Skip to content

Record Flow 9.1.0 qualification and canary evidence #133

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
vriesd merged 2 commits into from
Sep 27, 2026
Merged

Record Flow 9.1.0 qualification and canary evidence #133

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a848a0a
Add verified Flow 9.1.0 qualification evidence
vriesdcrv Sep 27, 2026
b6a3a03
Preserve original report bytes outside formatter scope
vriesdcrv Sep 27, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions evals/canary/9.1.0.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"actors":[{"actualModel":{"kind":"observed","value":{"family":"gpt-6-sol","gateway":null,"model":"gpt-6-sol","revision":null,"routeProvider":"openai"}},"requestedModel":{"family":"gpt-6-sol","gateway":null,"model":"gpt-6-sol","revision":null,"routeProvider":"openai"},"role":"manager","sessionIds":["id_7c44642805b4dea4"]},{"actualModel":{"kind":"observed","value":{"family":"gpt-6-sol","gateway":null,"model":"gpt-6-sol","revision":null,"routeProvider":"openai"}},"requestedModel":{"family":"gpt-6-sol","gateway":null,"model":"gpt-6-sol","revision":null,"routeProvider":"openai"},"role":"reviewer","sessionIds":["id_a1449d50ab9ebaf1"]}],"artifact":{"packageVersion":"9.1.0","sourceCommit":"b29a7b41d9cd88336d256e07f895fa2e347c8c7f","sourceTreeSha256":"sha256:1fd0f719594c5a21394f3fa143e1f24ae34c88381cd1baf2b29e666ea593192a","tarballSha256":"sha256:0b7f7a66bf1910b5d0da3a235f891d532b4aa352a2dbd25e398325c18e051b24","unpackedManifestSha256":"sha256:ad4c9ef4a8a1083f5ad9fb634939bde7651d8a52a9481f3c1fcb59f76c75512f"},"artifactSha256":"sha256:6c1714ac16174b57c99947be155b10bf09587f94dcd7c6cf47d176dd1ce38f78","artifacts":{"installation":{"bytes":483,"path":"artifacts/9.1.0-installation.json","sha256":"sha256:38996dbd5b3cdd396d668079d42da424cbb4b3e7846d234248baf4bdc963949c"},"session":{"bytes":5782,"path":"artifacts/9.1.0-session.json","sha256":"sha256:1367edb1044bbc503068180ce9be0cb69e165b1e796505bbea6c885a67d72499"},"transcript":{"bytes":177916,"path":"artifacts/9.1.0-transcript.json","sha256":"sha256:64b83bac3e11491be58ccf1522f4ff4256e02c6301f37c8acc968eef120c6ac0"}},"checklistSha256":"sha256:bcaa925277568ce9b67c50f0785c3bfbadfa5bb40a6f36b39fad63c21a605110","checklistVersion":"phase9-canary-v1","checks":{"captures-validation":true,"closes-with-delivery":true,"dispatches-reviewer":true,"installs-packed-artifact":true,"loads-flow-tools":true,"saves-plan":true},"derivationVersion":"canary-evidence-v1","expiresAt":"2026-09-30T06:24:21.140Z","hostConfigSha256":"sha256:8becbc6a5ddbeab4da98199c3f96e553aa0578c5154501305509c0ac9056e377","operator":"operator-approved","pluginEntrySha256":"sha256:b14e636e9bb2952a38cea83cd690dd5a304eedc74ab96c96a32a399ee3e05777","preparedSha256":"sha256:fee36f405eccd318023324fb086ea83424c541fb91c21ccdde2031d2d86af1b1","recordSha256":"sha256:f4b729e4e1d66a2badbdc9f34c6bedbc044e59bd9dd62a254e27f8e14611e461","recordedAt":"2026-09-27T06:24:21.140Z","releaseTag":"v9.1.0","schemaVersion":1,"status":"passed"}
1 change: 1 addition & 0 deletions evals/canary/artifacts/9.1.0-installation.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"artifactSha256":"sha256:6c1714ac16174b57c99947be155b10bf09587f94dcd7c6cf47d176dd1ce38f78","installedPluginSha256":"sha256:b14e636e9bb2952a38cea83cd690dd5a304eedc74ab96c96a32a399ee3e05777","pluginEntrySha256":"sha256:b14e636e9bb2952a38cea83cd690dd5a304eedc74ab96c96a32a399ee3e05777","preparedSha256":"sha256:fee36f405eccd318023324fb086ea83424c541fb91c21ccdde2031d2d86af1b1","schemaVersion":1,"tarballSha256":"sha256:0b7f7a66bf1910b5d0da3a235f891d532b4aa352a2dbd25e398325c18e051b24"}
1 change: 1 addition & 0 deletions evals/canary/artifacts/9.1.0-session.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"approval":"approved","closure":{"kind":"completed","operationId":"close-canary-greeting-1","recordedRevision":8,"summary":"Greeting export and two Bun cases implemented; whole-fixture bun test passed; independent review passed."},"goal":"Add canaryGreeting(name: string) to src/canary.ts returning `Hello, ${name}!`, preserve the existing canary export, add Bun tests for Ada and empty name, validate with whole-fixture `bun test`, independently review, and close completed without editing .opencode or publishing.","id":"id_74464f6faf22f8c4","operations":[{"committedRevision":1,"id":"save-canary-greeting-1","inputDigest":"sha256:aa4abf2e18efc7454b89830b8a38d4aa44e7922b40e499b611de4b2cdac058ea","kind":"plan-save"},{"committedRevision":2,"id":"approve-canary-greeting-1","inputDigest":"sha256:27e53c5ec90047fb55b27ebcb00557c1d8e1150715c7e32b343324ea63036a1a","kind":"plan-approve"},{"committedRevision":3,"entityId":"run:1e35ddac-dce0-4173-8530-999edc3417c7","id":"run-canary-greeting-1","inputDigest":"sha256:32c793939daf82288bbae6a2f5a816dc05344ff5f2a22f8f217c56adf2f50a1c","kind":"run-start"},{"committedRevision":6,"entityId":"id_6816f6305443b3cf","id":"review-canary-greeting-1","inputDigest":"sha256:9ab2ce4b33e110ec9da2c1507d831104e0f9eeba59e82634d60c63e47e041b33","kind":"review-start"},{"committedRevision":7,"entityId":"run:1e35ddac-dce0-4173-8530-999edc3417c7","id":"review-submit:canary-greeting-a3a9a01b-v1","inputDigest":"sha256:b6eeed145d4757293af837f6b1dadec9208710fe4b3ebdd5f6e412ed626cd117","kind":"feature-complete"},{"committedRevision":8,"id":"close-canary-greeting-1","inputDigest":"sha256:58d4a003322450e2abc7d643b71503cd2436f51ba5f37861d07946bfb806dea1","kind":"session-close"}],"plan":{"decisions":["The requested whole-fixture gate is bun test; its success is an exit-code assertion and behavioral output from the Bun tests.","Use src/canary.test.ts for the two cases, leaving src/canary.ts existing export intact."],"evidence":[{"assertions":[],"command":"bun test","environment":"Fixture workspace on Linux with Bun","platform":"linux","requirement":"Whole-fixture Bun test suite and greeting behavior","scope":"gate"}],"features":[{"dependsOn":[],"id":"canary-greeting","summary":"Export canaryGreeting(name: string) with the exact greeting, preserve canary, and test Ada and empty-name behavior.","targets":["src/canary.ts","src/canary.test.ts"],"title":"Canary greeting and tests","validation":["bun test","Review exact greeting results for Ada and empty name and confirm the canary export remains unchanged."]}],"overview":"Add a typed greeting function in src/canary.ts and a colocated Bun test file, then run the whole-fixture gate and independent review before closure.","requirements":["canaryGreeting(name: string) returns `Hello, ${name}!` for Ada and empty string.","The existing canary export remains unchanged.","Bun tests cover Ada and empty name.","Whole-fixture bun test passes; independent Flow review and completed closure occur.","Do not edit .opencode, commit, push or publish."],"summary":"Add and verify a canary greeting export with Ada and empty-name Bun tests while preserving the existing canary export."},"revision":8,"runs":[{"artifactsChanged":[{"path":"src/canary.ts"},{"path":"src/canary.test.ts"}],"attempt":1,"featureId":"canary-greeting","id":"run:1e35ddac-dce0-4173-8530-999edc3417c7","reviews":[{"createdRevision":6,"featureId":"canary-greeting","id":"id_6816f6305443b3cf","kind":"final","operationId":"review-canary-greeting-1","packet":{"riskLenses":["Does the additive export preserve existing callers and the canary default behavior?","Does the public function honor its declared string boundary and exact greeting contract?"],"summary":"Baseline HEAD 6c1d2b6e6718fedee1f7f463f587c0693ea171d6 was clean with no untracked files. Modified tracked regular src/canary.ts (index mode 100644, working regular mode 664) by appending typed function; original canary export line unchanged. Added untracked regular src/canary.test.ts (mode 664) with Ada and empty-name tests. No deletions, renames, generated artifacts, executable-mode changes, or pre-existing unrelated work. Focused bun test failed before implementation with missing named export; final broad bun test passed 2 tests, 0 failures."},"result":{"findings":[],"recordedRevision":7,"terminalDisposition":"submitted","verdict":"passed"},"runId":"run:1e35ddac-dce0-4173-8530-999edc3417c7","sourceDigest":"sha256:9ffac36ca9a5e5073a4b5e7de56f4f24635c8beb72058947c2f58684cbb67747","validationIds":["9386d920-7b76-4841-8b67-97ff4a4b557d"]}],"startedRevision":3,"state":"completed","summary":"Final review: canary-greeting verified. Greeting, original canary export, Ada and empty-name tests, and whole-fixture bun test verified; no .opencode changes or publishing in supplied baseline inventory. Independent review submitted; completed closure remains manager-owned. No prior findings.","validations":[{"command":"bun test","exitCode":1,"featureId":"canary-greeting","hostPlatform":"linux","id":"e2ffee7c-d980-45c2-b1f2-92984b79a043","outputComplete":true,"outputDigest":"sha256:8dceab6735524435c32305028850b2f172434d95a4d9f45c890756bc50a04684","recordedRevision":4,"runId":"run:1e35ddac-dce0-4173-8530-999edc3417c7","scope":"focused","sourceDigest":"sha256:820f3fec94cc65b4dd71f1acf844edc555bfb49a7050b2c8a54b949d19b9761a"},{"command":"bun test","exitCode":0,"featureId":"canary-greeting","hostPlatform":"linux","id":"9386d920-7b76-4841-8b67-97ff4a4b557d","outputComplete":true,"outputDigest":"sha256:133bee86e31a401ae8e5673bdcba6cdd388a17060b5e7bc7b7daf1a05da62dc6","recordedRevision":5,"runId":"run:1e35ddac-dce0-4173-8530-999edc3417c7","scope":"broad","sourceDigest":"sha256:9ffac36ca9a5e5073a4b5e7de56f4f24635c8beb72058947c2f58684cbb67747"}]}],"version":5}
1 change: 1 addition & 0 deletions evals/canary/artifacts/9.1.0-transcript.json
View file
Open in desktop

Large diffs are not rendered by default.

1 change: 1 addition & 0 deletions evals/qualification/9.1.0-original-report.snapshot
View file
Open in desktop

Large diffs are not rendered by default.

54 changes: 54 additions & 0 deletions evals/qualification/9.1.0-redaction-receipt.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,54 @@
{
"changes": [
{
"attemptId": "attempt-cell-b092d71fc74d45427db84badd81e3cdc348419ab5f6abc90e9011896b2ee2d64",
"changedFields": [
"gradeInput.allCalls.25.output",
"gradeInput.allCalls.25.rawOutput",
"gradeInput.allCalls.25.metadata.output"
],
"derivedSha256": "sha256:fe4ac3f8eb45835cd614f8f26246d8026f2cd3091f7a6d50fdeccaf217e5c387",
"originalSha256": "sha256:fccaf0027db0264855855a03ca4ea7f58f3ce015dd6d120a5bb7e99232ae4214"
},
{
"attemptId": "attempt-cell-939bdc83e55dde978fb61a182cd32d50bb589b0c1bf3afbf29326827edd89d09",
"changedFields": [
"gradeInput.allCalls.12.output",
"gradeInput.allCalls.12.rawOutput",
"gradeInput.allCalls.12.metadata.output"
],
"derivedSha256": "sha256:d19c7260b5e503415ba05395afff71833eb4da75eb54cef4e906ec8be7522245",
"originalSha256": "sha256:5f4171184203890a82f6d0bc497dcf7ba7f2106e7bd36c3c7afb57c3cc08eddb"
},
{
"attemptId": "attempt-cell-7099f0b9d8e57505d23629b87b3b4a73413bade2fbd5939deba177a4949c1a9b",
"changedFields": [
"gradeInput.allCalls.13.output",
"gradeInput.allCalls.13.rawOutput",
"gradeInput.allCalls.13.metadata.output"
],
"derivedSha256": "sha256:6ed7f56d2f1e9d3a28557dc80f338852e5d22fa22b0f56fa2af977aecfd0381f",
"originalSha256": "sha256:ba26b9ec0b6fc309be89a4b96abe1074236813417f9896cf14aa26108c5b51d1"
},
{
"attemptId": "attempt-cell-1e7e501f19ee3750f3ac23f6b4487e6b41bdc301bc066261a7bbf0c073f1ec03",
"changedFields": [
"gradeInput.allCalls.11.output",
"gradeInput.allCalls.11.rawOutput",
"gradeInput.allCalls.11.metadata.output"
],
"derivedSha256": "sha256:bf64f48e0dab12611f4f87f44319035e08a1e777ac7bee87661e0824f54db328",
"originalSha256": "sha256:3c78fdff2174b9deebf18be38e7203950a3a057f1c81cd5016a662392084aae5"
}
],
"derivedReportSha256": "sha256:ff0314c2af85f5a5dd32f1c99a3052978f0bfb423abee8e0494f7c0d2f6c212f",
"kind": "post-capture-output-path-redaction",
"purpose": "Post-capture privacy redaction of local toolchain paths in diagnostic tool outputs; recorded decisions and grades are unchanged.",
"qualifiedBundleSha256": "sha256:86bbc934222c2715d315521ff5041edc718eba6492ff679db50a6d494fc1bd6d",
"redaction": {
"replacement": "<redacted-home>/",
"scope": "gradeInput.allCalls output, rawOutput, and metadata.output strings only"
},
"schemaVersion": 1,
"sourceReportSha256": "sha256:0a6525b8e24792d1109a2d62fc70ddac2614f00d5fff631120fd482a18cee1ee"
}
1 change: 1 addition & 0 deletions .../bundles/qb1-86bbc934222c2715d315521ff5041edc718eba6492ff679db50a6d494fc1bd6d/bundle.json
View file
Open in desktop

Large diffs are not rendered by default.

1 change: 1 addition & 0 deletions ...94fc1bd6d/objects/sha256-0158a03cf7e8742b64d4db45174ac454e4fd4579ab8f26fceda483da2451661d
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"actors":[{"actualModel":{"kind":"observed","value":{"family":"gpt-6-sol","gateway":null,"model":"gpt-6-sol","revision":null,"routeProvider":"openai"}},"requestedModel":{"family":"gpt-6-sol","gateway":null,"model":"gpt-6-sol","revision":null,"routeProvider":"openai"},"role":"manager","sessionIds":["id_7c44642805b4dea4"]},{"actualModel":{"kind":"observed","value":{"family":"gpt-6-sol","gateway":null,"model":"gpt-6-sol","revision":null,"routeProvider":"openai"}},"requestedModel":{"family":"gpt-6-sol","gateway":null,"model":"gpt-6-sol","revision":null,"routeProvider":"openai"},"role":"reviewer","sessionIds":["id_a1449d50ab9ebaf1"]}],"artifact":{"packageVersion":"9.1.0","sourceCommit":"b29a7b41d9cd88336d256e07f895fa2e347c8c7f","sourceTreeSha256":"sha256:1fd0f719594c5a21394f3fa143e1f24ae34c88381cd1baf2b29e666ea593192a","tarballSha256":"sha256:0b7f7a66bf1910b5d0da3a235f891d532b4aa352a2dbd25e398325c18e051b24","unpackedManifestSha256":"sha256:ad4c9ef4a8a1083f5ad9fb634939bde7651d8a52a9481f3c1fcb59f76c75512f"},"artifactSha256":"sha256:6c1714ac16174b57c99947be155b10bf09587f94dcd7c6cf47d176dd1ce38f78","artifacts":{"installation":{"bytes":483,"path":"artifacts/9.1.0-installation.json","sha256":"sha256:38996dbd5b3cdd396d668079d42da424cbb4b3e7846d234248baf4bdc963949c"},"session":{"bytes":5782,"path":"artifacts/9.1.0-session.json","sha256":"sha256:1367edb1044bbc503068180ce9be0cb69e165b1e796505bbea6c885a67d72499"},"transcript":{"bytes":177916,"path":"artifacts/9.1.0-transcript.json","sha256":"sha256:64b83bac3e11491be58ccf1522f4ff4256e02c6301f37c8acc968eef120c6ac0"}},"checklistSha256":"sha256:bcaa925277568ce9b67c50f0785c3bfbadfa5bb40a6f36b39fad63c21a605110","checklistVersion":"phase9-canary-v1","checks":{"captures-validation":true,"closes-with-delivery":true,"dispatches-reviewer":true,"installs-packed-artifact":true,"loads-flow-tools":true,"saves-plan":true},"derivationVersion":"canary-evidence-v1","expiresAt":"2026-09-30T06:24:21.140Z","hostConfigSha256":"sha256:8becbc6a5ddbeab4da98199c3f96e553aa0578c5154501305509c0ac9056e377","operator":"operator-approved","pluginEntrySha256":"sha256:b14e636e9bb2952a38cea83cd690dd5a304eedc74ab96c96a32a399ee3e05777","preparedSha256":"sha256:fee36f405eccd318023324fb086ea83424c541fb91c21ccdde2031d2d86af1b1","recordSha256":"sha256:f4b729e4e1d66a2badbdc9f34c6bedbc044e59bd9dd62a254e27f8e14611e461","recordedAt":"2026-09-27T06:24:21.140Z","releaseTag":"v9.1.0","schemaVersion":1,"status":"passed"}
Loading
Loading