diff --git a/doc/architecture/runner-rich-acp-capabilities.md b/doc/architecture/runner-rich-acp-capabilities.md index 8f3105fe08a..a5d9a6ed21d 100644 --- a/doc/architecture/runner-rich-acp-capabilities.md +++ b/doc/architecture/runner-rich-acp-capabilities.md @@ -79,14 +79,25 @@ than being credited as passing. On `807feaecf`, typecheck/build and CI reproduced a test-fixture typing error; shared prerequisite commit `bb56af7fb` fixes it. These sources predate the latest review and continuation fixes. -On integrated `bd4cc29c3`, full build, recursive typecheck and token gates pass; -the full test suite and runner verification remain in progress. The shared PR -now includes test-only repairs for connection setup context and waiting for the -startup row’s persisted PID; targeted tests, typechecks and token gates pass. +On integrated `bd4cc29c3`, full build, recursive typecheck and token gates pass. +The completed full test attempt records 11,598 passing tests, six failed tests, +2,640 skipped tests and 43 failed files. Four cases fail before assertions during +database bootstrap; other files fail setup or cleanup. Two separate cases time +out at 15 seconds and 300 seconds and remain unclassified. This is not a green +repository test run. All Runner verification stages pass across retained, +targeted retries, including 2,533 base TypeScript tests, Rust, 22 SDK tests, +537 scenario tests, 25 main browser tests, six SDK browser tests, 43 scenario +browser tests, 112 issue-thread browser tests, import/package gates and an actual +clean-consumer pack/install. The aggregate `verify` command was not rerun from +the beginning after those repairs. The +[validation checkpoint](runner-rich-acp-validation-2026-09-29.json) retains source +revisions, log hashes, failed attempts and the exact scope of each pass. +The shared PR includes test setup/settlement repairs, corrected baseline browser +expectations, the standalone devtool loader repair and verification-script fixes. The private embedded Postgres package required its declared postinstall to restore shipped dylib symlinks before live startup; a credential-free server health check and subsequent paid question passed with the repair hashed in -their evidence. Final full-suite results and current-head CI remain required. +their evidence. A green full-suite run and final-head CI remain required. The Copilot attempt increased the visible included-credit counter from 5 to 6; additional usage remained disabled at a $0 budget. Per-run USD is unknown. diff --git a/doc/architecture/runner-rich-acp-validation-2026-09-29.json b/doc/architecture/runner-rich-acp-validation-2026-09-29.json new file mode 100644 index 00000000000..cc6a8d3952c --- /dev/null +++ b/doc/architecture/runner-rich-acp-validation-2026-09-29.json @@ -0,0 +1,155 @@ +{ + "schema": "paperclip.rich-acp-validation-checkpoint.v1", + "updatedAt": "2026-09-29T18:52:19.212615+00:00", + "qualificationStatus": "pending", + "runtimeSource": "bd4cc29c3017ed5e1484423e842fd48e3b2f49f3", + "validationSourcePatches": [ + "60dd81f2a709a8f8b41d7ec7b225230011df1dbd", + "2fa4f725eb8d0cd58ee8a1207b8065a664fb2363", + "28c82b358e0214f16a0a2cf47006331d89a4d3df", + "aa1a4ec328054bcece9637d33729f64cd97df419", + "f792c41f9f8bdaca0cc5e2877ed95ed881a7f7bb", + "4f2709a611de58b586b122167ca049a19e8d38d0", + "1ac2b2299065ce6767c5541f5cda39190bb436e4", + "ca28efc2461c43ca4b82822028ad60969e250502", + "0759fac2976a49331f65f08c4d9406dc89b8424c" + ], + "scope": "Credential-free validation of the bd4 runtime plus committed test, documentation, devtool-loader and verification-script repairs. Frozen paid runtime bytes were not changed. Earlier failed attempts remain retained. This checkpoint does not certify paid qualification.", + "repositoryBuildTypecheckAndTokens": [ + { + "name": "full-build", + "command": [ + "pnpm", + "build" + ], + "exitCode": 0, + "startedAt": "2026-09-29T17:46:17.343584+00:00", + "finishedAt": "2026-09-29T17:46:53.273027+00:00", + "logSha256": "1ccfe26fcfa853d1f89d0a16e5542cac9074e1a5ac29708763dd73c4072b7efc" + }, + { + "name": "full-typecheck", + "command": [ + "pnpm", + "-r", + "typecheck" + ], + "exitCode": 0, + "startedAt": "2026-09-29T17:46:53.273345+00:00", + "finishedAt": "2026-09-29T17:47:32.857318+00:00", + "logSha256": "d75eabf0e16eccc769550fbd228fbf30a915d00e4dbdd7ec4f96ec33afacc6ca" + }, + { + "name": "final-token-gates", + "command": [ + "pnpm", + "check:token-gates" + ], + "exitCode": 0, + "startedAt": "2026-09-29T17:47:32.858014+00:00", + "finishedAt": "2026-09-29T17:47:33.697535+00:00", + "logSha256": "7e234af112ebd5788a15cde62fc4e27c18997813fd4bfc23d0812d02af1fb33e" + } + ], + "repositoryTests": { + "command": [ + "pnpm", + "test:run" + ], + "exitCode": 1, + "passedTests": 11598, + "failedTests": 6, + "skippedTests": 2640, + "passedFiles": 536, + "failedFiles": 43, + "skippedFiles": 140, + "logSha256": "1d5f3789bfeab0461499354c171688ccb82128660bec756e159cbc0580bf7174", + "failureClasses": [ + { + "class": "embedded_postgres_bootstrap", + "failedCases": 4, + "detail": "The four cases fail before assertions at initdb after five attempts. Many other files fail setup or cleanup. This log has generic bootstrap errors; a separate exact-initdb reproduction records semget ENOSPC." + }, + { + "class": "unclassified_timeout", + "failedCases": 2, + "detail": "Authenticated Workspace docs.read times out at 15 seconds; real Git filename snapshot streaming times out at 300 seconds. No passing retry is credited." + } + ], + "completeGreenRun": false + }, + "runnerVerification": { + "status": "all_stages_pass_across_retained_retries", + "singleUninterruptedVerifyPassed": false, + "baseBuildTypecheckReplayTypescriptRustSdk": { + "logSha256": "1c3d8ce9bce225ed345ea7567a64065357c26b7853f2ac7585fd9244dfdef9e6", + "typescriptPassed": 2533, + "typescriptSkipped": 11, + "sdkPassed": 22, + "note": "The original aggregate invocation stopped at one scenario fixture failure. All preceding build, typecheck, replay, TypeScript, Rust and SDK stages passed; the repaired scenario stage passed below." + }, + "scenarios": { + "passed": 537, + "skipped": 3, + "logSha256": "54a62a3eceff47c4a6c617ed1f3d11b7a49cc8f02f572e8974208b94e951d9f6" + }, + "browser": { + "passed": 25, + "logSha256": "c2eb80b3b7352b204842b16b2a8284619cefdfd60a329da6d68b903128e76090" + }, + "browserSdk": { + "passed": 6, + "logSha256": "7c99f3c6e2558952ecbf7126f12be35e5748720a6a6aeba789fa68e245cf8964" + }, + "browserScenarioExplorerAndChat": { + "passed": 43, + "logSha256": "9880ec250725c7c69a109df764ade0e5b509cd61ebc8a10229a2959d44f327c1", + "note": "The first 43-case suite passed; the following issue-thread suite in that same command failed two stale expectations. Its repaired complete retry is separate below." + }, + "browserIssueThread": { + "passed": 112, + "logSha256": "827bb9f827936eb60c24cabd3064ef332af664770b978031734920d0de44cafb" + }, + "importScannerTests": { + "passed": 19, + "logSha256": "f0954fe6f478ada7044ebed789c15b9de855b420d4809222441533a0905dc35f" + }, + "importAndPackageGates": { + "forbidden": "passed", + "tracked": "passed", + "packageBoundary": "passed", + "receiptsSha256": [ + "5014d7931025f522ce522e76ee4fb27d7b4c82688c4db1e0f38cea5f41032954", + "3e6ba97dfd9d87781c1b3d9fc7b5e7713ea90a25943a0a8c8d6147167bfb1633" + ] + }, + "cleanConsumer": { + "name": "check:clean-consumers", + "startedAt": "2026-09-29T18:48:20.499452+00:00", + "finishedAt": "2026-09-29T18:50:25.705111+00:00", + "exitCode": 0, + "logSha256": "facbaee578adf24b76907c2e36114dca8f1e0389d04672f9fd5903fd6ae77de6" + }, + "docs": { + "files": 53, + "status": "passed", + "logSha256": "75d9bdc5d43cc60d514388e0e17091054d321d1ebebb089203e3563272bece27" + }, + "otherPassedStages": [ + "check:browser-tokens", + "check:numbered-milestones", + "check:conformance-parity", + "check:replay-parity", + "trace:conformance", + "replay:fixture", + "trace:local-runner" + ], + "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." + ] +}