From b68f69a8012886ec030b176467d7c75284bb4062 Mon Sep 17 00:00:00 2001 From: Dotta <34892728+cryppadotta@users.noreply.github.com> Date: Thu, 5 Nov 2026 17:57:18 -0600 Subject: [PATCH] test(evals): pin author self-use and credential guard corrections (#19357) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ## Thinking Path > - Paperclip manages agents and their work. > - The protected chat catalog selects an immutable evaluated source. > - The measured parent produced seven independently reviewed passes out of ten. > - The authoring observer rejected valid author-only use, and two credential wording guards needed stricter boundaries. > - The reviewed source corrects those observers and declares each affected oracle version. > - This PR pins that source without changing the original questions or run limits. ## Linked Issues or Issue Description Refs #19346, #19095, #19093. **What happened?** The measured authoring response described real saved author-only use. The old observer required zero assignments and wrongly rejected an audited author-only assignment. The credential scanner also needed to retain an unsafe comma-separated destination and mixed reference/password requests. These are evaluation-layer corrections. The parent timeline and company runs did not complete; no causal latency fix is claimed here. **Expected behavior** Select the reviewed immutable observer source. Keep all original scenario identities, questions, conditions, actor/resource proof, counts, clocks, credentials, model, permissions and zero retries unchanged. **Steps to reproduce** Run the source authoring and shared credential consumer controls. Compare the committed candidate descriptor snapshot with source `d1ab241cac0db7f700fadaaf62ffb3d2b51cf0c3`. ## What Changed - Scope the private Company creation observer to the exact Create secret dialog. Its successful close can open a separate details Sheet without making the observer wait for that Sheet. - Admit blank or bounded non-secret metadata defaults only for the Company saved-secret-name question variant. Verify the same canonical payload in independent human accounting. - Pin source `d1ab241cac0db7f700fadaaf62ffb3d2b51cf0c3`, tree `c4efaef62405cbb37236ad01db1187cf8a156868`. - Store exact descriptor SHA256 `60db015337e807ff53a376b6db11c375a239097b224d2253dad68ecd0b0f61f3`. - Update only seven oracle-version leaves: authoring v5, company v11, personal v12, and four shared external consumers v6. Source-file lists remain fixed. - Retain provenance anchors, historical conditions and failures. Update the single expected-target assertion. Exactly three metadata/test files change. ## Verification - 41 manifest, adapter, reconciliation and CLI controls pass on this actual pin projection. - Qualified source: one actual-worker offline browser canary passes all three creation, failed-POST and missing-form mechanisms. Full E2E types pass on this successor. Reused unchanged proof: 286 distinct controls across authoring, Company saved-name question, human accounting and shared-consumer/declaration suites pass. Full E2E typecheck passes. All 242 declarations load with zero fixture callbacks. - SDK506 inputs and registry `efa70621` remain unchanged. Launcher SHA256 `2b9a6953`, private transport interfaces, production/UI/CLI source, lockfile and workflows remain unchanged from the measured source. - All 244 YAML queries, context and expected outcomes are byte-identical to the parent. All descriptor native/human counts, clocks, authentication, setup policy and source-file lists remain fixed. - The parent source has seven measured semantic passes out of ten. The new authoring and credential oracle versions are native-unrun. Existing failed grades remain failed. - The isolated company concurrency diagnostic [run42124035785](https://github.com/paperclipai/paperclip/actions/runs/42124035785) is a separate measurement. This pin does not alter concurrency or claim to fix native noncompletion. - Repo-wide build/tests were not repeated for this three-file metadata update. Normal PR CI remains required. ## Risks - The name character set does not prove secrecy. The saved-key-name variant can admit a credential-shaped synthetic default; this general classifier limit remains unfixed and tracked in #19093. These are finite experimental journeys only. Independent review must reject any actual credential-like or unknown-value prefill without clear public-metadata/proposed-name grounding, even if autograding is green. If safety cannot be established, the journey cannot receive PASS credit. Secure UI save, human answer, canonical payload/hash, audit, binding and byte-leak checks remain mandatory. - Earlier CI includes three explicit runner-shutdown cancellations and one deferred-observer test assertion at line573. Those outcomes remain retained and unresolved; the Company dialog repair makes no claim to fix them. New exact-head CI is required. - The Company dialog mismatch was established from production source and an actual-worker model-free regression before the next secure-save step. The prior isolated attempt did not reach private entry, so it is not evidence of an observed private-save failure. - A valid review warning remains as a documented follow-up in #19093: safe closing comma exclusions such as “only there” can be falsely rejected by the credential wording guard. The pin authorizes bounded experimental journeys only. If a valid actual handoff hits that guard, its failed grade is retained; no regex failure is waived or counted as PASS. Independent semantic review remains required for both secret handoffs. - Isolated Company original5055 remains FAILED. A real succeeded native took255949ms and produced a valid saved-name question, but the observer rejected its proposed non-secret metadata default. Secure entry and the second native were not reached. This successor repairs that assertion boundary only. - The next selected74/466/578 run is an explicit bounded lower-concurrency functional experiment at the existing cap2, same model, original clocks and zero retries. It is not evidence of a latency fix or reliability improvement. - Local observer proof is not a new native PASS. Timeline and company noncompletion remain unresolved, and no clock increase is included. - A secure handoff still requires independent semantic review before PASS credit. Actual saved resources, owner/audit evidence, provider outcomes and privacy gates remain required. - The source catalog remains separate from master. This PR does not merge the core or full catalog feature changes into master. ## Model Used OpenAI Codex, `gpt-6.1-sol`, with repository tools and code execution. The host does not expose the context-window size. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --- .../chat-full-catalog-testops-manifest.json | 50 +++++++++---------- ...hat-full-catalog-testops-manifest.test.mjs | 2 +- .../chat-repair-candidate-descriptors.json | 14 +++--- 3 files changed, 33 insertions(+), 33 deletions(-) diff --git a/tests/runner-e2e/chat-full-catalog-testops-manifest.json b/tests/runner-e2e/chat-full-catalog-testops-manifest.json index ab3dc58cc82..236431f640b 100644 --- a/tests/runner-e2e/chat-full-catalog-testops-manifest.json +++ b/tests/runner-e2e/chat-full-catalog-testops-manifest.json @@ -1,6 +1,6 @@ { "schema": "paperclip.chat-full-catalog-testops-manifest/v1", - "targetSha": "7ccfc33bf074e37d8fd901a6e8453d1b45307e82", + "targetSha": "d1ab241cac0db7f700fadaaf62ffb3d2b51cf0c3", "metadataSourceSha": "de0941835cc8f0d01c982574ee258e110babdbeb", "profile": "runner-opencode", "model": "openrouter/deepseek/deepseek-v4.1-flash-1017", @@ -172,7 +172,7 @@ "baseTargetSha": "3b66c3c144360ddf32714a0742fd774b8ceafb16", "previousTargetSha": "ab2019e976076ec0eb60b026844f3d9211cb0208", "definitionSourceSha": "de0941835cc8f0d01c982574ee258e110babdbeb", - "candidateDescriptorSha256": "e1b7de947567569d96fcc9dca607ef5807ffaba4bf994562c0c7ab46d1856df6", + "candidateDescriptorSha256": "60db015337e807ff53a376b6db11c375a239097b224d2253dad68ecd0b0f61f3", "changedDefinitionFiles": [ { "path": "tests/runner-e2e/chat-scenarios/companies.yaml", @@ -199,7 +199,7 @@ "sha256": "91a9ddc4f5357f19a2cdc73ff8a090c741d14780e4ed502c856ebd557986f7e1" } ], - "conditions": "Historical qualification conditions (retained; statements that all requests or sourceFiles remain fixed refer to those earlier successors): New candidate measurements only. Original definitions, prior failed attempts and source6 ab201 remain historical. This target retains that catalog and integrates merged runtime fixes #18711, #18713 and #18718, with the prior-run restoration condition adapted to its existing owner. It adds the reviewed previous-question locator, attributed human-only denial and conditional-outcome oracle, and actor-sensitive timeline narrative/recorded-reassignment fixes. Closed finish diagnostics retain an effective schema digest, hashed call correlation and bounded type/category enums only. Historical MCP timeout and continuation-shape causes remain unresolved; no new all-ten PASS is claimed. Queries, model, human/native counts and original clocks remain fixed; the earlier Studio144 explicit 2..3 accounting stays. Core PRs18717/18734/18742 are now merged. SDK115 completion remains UNKNOWN and the other five SDK cases remain held. Full244 runtime catalog is not merged to master and the196/244 gate is unchanged. This successor binds the seven reviewed scenario repairs plus framework evidence: canonical skill navigation, original announcement phase clock, attributed timeline context, bound hire revision history, credential warning and configuration-question admission, completed team visibility, and canonical private framework evidence. Twelve declaration fields across eleven cases change only oracle versions and skill source-file provenance. All original requests, setup, human/native bounds, model and clocks remain fixed. Historical failed attempts and missing-original UNKNOWN grades remain unchanged; no uniform-ten PASS is claimed. The existing SDK506/efa qualification is reused only for byte-identical registered source inputs. This next successor adds reviewed question-surface observation, grounded scenario grading and safe credential-guidance boundaries after the retained uniform attempt. Eleven existing oracle-version leaves advance; all sourceFiles declarations, requests, setup, counts, clocks, model, launcher and private protocol helpers remain fixed. Component qualification does not attest a new uniform-ten pass.\n\nPrevious successor conditions (retained): This successor measures five reviewed repairs at the retained original model and bounds. Exactly one request is clarified: multipart53 now explicitly asks to walk through the visible form; its original broad request and failures4623/4717 remain historical. The previous inventory0cf530 is retained and the disclosed clarified inventory is814bb363. Other243 catalog requests are unchanged. The company-secret second human message now references the actual saved non-secret metadata instead of repeating the initial request; native continuation must remain attributed to the actual agent. Five oracle-version leaves and four source-file additions change; launcher, private helpers, SDK506/efa, identities, counts, clocks and the196/244 gate remain fixed. All five successor journeys remain unrun; component proof is not a PASS. For Team610, independently saved canonical skill/version/member proof establishes recovery; no required recovery-success phrase is imposed. A contradictory current denial still fails. If the required skill remains missing, truthful disclosure of that condition remains required.\n\nPrevious retained successor conditions: This target adds the reviewed personal secure-entry confirmation handoff, the typographic team partial-warning observer correction, and the company-secret authorization fix from unmerged core PR #19325. Personal v10 retains two declared logical human actions: one canonical chat request plus one independently verified same-human secure-save confirmation handoff. Raw chat comments remain one. Team v5 accepts the actual named-skill warning with a typographic apostrophe; saved-state, repeat, runtime, link, and false-success checks remain required. The company route returns scoped 403 guidance before malformed-body validation and preserves board-only creation. Its effect on the unfinished native turn is unproven. The three affected journeys are unrun on this target. Existing failed attempts remain failed. All queries, expected outcomes, native and human bounds, clocks, profile, model, launcher, private protocol, SDK506/efa, and the 196/244 admission gate remain fixed, including the recorded case53 query clarification. Local component proof is not native feature qualification or main/core merge credit.\n\nPrevious retained successor conditions: This target repairs personal secure-entry observation and truthful human acknowledgment, company secure-entry language and ordinary visible menu navigation, team current-skill claim attribution, and native completion feedback that asks for usable product links. Personal v11 expands visible Details before entry when needed, binds the exact value-entry dialog instead of the underlying definition sheet, and sends a truthful secure-save acknowledgment on the plain-comment path. The latter path was not reached by the prior failed attempt. Company v9 and the four shared-language consumers v5 keep explicit non-chat exclusions local to secure entry. Team v6 retains independent saved-state proof and rejects contradictory current claims. The source includes the separately reviewed, unmerged completion-feedback core hunk. All affected native journeys remain unrun on this target; original failures remain failed. The prior personal first native took580602ms, so completion within the unchanged660s remains unproven. Queries, counts, clocks, model, retries, SDK506/efa, launcher and private transfer interfaces are unchanged from the previous target; the recorded case53 clarification remains retained. Local control proof is not native PASS or a core merge.\n\nPrevious retained successor conditions: This unrun successor adds only the reviewed Company reference, credential-request and actor-boundary corrections plus Team current-assertion temporal scoping. Canonical server default reference metadata is accepted without accepting unknown fields or relaxed policy. Independent unsafe transfer requests remain rejected. Team current denials cannot be hidden by unrelated historical recovery prose. Versions and descriptor bytes are unchanged from the previous unrun target. The six changed source files pass233 affected controls and full E2E types. All prior native failures and the personal latency limitation remain. All queries, run counts, clocks, model, retries, launcher, SDK506 and private interfaces remain unchanged.\n\nCurrent successor conditions: This final reviewed successor adds only bounded Team historical-assertion scope, the actual visible Account-menu path to Company settings, and nearest secure-destination attribution with ordinary secure page/form suffixes. Current contradictions and intervening public destinations remain rejected. The six changed source paths pass271 affected controls, two offline browser canaries and full E2E types. Descriptor bytes and unrun versions remain unchanged. All original failures, queries, counts, clocks, model, retries, SDK506, launcher, production inputs and private interfaces are retained. Native acceptance remains unproved until the next actual run.", + "conditions": "Historical qualification conditions (retained; statements that all requests or sourceFiles remain fixed refer to those earlier successors): New candidate measurements only. Original definitions, prior failed attempts and source6 ab201 remain historical. This target retains that catalog and integrates merged runtime fixes #18711, #18713 and #18718, with the prior-run restoration condition adapted to its existing owner. It adds the reviewed previous-question locator, attributed human-only denial and conditional-outcome oracle, and actor-sensitive timeline narrative/recorded-reassignment fixes. Closed finish diagnostics retain an effective schema digest, hashed call correlation and bounded type/category enums only. Historical MCP timeout and continuation-shape causes remain unresolved; no new all-ten PASS is claimed. Queries, model, human/native counts and original clocks remain fixed; the earlier Studio144 explicit 2..3 accounting stays. Core PRs18717/18734/18742 are now merged. SDK115 completion remains UNKNOWN and the other five SDK cases remain held. Full244 runtime catalog is not merged to master and the196/244 gate is unchanged. This successor binds the seven reviewed scenario repairs plus framework evidence: canonical skill navigation, original announcement phase clock, attributed timeline context, bound hire revision history, credential warning and configuration-question admission, completed team visibility, and canonical private framework evidence. Twelve declaration fields across eleven cases change only oracle versions and skill source-file provenance. All original requests, setup, human/native bounds, model and clocks remain fixed. Historical failed attempts and missing-original UNKNOWN grades remain unchanged; no uniform-ten PASS is claimed. The existing SDK506/efa qualification is reused only for byte-identical registered source inputs. This next successor adds reviewed question-surface observation, grounded scenario grading and safe credential-guidance boundaries after the retained uniform attempt. Eleven existing oracle-version leaves advance; all sourceFiles declarations, requests, setup, counts, clocks, model, launcher and private protocol helpers remain fixed. Component qualification does not attest a new uniform-ten pass.\n\nPrevious successor conditions (retained): This successor measures five reviewed repairs at the retained original model and bounds. Exactly one request is clarified: multipart53 now explicitly asks to walk through the visible form; its original broad request and failures4623/4717 remain historical. The previous inventory0cf530 is retained and the disclosed clarified inventory is814bb363. Other243 catalog requests are unchanged. The company-secret second human message now references the actual saved non-secret metadata instead of repeating the initial request; native continuation must remain attributed to the actual agent. Five oracle-version leaves and four source-file additions change; launcher, private helpers, SDK506/efa, identities, counts, clocks and the196/244 gate remain fixed. All five successor journeys remain unrun; component proof is not a PASS. For Team610, independently saved canonical skill/version/member proof establishes recovery; no required recovery-success phrase is imposed. A contradictory current denial still fails. If the required skill remains missing, truthful disclosure of that condition remains required.\n\nPrevious retained successor conditions: This target adds the reviewed personal secure-entry confirmation handoff, the typographic team partial-warning observer correction, and the company-secret authorization fix from unmerged core PR #19325. Personal v10 retains two declared logical human actions: one canonical chat request plus one independently verified same-human secure-save confirmation handoff. Raw chat comments remain one. Team v5 accepts the actual named-skill warning with a typographic apostrophe; saved-state, repeat, runtime, link, and false-success checks remain required. The company route returns scoped 403 guidance before malformed-body validation and preserves board-only creation. Its effect on the unfinished native turn is unproven. The three affected journeys are unrun on this target. Existing failed attempts remain failed. All queries, expected outcomes, native and human bounds, clocks, profile, model, launcher, private protocol, SDK506/efa, and the 196/244 admission gate remain fixed, including the recorded case53 query clarification. Local component proof is not native feature qualification or main/core merge credit.\n\nPrevious retained successor conditions: This target repairs personal secure-entry observation and truthful human acknowledgment, company secure-entry language and ordinary visible menu navigation, team current-skill claim attribution, and native completion feedback that asks for usable product links. Personal v11 expands visible Details before entry when needed, binds the exact value-entry dialog instead of the underlying definition sheet, and sends a truthful secure-save acknowledgment on the plain-comment path. The latter path was not reached by the prior failed attempt. Company v9 and the four shared-language consumers v5 keep explicit non-chat exclusions local to secure entry. Team v6 retains independent saved-state proof and rejects contradictory current claims. The source includes the separately reviewed, unmerged completion-feedback core hunk. All affected native journeys remain unrun on this target; original failures remain failed. The prior personal first native took580602ms, so completion within the unchanged660s remains unproven. Queries, counts, clocks, model, retries, SDK506/efa, launcher and private transfer interfaces are unchanged from the previous target; the recorded case53 clarification remains retained. Local control proof is not native PASS or a core merge.\n\nPrevious retained successor conditions: This unrun successor adds only the reviewed Company reference, credential-request and actor-boundary corrections plus Team current-assertion temporal scoping. Canonical server default reference metadata is accepted without accepting unknown fields or relaxed policy. Independent unsafe transfer requests remain rejected. Team current denials cannot be hidden by unrelated historical recovery prose. Versions and descriptor bytes are unchanged from the previous unrun target. The six changed source files pass233 affected controls and full E2E types. All prior native failures and the personal latency limitation remain. All queries, run counts, clocks, model, retries, launcher, SDK506 and private interfaces remain unchanged.\n\nPrevious retained successor conditions: This final reviewed successor adds only bounded Team historical-assertion scope, the actual visible Account-menu path to Company settings, and nearest secure-destination attribution with ordinary secure page/form suffixes. Current contradictions and intervening public destinations remain rejected. The six changed source paths pass271 affected controls, two offline browser canaries and full E2E types. Descriptor bytes and unrun versions remain unchanged. All original failures, queries, counts, clocks, model, retries, SDK506, launcher, production inputs and private interfaces are retained. Native acceptance remains unproved until the next actual run.\n\nPrevious retained successor conditions: The measured parent reached seven independently reviewed passes out of ten. This successor changes only author-skill observation and the staged unsafe credential destination guard. Author v5 accepts proven author-only self-use without inventing assignment requirements, but preserves explicit global-assignment denial and source/resource proof. Shared guard semantics are versioned once across all six declared dependents: company v10, personal v12, and four external v6 consumers. The seven descriptor changes are oracle-version leaves only. All244 YAML identities, queries, context, expected outcomes, native/human bounds, clocks, credentials, model, SDK506, launcher and private interfaces remain unchanged. Local qualification passes214 affected controls and full E2E types. These versions remain native-unrun. Timeline and company native noncompletion remain unresolved; this source makes no latency or concurrency fix claim. The isolated company concurrency diagnostic run42124035785 remains a separate measurement. All original failures remain failed.\n\nPrevious retained successor conditions: The isolated company attempt5055 failed after a succeeded255949ms native turn produced a valid actor-bound secure saved-name question with a non-secret proposed metadata default. The previous oracle rejected any initialText. This successor admits only blank or bounded metadata defaults in the company saved-secret-name variant and verifies the same canonical payload in independent human accounting. Company v11 is native-unrun. Secure entry and the second native were not reached in the failed original. This is an assertion repair, not a runtime, latency or concurrency fix. All244 definitions retain their queries, contexts, expected outcomes, native/human bounds, clocks, credentials and model. The parent full-ten remains seven of ten measured passes. New local qualification passes286 distinct affected controls and full E2E types; SDK506, launcher and private interfaces remain unchanged. All failed originals stay failed.\n\nCurrent successor conditions: This successor scopes the Company private-entry observer to the actual Create secret dialog. A successful201 closes that form while opening a separate details Sheet; the old generic dialog locator could rebind and wait on the wrong Sheet. The actual worker-branch model-free canary proves successful creation with details still open and rejects failed POST or missing form. Full E2E types pass;286 unchanged functional controls are reused. Company v11 and descriptor bytes remain unchanged and native-unrun. No actual private Company save failure is claimed from the prior pre-entry attempt. The earlier CI runner shutdown cancellations and the test573 deferred-observer assertion are retained and unresolved; this observer repair makes no claim to fix them. New normal CI remains required. All244 conditions, queries, counts, clocks, credentials, model, SDK506, trusted private protocol and launcher remain unchanged.", "changedFields": [ { "key": "activity.work-timeline", @@ -643,7 +643,7 @@ "key": "secrets.configure-company-secret", "field": "oracleVersion", "previous": "paperclip.chat-catalog.external.v1", - "current": "paperclip.chat-catalog.company-secret-controller-baseline.v9" + "current": "paperclip.chat-catalog.company-secret-controller-baseline.v11" }, { "key": "secrets.personal-secret", @@ -707,7 +707,7 @@ "key": "secrets.personal-secret", "field": "oracleVersion", "previous": "paperclip.chat-catalog.external.v1", - "current": "paperclip.chat-catalog.personal-secret.v11" + "current": "paperclip.chat-catalog.personal-secret.v12" }, { "key": "skills.author-skill", @@ -735,7 +735,7 @@ "key": "skills.author-skill", "field": "oracleVersion", "previous": "paperclip.chat-catalog.integrator.v1", - "current": "paperclip.chat-catalog.skill-authoring.v4" + "current": "paperclip.chat-catalog.skill-authoring.v5" }, { "key": "skills.author-skill", @@ -919,25 +919,25 @@ "key": "connection-setup.secure-api-key", "field": "oracleVersion", "previous": "paperclip.chat-catalog.external.v1", - "current": "paperclip.chat-catalog.external.v5" + "current": "paperclip.chat-catalog.external.v6" }, { "key": "secrets.least-scope-delivery", "field": "oracleVersion", "previous": "paperclip.chat-catalog.external.v1", - "current": "paperclip.chat-catalog.external.v5" + "current": "paperclip.chat-catalog.external.v6" }, { "key": "secrets.secret-proposal", "field": "oracleVersion", "previous": "paperclip.chat-catalog.external.v1", - "current": "paperclip.chat-catalog.external.v5" + "current": "paperclip.chat-catalog.external.v6" }, { "key": "secrets.vault-reference", "field": "oracleVersion", "previous": "paperclip.chat-catalog.external.v1", - "current": "paperclip.chat-catalog.external.v5" + "current": "paperclip.chat-catalog.external.v6" }, { "key": "teams.install-team", @@ -1366,7 +1366,7 @@ "key": "secrets.configure-company-secret", "field": "oracleVersion", "previous": "paperclip.chat-catalog.external.v1", - "current": "paperclip.chat-catalog.company-secret-controller-baseline.v9" + "current": "paperclip.chat-catalog.company-secret-controller-baseline.v11" }, { "key": "secrets.personal-secret", @@ -1441,7 +1441,7 @@ "key": "secrets.personal-secret", "field": "oracleVersion", "previous": "paperclip.chat-catalog.external.v1", - "current": "paperclip.chat-catalog.personal-secret.v11" + "current": "paperclip.chat-catalog.personal-secret.v12" }, { "key": "skills.author-skill", @@ -1469,7 +1469,7 @@ "key": "skills.author-skill", "field": "oracleVersion", "previous": "paperclip.chat-catalog.integrator.v1", - "current": "paperclip.chat-catalog.skill-authoring.v4" + "current": "paperclip.chat-catalog.skill-authoring.v5" }, { "key": "skills.enable-for-agent", @@ -1697,25 +1697,25 @@ "key": "connection-setup.secure-api-key", "field": "oracleVersion", "previous": "paperclip.chat-catalog.external.v1", - "current": "paperclip.chat-catalog.external.v5" + "current": "paperclip.chat-catalog.external.v6" }, { "key": "secrets.least-scope-delivery", "field": "oracleVersion", "previous": "paperclip.chat-catalog.external.v1", - "current": "paperclip.chat-catalog.external.v5" + "current": "paperclip.chat-catalog.external.v6" }, { "key": "secrets.secret-proposal", "field": "oracleVersion", "previous": "paperclip.chat-catalog.external.v1", - "current": "paperclip.chat-catalog.external.v5" + "current": "paperclip.chat-catalog.external.v6" }, { "key": "secrets.vault-reference", "field": "oracleVersion", "previous": "paperclip.chat-catalog.external.v1", - "current": "paperclip.chat-catalog.external.v5" + "current": "paperclip.chat-catalog.external.v6" }, { "key": "teams.install-team", @@ -1855,7 +1855,7 @@ }, "candidateLauncherSnapshot": { "path": "fixtures/chat-repair-candidate-launcher.txt", - "targetSha": "7ccfc33bf074e37d8fd901a6e8453d1b45307e82", + "targetSha": "d1ab241cac0db7f700fadaaf62ffb3d2b51cf0c3", "sourcePath": "tests/runner-e2e/launch.ts", "gitBlobOid": "c88df15f509b2ac8638af826647a97d45f16bd1f" } @@ -6620,7 +6620,7 @@ "connection-setup/credentials" ], "checks": null, - "oracleVersion": "paperclip.chat-catalog.external.v5", + "oracleVersion": "paperclip.chat-catalog.external.v6", "sourceFiles": [ "chat-catalog-domains/external-secure-key.ts", "chat-query-attachments.ts", @@ -11190,7 +11190,7 @@ "connection-setup/credentials" ], "checks": null, - "oracleVersion": "paperclip.chat-catalog.company-secret-controller-baseline.v9", + "oracleVersion": "paperclip.chat-catalog.company-secret-controller-baseline.v11", "sourceFiles": [ "chat-catalog-domains/external-company-secret.ts", "chat-catalog-domains/external-secret-question.ts", @@ -11246,7 +11246,7 @@ "secrets/runtime-delivery" ], "checks": null, - "oracleVersion": "paperclip.chat-catalog.external.v5", + "oracleVersion": "paperclip.chat-catalog.external.v6", "sourceFiles": [ "chat-catalog-domains/external-secret-delivery.ts", "chat-catalog-domains/external-secret-endpoint.ts", @@ -11310,7 +11310,7 @@ "secrets/user-secrets" ], "checks": null, - "oracleVersion": "paperclip.chat-catalog.personal-secret.v11", + "oracleVersion": "paperclip.chat-catalog.personal-secret.v12", "sourceFiles": [ "chat-catalog-domains/external-personal-secret.ts", "chat-catalog-domains/external-personal-secret-confirmation.ts", @@ -11376,7 +11376,7 @@ "secrets/proposals" ], "checks": null, - "oracleVersion": "paperclip.chat-catalog.external.v5", + "oracleVersion": "paperclip.chat-catalog.external.v6", "sourceFiles": [ "chat-catalog-domains/external-secret-proposal.ts", "chat-catalog-domains/external-secret-scan.ts", @@ -11439,7 +11439,7 @@ "secrets/vault-import" ], "checks": null, - "oracleVersion": "paperclip.chat-catalog.external.v5", + "oracleVersion": "paperclip.chat-catalog.external.v6", "sourceFiles": [ "chat-catalog-domains/external-vault-reference.ts", "chat-catalog-domains/external-fixtures.ts", @@ -11497,7 +11497,7 @@ "skills/authoring" ], "checks": null, - "oracleVersion": "paperclip.chat-catalog.skill-authoring.v4", + "oracleVersion": "paperclip.chat-catalog.skill-authoring.v5", "sourceFiles": [ "chat-catalog-domains/integrator-support.ts", "chat-catalog-domains/internal-support.ts", diff --git a/tests/runner-e2e/chat-full-catalog-testops-manifest.test.mjs b/tests/runner-e2e/chat-full-catalog-testops-manifest.test.mjs index 5479c0ba94d..61b43d4ff9b 100644 --- a/tests/runner-e2e/chat-full-catalog-testops-manifest.test.mjs +++ b/tests/runner-e2e/chat-full-catalog-testops-manifest.test.mjs @@ -103,7 +103,7 @@ test('repair source metadata binds the corrected candidate and explicit changed const repair = manifest.source.repairMetadata; assert.equal(repair.baseTargetSha, '3b66c3c144360ddf32714a0742fd774b8ceafb16'); assert.equal(repair.previousTargetSha, 'ab2019e976076ec0eb60b026844f3d9211cb0208'); - assert.equal(manifest.targetSha, '7ccfc33bf074e37d8fd901a6e8453d1b45307e82'); + assert.equal(manifest.targetSha, 'd1ab241cac0db7f700fadaaf62ffb3d2b51cf0c3'); assert.equal(repair.definitionSourceSha, manifest.metadataSourceSha); assert.equal(repair.candidateDescriptorSnapshot, 'fixtures/chat-repair-candidate-descriptors.json'); const descriptorBytes = readFileSync(new URL(repair.candidateDescriptorSnapshot, import.meta.url)); diff --git a/tests/runner-e2e/fixtures/chat-repair-candidate-descriptors.json b/tests/runner-e2e/fixtures/chat-repair-candidate-descriptors.json index 5969dcc4639..c38dccd72b7 100644 --- a/tests/runner-e2e/fixtures/chat-repair-candidate-descriptors.json +++ b/tests/runner-e2e/fixtures/chat-repair-candidate-descriptors.json @@ -2599,7 +2599,7 @@ "chat-catalog-domains/identity-support.ts", "chat-scenarios/connection-setup.yaml" ], - "oracleVersion": "paperclip.chat-catalog.external.v5", + "oracleVersion": "paperclip.chat-catalog.external.v6", "expectedRunCount": 1, "turnTimeoutMs": 120000, "attemptTimeoutMs": 420000, @@ -4909,7 +4909,7 @@ "chat-flow.ts", "chat-scenarios/secrets.yaml" ], - "oracleVersion": "paperclip.chat-catalog.company-secret-controller-baseline.v9", + "oracleVersion": "paperclip.chat-catalog.company-secret-controller-baseline.v11", "expectedRunCount": 2, "expectedHumanMessageCount": 2, "turnTimeoutMs": 120000, @@ -4948,7 +4948,7 @@ "../../packages/plugins/sdk/dist/index.js", "chat-scenarios/secrets.yaml" ], - "oracleVersion": "paperclip.chat-catalog.external.v5", + "oracleVersion": "paperclip.chat-catalog.external.v6", "expectedRunCount": 3, "expectedHumanMessageCount": 1, "minimumRunCount": 3, @@ -4990,7 +4990,7 @@ "../../ui/src/pages/secrets/SetMyUserSecretDialog.tsx", "chat-scenarios/secrets.yaml" ], - "oracleVersion": "paperclip.chat-catalog.personal-secret.v11", + "oracleVersion": "paperclip.chat-catalog.personal-secret.v12", "expectedRunCount": 3, "expectedHumanMessageCount": 2, "minimumRunCount": 3, @@ -5022,7 +5022,7 @@ "../../server/src/services/secret-proposal-notifications.ts", "chat-scenarios/secrets.yaml" ], - "oracleVersion": "paperclip.chat-catalog.external.v5", + "oracleVersion": "paperclip.chat-catalog.external.v6", "expectedRunCount": 4, "expectedHumanMessageCount": 4, "minimumRunCount": 4, @@ -5070,7 +5070,7 @@ "../../ui/src/pages/secrets/ImportFromVaultDialog.tsx", "chat-scenarios/secrets.yaml" ], - "oracleVersion": "paperclip.chat-catalog.external.v5", + "oracleVersion": "paperclip.chat-catalog.external.v6", "expectedRunCount": 3, "expectedHumanMessageCount": 2, "minimumRunCount": 2, @@ -5094,7 +5094,7 @@ "../../ui/src/pages/CompanySkills.tsx", "../../ui/src/lib/company-skill-routes.ts" ], - "oracleVersion": "paperclip.chat-catalog.skill-authoring.v4", + "oracleVersion": "paperclip.chat-catalog.skill-authoring.v5", "expectedRunCount": 1, "expectedHumanMessageCount": 1, "turnTimeoutMs": 120000,