "corrections_per_successful_task": 0.0,
+      "corrections_successful": 0,
       "external_cost_successful_usd": 0.0,
       "external_cost_unknown_successful": 1,
-      "total_cost_with_shift_successful_usd": 0.0,
-      "total_cost_with_shift_measured_successful": 0,
-      "external_tokens_successful": 0,
       "external_tokens_measured_successful": 0,
-      "artifacts_used_successful": 0,
-      "corrections_successful": 0,
-      "bytes_before_successful": 24000,
-      "bytes_after_successful": 24000,
-      "turns_successful": 0,
-      "hook_triggers_successful": 0,
-      "failure_rate": 0.0,
-      "task_count": 1,
-      "successful_task_count": 1,
-      "tokens_per_task_including_failures": null,
-      "wall_time_seconds_per_task_including_failures": 12.0,
-      "provider_cached_tokens_per_task_including_failures": 0.0,
-      "primary_cost_per_task_including_failures_usd": null,
-      "total_cost_with_shift_per_task_including_failures_usd": null,
-      "tokens_per_successful_task": null,
-      "wall_time_seconds_per_successful_task": 12.0,
-      "provider_cached_tokens_per_successful_task": 0.0,
-      "primary_cost_per_successful_task_usd": null,
-      "total_cost_with_shift_per_successful_task_usd": null,
       "external_tokens_per_successful_task": null,
-      "artifacts_used_per_successful_task": 0.0,
-      "corrections_per_successful_task": 0.0,
-      "byte_reduction_ratio": 1.0,
-      "compression_strategy": "baseline",
-      "is_baseline_strategy": true,
-      "bytes_saved_successful": 0,
-      "bytes_saved_per_successful_task": 0.0,
-      "byte_savings_pct": 0.0,
-      "token_proxy_saved_successful": 0,
-      "token_proxy_saved_per_successful_task": 0.0,
+      "external_tokens_successful": 0,
+      "failed_runs": 0,
+      "failure_rate": 0.0,
+      "hook_triggers_successful": 0,
+      "is_baseline_strategy": false,
       "observed_telemetry": {
-        "tokens": "unavailable",
-        "primary_cost": "unavailable",
-        "external_tokens": "unavailable",
         "byte_savings": "observed",
+        "external_tokens": "unavailable",
+        "primary_cost": "unavailable",
+        "provider_cache": "unavailable",
         "token_proxy": "inferred",
-        "wall_time": "observed",
-        "provider_cache": "unavailable"
-      }
-    },
-    "context_pack_auto": {
-      "runs": 1,
-      "successful_runs": 1,
-      "failed_runs": 0,
-      "total_tokens_all_runs": 0,
-      "primary_tokens_measured_runs": 0,
+        "tokens": "unavailable",
+        "wall_time": "observed"
+      },
       "primary_cost_all_runs_usd": 0.0,
       "primary_cost_measured_runs": 0,
-      "wall_time_seconds_all_runs": 11.0,
-      "wall_time_seconds_measured_runs": 1,
+      "primary_cost_measured_successful": 0,
+      "primary_cost_per_successful_task_usd": null,
+      "primary_cost_per_task_including_failures_usd": null,
+      "primary_cost_successful_usd": 0.0,
+      "primary_tokens_measured_runs": 0,
+      "primary_tokens_measured_successful": 0,
       "provider_cached_tokens_all_runs": 0,
       "provider_cached_tokens_measured_runs": 0,
-      "total_cost_with_shift_all_runs_usd": 0.0,
-      "total_cost_with_shift_measured_runs": 0,
-      "total_tokens_successful": 0,
-      "primary_tokens_measured_successful": 0,
-      "primary_cost_successful_usd": 0.0,
-      "primary_cost_measured_successful": 0,
-      "wall_time_seconds_successful": 11.0,
-      "wall_time_seconds_measured_successful": 1,
-      "provider_cached_tokens_successful": 0,
       "provider_cached_tokens_measured_successful": 0,
-      "external_cost_successful_usd": 0.0,
-      "external_cost_unknown_successful": 1,
-      "total_cost_with_shift_successful_usd": 0.0,
-      "total_cost_with_shift_measured_successful": 0,
-      "external_tokens_successful": 0,
-      "external_tokens_measured_successful": 0,
-      "artifacts_used_successful": 0,
-      "corrections_successful": 0,
-      "bytes_before_successful": 24000,
-      "bytes_after_successful": 6000,
-      "turns_successful": 0,
-      "hook_triggers_successful": 0,
-      "failure_rate": 0.0,
-      "task_count": 1,
+      "provider_cached_tokens_per_successful_task": 0.0,
+      "provider_cached_tokens_per_task_including_failures": 0.0,
+      "provider_cached_tokens_successful": 0,
+      "runs": 1,
+      "successful_runs": 1,
       "successful_task_count": 1,
+      "task_count": 1,
+      "token_proxy_saved_per_successful_task": 4500.0,
+      "token_proxy_saved_successful": 4500,
+      "tokens_per_successful_task": null,
       "tokens_per_task_including_failures": null,
-      "wall_time_seconds_per_task_including_failures": 11.0,
-      "provider_cached_tokens_per_task_including_failures": 0.0,
-      "primary_cost_per_task_including_failures_usd": null,
+      "total_cost_with_shift_all_runs_usd": 0.0,
+      "total_cost_with_shift_measured_runs": 0,
+      "total_cost_with_shift_measured_successful": 0,
+      "total_cost_with_shift_per_successful_task_usd": null,
       "total_cost_with_shift_per_task_including_failures_usd": null,
-      "tokens_per_successful_task": null,
+      "total_cost_with_shift_successful_usd": 0.0,
+      "total_tokens_all_runs": 0,
+      "total_tokens_successful": 0,
+      "turns_successful": 0,
+      "wall_time_seconds_all_runs": 11.0,
+      "wall_time_seconds_measured_runs": 1,
+      "wall_time_seconds_measured_successful": 1,
       "wall_time_seconds_per_successful_task": 11.0,
-      "provider_cached_tokens_per_successful_task": 0.0,
-      "primary_cost_per_successful_task_usd": null,
-      "total_cost_with_shift_per_successful_task_usd": null,
-      "external_tokens_per_successful_task": null,
-      "artifacts_used_per_successful_task": 0.0,
-      "corrections_per_successful_task": 0.0,
-      "byte_reduction_ratio": 0.25,
-      "compression_strategy": "context_pack_auto",
-      "is_baseline_strategy": false,
-      "bytes_saved_successful": 18000,
-      "bytes_saved_per_successful_task": 18000.0,
-      "byte_savings_pct": 75.0,
-      "token_proxy_saved_successful": 4500,
-      "token_proxy_saved_per_successful_task": 4500.0,
-      "observed_telemetry": {
-        "tokens": "unavailable",
-        "primary_cost": "unavailable",
-        "external_tokens": "unavailable",
-        "byte_savings": "observed",
-        "token_proxy": "inferred",
-        "wall_time": "observed",
-        "provider_cache": "unavailable"
-      }
-    }
-  },
-  "comparisons": [
-    {
-      "variant": "context_pack_auto",
-      "baseline_variant": "baseline",
-      "quality_gate": "pass",
-      "baseline_failure_rate": 0.0,
-      "variant_failure_rate": 0.0,
-      "failure_rate_delta_pp": 0.0,
-      "matched_successful_task_count": 1,
-      "baseline_successful_task_count": 1,
-      "missing_baseline_success_tasks": [],
-      "baseline_corrections_per_successful_task": 0.0,
-      "variant_corrections_per_successful_task": 0.0,
-      "paired_corrections_task_count": 1,
-      "corrections_delta_per_successful_task": 0.0,
-      "token_savings_pct": null,
-      "paired_token_task_count": 0,
-      "wall_time_delta_seconds_per_successful_task": -1.0,
-      "wall_time_change_pct": -8.333333333333332,
-      "paired_wall_time_task_count": 1,
-      "cost_savings_pct_with_shift": null,
-      "paired_cost_task_count": 0
+      "wall_time_seconds_per_task_including_failures": 11.0,
+      "wall_time_seconds_successful": 11.0
     }
-  ],
-  "claim_status": "insufficient_paired_data",
-  "caveat": "Proxy byte reductions are reported separately from matched-task token/cost metrics; shifted cost savings require measured primary cost and measured external cost when external tokens are present. Wall time and provider cached-token fields are diagnostic telemetry, not proof of ContextGuard-caused token or cost savings; provider-cache discounts must stay separate from token-reduction claims."
+  }
 }