mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-12 06:10:44 +01:00
docs: publish calibrated native launcher admission
Co-Authored-By: Paperclip <noreply@paperclip.ing>
This commit is contained in:
DottaandPaperclip committed
1 parent
402ee94c52
commit
0e3650d87b
11 files changed
+1802
No files matched your search
@@ -0,0 +1,312 @@
|
||||
{
|
||||
"schema": "paperclip.native-completion-preflight.v1",
|
||||
"sourceSha": "e74ed61a69fbdd8b3a8f15dd6456bc3140246e33",
|
||||
"sourceFingerprint": "a01593363d6512e30d8149fcf4f34adfff8b07aeef7f845f0c9bbed3cb7b979f",
|
||||
"fixtureFingerprint": "a50581c04f3d87843d69f92050712977f8e114e4c2f23f96f243fd5386119f27",
|
||||
"manifestFingerprint": "b92f3ab7d561188bc09214433b264f2e7810e8ccdc237f68caa82e1aecc1811e",
|
||||
"variant": "historical",
|
||||
"baseSha": "59c07ede72dc08b8aba149a01cc11e0b7a204621",
|
||||
"archiveSha": "9138f570c341c251a5727c32d6615ce238bc8e03",
|
||||
"sourceErrors": [],
|
||||
"immutable": true,
|
||||
"layering": true,
|
||||
"sourceMetadata": {
|
||||
"schema": "paperclip.native-completion-source-metadata.v1",
|
||||
"lineage": {
|
||||
"strategy": "full_ancestry",
|
||||
"shallow": true,
|
||||
"sha": "e74ed61a69fbdd8b3a8f15dd6456bc3140246e33",
|
||||
"baseSha": "59c07ede72dc08b8aba149a01cc11e0b7a204621",
|
||||
"anchor": null
|
||||
},
|
||||
"hydration": {
|
||||
"present": false,
|
||||
"verified": false,
|
||||
"archiveSha256": null,
|
||||
"checksumSha256": null
|
||||
},
|
||||
"worktreeEntries": [],
|
||||
"errors": []
|
||||
},
|
||||
"sourceMetadataErrors": [],
|
||||
"sourceMetadataFingerprint": "213fd8921ea70a629f77c59858957e032a4b658e0c2c8cf9a0538f6028fcbf3f",
|
||||
"measuredAt": "2026-10-03T05:01:32.928Z",
|
||||
"providerCalls": 0,
|
||||
"live": "not_run",
|
||||
"expectedCells": 6,
|
||||
"expectedTurns": 6,
|
||||
"maximumAttemptsPerCell": 1,
|
||||
"setup": {
|
||||
"passed": true,
|
||||
"sdkExitCode": 0,
|
||||
"runnerTypeScriptExitCode": 0,
|
||||
"runnerdExitCode": 0,
|
||||
"evidence": [
|
||||
{
|
||||
"file": "setup-sdk.txt",
|
||||
"sha256": "01ba4719c80b6fe911b091a7c05124b64eeece964e09c058ef8f9805daca546b"
|
||||
},
|
||||
{
|
||||
"file": "setup-runner-typescript.txt",
|
||||
"sha256": "239fcb77a2f4cecbaf744b3d82a8fb3ddc919d9c2d7e96e23ed0d3d6464a8167"
|
||||
},
|
||||
{
|
||||
"file": "setup-runnerd.txt",
|
||||
"sha256": "ba3c9262f015eb5af7ee896db9e0ad9b1094ad485c819a355bfea1d9c914e4c8"
|
||||
}
|
||||
],
|
||||
"runnerdProvenance": {
|
||||
"schema": "paperclip.native-completion-runnerd-provenance.v1",
|
||||
"mode": "fresh_local_build",
|
||||
"passed": true,
|
||||
"selectedPath": "packages/paperclip-runner/runner/target/debug/paperclip-runnerd",
|
||||
"binarySha256": "8e4d54800e3b4b829621b12a9d8ce434c89445492abe7584d4465922e3ff5cea",
|
||||
"binaryBytes": 84271504,
|
||||
"archiveMemberBytes": null,
|
||||
"sourceSha": "e74ed61a69fbdd8b3a8f15dd6456bc3140246e33",
|
||||
"sourceFingerprint": "a01593363d6512e30d8149fcf4f34adfff8b07aeef7f845f0c9bbed3cb7b979f",
|
||||
"archiveSha256": null,
|
||||
"workflowRunId": null,
|
||||
"workflowRunAttempt": null,
|
||||
"artifactName": null,
|
||||
"errors": []
|
||||
},
|
||||
"buildOutputFingerprint": "b131fe332da31bb4c1b3b8fbaf70f98e96f70de12c426dd087b47037f649b7d4",
|
||||
"runnerdSha256": "8e4d54800e3b4b829621b12a9d8ce434c89445492abe7584d4465922e3ff5cea",
|
||||
"runnerdSelectedPath": "packages/paperclip-runner/runner/target/debug/paperclip-runnerd",
|
||||
"runnerdSourceSha": "e74ed61a69fbdd8b3a8f15dd6456bc3140246e33",
|
||||
"runnerdSourceFingerprint": "a01593363d6512e30d8149fcf4f34adfff8b07aeef7f845f0c9bbed3cb7b979f"
|
||||
},
|
||||
"gates": [
|
||||
{
|
||||
"id": "NC-schemas",
|
||||
"name": "Variant-native completion schemas",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"files": [
|
||||
{
|
||||
"file": "src/contracts/completion-result.test.ts",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"requirements": [
|
||||
{
|
||||
"name": "distinguishes user-facing answer content",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "propagates answer and wait descriptions",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "requires a reason code for verification that was not run",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"total": 13,
|
||||
"passedTests": 13,
|
||||
"failedTests": 0,
|
||||
"pendingTests": 0,
|
||||
"evidence": {
|
||||
"file": "NC-schemas.json",
|
||||
"sha256": "65801fe5e8dd6b4496a4e6e221f93ae3429b1f0001bc877ed0f198de066db9bd"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-tools",
|
||||
"name": "Native tool delivery and retained provider catalogs",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"files": [
|
||||
{
|
||||
"file": "src/drivers/codex/codex-app-server-driver.lifecycle.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "src/drivers/runner-tool-bridge.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "src/drivers/opencode/mcp-bridge.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "src/live/runnerd-codex-transport.test.ts",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"requirements": [
|
||||
{
|
||||
"name": "runner semantic MCP bridge binds to loopback",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "OpenCode MCP bridge binds to loopback",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves stock Codex instructions on task recovery",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves stock Codex instructions on prepared recovery",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves stock Codex instructions on direct recovery",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "includes ACPX terminal tools in the authenticated bridge catalog",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"total": 222,
|
||||
"passedTests": 7,
|
||||
"failedTests": 0,
|
||||
"pendingTests": 215,
|
||||
"evidence": {
|
||||
"file": "NC-tools.json",
|
||||
"sha256": "43807dc3c0a5ed228e6c8628110612acbbaf1a2abfeb9386b8dda1873a31c016"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-resume",
|
||||
"name": "Variant-native fingerprint and checkpoint refresh",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"files": [
|
||||
{
|
||||
"file": "server/src/services/native-runtime/native-session-resume.test.ts",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"requirements": [
|
||||
{
|
||||
"name": "refreshes retained 'completion descriptions'",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "refreshes retained 'task-bound human-input description'",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"total": 44,
|
||||
"passedTests": 2,
|
||||
"failedTests": 0,
|
||||
"pendingTests": 42,
|
||||
"evidence": {
|
||||
"file": "NC-resume.json",
|
||||
"sha256": "feec780625e8f9557090eda4ea8a8d545c707b8e93bae8fbd9ffd0ec49a0911a"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-eval",
|
||||
"name": "Independent native oracle, defaults, admission and attempt policy",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"files": [
|
||||
{
|
||||
"file": "tests/runner-e2e/native-completion-scoring.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/native-completion-defaults.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/native-completion-admission.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/automatic-retry.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/context-integrity.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/context-integrity-evidence.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/context-integrity-flow-logs.test.ts",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"requirements": [
|
||||
{
|
||||
"name": "allows toolchain paths and excludes every present or future credential",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "retains credential-free prerequisites inside the exact campaign root",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "retains the first transient_infrastructure failure without a second attempt",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "retains the first provider_variance failure without a second attempt",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"total": 105,
|
||||
"passedTests": 105,
|
||||
"failedTests": 0,
|
||||
"pendingTests": 0,
|
||||
"evidence": {
|
||||
"file": "NC-eval.json",
|
||||
"sha256": "e2926c0b44b5642b7c8c33943e502fdc87e67920f07db980c4fb74ad95e28e32"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-node",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-node.txt",
|
||||
"sha256": "3e09ffb62c22a05a2ca289fa51f77b9049d3f1feaa3d2d8c2e5f0e4ca4de0112"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-typecheck",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-typecheck.txt",
|
||||
"sha256": "01ba4719c80b6fe911b091a7c05124b64eeece964e09c058ef8f9805daca546b"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-rust-carrier",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-rust-carrier.txt",
|
||||
"sha256": "15d4b7ea22f8031647ce57d2eb37ddb9465f697e1469f81155c1c195ab09298c"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-discovery",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-discovery.txt",
|
||||
"sha256": "3097ab7907c3b49d43920fab50d0b180b70cb6895c0bd1a58f72fd740fec6567"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-manifest",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-manifest.txt",
|
||||
"sha256": "7f5d044db6a7813857e842095c5e3aa749a98570a96ff9939483de9452322502"
|
||||
}
|
||||
}
|
||||
],
|
||||
"passed": true
|
||||
}
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"schema": "paperclip.native-completion-synthetic-hosted-calibration.v1",
|
||||
"synthetic": true,
|
||||
"actualGitHubWorkflow": false,
|
||||
"providerCalls": 0,
|
||||
"sourceSha": "e74ed61a69fbdd8b3a8f15dd6456bc3140246e33",
|
||||
"receiptPath": "/private/tmp/paperclip-native-calibrated-baseline-synthetic-hosted/native-completion-prerequisites/c6b1c7c2-87b7-4a52-8a0c-86f640d09a91/preflight.json",
|
||||
"archiveSha256": "86e4342be7c5b7cbc6ab49748c3b92a577bb8bfced890623e2317c8e39d4aa24",
|
||||
"publicMetadata": {
|
||||
"GITHUB_ACTIONS": true,
|
||||
"GITHUB_RUN_ID": "8675309",
|
||||
"GITHUB_RUN_ATTEMPT": "1"
|
||||
},
|
||||
"prepareAndVerifyPassed": true
|
||||
}
|
||||
+321
@@ -0,0 +1,321 @@
|
||||
{
|
||||
"schema": "paperclip.native-completion-preflight.v1",
|
||||
"sourceSha": "e74ed61a69fbdd8b3a8f15dd6456bc3140246e33",
|
||||
"sourceFingerprint": "a01593363d6512e30d8149fcf4f34adfff8b07aeef7f845f0c9bbed3cb7b979f",
|
||||
"fixtureFingerprint": "a50581c04f3d87843d69f92050712977f8e114e4c2f23f96f243fd5386119f27",
|
||||
"manifestFingerprint": "b92f3ab7d561188bc09214433b264f2e7810e8ccdc237f68caa82e1aecc1811e",
|
||||
"variant": "historical",
|
||||
"baseSha": "59c07ede72dc08b8aba149a01cc11e0b7a204621",
|
||||
"archiveSha": "9138f570c341c251a5727c32d6615ce238bc8e03",
|
||||
"sourceErrors": [],
|
||||
"immutable": true,
|
||||
"layering": true,
|
||||
"sourceMetadata": {
|
||||
"schema": "paperclip.native-completion-source-metadata.v1",
|
||||
"lineage": {
|
||||
"strategy": "full_ancestry",
|
||||
"shallow": true,
|
||||
"sha": "e74ed61a69fbdd8b3a8f15dd6456bc3140246e33",
|
||||
"baseSha": "59c07ede72dc08b8aba149a01cc11e0b7a204621",
|
||||
"anchor": null
|
||||
},
|
||||
"hydration": {
|
||||
"present": true,
|
||||
"verified": true,
|
||||
"archiveSha256": "86e4342be7c5b7cbc6ab49748c3b92a577bb8bfced890623e2317c8e39d4aa24",
|
||||
"checksumSha256": "fc9675af8e16510a54009ff3963d334d6f7dc22316c02c0fd3409da4a44413a8"
|
||||
},
|
||||
"worktreeEntries": [
|
||||
"?? runner-e2e-build/runner-e2e-build-bundle.tar.gz",
|
||||
"?? runner-e2e-build/runner-e2e-build-bundle.tar.gz.sha256"
|
||||
],
|
||||
"errors": []
|
||||
},
|
||||
"sourceMetadataErrors": [],
|
||||
"sourceMetadataFingerprint": "bd3d496010375d7fecd12d41d352bbde45fdf047191590d7d900100904109cce",
|
||||
"measuredAt": "2026-10-03T05:02:42.790Z",
|
||||
"providerCalls": 0,
|
||||
"live": "not_run",
|
||||
"expectedCells": 6,
|
||||
"expectedTurns": 6,
|
||||
"maximumAttemptsPerCell": 1,
|
||||
"setup": {
|
||||
"passed": true,
|
||||
"sdkExitCode": 0,
|
||||
"runnerTypeScriptExitCode": 0,
|
||||
"runnerdExitCode": null,
|
||||
"evidence": [
|
||||
{
|
||||
"file": "setup-sdk.txt",
|
||||
"sha256": "01ba4719c80b6fe911b091a7c05124b64eeece964e09c058ef8f9805daca546b"
|
||||
},
|
||||
{
|
||||
"file": "setup-runner-typescript.txt",
|
||||
"sha256": "239fcb77a2f4cecbaf744b3d82a8fb3ddc919d9c2d7e96e23ed0d3d6464a8167"
|
||||
},
|
||||
{
|
||||
"file": "setup-runnerd.txt",
|
||||
"sha256": "6224e6b1541ab3f1c9fec6eb08ef1ed95d5fd1700ab86131b824fd86f44fab3c"
|
||||
}
|
||||
],
|
||||
"runnerdProvenance": {
|
||||
"schema": "paperclip.native-completion-runnerd-provenance.v1",
|
||||
"mode": "trusted_hosted_archive",
|
||||
"passed": true,
|
||||
"selectedPath": "packages/paperclip-runner/runner/target/debug/paperclip-runnerd",
|
||||
"binarySha256": "8e4d54800e3b4b829621b12a9d8ce434c89445492abe7584d4465922e3ff5cea",
|
||||
"binaryBytes": 84271504,
|
||||
"archiveMemberBytes": 84271504,
|
||||
"sourceSha": "e74ed61a69fbdd8b3a8f15dd6456bc3140246e33",
|
||||
"sourceFingerprint": "a01593363d6512e30d8149fcf4f34adfff8b07aeef7f845f0c9bbed3cb7b979f",
|
||||
"archiveSha256": "86e4342be7c5b7cbc6ab49748c3b92a577bb8bfced890623e2317c8e39d4aa24",
|
||||
"workflowRunId": "8675309",
|
||||
"workflowRunAttempt": "1",
|
||||
"artifactName": "runner-e2e-build-e74ed61a69fbdd8b3a8f15dd6456bc3140246e33-8675309-1",
|
||||
"errors": []
|
||||
},
|
||||
"buildOutputFingerprint": "b131fe332da31bb4c1b3b8fbaf70f98e96f70de12c426dd087b47037f649b7d4",
|
||||
"runnerdSha256": "8e4d54800e3b4b829621b12a9d8ce434c89445492abe7584d4465922e3ff5cea",
|
||||
"runnerdSelectedPath": "packages/paperclip-runner/runner/target/debug/paperclip-runnerd",
|
||||
"runnerdSourceSha": "e74ed61a69fbdd8b3a8f15dd6456bc3140246e33",
|
||||
"runnerdSourceFingerprint": "a01593363d6512e30d8149fcf4f34adfff8b07aeef7f845f0c9bbed3cb7b979f"
|
||||
},
|
||||
"gates": [
|
||||
{
|
||||
"id": "NC-schemas",
|
||||
"name": "Variant-native completion schemas",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"files": [
|
||||
{
|
||||
"file": "src/contracts/completion-result.test.ts",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"requirements": [
|
||||
{
|
||||
"name": "distinguishes user-facing answer content",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "propagates answer and wait descriptions",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "requires a reason code for verification that was not run",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"total": 13,
|
||||
"passedTests": 13,
|
||||
"failedTests": 0,
|
||||
"pendingTests": 0,
|
||||
"evidence": {
|
||||
"file": "NC-schemas.json",
|
||||
"sha256": "c53cb8fdd50ab7cd7a3e2a53f0f9dc9f9f690cbcf136af2709a0cb216a75dab5"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-tools",
|
||||
"name": "Native tool delivery and retained provider catalogs",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"files": [
|
||||
{
|
||||
"file": "src/drivers/codex/codex-app-server-driver.lifecycle.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "src/drivers/runner-tool-bridge.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "src/drivers/opencode/mcp-bridge.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "src/live/runnerd-codex-transport.test.ts",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"requirements": [
|
||||
{
|
||||
"name": "runner semantic MCP bridge binds to loopback",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "OpenCode MCP bridge binds to loopback",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves stock Codex instructions on task recovery",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves stock Codex instructions on prepared recovery",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves stock Codex instructions on direct recovery",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "includes ACPX terminal tools in the authenticated bridge catalog",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"total": 222,
|
||||
"passedTests": 7,
|
||||
"failedTests": 0,
|
||||
"pendingTests": 215,
|
||||
"evidence": {
|
||||
"file": "NC-tools.json",
|
||||
"sha256": "a9616ba4d7493a6f720bfea4f43e642c40d348f0ffabed45faa6bda77940f72e"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-resume",
|
||||
"name": "Variant-native fingerprint and checkpoint refresh",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"files": [
|
||||
{
|
||||
"file": "server/src/services/native-runtime/native-session-resume.test.ts",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"requirements": [
|
||||
{
|
||||
"name": "refreshes retained 'completion descriptions'",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "refreshes retained 'task-bound human-input description'",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"total": 44,
|
||||
"passedTests": 2,
|
||||
"failedTests": 0,
|
||||
"pendingTests": 42,
|
||||
"evidence": {
|
||||
"file": "NC-resume.json",
|
||||
"sha256": "2f7ca7153ea5e1b50bc631af83c72c3f60bc3f10d8f390e6609be451153fd5f7"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-eval",
|
||||
"name": "Independent native oracle, defaults, admission and attempt policy",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"files": [
|
||||
{
|
||||
"file": "tests/runner-e2e/native-completion-scoring.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/native-completion-defaults.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/native-completion-admission.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/automatic-retry.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/context-integrity.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/context-integrity-evidence.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/context-integrity-flow-logs.test.ts",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"requirements": [
|
||||
{
|
||||
"name": "allows toolchain paths and excludes every present or future credential",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "retains credential-free prerequisites inside the exact campaign root",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "retains the first transient_infrastructure failure without a second attempt",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "retains the first provider_variance failure without a second attempt",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"total": 105,
|
||||
"passedTests": 105,
|
||||
"failedTests": 0,
|
||||
"pendingTests": 0,
|
||||
"evidence": {
|
||||
"file": "NC-eval.json",
|
||||
"sha256": "aa5d7befe0bd7ac69e67537b75f57270522cd2f22c980f810874a75010ecc571"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-node",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-node.txt",
|
||||
"sha256": "eddd84055b81f76da78ecd0c92a9d8e22f67fce054a612be8033ac7284397406"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-typecheck",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-typecheck.txt",
|
||||
"sha256": "01ba4719c80b6fe911b091a7c05124b64eeece964e09c058ef8f9805daca546b"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-discovery",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-discovery.txt",
|
||||
"sha256": "3097ab7907c3b49d43920fab50d0b180b70cb6895c0bd1a58f72fd740fec6567"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-hosted-runnerd",
|
||||
"name": "Trusted hosted runnerd provenance; Rust calibration not executed",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"executed": false,
|
||||
"calibration": "not_executed",
|
||||
"reuse": "trusted_same_run_build",
|
||||
"total": 0,
|
||||
"passedTests": 0,
|
||||
"evidence": {
|
||||
"file": "NC-hosted-runnerd.txt",
|
||||
"sha256": "0eb5ee0464c807e7af174833634f0e3fae6f099343207796ba88fbe27f8cadb2"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-manifest",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-manifest.txt",
|
||||
"sha256": "7f5d044db6a7813857e842095c5e3aa749a98570a96ff9939483de9452322502"
|
||||
}
|
||||
}
|
||||
],
|
||||
"passed": true
|
||||
}
|
||||
@@ -0,0 +1,336 @@
|
||||
{
|
||||
"schema": "paperclip.native-completion-preflight.v1",
|
||||
"sourceSha": "d6e59e4712a3158ab4cd7d58deff1389b4578c21",
|
||||
"sourceFingerprint": "88c8cc71ce04c3037ae311fd2aa8daaa083000ab031b2e01a0cf5598d646c456",
|
||||
"fixtureFingerprint": "a50581c04f3d87843d69f92050712977f8e114e4c2f23f96f243fd5386119f27",
|
||||
"manifestFingerprint": "b92f3ab7d561188bc09214433b264f2e7810e8ccdc237f68caa82e1aecc1811e",
|
||||
"variant": "candidate",
|
||||
"baseSha": "59c07ede72dc08b8aba149a01cc11e0b7a204621",
|
||||
"archiveSha": "9138f570c341c251a5727c32d6615ce238bc8e03",
|
||||
"sourceErrors": [],
|
||||
"immutable": true,
|
||||
"layering": true,
|
||||
"sourceMetadata": {
|
||||
"schema": "paperclip.native-completion-source-metadata.v1",
|
||||
"lineage": {
|
||||
"strategy": "full_ancestry",
|
||||
"shallow": true,
|
||||
"sha": "d6e59e4712a3158ab4cd7d58deff1389b4578c21",
|
||||
"baseSha": "59c07ede72dc08b8aba149a01cc11e0b7a204621",
|
||||
"anchor": null
|
||||
},
|
||||
"hydration": {
|
||||
"present": false,
|
||||
"verified": false,
|
||||
"archiveSha256": null,
|
||||
"checksumSha256": null
|
||||
},
|
||||
"worktreeEntries": [],
|
||||
"errors": []
|
||||
},
|
||||
"sourceMetadataErrors": [],
|
||||
"sourceMetadataFingerprint": "0b34119569af5ca4cb9a4443b7ed9f3983e93df17f0eeaf92a0410c1454d1724",
|
||||
"measuredAt": "2026-10-03T05:01:34.005Z",
|
||||
"providerCalls": 0,
|
||||
"live": "not_run",
|
||||
"expectedCells": 6,
|
||||
"expectedTurns": 6,
|
||||
"maximumAttemptsPerCell": 1,
|
||||
"setup": {
|
||||
"passed": true,
|
||||
"sdkExitCode": 0,
|
||||
"runnerTypeScriptExitCode": 0,
|
||||
"runnerdExitCode": 0,
|
||||
"evidence": [
|
||||
{
|
||||
"file": "setup-sdk.txt",
|
||||
"sha256": "01ba4719c80b6fe911b091a7c05124b64eeece964e09c058ef8f9805daca546b"
|
||||
},
|
||||
{
|
||||
"file": "setup-runner-typescript.txt",
|
||||
"sha256": "e45e5d6d0e72860b49f56e66049208e3a71bc0e9855692c08a97856e4c1dd955"
|
||||
},
|
||||
{
|
||||
"file": "setup-runnerd.txt",
|
||||
"sha256": "55f620e87dc9cee6e9e299c531e388c13a9985dc62d3c894ac5df284edec65e8"
|
||||
}
|
||||
],
|
||||
"runnerdProvenance": {
|
||||
"schema": "paperclip.native-completion-runnerd-provenance.v1",
|
||||
"mode": "fresh_local_build",
|
||||
"passed": true,
|
||||
"selectedPath": "packages/paperclip-runner/runner/target/debug/paperclip-runnerd",
|
||||
"binarySha256": "de11e42c462a3617ab8b8276f3f0e86e7f4a479e2d437eff2b3893e06dc39d0e",
|
||||
"binaryBytes": 84259808,
|
||||
"archiveMemberBytes": null,
|
||||
"sourceSha": "d6e59e4712a3158ab4cd7d58deff1389b4578c21",
|
||||
"sourceFingerprint": "88c8cc71ce04c3037ae311fd2aa8daaa083000ab031b2e01a0cf5598d646c456",
|
||||
"archiveSha256": null,
|
||||
"workflowRunId": null,
|
||||
"workflowRunAttempt": null,
|
||||
"artifactName": null,
|
||||
"errors": []
|
||||
},
|
||||
"buildOutputFingerprint": "d12136329d21552f65694670a8d7e41a4b821460c5e986dd7e1a8a471cfca451",
|
||||
"runnerdSha256": "de11e42c462a3617ab8b8276f3f0e86e7f4a479e2d437eff2b3893e06dc39d0e",
|
||||
"runnerdSelectedPath": "packages/paperclip-runner/runner/target/debug/paperclip-runnerd",
|
||||
"runnerdSourceSha": "d6e59e4712a3158ab4cd7d58deff1389b4578c21",
|
||||
"runnerdSourceFingerprint": "88c8cc71ce04c3037ae311fd2aa8daaa083000ab031b2e01a0cf5598d646c456"
|
||||
},
|
||||
"gates": [
|
||||
{
|
||||
"id": "NC-schemas",
|
||||
"name": "Variant-native completion schemas",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"files": [
|
||||
{
|
||||
"file": "src/contracts/completion-result.test.ts",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"requirements": [
|
||||
{
|
||||
"name": "distinguishes user-facing answer content",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "propagates answer and wait descriptions",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "requires a reason code for verification that was not run",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"total": 13,
|
||||
"passedTests": 13,
|
||||
"failedTests": 0,
|
||||
"pendingTests": 0,
|
||||
"evidence": {
|
||||
"file": "NC-schemas.json",
|
||||
"sha256": "beb9ffd8c3ec87a88dcc1e87a48eaf16cc89529025f616acf8563a08aa2b2cd8"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-tools",
|
||||
"name": "Native tool delivery and retained provider catalogs",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"files": [
|
||||
{
|
||||
"file": "src/drivers/codex/codex-app-server-driver.lifecycle.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "src/drivers/runner-tool-bridge.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "src/drivers/opencode/mcp-bridge.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "src/live/runnerd-codex-transport.test.ts",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"requirements": [
|
||||
{
|
||||
"name": "runner semantic MCP bridge binds to loopback",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "OpenCode MCP bridge binds to loopback",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves stock Codex instructions on task recovery",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves stock Codex instructions on prepared recovery",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves stock Codex instructions on direct recovery",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "includes ACPX terminal tools in the authenticated bridge catalog",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves answer and internal wait descriptions in the serialized native codex tool catalog",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves answer and internal wait descriptions in the serialized native opencode tool catalog",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves answer and internal wait descriptions in the serialized native claude_managed tool catalog",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves answer and internal wait descriptions in the serialized native aws_agentcore tool catalog",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves answer and internal wait descriptions in the serialized native acpx tool catalog",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"total": 226,
|
||||
"passedTests": 11,
|
||||
"failedTests": 0,
|
||||
"pendingTests": 215,
|
||||
"evidence": {
|
||||
"file": "NC-tools.json",
|
||||
"sha256": "8e1bdb447b10230758894733dc14a68eb0f6272aacfa24128201afaca668ff19"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-resume",
|
||||
"name": "Variant-native fingerprint and checkpoint refresh",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"files": [
|
||||
{
|
||||
"file": "server/src/services/native-runtime/native-session-resume.test.ts",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"requirements": [
|
||||
{
|
||||
"name": "refreshes retained 'completion descriptions'",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "refreshes retained 'task-bound human-input description'",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "native completion tool guidance",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"total": 45,
|
||||
"passedTests": 3,
|
||||
"failedTests": 0,
|
||||
"pendingTests": 42,
|
||||
"evidence": {
|
||||
"file": "NC-resume.json",
|
||||
"sha256": "d8a2df2cb840ad2d0a8461637c3661ac2d735af73a05bbec59879885aaa9ec04"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-eval",
|
||||
"name": "Independent native oracle, defaults, admission and attempt policy",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"files": [
|
||||
{
|
||||
"file": "tests/runner-e2e/native-completion-scoring.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/native-completion-defaults.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/native-completion-admission.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/automatic-retry.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/context-integrity.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/context-integrity-evidence.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/context-integrity-flow-logs.test.ts",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"requirements": [
|
||||
{
|
||||
"name": "allows toolchain paths and excludes every present or future credential",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "retains credential-free prerequisites inside the exact campaign root",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "retains the first transient_infrastructure failure without a second attempt",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "retains the first provider_variance failure without a second attempt",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"total": 105,
|
||||
"passedTests": 105,
|
||||
"failedTests": 0,
|
||||
"pendingTests": 0,
|
||||
"evidence": {
|
||||
"file": "NC-eval.json",
|
||||
"sha256": "6cfdf1ef34030e01d290dea7ba89e78212616ff266a18a86ea608b49b1bde576"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-node",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-node.txt",
|
||||
"sha256": "5ad4d9a57ff3a5cdb5c1e00ce1c618580458bf7e5875885058ed5e7f7cab3ffd"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-typecheck",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-typecheck.txt",
|
||||
"sha256": "01ba4719c80b6fe911b091a7c05124b64eeece964e09c058ef8f9805daca546b"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-rust-carrier",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-rust-carrier.txt",
|
||||
"sha256": "8b8ce3ae663605d5513e27315c9adaa72b555e6fcfce067038183327b52421a6"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-discovery",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-discovery.txt",
|
||||
"sha256": "3097ab7907c3b49d43920fab50d0b180b70cb6895c0bd1a58f72fd740fec6567"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-manifest",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-manifest.txt",
|
||||
"sha256": "7f5d044db6a7813857e842095c5e3aa749a98570a96ff9939483de9452322502"
|
||||
}
|
||||
}
|
||||
],
|
||||
"passed": true
|
||||
}
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"schema": "paperclip.native-completion-synthetic-hosted-calibration.v1",
|
||||
"synthetic": true,
|
||||
"actualGitHubWorkflow": false,
|
||||
"providerCalls": 0,
|
||||
"sourceSha": "d6e59e4712a3158ab4cd7d58deff1389b4578c21",
|
||||
"receiptPath": "/private/tmp/paperclip-native-calibrated-candidate-synthetic-hosted/native-completion-prerequisites/cbcbf605-d5af-4097-9e5d-8ba37ebb0b67/preflight.json",
|
||||
"archiveSha256": "bcc35dcd5dff3103c0ab44c418374c36bc7221b37d70ee0c9a2fba55093c81b2",
|
||||
"publicMetadata": {
|
||||
"GITHUB_ACTIONS": true,
|
||||
"GITHUB_RUN_ID": "8675309",
|
||||
"GITHUB_RUN_ATTEMPT": "1"
|
||||
},
|
||||
"prepareAndVerifyPassed": true
|
||||
}
|
||||
+345
@@ -0,0 +1,345 @@
|
||||
{
|
||||
"schema": "paperclip.native-completion-preflight.v1",
|
||||
"sourceSha": "d6e59e4712a3158ab4cd7d58deff1389b4578c21",
|
||||
"sourceFingerprint": "88c8cc71ce04c3037ae311fd2aa8daaa083000ab031b2e01a0cf5598d646c456",
|
||||
"fixtureFingerprint": "a50581c04f3d87843d69f92050712977f8e114e4c2f23f96f243fd5386119f27",
|
||||
"manifestFingerprint": "b92f3ab7d561188bc09214433b264f2e7810e8ccdc237f68caa82e1aecc1811e",
|
||||
"variant": "candidate",
|
||||
"baseSha": "59c07ede72dc08b8aba149a01cc11e0b7a204621",
|
||||
"archiveSha": "9138f570c341c251a5727c32d6615ce238bc8e03",
|
||||
"sourceErrors": [],
|
||||
"immutable": true,
|
||||
"layering": true,
|
||||
"sourceMetadata": {
|
||||
"schema": "paperclip.native-completion-source-metadata.v1",
|
||||
"lineage": {
|
||||
"strategy": "full_ancestry",
|
||||
"shallow": true,
|
||||
"sha": "d6e59e4712a3158ab4cd7d58deff1389b4578c21",
|
||||
"baseSha": "59c07ede72dc08b8aba149a01cc11e0b7a204621",
|
||||
"anchor": null
|
||||
},
|
||||
"hydration": {
|
||||
"present": true,
|
||||
"verified": true,
|
||||
"archiveSha256": "bcc35dcd5dff3103c0ab44c418374c36bc7221b37d70ee0c9a2fba55093c81b2",
|
||||
"checksumSha256": "c804c3b014ccf7c2c30dd3bc3956ee34c029d1627dea05e7b0f17406e83f82e0"
|
||||
},
|
||||
"worktreeEntries": [
|
||||
"?? runner-e2e-build/runner-e2e-build-bundle.tar.gz",
|
||||
"?? runner-e2e-build/runner-e2e-build-bundle.tar.gz.sha256"
|
||||
],
|
||||
"errors": []
|
||||
},
|
||||
"sourceMetadataErrors": [],
|
||||
"sourceMetadataFingerprint": "65f5f8996c5596fbb53575aa9b063e330ea7913781f9627608fb77a95753b652",
|
||||
"measuredAt": "2026-10-03T05:02:38.374Z",
|
||||
"providerCalls": 0,
|
||||
"live": "not_run",
|
||||
"expectedCells": 6,
|
||||
"expectedTurns": 6,
|
||||
"maximumAttemptsPerCell": 1,
|
||||
"setup": {
|
||||
"passed": true,
|
||||
"sdkExitCode": 0,
|
||||
"runnerTypeScriptExitCode": 0,
|
||||
"runnerdExitCode": null,
|
||||
"evidence": [
|
||||
{
|
||||
"file": "setup-sdk.txt",
|
||||
"sha256": "01ba4719c80b6fe911b091a7c05124b64eeece964e09c058ef8f9805daca546b"
|
||||
},
|
||||
{
|
||||
"file": "setup-runner-typescript.txt",
|
||||
"sha256": "e45e5d6d0e72860b49f56e66049208e3a71bc0e9855692c08a97856e4c1dd955"
|
||||
},
|
||||
{
|
||||
"file": "setup-runnerd.txt",
|
||||
"sha256": "01847c9a03780f7a30baa436f65bdbb29577c967909e145cdb9257681ac8dded"
|
||||
}
|
||||
],
|
||||
"runnerdProvenance": {
|
||||
"schema": "paperclip.native-completion-runnerd-provenance.v1",
|
||||
"mode": "trusted_hosted_archive",
|
||||
"passed": true,
|
||||
"selectedPath": "packages/paperclip-runner/runner/target/debug/paperclip-runnerd",
|
||||
"binarySha256": "de11e42c462a3617ab8b8276f3f0e86e7f4a479e2d437eff2b3893e06dc39d0e",
|
||||
"binaryBytes": 84259808,
|
||||
"archiveMemberBytes": 84259808,
|
||||
"sourceSha": "d6e59e4712a3158ab4cd7d58deff1389b4578c21",
|
||||
"sourceFingerprint": "88c8cc71ce04c3037ae311fd2aa8daaa083000ab031b2e01a0cf5598d646c456",
|
||||
"archiveSha256": "bcc35dcd5dff3103c0ab44c418374c36bc7221b37d70ee0c9a2fba55093c81b2",
|
||||
"workflowRunId": "8675309",
|
||||
"workflowRunAttempt": "1",
|
||||
"artifactName": "runner-e2e-build-d6e59e4712a3158ab4cd7d58deff1389b4578c21-8675309-1",
|
||||
"errors": []
|
||||
},
|
||||
"buildOutputFingerprint": "d12136329d21552f65694670a8d7e41a4b821460c5e986dd7e1a8a471cfca451",
|
||||
"runnerdSha256": "de11e42c462a3617ab8b8276f3f0e86e7f4a479e2d437eff2b3893e06dc39d0e",
|
||||
"runnerdSelectedPath": "packages/paperclip-runner/runner/target/debug/paperclip-runnerd",
|
||||
"runnerdSourceSha": "d6e59e4712a3158ab4cd7d58deff1389b4578c21",
|
||||
"runnerdSourceFingerprint": "88c8cc71ce04c3037ae311fd2aa8daaa083000ab031b2e01a0cf5598d646c456"
|
||||
},
|
||||
"gates": [
|
||||
{
|
||||
"id": "NC-schemas",
|
||||
"name": "Variant-native completion schemas",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"files": [
|
||||
{
|
||||
"file": "src/contracts/completion-result.test.ts",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"requirements": [
|
||||
{
|
||||
"name": "distinguishes user-facing answer content",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "propagates answer and wait descriptions",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "requires a reason code for verification that was not run",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"total": 13,
|
||||
"passedTests": 13,
|
||||
"failedTests": 0,
|
||||
"pendingTests": 0,
|
||||
"evidence": {
|
||||
"file": "NC-schemas.json",
|
||||
"sha256": "2795e9b860fa7544b09eac30bf7a63ad21b1fe13e6fdb763250aa33dc6bfdfca"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-tools",
|
||||
"name": "Native tool delivery and retained provider catalogs",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"files": [
|
||||
{
|
||||
"file": "src/drivers/codex/codex-app-server-driver.lifecycle.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "src/drivers/runner-tool-bridge.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "src/drivers/opencode/mcp-bridge.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "src/live/runnerd-codex-transport.test.ts",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"requirements": [
|
||||
{
|
||||
"name": "runner semantic MCP bridge binds to loopback",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "OpenCode MCP bridge binds to loopback",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves stock Codex instructions on task recovery",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves stock Codex instructions on prepared recovery",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves stock Codex instructions on direct recovery",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "includes ACPX terminal tools in the authenticated bridge catalog",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves answer and internal wait descriptions in the serialized native codex tool catalog",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves answer and internal wait descriptions in the serialized native opencode tool catalog",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves answer and internal wait descriptions in the serialized native claude_managed tool catalog",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves answer and internal wait descriptions in the serialized native aws_agentcore tool catalog",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "preserves answer and internal wait descriptions in the serialized native acpx tool catalog",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"total": 226,
|
||||
"passedTests": 11,
|
||||
"failedTests": 0,
|
||||
"pendingTests": 215,
|
||||
"evidence": {
|
||||
"file": "NC-tools.json",
|
||||
"sha256": "370be266202fa3f24687f1961723caffd25453f0855560a02820cc97f94f1fa1"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-resume",
|
||||
"name": "Variant-native fingerprint and checkpoint refresh",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"files": [
|
||||
{
|
||||
"file": "server/src/services/native-runtime/native-session-resume.test.ts",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"requirements": [
|
||||
{
|
||||
"name": "refreshes retained 'completion descriptions'",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "refreshes retained 'task-bound human-input description'",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "native completion tool guidance",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"total": 45,
|
||||
"passedTests": 3,
|
||||
"failedTests": 0,
|
||||
"pendingTests": 42,
|
||||
"evidence": {
|
||||
"file": "NC-resume.json",
|
||||
"sha256": "ae13817e082482e578b29325badf411c19254ba1329c30c45c3168629dab32a3"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-eval",
|
||||
"name": "Independent native oracle, defaults, admission and attempt policy",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"files": [
|
||||
{
|
||||
"file": "tests/runner-e2e/native-completion-scoring.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/native-completion-defaults.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/native-completion-admission.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/automatic-retry.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/context-integrity.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/context-integrity-evidence.test.ts",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"file": "tests/runner-e2e/context-integrity-flow-logs.test.ts",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"requirements": [
|
||||
{
|
||||
"name": "allows toolchain paths and excludes every present or future credential",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "retains credential-free prerequisites inside the exact campaign root",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "retains the first transient_infrastructure failure without a second attempt",
|
||||
"passed": true
|
||||
},
|
||||
{
|
||||
"name": "retains the first provider_variance failure without a second attempt",
|
||||
"passed": true
|
||||
}
|
||||
],
|
||||
"total": 105,
|
||||
"passedTests": 105,
|
||||
"failedTests": 0,
|
||||
"pendingTests": 0,
|
||||
"evidence": {
|
||||
"file": "NC-eval.json",
|
||||
"sha256": "1ccdd029f8a63262a96a2fec282017abcace3001195b16eefbb640118ae966dc"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-node",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-node.txt",
|
||||
"sha256": "9fc98ebd69aef3664f5f517112c1471956db255e6eca39e272f847f201d1e78a"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-typecheck",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-typecheck.txt",
|
||||
"sha256": "01ba4719c80b6fe911b091a7c05124b64eeece964e09c058ef8f9805daca546b"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-discovery",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-discovery.txt",
|
||||
"sha256": "3097ab7907c3b49d43920fab50d0b180b70cb6895c0bd1a58f72fd740fec6567"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-hosted-runnerd",
|
||||
"name": "Trusted hosted runnerd provenance; Rust calibration not executed",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"executed": false,
|
||||
"calibration": "not_executed",
|
||||
"reuse": "trusted_same_run_build",
|
||||
"total": 0,
|
||||
"passedTests": 0,
|
||||
"evidence": {
|
||||
"file": "NC-hosted-runnerd.txt",
|
||||
"sha256": "bb1b62a609be3c43d4b3704fa3d5fd444b49ac77296a90baa1476b38bb7de4e5"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "NC-manifest",
|
||||
"passed": true,
|
||||
"exitCode": 0,
|
||||
"evidence": {
|
||||
"file": "NC-manifest.txt",
|
||||
"sha256": "7f5d044db6a7813857e842095c5e3aa749a98570a96ff9939483de9452322502"
|
||||
}
|
||||
}
|
||||
],
|
||||
"passed": true
|
||||
}
|
||||
+128
@@ -0,0 +1,128 @@
|
||||
{
|
||||
"schema": "paperclip.native-completion-hosted-frame-replay.v1",
|
||||
"providerCalls": 0,
|
||||
"originalVerdictsChanged": false,
|
||||
"actualLauncherReplayed": false,
|
||||
"rows": [
|
||||
{
|
||||
"variant": "candidate",
|
||||
"sourceSha": "0a9c5a75164cd0b02115ff12273aadb6a86c9464",
|
||||
"receiptSha256": "e71e8216914c2f9432dfafa8351780abfdadaf9ed658b808bc921fe166c6403e",
|
||||
"logSha256": "f9fa01b71a6561f03154621ce5c19917bafb9614aa7d3d4a16cadeb169607d01",
|
||||
"matchesHash": true,
|
||||
"framedProofPass": true,
|
||||
"originalPassed": false,
|
||||
"providerCalls": 0
|
||||
},
|
||||
{
|
||||
"variant": "candidate",
|
||||
"sourceSha": "0a9c5a75164cd0b02115ff12273aadb6a86c9464",
|
||||
"receiptSha256": "e4aa804ea6215c0eb6bc2df975f591a64ccf3726529c16b00c9360a3866a03d2",
|
||||
"logSha256": "f9fa01b71a6561f03154621ce5c19917bafb9614aa7d3d4a16cadeb169607d01",
|
||||
"matchesHash": true,
|
||||
"framedProofPass": true,
|
||||
"originalPassed": false,
|
||||
"providerCalls": 0
|
||||
},
|
||||
{
|
||||
"variant": "candidate",
|
||||
"sourceSha": "0a9c5a75164cd0b02115ff12273aadb6a86c9464",
|
||||
"receiptSha256": "7d295024d23dd81bf7d56e807378c0a2ff94faf49886e0739aa42876a641a058",
|
||||
"logSha256": "f9fa01b71a6561f03154621ce5c19917bafb9614aa7d3d4a16cadeb169607d01",
|
||||
"matchesHash": true,
|
||||
"framedProofPass": true,
|
||||
"originalPassed": false,
|
||||
"providerCalls": 0
|
||||
},
|
||||
{
|
||||
"variant": "candidate",
|
||||
"sourceSha": "0a9c5a75164cd0b02115ff12273aadb6a86c9464",
|
||||
"receiptSha256": "263ee5cf8d11dc41b1e9ae716f9e12e38a2f6b145a081918d92c27f9b32efe5c",
|
||||
"logSha256": "f9fa01b71a6561f03154621ce5c19917bafb9614aa7d3d4a16cadeb169607d01",
|
||||
"matchesHash": true,
|
||||
"framedProofPass": true,
|
||||
"originalPassed": false,
|
||||
"providerCalls": 0
|
||||
},
|
||||
{
|
||||
"variant": "candidate",
|
||||
"sourceSha": "0a9c5a75164cd0b02115ff12273aadb6a86c9464",
|
||||
"receiptSha256": "4c6c4a1ab533e4d590cd642f133625f1fb1a2325279279514e200075f74f66e3",
|
||||
"logSha256": "f9fa01b71a6561f03154621ce5c19917bafb9614aa7d3d4a16cadeb169607d01",
|
||||
"matchesHash": true,
|
||||
"framedProofPass": true,
|
||||
"originalPassed": false,
|
||||
"providerCalls": 0
|
||||
},
|
||||
{
|
||||
"variant": "candidate",
|
||||
"sourceSha": "0a9c5a75164cd0b02115ff12273aadb6a86c9464",
|
||||
"receiptSha256": "2b336a30defb0c0cd5c481b28bccac4c2d7b61b012b0b7aecd3cab9b3aa78c83",
|
||||
"logSha256": "f9fa01b71a6561f03154621ce5c19917bafb9614aa7d3d4a16cadeb169607d01",
|
||||
"matchesHash": true,
|
||||
"framedProofPass": true,
|
||||
"originalPassed": false,
|
||||
"providerCalls": 0
|
||||
},
|
||||
{
|
||||
"variant": "baseline",
|
||||
"sourceSha": "00a761b967f9f73b0f45069c0ba828fae277a76e",
|
||||
"receiptSha256": "505e2b89978aeef25b859e942a472c574f5807aa20c2275341e5968a3bbb4392",
|
||||
"logSha256": "8cde738885a32c3ba83e20cde54dd065c5cdde25449db1d4dc4cf0e3719f071a",
|
||||
"matchesHash": true,
|
||||
"framedProofPass": true,
|
||||
"originalPassed": false,
|
||||
"providerCalls": 0
|
||||
},
|
||||
{
|
||||
"variant": "baseline",
|
||||
"sourceSha": "00a761b967f9f73b0f45069c0ba828fae277a76e",
|
||||
"receiptSha256": "b9b67ff51d8ab679d14926869418e5d5a920bbf9c994900892fa61241467afc2",
|
||||
"logSha256": "8cde738885a32c3ba83e20cde54dd065c5cdde25449db1d4dc4cf0e3719f071a",
|
||||
"matchesHash": true,
|
||||
"framedProofPass": true,
|
||||
"originalPassed": false,
|
||||
"providerCalls": 0
|
||||
},
|
||||
{
|
||||
"variant": "baseline",
|
||||
"sourceSha": "00a761b967f9f73b0f45069c0ba828fae277a76e",
|
||||
"receiptSha256": "ec044f5520cd07ff349fd1f6051bc4a96de8c3bfaa247a09394e1c6f949559fa",
|
||||
"logSha256": "8cde738885a32c3ba83e20cde54dd065c5cdde25449db1d4dc4cf0e3719f071a",
|
||||
"matchesHash": true,
|
||||
"framedProofPass": true,
|
||||
"originalPassed": false,
|
||||
"providerCalls": 0
|
||||
},
|
||||
{
|
||||
"variant": "baseline",
|
||||
"sourceSha": "00a761b967f9f73b0f45069c0ba828fae277a76e",
|
||||
"receiptSha256": "d4422c6637b0cf9ff38edd06dd0cac7485e3685755c633f14bc905c2ce9aab21",
|
||||
"logSha256": "8cde738885a32c3ba83e20cde54dd065c5cdde25449db1d4dc4cf0e3719f071a",
|
||||
"matchesHash": true,
|
||||
"framedProofPass": true,
|
||||
"originalPassed": false,
|
||||
"providerCalls": 0
|
||||
},
|
||||
{
|
||||
"variant": "baseline",
|
||||
"sourceSha": "00a761b967f9f73b0f45069c0ba828fae277a76e",
|
||||
"receiptSha256": "ca5deb11c6215ccfbb2479c5f57c585dd2d03451cb6f8488a3999dc1da13ae57",
|
||||
"logSha256": "8cde738885a32c3ba83e20cde54dd065c5cdde25449db1d4dc4cf0e3719f071a",
|
||||
"matchesHash": true,
|
||||
"framedProofPass": true,
|
||||
"originalPassed": false,
|
||||
"providerCalls": 0
|
||||
},
|
||||
{
|
||||
"variant": "baseline",
|
||||
"sourceSha": "00a761b967f9f73b0f45069c0ba828fae277a76e",
|
||||
"receiptSha256": "f191191bf70dfe08ca60d33404d271f02a211adc5c0a448c273f25ef06827d23",
|
||||
"logSha256": "8cde738885a32c3ba83e20cde54dd065c5cdde25449db1d4dc4cf0e3719f071a",
|
||||
"matchesHash": true,
|
||||
"framedProofPass": true,
|
||||
"originalPassed": false,
|
||||
"providerCalls": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
+20
@@ -0,0 +1,20 @@
|
||||
// Provider-free synthetic hosted metadata/hydration calibration; never dispatches a workflow.
|
||||
import {spawnSync} from "node:child_process";
|
||||
import {mkdirSync,writeFileSync,readFileSync,existsSync} from "node:fs";
|
||||
import {createHash} from "node:crypto";
|
||||
import {resolve,join} from "node:path";
|
||||
import {pathToFileURL} from "node:url";
|
||||
const root=resolve(process.argv[2]),output=resolve(process.argv[3]);
|
||||
const sha=spawnSync("git",["rev-parse","HEAD"],{cwd:root,encoding:"utf8"}).stdout.trim();
|
||||
const hydration=join(root,"runner-e2e-build");if(existsSync(hydration))throw Error("Refuse to replace existing hydration evidence");
|
||||
mkdirSync(hydration);mkdirSync(output,{recursive:true});
|
||||
const archive=join(hydration,"runner-e2e-build-bundle.tar.gz");
|
||||
const member="packages/paperclip-runner/runner/target/debug/paperclip-runnerd";
|
||||
const packed=spawnSync("tar",["-czf",archive,member],{cwd:root});if(packed.status!==0)throw Error("Synthetic archive failed");
|
||||
const archiveSha=createHash("sha256").update(readFileSync(archive)).digest("hex");
|
||||
writeFileSync(archive+".sha256",`${archiveSha} runner-e2e-build-bundle.tar.gz\n`);
|
||||
process.env.GITHUB_ACTIONS="true";process.env.GITHUB_RUN_ID="8675309";process.env.GITHUB_RUN_ATTEMPT="1";process.env.PAPERCLIP_RUNNER_E2E_SOURCE_SHA=sha;
|
||||
const {prepareNativeCompletionPreflight}=await import(pathToFileURL(join(root,"tests/runner-e2e/native-completion-admission.ts")));
|
||||
const receiptPath=prepareNativeCompletionPreflight(output);
|
||||
writeFileSync(join(output,"synthetic-calibration.json"),JSON.stringify({schema:"paperclip.native-completion-synthetic-hosted-calibration.v1",synthetic:true,actualGitHubWorkflow:false,providerCalls:0,sourceSha:sha,receiptPath,archiveSha256:archiveSha,publicMetadata:{GITHUB_ACTIONS:true,GITHUB_RUN_ID:"8675309",GITHUB_RUN_ATTEMPT:"1"},prepareAndVerifyPassed:true},null,2)+"\n");
|
||||
console.log(`Synthetic hosted prepare+verify PASS: ${receiptPath}`);
|
||||
@@ -0,0 +1,296 @@
|
||||
{
|
||||
"schema": "paperclip.native-completion-calibrated-manifest.v1",
|
||||
"baseSha": "59c07ede72dc08b8aba149a01cc11e0b7a204621",
|
||||
"sources": {
|
||||
"candidate": "d6e59e4712a3158ab4cd7d58deff1389b4578c21",
|
||||
"baseline": "e74ed61a69fbdd8b3a8f15dd6456bc3140246e33"
|
||||
},
|
||||
"declaredImmediateParents": {
|
||||
"candidate": "0a9c5a75164cd0b02115ff12273aadb6a86c9464",
|
||||
"historical": "00a761b967f9f73b0f45069c0ba828fae277a76e"
|
||||
},
|
||||
"targetBranches": {
|
||||
"candidate": "codex/native-completion-master-calibrated-candidate",
|
||||
"baseline": "codex/native-completion-master-calibrated-baseline"
|
||||
},
|
||||
"admissions": {
|
||||
"candidate": {
|
||||
"local": {
|
||||
"path": "doc/plans/2026-10-02-native-completion-calibrated-admission/candidate-local.json",
|
||||
"sha256": "aa8cc5ce249a500b41764ec231ed02268ee09f900eef3687e6c11dcf2ea91331",
|
||||
"sourceFingerprint": "88c8cc71ce04c3037ae311fd2aa8daaa083000ab031b2e01a0cf5598d646c456",
|
||||
"fixtureFingerprint": "a50581c04f3d87843d69f92050712977f8e114e4c2f23f96f243fd5386119f27",
|
||||
"manifestFingerprint": "b92f3ab7d561188bc09214433b264f2e7810e8ccdc237f68caa82e1aecc1811e",
|
||||
"passed": true,
|
||||
"providerCalls": 0,
|
||||
"actualLauncherPrepareAndVerify": true,
|
||||
"synthetic": false,
|
||||
"selectedTypeScriptAssertions": 132,
|
||||
"explicitlySkippedTypeScriptAssertions": 257,
|
||||
"nodeCalibrations": 128,
|
||||
"rustCalibrations": 1,
|
||||
"runnerdProvenance": {
|
||||
"schema": "paperclip.native-completion-runnerd-provenance.v1",
|
||||
"mode": "fresh_local_build",
|
||||
"passed": true,
|
||||
"selectedPath": "packages/paperclip-runner/runner/target/debug/paperclip-runnerd",
|
||||
"binarySha256": "de11e42c462a3617ab8b8276f3f0e86e7f4a479e2d437eff2b3893e06dc39d0e",
|
||||
"binaryBytes": 84259808,
|
||||
"archiveMemberBytes": null,
|
||||
"sourceSha": "d6e59e4712a3158ab4cd7d58deff1389b4578c21",
|
||||
"sourceFingerprint": "88c8cc71ce04c3037ae311fd2aa8daaa083000ab031b2e01a0cf5598d646c456",
|
||||
"archiveSha256": null,
|
||||
"workflowRunId": null,
|
||||
"workflowRunAttempt": null,
|
||||
"artifactName": null,
|
||||
"errors": []
|
||||
}
|
||||
},
|
||||
"syntheticHosted": {
|
||||
"path": "doc/plans/2026-10-02-native-completion-calibrated-admission/candidate-syntheticHosted.json",
|
||||
"sha256": "3ced220c7e732c7ce132a1358bd7142534b06a31b249bfc7750358073f4b8417",
|
||||
"sourceFingerprint": "88c8cc71ce04c3037ae311fd2aa8daaa083000ab031b2e01a0cf5598d646c456",
|
||||
"fixtureFingerprint": "a50581c04f3d87843d69f92050712977f8e114e4c2f23f96f243fd5386119f27",
|
||||
"manifestFingerprint": "b92f3ab7d561188bc09214433b264f2e7810e8ccdc237f68caa82e1aecc1811e",
|
||||
"passed": true,
|
||||
"providerCalls": 0,
|
||||
"actualLauncherPrepareAndVerify": true,
|
||||
"synthetic": true,
|
||||
"selectedTypeScriptAssertions": 132,
|
||||
"explicitlySkippedTypeScriptAssertions": 257,
|
||||
"nodeCalibrations": 128,
|
||||
"rustCalibrations": 0,
|
||||
"runnerdProvenance": {
|
||||
"schema": "paperclip.native-completion-runnerd-provenance.v1",
|
||||
"mode": "trusted_hosted_archive",
|
||||
"passed": true,
|
||||
"selectedPath": "packages/paperclip-runner/runner/target/debug/paperclip-runnerd",
|
||||
"binarySha256": "de11e42c462a3617ab8b8276f3f0e86e7f4a479e2d437eff2b3893e06dc39d0e",
|
||||
"binaryBytes": 84259808,
|
||||
"archiveMemberBytes": 84259808,
|
||||
"sourceSha": "d6e59e4712a3158ab4cd7d58deff1389b4578c21",
|
||||
"sourceFingerprint": "88c8cc71ce04c3037ae311fd2aa8daaa083000ab031b2e01a0cf5598d646c456",
|
||||
"archiveSha256": "bcc35dcd5dff3103c0ab44c418374c36bc7221b37d70ee0c9a2fba55093c81b2",
|
||||
"workflowRunId": "8675309",
|
||||
"workflowRunAttempt": "1",
|
||||
"artifactName": "runner-e2e-build-d6e59e4712a3158ab4cd7d58deff1389b4578c21-8675309-1",
|
||||
"errors": []
|
||||
}
|
||||
}
|
||||
},
|
||||
"baseline": {
|
||||
"local": {
|
||||
"path": "doc/plans/2026-10-02-native-completion-calibrated-admission/baseline-local.json",
|
||||
"sha256": "fd38fc0ab324127aa6d464af54c0b32dc48ad3941eb08d08d011ca77c9e915ed",
|
||||
"sourceFingerprint": "a01593363d6512e30d8149fcf4f34adfff8b07aeef7f845f0c9bbed3cb7b979f",
|
||||
"fixtureFingerprint": "a50581c04f3d87843d69f92050712977f8e114e4c2f23f96f243fd5386119f27",
|
||||
"manifestFingerprint": "b92f3ab7d561188bc09214433b264f2e7810e8ccdc237f68caa82e1aecc1811e",
|
||||
"passed": true,
|
||||
"providerCalls": 0,
|
||||
"actualLauncherPrepareAndVerify": true,
|
||||
"synthetic": false,
|
||||
"selectedTypeScriptAssertions": 127,
|
||||
"explicitlySkippedTypeScriptAssertions": 257,
|
||||
"nodeCalibrations": 128,
|
||||
"rustCalibrations": 1,
|
||||
"runnerdProvenance": {
|
||||
"schema": "paperclip.native-completion-runnerd-provenance.v1",
|
||||
"mode": "fresh_local_build",
|
||||
"passed": true,
|
||||
"selectedPath": "packages/paperclip-runner/runner/target/debug/paperclip-runnerd",
|
||||
"binarySha256": "8e4d54800e3b4b829621b12a9d8ce434c89445492abe7584d4465922e3ff5cea",
|
||||
"binaryBytes": 84271504,
|
||||
"archiveMemberBytes": null,
|
||||
"sourceSha": "e74ed61a69fbdd8b3a8f15dd6456bc3140246e33",
|
||||
"sourceFingerprint": "a01593363d6512e30d8149fcf4f34adfff8b07aeef7f845f0c9bbed3cb7b979f",
|
||||
"archiveSha256": null,
|
||||
"workflowRunId": null,
|
||||
"workflowRunAttempt": null,
|
||||
"artifactName": null,
|
||||
"errors": []
|
||||
}
|
||||
},
|
||||
"syntheticHosted": {
|
||||
"path": "doc/plans/2026-10-02-native-completion-calibrated-admission/baseline-syntheticHosted.json",
|
||||
"sha256": "22f66cf9e4114a9898299258a959147804a959bd6244d3e7a00b819c901fd34e",
|
||||
"sourceFingerprint": "a01593363d6512e30d8149fcf4f34adfff8b07aeef7f845f0c9bbed3cb7b979f",
|
||||
"fixtureFingerprint": "a50581c04f3d87843d69f92050712977f8e114e4c2f23f96f243fd5386119f27",
|
||||
"manifestFingerprint": "b92f3ab7d561188bc09214433b264f2e7810e8ccdc237f68caa82e1aecc1811e",
|
||||
"passed": true,
|
||||
"providerCalls": 0,
|
||||
"actualLauncherPrepareAndVerify": true,
|
||||
"synthetic": true,
|
||||
"selectedTypeScriptAssertions": 127,
|
||||
"explicitlySkippedTypeScriptAssertions": 257,
|
||||
"nodeCalibrations": 128,
|
||||
"rustCalibrations": 0,
|
||||
"runnerdProvenance": {
|
||||
"schema": "paperclip.native-completion-runnerd-provenance.v1",
|
||||
"mode": "trusted_hosted_archive",
|
||||
"passed": true,
|
||||
"selectedPath": "packages/paperclip-runner/runner/target/debug/paperclip-runnerd",
|
||||
"binarySha256": "8e4d54800e3b4b829621b12a9d8ce434c89445492abe7584d4465922e3ff5cea",
|
||||
"binaryBytes": 84271504,
|
||||
"archiveMemberBytes": 84271504,
|
||||
"sourceSha": "e74ed61a69fbdd8b3a8f15dd6456bc3140246e33",
|
||||
"sourceFingerprint": "a01593363d6512e30d8149fcf4f34adfff8b07aeef7f845f0c9bbed3cb7b979f",
|
||||
"archiveSha256": "86e4342be7c5b7cbc6ab49748c3b92a577bb8bfced890623e2317c8e39d4aa24",
|
||||
"workflowRunId": "8675309",
|
||||
"workflowRunAttempt": "1",
|
||||
"artifactName": "runner-e2e-build-e74ed61a69fbdd8b3a8f15dd6456bc3140246e33-8675309-1",
|
||||
"errors": []
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"syntheticHostedCalibration": {
|
||||
"actualGitHubWorkflow": false,
|
||||
"credentialAccess": false,
|
||||
"providerCalls": 0,
|
||||
"descriptorPaths": {
|
||||
"candidate": "doc/plans/2026-10-02-native-completion-calibrated-admission/candidate-synthetic-label.json",
|
||||
"baseline": "doc/plans/2026-10-02-native-completion-calibrated-admission/baseline-synthetic-label.json"
|
||||
}
|
||||
},
|
||||
"cellsPerVariant": [
|
||||
{
|
||||
"executionId": "native-completion.runner-codex.local.assigned-skill-explicit-invocation",
|
||||
"suiteDefinitionHash": "96e18a7bcde391304cbdb2e811276e95f7c6a99c01b183facd7c5e1e4a98363d",
|
||||
"profileId": "runner-codex",
|
||||
"provider": "codex",
|
||||
"model": "gpt-5.6-sol",
|
||||
"credential": "OPENAI_API_KEY",
|
||||
"environment": "local",
|
||||
"caseId": "assigned-skill-explicit-invocation",
|
||||
"expectedRunCount": 1,
|
||||
"automaticRetryPolicy": "single_attempt",
|
||||
"deadlineMs": 720000,
|
||||
"modelQualification": {
|
||||
"source": "adapter_constant",
|
||||
"qualificationId": "codex:qualified-model"
|
||||
}
|
||||
},
|
||||
{
|
||||
"executionId": "native-completion.runner-codex.local.native-blocked-report",
|
||||
"suiteDefinitionHash": "96e18a7bcde391304cbdb2e811276e95f7c6a99c01b183facd7c5e1e4a98363d",
|
||||
"profileId": "runner-codex",
|
||||
"provider": "codex",
|
||||
"model": "gpt-5.6-sol",
|
||||
"credential": "OPENAI_API_KEY",
|
||||
"environment": "local",
|
||||
"caseId": "native-blocked-report",
|
||||
"expectedRunCount": 1,
|
||||
"automaticRetryPolicy": "single_attempt",
|
||||
"deadlineMs": 300000,
|
||||
"modelQualification": {
|
||||
"source": "adapter_constant",
|
||||
"qualificationId": "codex:qualified-model"
|
||||
}
|
||||
},
|
||||
{
|
||||
"executionId": "native-completion.runner-opencode.local.assigned-skill-explicit-invocation",
|
||||
"suiteDefinitionHash": "96e18a7bcde391304cbdb2e811276e95f7c6a99c01b183facd7c5e1e4a98363d",
|
||||
"profileId": "runner-opencode",
|
||||
"provider": "opencode",
|
||||
"model": "openrouter/deepseek/deepseek-v4-flash-0731",
|
||||
"credential": "OPENROUTER_API_KEY",
|
||||
"environment": "local",
|
||||
"caseId": "assigned-skill-explicit-invocation",
|
||||
"expectedRunCount": 1,
|
||||
"automaticRetryPolicy": "single_attempt",
|
||||
"deadlineMs": 720000,
|
||||
"modelQualification": {
|
||||
"source": "adapter_constant",
|
||||
"qualificationId": "opencode:qualified-model"
|
||||
}
|
||||
},
|
||||
{
|
||||
"executionId": "native-completion.runner-opencode.local.native-blocked-report",
|
||||
"suiteDefinitionHash": "96e18a7bcde391304cbdb2e811276e95f7c6a99c01b183facd7c5e1e4a98363d",
|
||||
"profileId": "runner-opencode",
|
||||
"provider": "opencode",
|
||||
"model": "openrouter/deepseek/deepseek-v4-flash-0731",
|
||||
"credential": "OPENROUTER_API_KEY",
|
||||
"environment": "local",
|
||||
"caseId": "native-blocked-report",
|
||||
"expectedRunCount": 1,
|
||||
"automaticRetryPolicy": "single_attempt",
|
||||
"deadlineMs": 300000,
|
||||
"modelQualification": {
|
||||
"source": "adapter_constant",
|
||||
"qualificationId": "opencode:qualified-model"
|
||||
}
|
||||
},
|
||||
{
|
||||
"executionId": "native-completion.runner-acpx-claude.local.assigned-skill-explicit-invocation",
|
||||
"suiteDefinitionHash": "96e18a7bcde391304cbdb2e811276e95f7c6a99c01b183facd7c5e1e4a98363d",
|
||||
"profileId": "runner-acpx-claude",
|
||||
"provider": "acpx",
|
||||
"model": "claude-sonnet-5",
|
||||
"credential": "ANTHROPIC_API_KEY",
|
||||
"environment": "local",
|
||||
"caseId": "assigned-skill-explicit-invocation",
|
||||
"expectedRunCount": 1,
|
||||
"automaticRetryPolicy": "single_attempt",
|
||||
"deadlineMs": 720000,
|
||||
"modelQualification": {
|
||||
"source": "qualified_runner_profile",
|
||||
"qualificationId": "acpx:claude"
|
||||
}
|
||||
},
|
||||
{
|
||||
"executionId": "native-completion.runner-acpx-claude.local.native-blocked-report",
|
||||
"suiteDefinitionHash": "96e18a7bcde391304cbdb2e811276e95f7c6a99c01b183facd7c5e1e4a98363d",
|
||||
"profileId": "runner-acpx-claude",
|
||||
"provider": "acpx",
|
||||
"model": "claude-sonnet-5",
|
||||
"credential": "ANTHROPIC_API_KEY",
|
||||
"environment": "local",
|
||||
"caseId": "native-blocked-report",
|
||||
"expectedRunCount": 1,
|
||||
"automaticRetryPolicy": "single_attempt",
|
||||
"deadlineMs": 300000,
|
||||
"modelQualification": {
|
||||
"source": "qualified_runner_profile",
|
||||
"qualificationId": "acpx:claude"
|
||||
}
|
||||
}
|
||||
],
|
||||
"workflow": ".github/workflows/runner-full-stack-e2e.yml",
|
||||
"workflowDispatchRef": "master",
|
||||
"maximumCells": 12,
|
||||
"expectedProviderTurns": 12,
|
||||
"maximumAttemptsPerCell": 1,
|
||||
"automaticRetryPolicy": "single_attempt",
|
||||
"budgetMonthlyCentsPerCompanyAndAgent": 1000,
|
||||
"fixtureIdentityVerified": true,
|
||||
"onlyDeclaredElevenNativeSourcesDiffer": true,
|
||||
"fixedMasterContextVerified": true,
|
||||
"providerCallsSoFar": 0,
|
||||
"liveStatus": "admitted_not_dispatched",
|
||||
"workflowRuns": {},
|
||||
"preservedZeroProviderCohorts": [
|
||||
{
|
||||
"candidate": "e18c2cf9e96a4d31acb6d03ce918dfe223107d3f",
|
||||
"baseline": "459455acb11a012a97ad1b4afb77a1dc024a88bc",
|
||||
"runs": [
|
||||
37091690197,
|
||||
37091691408
|
||||
],
|
||||
"cells": 12,
|
||||
"providerCalls": 0,
|
||||
"classification": "pre_provider_source_admission"
|
||||
},
|
||||
{
|
||||
"candidate": "0a9c5a75164cd0b02115ff12273aadb6a86c9464",
|
||||
"baseline": "00a761b967f9f73b0f45069c0ba828fae277a76e",
|
||||
"runs": [
|
||||
37097177178,
|
||||
37097164241
|
||||
],
|
||||
"cells": 12,
|
||||
"providerCalls": 0,
|
||||
"classification": "pre_provider_calibration_mock"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,3 +1,15 @@
|
||||
# Native completion qualification: calibrated hosted boundary
|
||||
|
||||
**TL;DR: model performance remains unmeasured; six task pairs are pending.** The candidate `d6e59e4712a3158ab4cd7d58deff1389b4578c21` and historical-description baseline `e74ed61a69fbdd8b3a8f15dd6456bc3140246e33` now pass complete actual launcher prepare→verify in both fresh local and explicitly synthetic hosted modes. The latter reproduces verified archive hydration, public source/run metadata and captured provenance framing without credentials or providers. It is a provider-free calibration, **not an actual trusted GitHub run**.
|
||||
|
||||
The [immutable calibrated manifest](2026-10-02-native-completion-calibrated-manifest.json) lists the same six cells in each variant, twelve expected provider turns total, no automatic retry and unchanged deadlines/budgets/models/auth/default instructions. Candidate 132 / historical 127 selected TypeScript assertions, 128 Node calibrations and one fresh local Rust normalization assertion pass. Each has 257 unrelated TypeScript assertions explicitly skipped. Synthetic hosted receipts report zero Rust execution rather than reusing those counts. [Local and synthetic receipts](2026-10-02-native-completion-calibrated-admission) preserve exact source/build hashes and separate simulation labels.
|
||||
|
||||
Only the previously reviewed eleven native implementation/unit-test files differ between variants. All five setup repair files are identical: a controlled mock receipt SHA, first-line framed provenance parsing plus positive/negative calibration, and matching immutable parent declarations. Production default/manual/shared-prompt/operational-skill bytes still match master `59c07ede`. The verifier's exact-source rejection and all behavioral oracles remain strict.
|
||||
|
||||
Both previous twelve-cell hosted cohorts stopped before providers and remain preserved below. [The twelve-retained-log replay](2026-10-02-native-completion-calibrated-admission/retained-frame-replay.json) validates exact hashes/framed proofs with no change to original failing verdicts. No model behavior reroll has occurred. Actual matched dispatch is the next step; this qualification does not measure fixed native prompt removal or general coding quality.
|
||||
|
||||
## Preserved prior qualification stages
|
||||
|
||||
# Native completion qualification on current master context
|
||||
|
||||
**TL;DR: task performance is still unmeasured.** All twelve cells in the corrected `0a9c5a7` / `00a761b` cohort stopped before providers: source bytes, shallow lineage, verified hydration and selected runner binary passed, but one admission unit test supplied a mocked valid receipt without its source SHA. The real immutable-source verifier correctly rejected that mock under hosted metadata. Zero provider calls and zero graded task pairs are confirmed by [all twelve retained receipts](2026-10-02-native-completion-qualified-hosted-setup.json). Six behavioral pairs remain pending; there are no measured newly failing or newly passing task outcomes.
|
||||
|
||||
@@ -506,3 +506,5 @@ PR #14961 is now independent of #14948 and based on master. Candidate `e18c2cf9e
|
||||
PR #14961 remains draft and unmerged. Corrected standalone candidate 0a9c5a751 / historical 00a761b96 preserve master 59 defaults/manual/shared/skills, differing only in the original eleven native description/refresh implementation and unit-test paths. Actual launcher prepare+verify admission passes on both. Six paired live outcomes are pending; the original twelve pre-provider failures and all local setup/calibration failures remain inspectable in the native report/recovery manifest. Closed terminal names and strict same-call grading are common to both variants; anonymous historical OpenCode evidence is not regraded. Hosted Rust calibration is explicitly not executed, with trusted same-run selected-binary proof; exact local Rust calibration and normal CI are separate evidence. No behavior rerolls or additional paid breadth are authorized.
|
||||
|
||||
The selected #14961 `0a9c5a7` / `00a761b` hosted cohort also stopped before providers. All twelve receipts prove zero calls; source isolation, lineage, hydration and selected native binary pass. One unit calibration omitted the source SHA from its mocked valid receipt, causing strict verification to reject it under hosted metadata. [The preserved twelve-receipt audit](2026-10-02-native-completion-qualified-hosted-setup.json) is a setup result; six behavioral pairs remain unmeasured. Only that test setup and the next exact parent-anchor declarations are being corrected.
|
||||
|
||||
Selected #14961 now freezes `d6e59e471` / `e74ed61a6` after the approved five-file setup-only repair. Both exact refs pass actual launcher local and explicitly synthetic hosted prepare→verify (no credentials/providers): 132/127 selected TypeScript, 128 Node each, one local Rust calibration each; synthetic mode truthfully records no Rust execution. [The calibrated immutable manifest](2026-10-02-native-completion-calibrated-manifest.json) keeps exactly six pairs/twelve initial expected provider turns, strict oracles and single attempts. Prior twelve-cell zero-provider setup cohorts remain intact; model outcomes are pending.
|
||||
Reference in new issue
Block a user