Publish provider-free EXP-001 live authorization preflight

PROGRAM_STATUS.md

@@ -43,7 +43,7 @@ Program state totals: active 4; waiting 16; complete 0.
 | 15 | [agent-recovery-policy](https://github.com/opsle/agent-recovery-policy) | concept | `1b733a111e26` | `THEORY` | [none; placeholder source directory only](https://github.com/opsle/agent-recovery-policy/blob/1b733a111e26e0a409fee3b96f627048531daefe/THEORY.md); placeholder only; no automated tests | No shared failure schema, attempt ledger, route evaluator, or comparative fixture set. | After decision evidence and route schemas stabilize, define same-failure convergence on synthetic failures. | `agent-routing-policy`, `agent-state-ledger`, `decision-evidence-protocol` | waiting |
 | 16 | [ephemeral-agent-workers](https://github.com/opsle/ephemeral-agent-workers) | concept | `ad96fcfdfac0` | `THEORY` | [none; placeholder source directory only](https://github.com/opsle/ephemeral-agent-workers/blob/ad96fcfdfac06d340b5e96d369634980cee78ef4/THEORY.md); placeholder only; no automated tests | Portable authority, claim, and handoff contracts are not ready; no safe synthetic containment harness exists. | Wait for prerequisite contracts, then define a fake worker adapter and destruction receipt without infrastructure changes. | `agent-execution-authorization`, `agent-resource-claims`, `verifiable-agent-handoff` | waiting |
 | 17 | [gearbox](https://github.com/opsle/gearbox) | concept | `f3fab9f292cf` | `PROTOTYPED` | [provider-free Python reference core with strict authority-policy admission, exact deterministic argv execution, content-addressed staged helper context, injected one-shot helper transport, passive process waiting, compact results, raw-artifact accounting, fail-closed budgets, and Visible Value receipts](https://github.com/opsle/gearbox/blob/f3fab9f292cf4eabd7200615d444f98881f57d55/src/opsle_gearbox/core.py); 19 of 19 provider-free automated tests passed locally, in PR #1 CI, and in final-main CI; ruff, shellcheck, actionlint, gitleaks, wheel build, receipt validation, and public raw-locator/hash checks passed | A production-quality bounded helper transport, independently verified isolation and termination, full Context Firewall integration, and a frozen comparative benchmark remain missing. | Freeze a provider-free deterministic-versus-direct baseline and helper-transport conformance corpus before considering any live model/provider run. | `context-firewall`, `decision-evidence-protocol`, `agent-trajectory-profiler`, `agent-routing-policy`, `agent-execution-authorization` | waiting |
-| 18 | [research](https://github.com/opsle/research) | program infrastructure | `9ee43197880c` | `PROTOTYPED` | [authoritative 20-repository ledger, machine-readable 17-concept theory registry, canonical theory map, normative Visible Value controls, and provider-free EXP-001 benchmark, launch, and one-block coordinator freezes with six content-addressed tasks, deterministic oracle, four arm contracts, sealed blinded allocation, exact subject configuration and adapter, exact four-authorization admission, private result-envelope templates, exact-revision interoperability, receipts, mutation tests, and integrity CI](program/THEORY_MAP.md); 75 of 75 program-registry, theory-registry, theory-map-hash, generated-status, repository anti-forgetting, EXP-001 freeze/preregistration/coordinator, Gearbox evidence, and Visible Value tests passed locally; PR #13 and exact main CI validated the provider-free coordinator release, and the offline harness replayed all 48 arms | EXP-001 lacks an exact live budgeted authorization set and catalogue/pricing preflight; its one-block coordinator is provider-free qualified, zero model/provider subjects have run, and the program has no canonical measured concept experiment. | Create and provider-free validate one exact four-label LIVE_PROVIDER_RUN authorization set plus a model catalogue/pricing preflight artifact; do not launch a provider/model subject. | — | active |
+| 18 | [research](https://github.com/opsle/research) | program infrastructure | `9ee43197880c` | `PROTOTYPED` | [authoritative 20-repository ledger, machine-readable 17-concept theory registry, canonical theory map, normative Visible Value controls, and provider-free EXP-001 benchmark, launch, one-block coordinator, external four-label LIVE_PROVIDER_RUN authorization, and current catalogue/pricing preflight artifacts with six content-addressed tasks, deterministic oracle, four arm contracts, sealed blinded allocation, exact subject configuration and adapter, exact authorization admission, private boundaries, receipts, mutation tests, and integrity CI](program/THEORY_MAP.md); 88 of 88 repository tests pass on the unreleased provider-free live-preflight branch, including 13 authorization validations and two byte-identical replays; PR #13 and exact main CI remain the released coordinator baseline | The exact live authorization set remains unconsumed and unreleased, account-specific API entitlement is unverified under the zero-provider-call policy, no immutable dated model snapshot is documented, and the program has no canonical measured concept experiment. | Independently review and release the provider-free live-authorization and catalogue/pricing preflight; do not consume authorization or launch a provider/model subject. | — | active |
 | 19 | [site](https://github.com/opsle/site) | program infrastructure | `28ad65be4750` | `PROTOTYPED` | [React/Vinext source implementation with content routes](https://github.com/opsle/site/blob/28ad65be4750dc849976fbf5c9eae9501c6bbb25/README.md); automated build/render tests present; not rerun because this reconciliation kept other repositories read-only | Wait for validated registry data and measured research; deployment requires separate authorization. | After registry merge, add a read-only registry ingestion design without deploying the site. | `research` | waiting |
 | 20 | [.github](https://github.com/opsle/.github) | program infrastructure | `01c38e726db7` | `THEORY` | [documentation-only organization profile](https://github.com/opsle/.github/blob/01c38e726db7c3e45059d25fccce55e071e35938/profile/README.md); not applicable to current single Markdown profile; consistency is unverified | No mechanical registry consistency check exists in this repository. | After registry merge, design a read-only consistency check for organization-profile repository links. | `research` | waiting |
 
@@ -55,11 +55,11 @@ Canonical map: `program/THEORY_MAP.md`. Machine registry: `program/theory-regist
 
 ## Highest-priority workstream
 
-Prepare EXP-001's final non-launch admission boundary: one exact four-label LIVE_PROVIDER_RUN authorization set plus a model catalogue/pricing preflight artifact, validated without launching any provider/model subject.
+Independently review and release the provider-free EXP-001 live-authorization and current catalogue/pricing preflight; do not consume authorization or launch any provider/model subject.
 
 `EXP-001` — **PLANNED** — How much context can an AI coding agent safely not see?
 
-Blockers: No machine-readable four-label budgeted authorization set exists; zero subject/provider runs are authorized or recorded. No distinct dated gpt-5.6-sol snapshot was publicly listed on 2026-08-29, so immutable model weights cannot be claimed and launch requires a catalogue-drift preflight.
+Blockers: The validated live authorization set remains unconsumed; separate execution authority is required before any provider/model subject launch. Account-specific API entitlement remains unverified under the zero-provider-call policy and requires a fresh fail-closed launch-time catalogue check. No distinct dated gpt-5.6-sol snapshot was publicly listed on 2026-08-30, so immutable model weights cannot be claimed.
 
 ## Exact recommended next execution
 

experiments/exp-001/README.md

@@ -64,6 +64,13 @@ commitments. Its committed qualification evidence is in
 Qualification uses non-launchable fixture authorizations and therefore neither
 authorizes nor executes a provider request.
 
+The unreleased provider-free live admission preparation is recorded in
+[`live-preflight-v1/`](live-preflight-v1/). Its public evidence is in
+[`program/evidence/exp-001-live-preflight/`](../../program/evidence/exp-001-live-preflight/).
+The actual exact four-label `LIVE_PROVIDER_RUN` set remains external to Git and
+outside every subject context. It is validated but unconsumed; this preparation
+does not authorize lifecycle advancement or launch a subject.
+
 ## Provider-free verification
 
 The harness fails closed unless the three pinned public Opsle dependencies are

experiments/exp-001/live-preflight-v1/README.md

@@ -0,0 +1,29 @@
+# EXP-001 live authorization and catalogue preflight v1
+
+Status: `PROVIDER_FREE_VALIDATION_ONLY`.
+
+This directory implements the provider-free creation and validation of one
+external four-label `LIVE_PROVIDER_RUN` authorization set and the current model
+catalogue/pricing preflight for the exact preregistered `gpt-5.6-sol`
+configuration.
+
+The live authorization set is intentionally outside Git and outside every
+subject context. The public evidence contains its auditable set ID and content
+identity but not the block ID, subject labels, per-label authorization IDs,
+allocation seed, arm mapping, raw evidence, or result envelopes.
+
+`preflight.py create` is exclusive-create: it refuses an existing destination,
+creates four unique label-bound records, marks every record `UNCONSUMED`, and
+does not expose any provider transport or execution path. `preflight.py qualify`
+validates without mutating the set, reproduces it twice from frozen inputs, and
+executes the required fail-closed negative cases in temporary copies.
+
+The catalogue contains only the exact preregistered candidate. Other providers
+or models are not eligible without a versioned preregistration amendment. Model
+availability and prices come from official OpenAI API documentation; account
+entitlement remains unresolved because this task permits zero provider calls.
+
+This preparation is not an EXP-001 run or result. It consumes no authorization,
+launches no subject, creates no result envelope, advances no lifecycle state,
+and makes no correctness, token, cost, latency, savings, or causal-benefit
+claim.

experiments/exp-001/live-preflight-v1/model-catalogue.json

@@ -0,0 +1,79 @@
+{
+  "protocol_version": "opsle.exp001.model-catalogue/v1",
+  "experiment_id": "EXP-001",
+  "purpose": "Current provider-free catalogue preflight for the exact preregistered EXP-001 live block configuration; this artifact does not authorize or launch any provider/model subject.",
+  "retrieved_at": "2026-08-30T18:49:10Z",
+  "catalogue_scope": "Only the exact preregistered candidate is eligible. Any provider or model substitution requires a versioned preregistration amendment and is outside this catalogue.",
+  "eligible_candidates": [
+    {
+      "provider": "OpenAI API",
+      "provider_id": "openai",
+      "model_id": "gpt-5.6-sol",
+      "model_family": "GPT-5.6",
+      "wire_api": "Responses API",
+      "endpoint": "https://api.openai.com/v1/responses",
+      "availability": "DOCUMENTED_API_MODEL_ACCOUNT_ACCESS_UNVERIFIED",
+      "availability_detail": "The official model page documents gpt-5.6-sol on v1/responses and lists API rate tiers. This provider-free task did not query account-specific entitlement.",
+      "pricing_basis": "USD_PER_1M_TEXT_TOKENS_STANDARD_SHORT_CONTEXT",
+      "input_price_usd": 4.0,
+      "cached_input_price_usd": 0.4,
+      "cache_write_price_usd": 5.0,
+      "output_price_usd": 20.0,
+      "long_context_input_price_usd": 8.0,
+      "long_context_cached_input_price_usd": 0.8,
+      "long_context_cache_write_price_usd": 10.0,
+      "long_context_output_price_usd": 30.0,
+      "long_context_threshold_input_tokens": 272000,
+      "context_window_tokens": 1050000,
+      "max_output_tokens": 128000,
+      "subscription_api_distinction": "Direct API usage pricing; ChatGPT or Codex subscription access is not used and does not authorize this experiment.",
+      "snapshot_id": null,
+      "pricing_status": "AUTHORITATIVELY_DOCUMENTED_FOR_DIRECT_API_STANDARD_TIER",
+      "pricing_promotion": "Official documentation states promotional pricing is available at least through 2026-11-21; a fresh launch-time check remains mandatory.",
+      "sources": [
+        {
+          "publisher": "OpenAI",
+          "title": "GPT-5.6 Sol Model",
+          "url": "https://developers.openai.com/api/docs/models/gpt-5.6-sol",
+          "retrieved_at": "2026-08-30T18:49:10Z",
+          "supports": [
+            "exact model identifier",
+            "model family",
+            "Responses API availability",
+            "context and output limits",
+            "short-context prices",
+            "long-context threshold",
+            "snapshot listing"
+          ]
+        },
+        {
+          "publisher": "OpenAI",
+          "title": "OpenAI API Pricing",
+          "url": "https://developers.openai.com/api/docs/pricing",
+          "retrieved_at": "2026-08-30T18:49:10Z",
+          "supports": [
+            "standard short-context token prices",
+            "standard long-context token prices",
+            "cached-input and cache-write prices",
+            "promotional pricing horizon"
+          ]
+        }
+      ],
+      "uncertainty_or_unavailable_fields": [
+        {
+          "field": "account_specific_api_entitlement",
+          "value": null,
+          "status": "UNRESOLVED_ZERO_PROVIDER_CALL_POLICY"
+        },
+        {
+          "field": "distinct_dated_snapshot_id",
+          "value": null,
+          "status": "UNAVAILABLE_OFFICIAL_PAGE_LISTS_ONLY_PUBLIC_MODEL_ID"
+        }
+      ]
+    }
+  ],
+  "authorization_effect": "NONE",
+  "provider_model_launch_count": 0,
+  "identity": "sha256:334a48850dacf3d9ad5d5c9088287fecc78925e64e10f974cb63575b74592b3c"
+}