tcl-rsync-snapshot-integrity-audit

Task gallery / Cloud operations / Version 1

Reference solution (oracle): Pass
No-op resistance check: Pass
QA verdict: taxonomy: Evaluating; QA: QA-H sweep (budget fairness)
Aggregate eligibility: Excluded / other version

Quality exclusion

Known task defect recorded

These per-version observations remain visible, but this version does not contribute to aggregate pass rates.

The task

The local backup service at /app/bin/snapshotctl uses Tcl 8.6 and the real /usr/bin/rsync to maintain incremental snapshots. Its create, audit, and recover commands are usable, but mixed-change generations, interrupted promotion, and chronological retention can leave reports or repository state inconsistent. Restore the controller without changing its public interface or replacing Tcl or rsync. The authoritative CLI…

Excerpt only; not a complete executable task specification. Task ID task_a822cbe2fcfa498f · version 1. Selection status: not fully recorded.

Results by model and effort

This exact task version only. Every rate is passes / valid runs with a Wilson 95% interval; n≤2 remains counts only. Macro aggregation does not apply within a single task. Baselines are summarized in the quality gates, not ranked. A passed no-op resistance check means that doing nothing did not solve the task.

Current evidence

Model / effort	Verifier result [95% Wilson]	Diagnostic labels / valid	HARNESS_ERROR · excluded	Outcome classes
Claude Opus 5 · default (unverified)	2/4 · 50.0% [15.0%, 85.0%] · preliminary	4 / 4	6	GOOD_FAILURE: 0 BAD_FAILURE: 2 GOOD_SUCCESS: 2 BAD_SUCCESS: 0

Legacy evidence

Model / effort	Verifier result [95% Wilson]	Diagnostic labels / valid	HARNESS_ERROR · excluded	Outcome classes

Every recorded run

12 recorded trials, including controls. Diagnostic labels do not replace verifier reward. Labels and quality checks are source declarations, not independently attested here. Internal evidence remains private; a missing public URL is shown explicitly. Records with invalid or absent rewards are not scored.

Run / model	Date / source	Reward / eligibility	Diagnostic class / source	Resources	Evidence
`trial_73230b3c4c374db7` oracle@@	Oct 13, 2026 console	1 · valid	GOOD_SUCCESS frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available
`trial_9e85dd4454744e82` nop@@	Oct 13, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available
`trial_b48242a48c7940dd` Claude Opus 5 · default (unverified)	Oct 14, 2026 console	1 · valid	GOOD_SUCCESS frozen-classifier	Tokens: 142,051 Turns: 123 Cost: $14.4233	Not publicly available
`trial_e5ebdc03e7444eb3` Claude Opus 5 · default (unverified)	Oct 14, 2026 console	0 · valid	BAD_FAILURE frozen-classifier	Tokens: 130,880 Turns: 116 Cost: $12.5165	Not publicly available
`trial_8a6efbc655814c79` Claude Opus 5 · default (unverified)	Oct 14, 2026 console	1 · valid	GOOD_SUCCESS frozen-classifier	Tokens: 135,903 Turns: 110 Cost: $12.7895	Not publicly available
`trial_07a0a98c6dc04be4` Claude Opus 5 · default (unverified)	Oct 14, 2026 console	0 · valid	BAD_FAILURE frozen-classifier	Tokens: 152,972 Turns: 81 Cost: $11.3199	Not publicly available
`trial_3ea8f510973d4a18` Claude Opus 5 · default (unverified)	Oct 14, 2026 console	0 · excludedharness_error	HARNESS_ERROR independent-review	Tokens: 0 Turns: 1 Cost: $0.0000	Not publicly available
`trial_5d878e1bac014b25` Claude Opus 5 · default (unverified)	Oct 14, 2026 console	0 · excludedharness_error	HARNESS_ERROR independent-review	Tokens: 0 Turns: 1 Cost: $0.0000	Not publicly available
`trial_66b8e382be5a4fbd` Claude Opus 5 · default (unverified)	Oct 14, 2026 console	0 · excludedharness_error	HARNESS_ERROR independent-review	Tokens: 0 Turns: 1 Cost: $0.0000	Not publicly available
`trial_a410bdec0cbb4624` Claude Opus 5 · default (unverified)	Oct 14, 2026 console	0 · excludedharness_error	HARNESS_ERROR independent-review	Tokens: 0 Turns: 1 Cost: $0.0000	Not publicly available
`trial_ed09b65b436743a4` Claude Opus 5 · default (unverified)	Oct 14, 2026 console	0 · excludedharness_error	HARNESS_ERROR independent-review	Tokens: 0 Turns: 1 Cost: $0.0000	Not publicly available
`trial_eda1c871ba364c8c` Claude Opus 5 · default (unverified)	Oct 14, 2026 console	0 · excludedharness_error	HARNESS_ERROR independent-review	Tokens: 0 Turns: 1 Cost: $0.0000	Not publicly available