Interactive replay prototype

Install -> Replay -> Inspect

A replay-safe, client-side click-through for the centerpiece demo. Walk the success path, then toggle into a failure inspection where the evidence chain surfaces the mismatch.

Start hub First replay Docs

Illustrative guided demo only. All events, receipts, trust deltas, and summaries are simulated client-side fixtures, not live customer telemetry. Starter posture is inspect-only where referenced.

Developer replay templates

Jump into preset, simulated replay postures. Templates only preselect scenario copy and starting step.

?template=

Failed tool chain Policy mismatch Retry storm Multi-agent divergence Timeout Recovery chain

Slice AB · inspect a failure

Policy mismatch surfaced

A canned failure path shows how a mismatch, continuity break, and negative trust delta become inspectable evidence.

Retry storm: Template loaded: review the recovery recommendation after repeated failure context is preserved.

ScenarioEscalation review

Trust delta

-14

Replay posture

Escalation review

StableWarningDrift detectedReplay availableRecovery suggested

Evidence continuity

Partial

Lineage completeness

Gaps detected

Replay confidence

Medium

T+00:14 · Step 5

Ops summary surfaces the failure evidence.

Forensics queued

The summary explains the mismatch, continuity break, and recommended inspection target in operations language.

Expected vs observed

Simulated replay diff for this step. Values are illustrative fixtures only.

trust -14

Intended mission path

failure evidence -> human review -> recovery recommendation

Observed tool chain

Trust Agent -> mismatch summary -> inspect GL-3091

Drift note: Replay confidence shifted because the summary depends on a confirmed scope mismatch.

Why trust broke

Divergence began when the runtime selected vendor.update instead of the vendor-read lookup path.
Continuity broke at the policy edge P-104 because the observed tool chain crossed from read scope into write authority.
Replay confidence shifted negative after GhostLog GL-3091 and drift scoring agreed on the same authority boundary break.

Recovery continuity

Checkpoint CP-23 created from the last clean read-only boundary.
Retry path stabilizes on vendor.lookup with write tools suppressed.
Posture trend moves from Drift detected back toward Warning.
Continuity re-established after the operator confirms policy edge P-104.

Evidence chain

finding: policy mismatch
review: required
impact: authority boundary

Trust Agent forensic summary

ops> policy mismatch: vendor.update exceeded support-read scope
ops> continuity break: baseline vendor-read versus observed vendor-write
ops> recommended action: inspect GL-3091 and policy edge P-104

GhostLog explorer

T+00:14.070summary.readylineage:TA-failuretrust -14checkpoint:CP-22

T+00:14.360finding.mismatchlineage:P-104trust -14checkpoint:CP-22

T+00:14.810inspect.targetlineage:GL-3091trust -14checkpoint:CP-22

Same mission, different runtime

OpenAI+6 guided / -12 failure

Fast policy echo, review still required

Same canned mission, simulated as a managed runtime handoff.

Ollama+4 guided / -9 failure

Local receipt chain, slower stabilization

Same canned mission, simulated as a local runtime replay.

Exports a static JSON bundle with steps, posture chips, truncated GhostLog events, diff summary, and timeline.

Simulated click-through. No live telemetry, no customer data, no autonomous action.