Andy Dixon
522de3b026
Snapshots, replays and experiments now record the runtime they ran under: build (module version, VCS commit, modified tree, commit time, Go version, platform), schema version, a digest of the non-secret configuration that ignores secret and credential changes, personality version, policy digest, model routing including per-mind overrides, prompt versions, deterministic subsystem versions and timezone. A replay compares its identity with the snapshot's and is an exact-candidate, a different-build (differences listed) or incompatible (schema differs; the replay stops before running). The first non-exact step is analysed into events only in the recording, events only in the replay, and the components they belong to, labelled as inferred; live model calls are named as their own source of difference. Migration 0022 is additive; unrecorded identities are reported as such.
32 lines
4.8 KiB
HTML
32 lines
4.8 KiB
HTML
{{define "content"}}
|
||
{{$r := .Data.Replay}}{{$m := .Data.Mind}}
|
||
<div class="pagehead mindhead"><div><p class="muted small"><a href="/minds/{{$m.Slug}}/replays">Replays</a> › {{$m.DisplayName}}</p><h1>Replay <span class="badge {{if eq $r.Status "done"}}ok{{else if eq $r.Status "failed"}}danger{{else}}warn{{end}}">{{$r.Status}}</span></h1>
|
||
<p class="muted">From snapshot <strong>{{.Data.Snapshot.Name}}</strong> (event {{.Data.Snapshot.EventSeq}}), events {{$r.FromSeq}}–{{$r.ToSeq}} · {{$r.Summary.Steps}} steps · {{$r.Summary.Cycles}} cycles · model calls: {{$r.Summary.LLMReplayed}} replayed, {{$r.Summary.LLMLive}} live{{with $r.Error}} · <span class="danger">{{.}}</span>{{end}}</p>
|
||
{{with .Data.Sandbox}}<p class="small">Sandbox mind: <a href="/minds/{{.Slug}}">{{.Slug}}</a> (disabled; kept for inspection) · <a href="/minds/{{$m.Slug}}/compare?with={{.Slug}}">compare with source</a></p>{{end}}</div>
|
||
<div class="row"><span class="badge ok">{{$r.Summary.Exact}} exact</span> <span class="badge warn">{{$r.Summary.Approximate}} approximate</span> <span class="badge danger">{{$r.Summary.Diverged}} diverged</span></div></div>
|
||
{{if eq $r.Status "running"}}<p class="muted small" data-live-refresh="5000">Running… this page refreshes.</p>{{end}}
|
||
<section class="grid cols-2">
|
||
<div class="card"><h2>Runtime identity</h2>
|
||
<p class="small">Compatibility with the snapshot's runtime: <span class="badge {{if eq $r.Compatibility "exact-candidate"}}ok{{else if eq $r.Compatibility "incompatible"}}danger{{else}}warn{{end}}">{{or $r.Compatibility "unrecorded"}}</span></p>
|
||
{{if $r.IdentityDiff}}<ul class="small">{{range $r.IdentityDiff}}<li>{{.}}</li>{{end}}</ul>{{else}}<p class="small muted">No differences recorded between the two runtimes.</p>{{end}}
|
||
<table class="kv-table small"><tr><th>Build</th><td>{{$r.Identity.Build.Version}} {{with $r.Identity.Build.Commit}}<code>{{trunc . 12}}</code>{{end}}{{if $r.Identity.Build.Modified}} <span class="badge warn small">modified tree</span>{{end}} · {{$r.Identity.Build.GoVersion}} {{$r.Identity.Build.OS}}/{{$r.Identity.Build.Arch}}</td></tr>
|
||
<tr><th>Schema</th><td>{{$r.Identity.SchemaVersion}}</td></tr><tr><th>Config digest</th><td><code>{{$r.Identity.ConfigDigest}}</code></td></tr><tr><th>Personality</th><td>v{{$r.Identity.PersonalityVersion}}</td></tr><tr><th>Policy digest</th><td><code>{{$r.Identity.PolicyDigest}}</code></td></tr>
|
||
<tr><th>Routing</th><td class="small">{{range $k, $v := $r.Identity.Routing}}{{$k}} → {{$v}}<br>{{else}}none{{end}}</td></tr><tr><th>Deterministic subsystems</th><td class="small">{{range $k, $v := $r.Identity.Deterministic}}{{$k}} v{{$v}} · {{end}}</td></tr><tr><th>Timezone</th><td>{{$r.Identity.Timezone}}</td></tr></table>
|
||
<p class="small muted">Exact steps prove the deterministic code and recorded model responses reproduced the events. A different build can still be exact; an incompatible schema is never run.</p></div>
|
||
<div class="card"><h2>First divergence</h2>
|
||
{{with $r.Divergence}}<p>Identical until step <strong>{{.Step}}</strong> (<a href="/events/{{.StimulusID}}">stimulus</a>), then <span class="badge warn">{{.Label}}</span>.</p>
|
||
<p class="small">Components involved (inferred from event types): {{range .Components}}<span class="badge small">{{.}}</span> {{end}}</p>
|
||
<p class="small muted">recorded in {{.RecordedIn}} · replayed in {{.ReplayedIn}}</p>
|
||
{{if .OnlyRecorded}}<h3 class="small muted">Only in the recording</h3><ul class="small mono">{{range .OnlyRecorded}}<li>{{.}}</li>{{end}}</ul>{{end}}
|
||
{{if .OnlyReplayed}}<h3 class="small muted">Only in the replay</h3><ul class="small mono">{{range .OnlyReplayed}}<li>{{.}}</li>{{end}}</ul>{{end}}
|
||
{{else}}<p class="muted">{{if eq $r.Status "done"}}None: every step was exact.{{else}}Not available.{{end}}</p>{{end}}</div>
|
||
</section>
|
||
<div class="card">
|
||
{{if .Data.Steps}}{{range .Data.Steps}}<div class="replay-step">
|
||
<div class="row"><span class="badge {{if eq .Label "exact"}}ok{{else if eq .Label "approximate"}}warn{{else}}danger{{end}}">{{.Label}}</span> <strong>{{.Index}}.</strong> <a href="/events/{{.StimulusID}}">{{trunc .Summary 120}}</a> <span class="small muted">· {{.Cycles}} cycle(s){{if .LLMReplayed}} · {{.LLMReplayed}} recorded model response(s){{end}}{{if .LLMLive}} · {{.LLMLive}} live call(s){{end}}</span></div>
|
||
{{with .Note}}<p class="small muted">{{.}}</p>{{end}}
|
||
<div class="grid cols-2"><div><h3 class="small muted">Recorded</h3><ul class="small mono">{{range .Original}}<li>{{.}}</li>{{else}}<li class="muted">nothing</li>{{end}}</ul></div><div><h3 class="small muted">Replayed</h3><ul class="small mono">{{range .Replayed}}<li>{{.}}</li>{{else}}<li class="muted">nothing</li>{{end}}</ul></div></div>
|
||
</div>{{end}}{{else}}<p class="muted">No steps recorded{{if eq $r.Status "running"}} yet{{end}}.</p>{{end}}
|
||
</div>
|
||
{{end}}
|