From 07369cc801c165ce8046024f80697706ebb7bd68 Mon Sep 17 00:00:00 2001 From: Dotta Date: Tue, 29 Sep 2026 15:58:36 -0500 Subject: [PATCH] docs: record host recovery and authenticated ACP qualification Retain failed attempts, new local and Daytona passes, current runtime identities, and remaining production gates. Co-Authored-By: Paperclip --- doc/architecture/runner-pi-capabilities.md | 16 +- .../runner-rich-acp-capabilities.md | 86 ++++-- ...ner-rich-acp-qualification-2026-09-29.json | 256 +++++++++++++++++- ...runner-rich-acp-validation-2026-09-29.json | 41 ++- 4 files changed, 361 insertions(+), 38 deletions(-) diff --git a/doc/architecture/runner-pi-capabilities.md b/doc/architecture/runner-pi-capabilities.md index a208e06a208..56d83aef11e 100644 --- a/doc/architecture/runner-pi-capabilities.md +++ b/doc/architecture/runner-pi-capabilities.md @@ -22,7 +22,15 @@ v7 has paid Product hello passes on local source `807feaecf` and Daytona source The [qualification checkpoint](runner-rich-acp-qualification-2026-09-29.json) retains exact profile, runtime, image and billing identities. Remaining Product journeys, native interactions and platform coverage are still unqualified; the -prepared `bd4cc29c3` local campaign has not launched. The canonical +`bd4cc29c3` local campaign passed hello and stopped at native questions: all +15 behavioral checks passed, but the required API evidence snapshot was absent. +The failed result is retained and the six later cells did not launch. A committed +harness-only fix captures the complete final API evidence; its paid retry passed +all 15 native-question checks. The following question-continuation case reached +Done but failed the exact final-message assertion: earlier pre-tool narration +was aggregated into the final item. Three runs settled across these two cells, +all owned processes exited, and five later cells did not launch. The native +message attribution defect remains open. The canonical [v7 declaration](../../packages/paperclip-runner/test-fixtures/pi-acp/profile-v7-identity.json) binds the exact wrapper, helper, extension and three target closures. @@ -611,8 +619,10 @@ same pinned PostgreSQL binary: `semget(..., 17, 03600)` fails with `No space lef on device` when only 16 semaphores are free. It exits in 0.557 seconds, removes its temporary directory, leaves no child process, and leaves IPC totals unchanged. The original Product bootstrap stderr remains unavailable. No unrelated database -or IPC object was changed. Further paid -qualification is held until a supported database resource path is available. +or IPC object was changed during that diagnosis. The later user-approved +fixed-snapshot host cleanup removed 4,892 stale semaphore sets and skipped 11 +whose recorded creator PID was present. Startup and graceful shutdown now pass; +the current checkpoint above supersedes this historical qualification hold. The [sanitized attempt ledger](../../packages/paperclip-runner/test-fixtures/pi-acp/paid-qualification-progress.darwin-arm64.json) diff --git a/doc/architecture/runner-rich-acp-capabilities.md b/doc/architecture/runner-rich-acp-capabilities.md index a5d9a6ed21d..05fead7b9dc 100644 --- a/doc/architecture/runner-rich-acp-capabilities.md +++ b/doc/architecture/runner-rich-acp-capabilities.md @@ -17,13 +17,15 @@ bound MCP names to provider-safe aliases, and rejects malformed native UI requests explicitly. Its four native question forms use an owned tool. Credential-free tests cover the new policy boundaries, real pinned native -processes, clean runtime builds and Product E2E assertions. Pi v7 has passed its -paid local hello case. Copilot v4 has passed local hello, question continuation, -plan approval and controller-restart recovery on the integrated `bd4cc29c3` -runtime; file-edit qualification failed during session startup. Pi's corrected Daytona hello also passed. Its first Daytona attempt created and -retired one sandbox but failed before inference because the launcher omitted the -build-owned remote artifact paths. Remaining -authenticated cases, platform coverage and Daytona Product E2E are still required. +processes, clean runtime builds and Product E2E assertions. On integrated source +`bd4cc29c3`, Cursor v4 has passed local hello, and Copilot v4 has passed all five +basic local journeys: hello, semantic questions, semantic plans, controller +restart and file edit/validation. Pi v7 has passed local hello on `807feaecf` and +Daytona hello on `bd4cc29c3`. Copilot also passed Daytona hello. Pi’s repaired +native-question evidence case passed 15/15; the following continuation case +exposed final-message aggregation of earlier narration. +These passes retain earlier failures and do not qualify native interactions, +all required platforms or the remaining remote journeys. The [harness priorities report](https://pages.paperclip.ing/2026-09-25-harness-priorities/) recommends Cursor and Copilot, followed by Pi, using the existing qualified ACPX @@ -46,10 +48,10 @@ candidate scorecards from historical runtime policies. | Current candidate | Latest observed result | Remaining work | | --- | --- | --- | -| Cursor v4, source `2e0b0fec0` | All three closures verify. Native instruction acknowledgement is enforced on new/load and automatic reload. Bounded todo projection preserves all IDs/statuses and marks shortened details. Exact-head Apex reports 5/5 | Authenticated current-profile Product tests, remaining platform and Daytona proof; paid tests await the account spend-limit decision | -| Copilot v4, source `2042ca14c` | Fresh/load model-request capture proves native instructions reach the executable. Lifetime ownership prevents instruction-write races. Native session notices preserve bounded fields without inventing originating-turn attribution. Exact-head Apex reports 5/5 | The continuation fix is paid-tested on `bd4cc29c3`: hello, semantic question/answer, plan approval and controller restart passed (six matchers each). File editing failed during `session.open`; diagnose before retrying. Remote and remaining platform qualification are open | -| Pi v7, sources `807feaecf` and `bd4cc29c3` | Local hello on `807feaecf` and Daytona hello on `bd4cc29c3` each passed all six matchers with one provider run, zero retries and complete owned cleanup. Delayed local billing was $0.000646464; remote model plus sandbox analytics stabilized at $0.0053185282. Apex reports 5/5 on the reviewed provider head | The eight-case local `bd4cc29c3` campaign remains held at the host database blocker. Remaining remote, native-interaction and platform cases plus final-source checks are required. Historical receipts retain their original retry policies; new supervisors explicitly enforce zero retries | -| All three, Linux/Daytona | The immutable `bd4cc29c3` image and actual server artifact admission pass. Pi hello attempt 02 passed all six matchers, followed by complete owned cleanup and stable delayed billing; failed attempt 01 remains retained | Resolve host database startup pressure, then qualify the remaining remote cases; Copilot's first remote attempt never reached fixture creation | +| Cursor v4, source `2e0b0fec0`; paid runtime `bd4cc29c3` | All three closures verify; native instructions and bounded todos are implemented. Exact-head Apex reports 5/5. Current-profile local hello passed six matchers with one authenticated run, complete process cleanup and unchanged semaphore count | The question-resume case failed reopening its provider session; the following three cases were not launched. A rebuilt `627451ecf` admission fix is being paid-tested. Native callbacks, restrictive permissions, other platforms and Daytona remain unqualified. The approved account on-demand cap is $25 | +| Copilot v4, source `2042ca14c`; paid runtime `bd4cc29c3` | Native instruction delivery and lifetime ownership have deterministic proof. Exact-head Apex reports 5/5. All five basic local journeys passed; file edit/validation passed seven matchers in one run with complete cleanup | Daytona hello also passed six matchers with complete cleanup. Native permissions, attached background-command settlement, remaining remote workflows and other platforms remain open. The original session startup timeout is retained without a proven root cause | +| Pi v7, sources `807feaecf` and `bd4cc29c3` | Local hello on `807feaecf` and Daytona hello on `bd4cc29c3` passed six matchers each with zero retries and complete owned cleanup. Remote model plus sandbox analytics stabilized at $0.0053185282. Apex reports 5/5 on the reviewed provider head | The `bd4cc29c3` campaign passed hello, then failed packaging native-question evidence despite 15 passing behavioral checks. The harness-only repair subsequently passed all 15 native checks. The next continuation case failed final-message aggregation; five later cells did not launch. Remote/platform evidence remains incomplete | +| All three, Linux/Daytona | The immutable `bd4cc29c3` image and actual server artifact admission pass. Pi hello attempt 02 passed; failed attempt 01 remains retained | The host database resource blocker is repaired. Copilot’s retry passed six matchers and its exact sandbox remained absent for the full 360-second observation. Remaining remote cases are unqualified | Cursor and Copilot ignore generic ACP `_meta.systemPrompt`; setting `AGENT_HOME` in the process environment does not make it part of model instructions. The v4 @@ -150,14 +152,60 @@ was absent throughout the full cleanup window and all owned processes retired. Three delayed reads stabilized at $0.000630644 OpenRouter usage plus $0.0046878842 sandbox analytics ($0.0053185282 combined, provisional provider accounting). -Further live tests are paused because a credential-free reproduction confirmed -host semaphore exhaustion during embedded PostgreSQL bootstrap (`semget` returned -`ENOSPC`). Copilot's diagnostic local and first Daytona attempts failed before -provider execution. The Daytona invocation never reached fixture creation or a -cloud-write path; its machine cleanup flag remains `unresolved_scope_not_captured` -and is retained separately from that source-order assessment. This host failure -does not explain the earlier Copilot provider-session startup timeout. The -remaining Pi local/native campaign is prepared but has not launched. +Host semaphore exhaustion was confirmed by a credential-free PostgreSQL +bootstrap reproduction (`semget` returned `ENOSPC`). With the user's approval, +a fixed-snapshot cleanup removed 4,892 stale sets (83,164 semaphores) and skipped +11 whose recorded creator PID was present. Startup and graceful shutdown now +pass. Private qualification supervisors were also repaired to let the owned +server shut down PostgreSQL before terminating launcher wrappers. Paid Cursor +hello and Copilot file runs each returned to the 255-set baseline without a +forced PostgreSQL kill; no provider runtime bytes changed. + +Cursor hello attempt 01 stopped in the private supervisor before provider +launch. A process-inspection race was reproduced and repaired; attempt 02 passed +six matchers with one run. Its matching account usage row is labeled Free (24K +tokens), while native token and dollar receipts remain unavailable. Copilot's +new file diagnostic passed seven matchers, exact file bytes and validation in +one run; its included-credit counter moved from 11 to 12 with additional usage +disabled. An initial workspace-only citation was rejected, then the model +registered its deliverable and completed in the same run. This is not a retry. + +Earlier Copilot local and first Daytona failures remain preserved. The remote +invocation never reached fixture creation or a cloud-write path; its machine +cleanup flag remains `unresolved_scope_not_captured`, separately from that +source-order assessment. Host exhaustion does not explain the earlier provider +session timeout. The Pi local/native campaign stopped at its second cell: hello passed, and all +15 native-question behavioral checks passed, but a required API snapshot was +missing. The failed Product result remains retained; the six later cells did +not launch. A minimal harness-only snapshot repair and seven focused regressions +are committed. The two calls cost $0.004005496 by delayed exclusive-key delta. +Cursor’s subsequent question-resume test also stopped its batch on a provider +reopen failure; all 56 owned processes exited and semaphore counts returned to +baseline. Its matching account row is Free (24.7K tokens). A credential-free reproduction shows that a fresh ACPX manager can return a +saved Cursor record without loading the native provider. The committed repair +forces an exact-model control to load that session and acknowledge current +instructions within the existing admission deadline, then renews the consumed +launch lease. Missing or incorrect acknowledgements still block prompting. +The original private sidecar stack is unavailable; this is corroborating +reproduction evidence. The fix passed 93 focused tests and package typecheck; +the rebuilt `627451ecf` runtime is now in a bounded paid continuation batch. +Later cases from the failed batch were not launched. + +Copilot Daytona hello attempt 02 passed six matchers with one run. All 45 owned +processes retired and the exact owned sandbox remained absent throughout the +360-second cleanup observation. Three delayed sandbox analytics reads stabilized +at $0.0039682144; this remains provisional infrastructure accounting, separate +from unavailable native per-run dollars and the account’s unchanged included-credit +counter. Additional Copilot usage remains disabled. + +Pi’s native-question retry on unchanged `bd4cc29c3` runtime and separate +`43c99f044` eval source passed 15/15 with complete required evidence. The next +question continuation reached Done with two succeeded runs, but failed one of +six matchers because the final item included earlier pre-tool narration. Retained +post-tool text deltas alone match the expected final marker. Both cells fully +settled, all 96 owned process identities retired across the two cells, and delayed +exclusive-key charges totaled $0.005707808. Five later cells did not launch; +the final-message defect remains under investigation. GitHub billing coverage was also audited: public standard-runner and self-hosted GitHub minute charges do not add a per-minute charge, but external fleet costs diff --git a/doc/architecture/runner-rich-acp-qualification-2026-09-29.json b/doc/architecture/runner-rich-acp-qualification-2026-09-29.json index 029453890c2..873765b1f9e 100644 --- a/doc/architecture/runner-rich-acp-qualification-2026-09-29.json +++ b/doc/architecture/runner-rich-acp-qualification-2026-09-29.json @@ -1,16 +1,16 @@ { "schema": "paperclip.rich-acp-qualification-checkpoint.v1", - "updatedAt": "2026-09-29T18:26:17.961300+00:00", + "updatedAt": "2026-09-29T20:58:14.579734+00:00", "qualificationStatus": "pending", "runtimeSource": "bd4cc29c3017ed5e1484423e842fd48e3b2f49f3", "modelReceiptPolicy": "Native per-run USD remains null/unpriced when absent. Included subscription credits, exclusive API-key charges and sandbox analytics are separate evidence. Unknown costs are never assumed zero.", "evidenceScope": "Sanitized checkpoint of retained private receipts; historical reports retain earlier attempts. This file is not an executable conformance result or production qualification certificate.", "currentProfilePaidCoverage": { - "cursor4": "No current-profile paid Product receipt. Historical local successes used Cursor2. Account spend-limit decision pending.", - "copilot4": "bd4 local hello, semantic question, semantic plan and controller-restart passed. File startup timeout unresolved; two diagnostic attempts failed before provider launch because private DB initialization failed. No successful Daytona Product run.", - "pi7": "807 local hello and bd4 Daytona hello passed. Current bd4 local8 campaign is reserved but not launched." + "cursor4": "bd4 local hello passed. Cold continuation failed; corroborating offline reproduction led to source627451ecf session-load repair. The rebuilt four-cell paid batch is running, with no result yet. Native callbacks, restrictive permissions, Daytona and remaining platforms are open.", + "copilot4": "bd4 all five basic local journeys and Daytona hello passed. Native permission denial and attached background settlement Product cases plus remaining remote/platform coverage are open. The original session.open timeout remains unexplained.", + "pi7": "Local and Daytona hello passed. After preserving an earlier missing-evidence failure, the harness-only repair on runtimebd4/eval43c99f0 produced a complete native-question pass15/15. The next question-continuation cell failed5/6: final-message aggregation included pre-tool narration. All three runs settled and owned cleanup passed; five later cells were not launched." }, - "hostBlocker": "Credential-free exact initdb reproduced semget ENOSPC; kernel semaphore pool nearly exhausted. No global IPC changes performed. Paid launches paused.", + "hostBlocker": "Resolved for live testing: user-approved fixed-snapshot cleanup removed 4,892 stale PostgreSQL semaphore sets, skipping 11 whose creator PID was present. Credential-free startup and role-aware shutdown passed; subsequent paid Cursor and Copilot runs restored the 255-set baseline. No broad follow-up IPC deletion is authorized.", "ciCostCoverage": "Public standard GitHub-hosted minutes and self-hosted GitHub runner charges are zero; external self-hosted fleet infrastructure costs and private evals CI incremental charges remain unmetered.", "attempts": [ { @@ -255,7 +255,11 @@ { "id": "pi-v7-local-bd4-campaign-20260929-01", "provider": "pi", - "status": "reserved_waiting_for_copilot_product_shutdown", + "status": "failed_second_cell_evidence_packaging", + "sourceRevision": "bd4cc29c3017ed5e1484423e842fd48e3b2f49f3", + "profileVersion": 7, + "profileDigest": "sha256:fec5b1448f4135710887133a9192747c476a825a56c255b52b17b1780ccb3761", + "model": "openrouter/deepseek/deepseek-v4-flash-0731", "cells": [ "extended-harnesses.runner-acpx-pi.local.hello-complete", "pi-native.runner-acpx-pi.local.native-questions", @@ -266,13 +270,243 @@ "pi-native.runner-acpx-pi.local.agent-files-fresh-run", "pi-native.runner-acpx-pi.local.restrictive-denial" ], + "maxRetries": 0, + "createdAt": "2026-09-29T18:23:16.046245+00:00", + "actualCostUsd": 0.004005496, + "reconciledAt": "2026-09-29T20:31:33.209288+00:00", + "costCoverage": "Exclusive OpenRouter key delayed180s delta: hello .000637804 plus nativequestions .003367692; native perrunUSD remains unpriced.", + "attemptCount": 2, + "productRunCount": 2, + "ownedProcessesRetired": true, + "postRunAuthorityPassed": true, + "observedAutomaticRetries": 0, + "completedCells": 2, + "unlaunchedCells": 6, + "failure": "Native questions completed15/15 behavioral assertions but required snapshots/api-state.json missing; Product outcome failed and campaign stopped. Hello passed6/6.", + "privateEvidenceName": "campaign.json", + "privateEvidenceSha256": "e095503ab4b32eaabf34db807d41454fcd3417796bbbcdd9033167092c984383" + }, + { + "provider": "copilot", "sourceRevision": "bd4cc29c3017ed5e1484423e842fd48e3b2f49f3", + "profileVersion": 4, + "profileDigest": "sha256:a119e436b4ad13ee70e1f58bedad4a0f20761b5fd982b752981f0cb1bc65f797", + "providerPackDigest": "sha256:c19135b9175fffe9b18c06ca735ba1610e6cb2e36305c760d763c1f41fa67d81", + "model": "gpt-5.6-luna", + "cell": "extended-harnesses.runner-acpx-copilot.local.file-edit-validate", + "id": "copilot-v4-local-file-20260929-02", + "status": "passed", + "actualCostUsd": null, + "createdAt": "2026-09-29T20:07:12.133150+00:00", + "maxRetries": 0, + "attemptCount": 1, + "includedCreditDelta": 1, + "ownedProcessesRetired": true, + "ownedProcessCount": 55, + "postRunAuthorityPassed": true, + "costCoverage": "GitHub includedcredit11->12; additionalusage remainsdisabled$0/$0; nativeperrunUSDunknown", + "reconciledAt": "2026-09-29T20:18:07.543888+00:00", + "productRunCount": 1, + "matcherPassCount": 7, + "matcherCount": 7, + "privateEvidenceName": "review-receipt.private.json", + "privateEvidenceSha256": "c2699ecf375181f9722652535f54db6712117a3b4e0708d0c44e6500034edcf1" + }, + { + "provider": "cursor", + "profileVersion": 4, + "profileDigest": "sha256:b1440d559ebc4eef5c7a582f1c81fc153270cfbafa1731a8ee76d83713bdf61b", + "sourceRevision": "bd4cc29c3017ed5e1484423e842fd48e3b2f49f3", + "model": "gpt-5.6-luna[context=272k,reasoning=medium,fast=false]", + "id": "cursor-v4-local-hello-20260929-01", + "status": "failed_supervisor_before_provider", + "actualCostUsd": null, + "createdAt": "2026-09-29T20:08:34.490882+00:00", + "cell": "extended-harnesses.runner-acpx-cursor.local.hello-complete", + "maxRetries": 0, + "attemptCount": 1, + "productRunCount": 0, + "ownedProcessesRetired": true, + "failure": "Process monitor CalledProcessError during PG startup; agent is confirming ps process-exit race. No Product run/browser/provider reached; root awaits complete failure proof before assigning actual cost0.", + "reconciledAt": "2026-09-29T20:10:39.989926+00:00", + "privateEvidenceName": "cursor-v4-bd4-hello-01" + }, + { + "provider": "cursor", + "profileVersion": 4, + "profileDigest": "sha256:b1440d559ebc4eef5c7a582f1c81fc153270cfbafa1731a8ee76d83713bdf61b", + "sourceRevision": "bd4cc29c3017ed5e1484423e842fd48e3b2f49f3", + "model": "gpt-5.6-luna[context=272k,reasoning=medium,fast=false]", + "id": "cursor-v4-local-hello-20260929-02", + "status": "passed", + "actualCostUsd": null, + "createdAt": "2026-09-29T20:13:46.584978+00:00", + "cell": "extended-harnesses.runner-acpx-cursor.local.hello-complete", + "maxRetries": 0, + "attemptCount": 1, + "productRunCount": 1, + "matcherPassCount": 6, + "matcherCount": 6, + "ownedProcessesRetired": true, + "ownedProcessCount": 47, + "postRunAuthorityPassed": true, + "reconciledAt": "2026-09-29T20:18:07.543888+00:00", + "accountObservedChargeUsd": 0, + "costCoverage": "Matching24Kmodelrow is explicitlyFree in Cursor account; native token/cost receipt is unavailable. Do not fabricate native priced usage.", + "privateEvidenceName": "analysis.private.json", + "privateEvidenceSha256": "e558d1dbde30f49fa09f0519de34e2eddd65694ce3ab8aadeb71b79040de249c" + }, + { + "id": "cursor-v4-local-remaining-20260929-01", + "provider": "cursor", + "status": "failed_first_cell_continuation", + "cells": [ + "extended-harnesses.runner-acpx-cursor.local.question-resume-complete", + "extended-harnesses.runner-acpx-cursor.local.plan-approve-complete", + "extended-harnesses.runner-acpx-cursor.local.structured-question-restart-resume", + "extended-harnesses.runner-acpx-cursor.local.file-edit-validate" + ], + "sourceRevision": "bd4cc29c3017ed5e1484423e842fd48e3b2f49f3", + "profileVersion": 4, + "profileDigest": "sha256:b1440d559ebc4eef5c7a582f1c81fc153270cfbafa1731a8ee76d83713bdf61b", + "model": "gpt-5.6-luna[context=272k,reasoning=medium,fast=false]", + "createdAt": "2026-09-29T20:28:30.857363+00:00", + "maxRetries": 0, + "actualCostUsd": null, + "attemptCount": 1, + "completedCells": 1, + "unlaunchedCells": 3, + "ownedProcessesRetired": true, + "ownedProcessCount": 56, + "postRunAuthorityPassed": true, + "failure": "Question continuation run.attach failed: ACPX sidecar session.open rejected; cause under investigation. Subsequent3cells not launched.", + "reconciledAt": "2026-09-29T20:33:09.782788+00:00", + "accountObservedChargeUsd": 0, + "costCoverage": "Matching20:29UTC gpt5.6-luna-medium accountrow is Free24.7Ktokens; accountonDemand0. Native perrunUSD unavailable, not fabricatedzero." + }, + { + "id": "copilot-v4-daytona-hello-20260929-02", + "provider": "copilot", + "status": "passed", + "cell": "extended-harnesses.runner-acpx-copilot.daytona.hello-complete", + "sourceRevision": "bd4cc29c3017ed5e1484423e842fd48e3b2f49f3", + "profileVersion": 4, + "profileDigest": "sha256:a119e436b4ad13ee70e1f58bedad4a0f20761b5fd982b752981f0cb1bc65f797", + "model": "gpt-5.6-luna", + "image": "ghcr.io/paperclipai/paperclip-daytona-runner@sha256:bff4c3f291087a0eeae37e4c20dd51857b92833eaf73ba3aca4157f37de1e109", + "createdAt": "2026-09-29T20:31:06.298515+00:00", + "maxRetries": 0, + "actualCostUsd": null, + "reconciledAt": "2026-09-29T20:43:18.535492+00:00", + "attemptCount": 1, + "productRunCount": 1, + "providerInferenceTurns": 1, + "matcherPassCount": 6, + "matcherCount": 6, + "ownedProcessesRetired": true, + "ownedProcessCount": 45, + "ownedSandboxCount": 1, + "cleanupStatus": "observed_absent_for_360_seconds", + "postRunAuthorityPassed": true, + "observedAutomaticRetries": 0, + "nativeUsd": null, + "costCoverage": "Exact owned sandbox delayed analytics$.0039682144. Copilot nativeUSDunknown; subscriptioncounter12->12 and additionalusage disabled0/0; accountcounter may lag. Source-bound720s infraupperbound$.053496 met. Runtimeestimate is separate from billing.", + "daytonaObservedCostUsd": 0.0039682144, + "costFinality": "Provisional sandbox-specific analytics stable across three delayed reads; invoice finality unknown.", + "privateEvidenceName": "review-receipt.private.json", + "privateEvidenceSha256": "2be810d807d12e35c237feb0b60d71b74e27727336f4c6a904a6dbbc0bfd2bab" + }, + { + "id": "pi-v7-local-bd4-campaign-20260929-02", + "provider": "pi", + "status": "failed_second_cell_final_message_projection", + "createdAt": "2026-09-29T20:44:04.035168+00:00", + "sourceRevision": "43c99f04403c0e1e5353b41b41dcab8fdade6a2f", + "runtimeSourceRevision": "bd4cc29c3017ed5e1484423e842fd48e3b2f49f3", + "evalSourceRevision": "43c99f04403c0e1e5353b41b41dcab8fdade6a2f", + "evalPatchCommit": "7e7563ca8b8f351b74b922f8c06aee612dfc84fa", + "evalPatchSha256": "18119aef75b5f5a13aa10c1c9c7f7a761b13257dd67d395ec575842663cd8266", + "runtimeBuildPerformed": false, + "cells": [ + "native-questions", + "question-resume-complete", + "plan-approve-complete", + "structured-question-restart-resume", + "file-edit-validate", + "agent-files-fresh-run", + "restrictive-denial" + ], + "expectedProductRuns": 11, + "model": "openrouter/deepseek/deepseek-v4-flash-0731", "profileVersion": 7, "profileDigest": "sha256:fec5b1448f4135710887133a9192747c476a825a56c255b52b17b1780ccb3761", - "model": "openrouter/deepseek/deepseek-v4-flash-0731", - "createdAt": "2026-09-29T18:23:16.046245+00:00", - "actualCostUsd": null, - "maxRetries": 0 + "providerPackDigest": "sha256:c19135b9175fffe9b18c06ca735ba1610e6cb2e36305c760d763c1f41fa67d81", + "maxRetries": 0, + "actualCostUsd": 0.005707808, + "completedCells": 2, + "unlaunchedCells": 5, + "productRunCount": 3, + "attemptCount": 1, + "inferenceKeyDeltaUsd": 0.005707808, + "ownedProcessesRetired": true, + "postRunAuthorityPassed": true, + "reconciledAt": "2026-09-29T20:56:40.420584+00:00", + "failure": "Question continuation reached Done with two succeeded native runs, but final item included earlier pre-tool narration; exact final response matcher failed. Retained deltas after the last tool concatenate to the exact expected marker. Five later cells were not launched.", + "costCoverage": "Exclusive OpenRouter key delta for two cells after 0/30/90/180s settlement; native per-run USD remains unpriced.", + "settledCells": [ + { + "cell": "native-questions", + "status": "passed", + "matcherPassCount": 15, + "matcherCount": 15, + "productRunCount": 1, + "exclusiveKeyDeltaUsd": 0.003543848, + "ownedProcessesRetired": true, + "ownedProcessCount": 44, + "postRunAuthorityPassed": true + }, + { + "cell": "question-resume-complete", + "status": "candidate_failure", + "matcherPassCount": 5, + "matcherCount": 6, + "productRunCount": 2, + "exclusiveKeyDeltaUsd": 0.00216396, + "ownedProcessesRetired": true, + "ownedProcessCount": 52, + "postRunAuthorityPassed": true + } + ], + "privateEvidenceName": "campaign.json", + "privateEvidenceSha256": "d0bb6e7045dad5ba44162d66dd3ec6db6cd31e9fbd4c88e926e99b05b4e06ad9" + }, + { + "id": "cursor-v4-local-627-remaining-20260929-01", + "provider": "cursor", + "status": "authorized", + "createdAt": "2026-09-29T20:56:40.420584+00:00", + "sourceRevision": "627451ecf15641504a485c6f868497177bd1bce8", + "profileVersion": 4, + "profileDigest": "sha256:b1440d559ebc4eef5c7a582f1c81fc153270cfbafa1731a8ee76d83713bdf61b", + "model": "gpt-5.6-luna[context=272k,reasoning=medium,fast=false]", + "cells": [ + "extended-harnesses.runner-acpx-cursor.local.question-resume-complete", + "extended-harnesses.runner-acpx-cursor.local.plan-approve-complete", + "extended-harnesses.runner-acpx-cursor.local.structured-question-restart-resume", + "extended-harnesses.runner-acpx-cursor.local.file-edit-validate" + ], + "expectedProductRuns": 7, + "maxRetries": 0, + "actualCostUsd": null } - ] + ], + "hostRecovery": { + "removedSets": 4892, + "removedSemaphores": 83164, + "skippedSets": 11, + "cleanupResultSha256": "105ad0e67c74078f8d3b62784ba08151712646c07289f93e7907fd0f306410ca", + "startupAndShutdownProofSha256": "0f9e42e295d87cbf45731be089f65bc9cd6d1a26e185ab1847f3a7d2d0291fbe", + "currentSupervisorHelperSha256": "c3c801ef7dc3ef969384dd9bb6d822fe6ab21025d40a4702abfdd9ee392d1148", + "scope": "The credential-free startup proof used an earlier role-aware helper revision. Current-helper cleanup is additionally proven by the paid Cursor hello and Copilot file runs. Private qualification supervisors changed; frozen runtime bytes did not." + } } diff --git a/doc/architecture/runner-rich-acp-validation-2026-09-29.json b/doc/architecture/runner-rich-acp-validation-2026-09-29.json index cc6a8d3952c..792150e8a67 100644 --- a/doc/architecture/runner-rich-acp-validation-2026-09-29.json +++ b/doc/architecture/runner-rich-acp-validation-2026-09-29.json @@ -1,6 +1,6 @@ { "schema": "paperclip.rich-acp-validation-checkpoint.v1", - "updatedAt": "2026-09-29T18:52:19.212615+00:00", + "updatedAt": "2026-09-29T20:58:14.579734+00:00", "qualificationStatus": "pending", "runtimeSource": "bd4cc29c3017ed5e1484423e842fd48e3b2f49f3", "validationSourcePatches": [ @@ -147,9 +147,40 @@ "otherStageReceiptSha256": "024be9b0a264f97d46ecaa724e72fed17ffd3c6380303dbfdc6a4596db2d5f56" }, "qualificationBlockers": [ - "Host PostgreSQL semaphore exhaustion; stale-object cleanup awaits user authorization.", - "Cursor account spending-limit decision pending.", - "Remaining authenticated local/native/Daytona cases and platform coverage; Copilot file startup timeout unresolved.", - "Complete infrastructure cost coverage and current final-head CI/review remain required." + "Remaining native/local/Daytona workflows and macOS x64 execution coverage; Pi final-message aggregation failure is under repair.", + "A complete green repository test run is still missing; the retained full run failed and has not been repeated after host recovery.", + "Shared prerequisite CI has a failed server job; its bounded retry was canceled. Current final-head CI/review remains required.", + "Complete infrastructure cost coverage remains unavailable; native per-run USD is unpriced for the subscription providers." + ], + "hostRecovery": { + "status": "complete", + "removedStaleSets": 4892, + "skippedBecauseCreatorPidPresent": 11, + "startupAndGracefulShutdown": "passed", + "currentPaidCleanup": "Cursor hello and Copilot file each returned to the 255-set baseline", + "frozenRuntimeModified": false + }, + "sharedPrerequisiteCi": { + "recordedAt": "2026-09-29T20:26:11.895912+00:00", + "sourceRevision": "11da146c3c39aea5605fdfac31e619fd8024227b", + "jobId": 109571559222, + "jobConclusion": "failure", + "testStepConclusion": "cancelled", + "classification": "runner_shutdown_during_test_step", + "evidence": "19:09:17Z: The runner has received a shutdown signal; 19:09:29Z: The operation was canceled.", + "logSha256": "cb927b9d77810c5c38f9d5ff22adf3f1daa8f5d9bc35f967c330eb8d2ee6b8cf", + "newTestFailureEstablished": false, + "additionalRetryRequested": false + }, + "sourcePatchVerification": [ + { + "source": "627451ecf15641504a485c6f868497177bd1bce8", + "scope": "Cursor cold-session admission repair and prior shared integration", + "focusedTests": 94, + "runnerTypecheck": "passed", + "sidecarAndProviderPackBuild": "passed", + "daemonBuild": "passed; bytes unchanged", + "paidQualification": "four-cell batch running; not yet passed" + } ] }