experiment: separate conversation from workspace

This commit is contained in:
2026-08-05 12:03:08 +01:00
parent 1cb79cb36b
commit 742bd09ddc
2 changed files with 135 additions and 93 deletions
+18 -41
View File
@@ -656,36 +656,18 @@ export default function ReasoningWorkspace({
</div>
) : (
<>
{/* ═══════════════ ZONE 1 — Active work ═══════════════ */}
{/* ═══════════════ CONVERSATION — vertical flow ═══════════════ */}
{hasSelectedQuestion && (
<div className="space-y-6">
{/* Investigation status & context — desktop: two-column; mobile: stacked */}
<div className="grid grid-cols-1 gap-6 md:grid-cols-3">
<InvestigationSummaryPanel graph={graph} selectedQuestion={selectedQ} result={result} updateStatus={updateStatus} />
<div className="md:col-span-2">
{hasSelectedQuestion && (
<>
{/* Current Investigation — primary focus, full width */}
<CurrentInvestigationCard selectedQuestion={selectedQ} graph={graph} />
</>
)}
</div>
</div>
{/* Post-update acknowledgement */}
{updateStatus === "success" && !isUpdating && <UpdateAcknowledgement updateResult={result} />}
{/* Active workspace (Question + Response)full-width column */}
{hasSelectedQuestion && (
<div className="space-y-6">
{isUpdating && (
<LoadingOverlay
isLoading={true}
elapsed={updateElapsed}
currentMessage={updateMsg}
variant="update"
/>
)}
{/* Response — directly beneath the question */}
{!isUpdating && canAnswer && (
<form onSubmit={handleUpdateCaptureAndSubmit} className="space-y-4 rounded-lg border border-gray-200 bg-white p-5">
<div>
@@ -716,8 +698,6 @@ export default function ReasoningWorkspace({
</div>
</form>
)}
</div>
)}
{/* Terminal state — when no active question */}
{status === "success" && !hasSelectedQuestion && (
@@ -732,32 +712,29 @@ export default function ReasoningWorkspace({
)}
</div>
{/* ═══════════════ ZONE 2 — Shared understanding ═══════════════ */}
)}
{/* History — growing naturally from Response */}
{investigationHistory.length > 0 && (
<InvestigationHistory turns={investigationHistory} />
)}
{/* ═══════════════ WORKSPACE — supporting context ═══════════════ */}
{hasSelectedQuestion && hasCurrentSummaryCondition && (
<div className="grid grid-cols-1 gap-6 lg:grid-cols-3">
<div className="lg:col-span-2">
<div className="space-y-6 lg:col-span-2">
<CurrentUnderstandingCard currentSummary={graph?.currentSummary || result?.updatedSituationGraph?.currentSummary} plainLanguage={propUnderstanding || null} />
<InvestigationSummaryPanel graph={graph} selectedQuestion={selectedQ} result={result} updateStatus={updateStatus} />
</div>
<div className="lg:col-span-1">
<div className="space-y-6 lg:col-span-1">
<OriginalSituation scenario={scenario} centralStatement={graph?.centralStatement} />
<InvestigationMap turnCount={investigationHistory.length} />
</div>
</div>
)}
{/* ═══════════════ ZONE 3 — Reference and record ═══════════════ */}
<div className="grid grid-cols-1 gap-6 md:grid-cols-3">
<div className="md:col-span-1">
<OriginalSituation scenario={scenario} centralStatement={graph?.centralStatement} />
</div>
{investigationHistory.length > 0 && (
<div className="md:col-span-2">
<InvestigationHistory turns={investigationHistory} />
</div>
)}
</div>
{/* Developer details — full-width beneath reference row */}
{/* Developer details — full-width beneath workspace */}
{(status === "success" || status === "error") && graph && (
<DeveloperDetails
graph={graph}
+70 -5
View File
@@ -125,12 +125,77 @@ Can grouping the interface into cognitive work zones make the wider canvas feel
Hypothesis:
A workspace organised around what the investigator is doing will feel more coherent than one organised around equal cards or equal columns.
Change:
Arrange existing components into three visibly related zones:
Result:
Partially confirmed.
1. Active work
2. Shared understanding
3. Reference and record
Learning:
The workspace feels more coherent when organised into cognitive work zones rather than a simple document stack.
However, another distinction emerged that is more important than the zones themselves.
The interface naturally separates into two different modes:
• the active conversation between investigator and facilitator
and
• the shared workspace describing the current understanding.
Unexpected learning:
History feels incorrect when treated as reference information.
History is actually the continuation of the investigator's conversation.
Every response immediately becomes history.
The notebook should therefore grow naturally from the Response area.
The Investigation Status card currently competes with the Current Investigation card.
The current question is the primary focus.
Status is supporting context.
Decision:
Keep the cognitive-zone concept.
Refine the zones around conversational flow instead of card grouping.
Next question:
Can the workspace clearly separate conversation from shared understanding?
### Experiment 03 — Conversation versus Workspace
Hypothesis
Investigators think in two simultaneous modes.
Mode 1:
The conversation.
Question
Response
History
Mode 2:
The shared workspace.
Status
Understanding
Situation
Map
Separating these should make the interface feel more like a facilitated investigation than a collection of cards.
Evaluation:
Pending visual review.