Jannik/PaperClipAI
1
0 Fork 0
mirror of https://github.com/paperclipai/paperclip.git synced 2026-11-06 23:20:53 +01:00
Code Issues Packages Projects Releases Wiki Activity

Record isolated two-case initial qualification and terminal reconciliation

Browse Source
This commit is contained in:
Dotta committed 2026-10-27 05:39:51 -05:00
1 parent 770f1c30e1
commit b602e342da
2 files changed
+112 -7
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/runner-e2e/chat-campaign-manifest.json
+107 -2
View File
@@ -3075,7 +3075,61 @@
"readiness": "implemented",
"executionId": "chat-features.runner-codex-subscription.local.companies.archive-company",
"blocker": null,
"attempts": [],
"attempts": [
{
"ordinal": 1,
"outcome": "passed",
"executionId": "chat-features.runner-codex-subscription.local.companies.archive-company",
"startedAt": "2026-10-27T10:29:19.521Z",
"finishedAt": "2026-10-27T10:31:23.533Z",
"sourceRevision": "c167a54162fadffe665b4d35a7a1308c6233b75d",
"workingTreeDigest": "6251a7763d81986af3d43a142a52c702da1bde2b57cee5aef2606e4418ccc698",
"definitionDigest": "e45461119cd11cbc7d9f3659a35bbd7a6c1ac72d5c5b2e4f187f97210ac8c7c7",
"suiteDefinitionDigest": "c0a8d311ea4dc7616bc8cef7a815457e5c013bd491d2ac6510f62500d3d0ac25",
"graderDigest": "e45461119cd11cbc7d9f3659a35bbd7a6c1ac72d5c5b2e4f187f97210ac8c7c7",
"model": "gpt-5.6-sol",
"profile": "runner-codex-subscription",
"environment": "local",
"automaticRetries": 0,
"correction": null,
"classification": "provisional_initial_pass_pending_final_closure",
"observedFailure": null,
"evidencePaths": [
"tests/runner-e2e/results/chat-catalog-campaign/two-lane-initial-pair-c167a54162.json",
"tests/runner-e2e/results/two-lane-initial-c167a54162fa-b95423a10d79997385db/chat-features/runner-codex-subscription/local/companies.archive-company/attempt-1/result.json",
"tests/runner-e2e/results/chat-catalog-campaign/active-companies.archive-company.json",
"tests/runner-e2e/results/chat-catalog-campaign/initial-pass-identity-review-companies.archive-company.json",
"tests/runner-e2e/results/chat-catalog-campaign/operations/two-lane-exact-absence-c167.json",
"tests/runner-e2e/results/chat-catalog-campaign/operations/two-lane-archive-replayed-completion.json"
],
"usage": {
"costUsd": null,
"tokens": 541825,
"coverage": "Actual heartbeat usage receipts, including cache; subscription cost unpriced unless complete billing; fixture costs excluded."
},
"cleanup": "passed",
"corePrDependencies": [],
"databaseLane": {
"lane": "owned-docker-postgres",
"image": "postgres@sha256:74935e72241653ca55e0414067e6d8763aceb8a810eb51b452253ec3dcfc4336",
"imageId": "sha256:74935e72241653ca55e0414067e6d8763aceb8a810eb51b452253ec3dcfc4336",
"version": "18.6-1.pgdg13+2"
},
"productIdentity": {
"kind": "source-build",
"productionSourceRevision": "8373d7867963674ff960d2345d0d28086f799bc7",
"snapshotSourceRevision": "c167a54162fadffe665b4d35a7a1308c6233b75d",
"nativeBinarySha256": "9d8af6b85b836a03092ade2273be6f29f5c2f6ec67ee891d83ee9693ba39d3b4",
"workspaceBuildDigest": "222e10a8a2a20d3015ec4470b952e2dd9b927dfe9390c4a5ed1e19d740c0e35b",
"receiptPaths": [
"tests/runner-e2e/results/chat-catalog-campaign/snapshot-two-lane-c167a54162.json",
"tests/runner-e2e/results/chat-catalog-campaign/snapshot-10d0ce63610.json",
"tests/runner-e2e/results/chat-catalog-campaign/snapshot-0fdcb539a8.json"
],
"coreCandidate": false
}
}
],
"qualifyingDefinitionDigest": "e45461119cd11cbc7d9f3659a35bbd7a6c1ac72d5c5b2e4f187f97210ac8c7c7",
"qualifyingGraderDigest": "e45461119cd11cbc7d9f3659a35bbd7a6c1ac72d5c5b2e4f187f97210ac8c7c7",
"productPolicy": {
@@ -3405,7 +3459,58 @@
"readiness": "implemented",
"executionId": "chat-features.runner-codex-subscription.local.connection-setup.choose-provider",
"blocker": null,
"attempts": [],
"attempts": [
{
"ordinal": 1,
"outcome": "failed",
"executionId": "chat-features.runner-codex-subscription.local.connection-setup.choose-provider",
"startedAt": "2026-10-27T10:29:19.551Z",
"finishedAt": "2026-10-27T10:30:11.290Z",
"sourceRevision": "c167a54162fadffe665b4d35a7a1308c6233b75d",
"workingTreeDigest": "c7fd9a3a9f33cdc907f3e8c61d5f40eeb107cc8f856e01552745cd438e4e27d7",
"definitionDigest": "2650b5969af7a28ce555ba5ec92dfb6cf3eb3c21dfce0b8ab99be9c41e2ff772",
"suiteDefinitionDigest": "c0a8d311ea4dc7616bc8cef7a815457e5c013bd491d2ac6510f62500d3d0ac25",
"graderDigest": "2650b5969af7a28ce555ba5ec92dfb6cf3eb3c21dfce0b8ab99be9c41e2ff772",
"model": "gpt-5.6-sol",
"profile": "runner-codex-subscription",
"environment": "local",
"automaticRetries": 0,
"correction": null,
"classification": "candidate_failure",
"observedFailure": "Actual reply does not explain the advertised Notion choices and unavailable prerequisite",
"evidencePaths": [
"tests/runner-e2e/results/chat-catalog-campaign/two-lane-initial-pair-c167a54162.json",
"tests/runner-e2e/results/two-lane-initial-c167a54162fa-41b15d773be40166eeb1/chat-features/runner-codex-subscription/local/connection-setup.choose-provider/attempt-1/result.json",
"tests/runner-e2e/results/chat-catalog-campaign/active-connection-setup.choose-provider.json"
],
"usage": {
"costUsd": null,
"tokens": 54395,
"coverage": "Actual heartbeat usage receipts, including cache; subscription cost unpriced unless complete billing; fixture costs excluded."
},
"cleanup": "passed",
"corePrDependencies": [],
"databaseLane": {
"lane": "owned-docker-postgres",
"image": "postgres@sha256:74935e72241653ca55e0414067e6d8763aceb8a810eb51b452253ec3dcfc4336",
"imageId": "sha256:74935e72241653ca55e0414067e6d8763aceb8a810eb51b452253ec3dcfc4336",
"version": "18.6-1.pgdg13+2"
},
"productIdentity": {
"kind": "source-build",
"productionSourceRevision": "8373d7867963674ff960d2345d0d28086f799bc7",
"snapshotSourceRevision": "c167a54162fadffe665b4d35a7a1308c6233b75d",
"nativeBinarySha256": "9d8af6b85b836a03092ade2273be6f29f5c2f6ec67ee891d83ee9693ba39d3b4",
"workspaceBuildDigest": "222e10a8a2a20d3015ec4470b952e2dd9b927dfe9390c4a5ed1e19d740c0e35b",
"receiptPaths": [
"tests/runner-e2e/results/chat-catalog-campaign/snapshot-two-lane-c167a54162.json",
"tests/runner-e2e/results/chat-catalog-campaign/snapshot-10d0ce63610.json",
"tests/runner-e2e/results/chat-catalog-campaign/snapshot-0fdcb539a8.json"
],
"coreCandidate": false
}
}
],
"qualifyingDefinitionDigest": "2650b5969af7a28ce555ba5ec92dfb6cf3eb3c21dfce0b8ab99be9c41e2ff772",
"qualifyingGraderDigest": "2650b5969af7a28ce555ba5ec92dfb6cf3eb3c21dfce0b8ab99be9c41e2ff772",
"productPolicy": {