forked from zts212653/clowder-ai
-
Notifications
You must be signed in to change notification settings - Fork 0
verdict(eval:friction): 2026-07-24-eval-friction-c1-third-clean-window #95
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.
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
Open
bouillipx
wants to merge
1
commit into
main
Choose a base branch
from
verdict/auto/eval-friction/2026-07-24-eval-friction-c1-third-clean-window
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
11 changes: 11 additions & 0 deletions
11
.../harness-feedback/bundles/2026-07-24-eval-friction-c1-third-clean-window/attribution.json
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,11 @@ | ||
| { | ||
| "verdictId": "2026-07-24-eval-friction-c1-third-clean-window", | ||
| "featureId": "F245", | ||
| "evalSnapshotId": "eval-F245-2026-07-24", | ||
| "generatedAt": "2026-07-24T03:06:35.690Z", | ||
| "findings": [], | ||
| "noFindingRecord": { | ||
| "reason": "no friction cluster surfaced in the selected window", | ||
| "evidence": "friction-rollup/cluster_count" | ||
| } | ||
| } |
15 changes: 15 additions & 0 deletions
15
docs/harness-feedback/bundles/2026-07-24-eval-friction-c1-third-clean-window/provenance.json
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,15 @@ | ||
| { | ||
| "verdictId": "2026-07-24-eval-friction-c1-third-clean-window", | ||
| "rawInputs": [ | ||
| { | ||
| "path": "docs/harness-feedback/bundles/2026-07-24-eval-friction-c1-third-clean-window/raw/rollup-report.json", | ||
| "sha256": "d65d8bb5a75d3813fc23623ecccea3f2e625bf26b49a545d8004be4ee11e0550" | ||
| } | ||
| ], | ||
| "generatedAt": "2026-07-24T03:06:35.690Z", | ||
| "generator": { | ||
| "name": "eval-friction-live-verdict", | ||
| "version": "1" | ||
| }, | ||
| "sanitizeRulesVersion": "f245-friction-rollup-v1" | ||
| } |
39 changes: 39 additions & 0 deletions
39
...ss-feedback/bundles/2026-07-24-eval-friction-c1-third-clean-window/raw/rollup-report.json
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,39 @@ | ||
| { | ||
| "verdictId": "2026-07-24-eval-friction-c1-third-clean-window", | ||
| "selector": { | ||
| "kind": "friction-rollup-snapshot", | ||
| "windowStartMs": 1784602800000, | ||
| "windowEndMs": 1784862000000, | ||
| "topN": 10, | ||
| "tokenCap": 4000 | ||
| }, | ||
| "window": { | ||
| "sinceMs": 1784602800000, | ||
| "untilMs": 1784862000000 | ||
| }, | ||
| "signalCount": 0, | ||
| "clusterCount": 0, | ||
| "degraded": false, | ||
| "droppedChannels": [], | ||
| "report": { | ||
| "window": { | ||
| "sinceMs": 1784602800000, | ||
| "untilMs": 1784862000000 | ||
| }, | ||
| "generatedAt": "2026-07-24T03:06:35.690Z", | ||
| "topClusters": [], | ||
| "actionableCandidates": [], | ||
| "referenceOnly": [], | ||
| "tailSummary": { | ||
| "clusterCount": 0, | ||
| "signalCount": 0, | ||
| "byChannel": {} | ||
| }, | ||
| "degraded": false, | ||
| "droppedChannels": [], | ||
| "tokenBudget": { | ||
| "cap": 4000, | ||
| "estimated": 78 | ||
| } | ||
| } | ||
| } |
25 changes: 25 additions & 0 deletions
25
docs/harness-feedback/bundles/2026-07-24-eval-friction-c1-third-clean-window/snapshot.json
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,25 @@ | ||
| { | ||
| "verdictId": "2026-07-24-eval-friction-c1-third-clean-window", | ||
| "evalSnapshotId": "eval-F245-2026-07-24", | ||
| "featureId": "F245", | ||
| "generatedAt": "2026-07-24T03:06:35.690Z", | ||
| "window": { | ||
| "startMs": 1784602800000, | ||
| "endMs": 1784862000000, | ||
| "durationHours": 72 | ||
| }, | ||
| "components": [ | ||
| { | ||
| "id": "friction-rollup", | ||
| "name": "friction rollup (Top-N + sensorForm)", | ||
| "confidence": "low", | ||
| "activationCounts": {}, | ||
| "frictionCounts": { | ||
| "cluster_count": 0, | ||
| "top_cluster_count": 0, | ||
| "tail_cluster_count": 0, | ||
| "tail_signal_count": 0 | ||
| } | ||
| } | ||
| ] | ||
| } |
30 changes: 30 additions & 0 deletions
30
docs/harness-feedback/verdicts/2026-07-24-eval-friction-c1-third-clean-window.md
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,30 @@ | ||
| --- | ||
| feature_ids: [F245] | ||
| topics: [harness-eval, eval-friction, live-verdict] | ||
| doc_kind: harness-feedback | ||
| feedback_type: live-verdict | ||
| domain_id: eval:friction | ||
| packet_id: 2026-07-24-eval-friction-c1-third-clean-window | ||
| source_snapshot: "snapshot:bundle/2026-07-24-eval-friction-c1-third-clean-window/snapshot" | ||
| --- | ||
|
|
||
| # Live Verdict — 2026-07-24-eval-friction-c1-third-clean-window | ||
|
|
||
| - Verdict: `keep_observe` | ||
| - Phenomenon: The current every-3d friction window from 2026-07-21 03:00 UTC to 2026-07-24 03:00 UTC produced no friction signals, no actionableCandidates, and no referenceOnly clusters. The two immediately preceding 72h windows (2026-07-15 03:00 UTC to 2026-07-18 03:00 UTC, and 2026-07-18 03:00 UTC to 2026-07-21 03:00 UTC) were also empty, so the domain is now three consecutive quiet windows past the earlier singleton. | ||
| - Harness: F245/friction-rollup (friction rollup (Top-N + sensorForm)) | ||
| - Root cause: No persistent root cause is observable in the current window. The earlier singleton still reads as a transient translation_gap or execution_gap rather than an active recurring harness, tool, or environment defect. (confidence low) | ||
| - Owner ask: Keep the every-3d friction rollup running and only escalate if a future 72h window surfaces any actionableCandidate, any recurring referenceOnly eval-domain cluster, or any repeated non-eval-domain cluster. | ||
| - Re-eval: next eval at 2026-07-27T03:00:00.000Z | ||
|
|
||
| Evidence: | ||
| - snapshot:bundle/2026-07-24-eval-friction-c1-third-clean-window/snapshot | ||
| - attribution:bundle/2026-07-24-eval-friction-c1-third-clean-window/eval-F245-2026-07-24:no-finding | ||
| - metric:friction-rollup.cluster_count | ||
| - metric:friction-rollup.top_cluster_count | ||
| - metric:friction-rollup.tail_signal_count | ||
|
|
||
| Counterarguments: | ||
| - Three clean windows still do not prove the harness is globally friction-free; a low-volume issue may simply not have recurred yet. | ||
| - The earlier singleton came from a specific workflow, so the quiet streak may reflect topic churn rather than durable recovery. | ||
| - If the next window reintroduces even one repeated cross-channel cluster, the current no-finding interpretation should be revised quickly. | ||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
When this verdict is used as the trend/closure record for
eval:friction, the streak is undercounted: the prior committed 2026-07-15 verdict covers 2026-07-12 03:00 to 2026-07-15 03:00 with zero clusters, followed by the zero 2026-07-18 and 2026-07-21 windows, and this new zero 2026-07-24 window. That makes four consecutive quiet 72h windows after the 2026-07-09 to 2026-07-12 singleton, not three, so the artifact now publishes an incorrect longitudinal result.Useful? React with 👍 / 👎.