@@ -1162,33 +1163,15 @@ function renderOverview() {
`).join('')
: '
No history yet
';
- // Recommended agents (use inline recs if available)
- let recAgents = [];
- if (INLINE_RECOMMENDATIONS && INLINE_RECOMMENDATIONS.length > 0) {
- recAgents = INLINE_RECOMMENDATIONS.slice(0, 6).map(r => ({ agent: r.agent, current: { recommendations: [{ priority: r.impact, target: r.source_of_truth_model || r.recommended_model, reason: r.rationale, score_before: r.score_before, score_after: r.score_after, score_delta: r.score_delta }], model: r.current_model_in_agent_versions || r.current_model, category: 'Core Dev', description: '', benchmark: { fit_score: r.score_after || 0 } } }));
- } else {
- recAgents = Object.entries(agentData.agents)
- .filter(([_, a]) => a.current.recommendations && a.current.recommendations.length > 0)
- .slice(0, 6);
- }
+ // Recommended agents from live data
+ const recAgents = Object.entries(agentData.agents || {})
+ .filter(([_, a]) => (a.current?.recommendations || []).length > 0)
+ .slice(0, 6);
document.getElementById('recCount').textContent = recAgents.length;
- if (INLINE_RECOMMENDATIONS && INLINE_RECOMMENDATIONS.length > 0) {
- document.getElementById('recAgents').innerHTML = recAgents.map((r, idx) => renderRecCard({
- agent: r.agent,
- current_model: r.current?.model || '',
- recommended_model: r.current?.recommendations?.[0]?.target || '',
- impact: r.current?.recommendations?.[0]?.priority?.toLowerCase() || 'medium',
- score_before: r.current?.recommendations?.[0]?.score_before || 0,
- score_after: r.current?.recommendations?.[0]?.score_after || 0,
- score_delta: r.current?.recommendations?.[0]?.score_delta || 0,
- rationale: r.current?.recommendations?.[0]?.reason || ''
- }, idx)).join('');
- } else {
- document.getElementById('recAgents').innerHTML = recAgents.map(([name, agent]) =>
- renderAgentCard(name, agent, true)
- ).join('');
- }
+ document.getElementById('recAgents').innerHTML = recAgents.map(([name, agent]) =>
+ renderAgentCard(name, agent, true)
+ ).join('');
}
// Render All Agents
@@ -1327,24 +1310,19 @@ function renderTimeline() {
// Render Recommendations (v3 style with swap visuals)
function renderRecommendations() {
- // Use inline recommendations or fall back to agent data
- let recs = [];
- if (INLINE_RECOMMENDATIONS && INLINE_RECOMMENDATIONS.length > 0) {
- recs = INLINE_RECOMMENDATIONS;
- } else {
- recs = Object.entries(agentData.agents)
- .filter(([_, a]) => a.current.recommendations && a.current.recommendations.length > 0)
- .map(([name, agent]) => ({
- agent: name,
- current_model: agent.current.model,
- recommended_model: agent.current.recommendations[0]?.target,
- impact: agent.current.recommendations[0]?.priority?.toLowerCase() || 'medium',
- score_before: agent.current.recommendations[0]?.score_before || 0,
- score_after: agent.current.recommendations[0]?.score_after || 0,
- score_delta: agent.current.recommendations[0]?.score_delta || 0,
- rationale: agent.current.recommendations[0]?.reason || ''
- }));
- }
+ const recs = Object.entries(agentData.agents || {})
+ .filter(([_, a]) => (a.current?.recommendations || []).length > 0)
+ .map(([name, agent]) => ({
+ agent: name,
+ current_model: agent.current?.model,
+ recommended_model: agent.current?.recommendations?.[0]?.target,
+ impact: agent.current?.recommendations?.[0]?.priority?.toLowerCase() || 'medium',
+ score_before: agent.current?.recommendations?.[0]?.score_before || 0,
+ score_after: agent.current?.recommendations?.[0]?.score_after || 0,
+ score_delta: agent.current?.recommendations?.[0]?.score_delta || 0,
+ rationale: agent.current?.recommendations?.[0]?.reason || '',
+ current_model_in_agent_versions: agent.current?.model
+ }));
if (recs.length === 0) {
document.getElementById('allRecommendations').innerHTML = '
No recommendations available
';
@@ -1493,7 +1471,7 @@ function renderHeatmap() {
h += `
${s}${marks} `;
+ onclick="openHmModal(event, '${ag.n}', '${hmModels[j].n}', ${s}, ${hmModels[j].if})">${s}${marks}`;
});
h += '';
});
@@ -1556,7 +1534,8 @@ function closeHmModal() {
}
// Show cell detail modal with Chart.js line chart and prompt history
-function showCellDetail(modelName, agentName) {
+function showCellDetail(event, modelName, agentName) {
+ event.stopPropagation();
const agent = agentData.agents[agentName];
if (!agent) {
console.error('Agent not found:', agentName);
@@ -1770,9 +1749,13 @@ function renderHmModalContent(tabName) {
case 'models':
content = renderModelsTab(agent);
break;
+ case 'graph':
+ content = renderGraphTab(agent);
+ break;
}
body.innerHTML = `
${content}
`;
+ if (tabName === 'graph') setTimeout(() => renderCellChart(hmCurrentAgent, agent.current?.model || ''), 50);
}
function renderPromptTab(agent) {
@@ -1911,6 +1894,46 @@ function renderModelsTab(agent) {
return html;
}
+function renderGraphTab(agent) {
+ return `
+
+
Performance Over Time
+
+
+
+
+
Prompt Change History
+
+ ${renderPromptHistory(agent)}
+
+
+ `;
+}
+
+function renderPromptHistory(agent) {
+ const promptChanges = (agent.history || []).filter(item => item.change_type === 'prompt_change');
+
+ if (promptChanges.length === 0) {
+ return '
No prompt change history found
';
+ }
+
+ let html = '
';
+ promptChanges.forEach(change => {
+ html += `
+
+
+ ${formatDate(change.date)}
+ ${change.commit ? change.commit.substring(0,7) : 'unknown'}
+
+ ${change.reason || 'No reason provided'}
+
+ `;
+ });
+ html += ' ';
+ return html;
+}
+
// Compute composite score for any model name
// Formula (v2): IF_score * 0.85 + context_window_bonus (SWE-bench removed — all values unverifiable)
function computeAgentScore(modelName) {
@@ -2344,7 +2367,7 @@ function simulateApply() {
progressStatus.textContent = 'Complete!';
progressResult.classList.add('show');
- const recs = INLINE_RECOMMENDATIONS && INLINE_RECOMMENDATIONS.length > 0 ? INLINE_RECOMMENDATIONS : [];
+ const recs = Object.values(agentData.agents || {}).filter(a => (a.current?.recommendations || []).length > 0);
progressResultText.textContent = `✅ ${recs.length} recommendations applied. Run 'bun run sync:evolution' to update dashboard.`;
}
}
@@ -2395,11 +2418,11 @@ function showResearchModal() {
step.classList.add('done');
});
- const recs = INLINE_RECOMMENDATIONS && INLINE_RECOMMENDATIONS.length > 0 ? INLINE_RECOMMENDATIONS : [];
- const modelsCount = new Set(recs.map(r => r.current_model).concat(recs.map(r => r.source_of_truth_model || r.recommended_model))).size;
- const recsCount = recs.filter(r => r.score_delta > 0).length;
-
- document.getElementById('researchSummaryText').textContent =
+ const recs = Object.values(agentData.agents || {}).filter(a => (a.current?.recommendations || []).length > 0);
+ const modelsCount = new Set(recs.flatMap(a => [a.current?.model, a.current?.recommendations?.[0]?.target])).size;
+ const recsCount = recs.filter(a => (a.current?.recommendations?.[0]?.score_delta || 0) > 0).length;
+
+ document.getElementById('researchSummaryText').textContent =
`${modelsCount} models evaluated. ${recsCount} recommendations found. ${recs.length - recsCount} idle models detected.`;
researchSummary.classList.add('show');
}
diff --git a/agent-evolution/index.standalone.html b/agent-evolution/index.standalone.html
index f756b9f..7174e12 100644
--- a/agent-evolution/index.standalone.html
+++ b/agent-evolution/index.standalone.html
@@ -983,6 +983,7 @@
Gitea History
Skills
Model Timeline
+
Performance Graph
@@ -1016,7 +1017,7 @@ Chart.defaults.borderColor = '#1e2d45';
Chart.defaults.font.family = "'Inter', sans-serif";
// Inline recommendation data fallback (from model-research-latest.json)
-const INLINE_RECOMMENDATIONS = []; // REMOVED — data now comes from agentData, not hardcoded
+const INLINE_RECOMMENDATIONS = []; // Deprecated — data now comes from agentData.agents[].current.recommendations
// Inline benchmark data (fallback when embedded data doesn't have model_benchmarks)
// SOURCE: agent-evolution/data/model-benchmarks-verified.json v2.0.0
@@ -5736,33 +5737,15 @@ function renderOverview() {
`).join('')
: '
No history yet
';
- // Recommended agents (use inline recs if available)
- let recAgents = [];
- if (INLINE_RECOMMENDATIONS && INLINE_RECOMMENDATIONS.length > 0) {
- recAgents = INLINE_RECOMMENDATIONS.slice(0, 6).map(r => ({ agent: r.agent, current: { recommendations: [{ priority: r.impact, target: r.source_of_truth_model || r.recommended_model, reason: r.rationale, score_before: r.score_before, score_after: r.score_after, score_delta: r.score_delta }], model: r.current_model_in_agent_versions || r.current_model, category: 'Core Dev', description: '', benchmark: { fit_score: r.score_after || 0 } } }));
- } else {
- recAgents = Object.entries(agentData.agents)
- .filter(([_, a]) => a.current.recommendations && a.current.recommendations.length > 0)
- .slice(0, 6);
- }
+ // Recommended agents from live data
+ const recAgents = Object.entries(agentData.agents || {})
+ .filter(([_, a]) => (a.current?.recommendations || []).length > 0)
+ .slice(0, 6);
document.getElementById('recCount').textContent = recAgents.length;
- if (INLINE_RECOMMENDATIONS && INLINE_RECOMMENDATIONS.length > 0) {
- document.getElementById('recAgents').innerHTML = recAgents.map((r, idx) => renderRecCard({
- agent: r.agent,
- current_model: r.current?.model || '',
- recommended_model: r.current?.recommendations?.[0]?.target || '',
- impact: r.current?.recommendations?.[0]?.priority?.toLowerCase() || 'medium',
- score_before: r.current?.recommendations?.[0]?.score_before || 0,
- score_after: r.current?.recommendations?.[0]?.score_after || 0,
- score_delta: r.current?.recommendations?.[0]?.score_delta || 0,
- rationale: r.current?.recommendations?.[0]?.reason || ''
- }, idx)).join('');
- } else {
- document.getElementById('recAgents').innerHTML = recAgents.map(([name, agent]) =>
- renderAgentCard(name, agent, true)
- ).join('');
- }
+ document.getElementById('recAgents').innerHTML = recAgents.map(([name, agent]) =>
+ renderAgentCard(name, agent, true)
+ ).join('');
}
// Render All Agents
@@ -6068,7 +6051,7 @@ function renderHeatmap() {
h += `
${s}${marks} `;
+ onclick="openHmModal(event, '${ag.n}', '${hmModels[j].n}', ${s}, ${hmModels[j].if})">${s}${marks}`;
});
h += '';
});
@@ -6131,7 +6114,8 @@ function closeHmModal() {
}
// Show cell detail modal with Chart.js line chart and prompt history
-function showCellDetail(modelName, agentName) {
+function showCellDetail(event, modelName, agentName) {
+ event.stopPropagation();
const agent = agentData.agents[agentName];
if (!agent) {
console.error('Agent not found:', agentName);
@@ -6345,9 +6329,13 @@ function renderHmModalContent(tabName) {
case 'models':
content = renderModelsTab(agent);
break;
+ case 'graph':
+ content = renderGraphTab(agent);
+ break;
}
body.innerHTML = `
${content}
`;
+ if (tabName === 'graph') setTimeout(() => renderCellChart(hmCurrentAgent, agent.current?.model || ''), 50);
}
function renderPromptTab(agent) {
@@ -6486,6 +6474,46 @@ function renderModelsTab(agent) {
return html;
}
+function renderGraphTab(agent) {
+ return `
+
+
Performance Over Time
+
+
+
+
+
Prompt Change History
+
+ ${renderPromptHistory(agent)}
+
+
+ `;
+}
+
+function renderPromptHistory(agent) {
+ const promptChanges = (agent.history || []).filter(item => item.change_type === 'prompt_change');
+
+ if (promptChanges.length === 0) {
+ return '
No prompt change history found
';
+ }
+
+ let html = '
';
+ promptChanges.forEach(change => {
+ html += `
+
+
+ ${formatDate(change.date)}
+ ${change.commit ? change.commit.substring(0,7) : 'unknown'}
+
+ ${change.reason || 'No reason provided'}
+
+ `;
+ });
+ html += ' ';
+ return html;
+}
+
// Compute composite score for any model name
// Formula (v2): IF_score * 0.85 + context_window_bonus (SWE-bench removed — all values unverifiable)
function computeAgentScore(modelName) {
@@ -6919,7 +6947,7 @@ function simulateApply() {
progressStatus.textContent = 'Complete!';
progressResult.classList.add('show');
- const recs = INLINE_RECOMMENDATIONS && INLINE_RECOMMENDATIONS.length > 0 ? INLINE_RECOMMENDATIONS : [];
+ const recs = Object.values(agentData.agents || {}).filter(a => (a.current?.recommendations || []).length > 0);
progressResultText.textContent = `✅ ${recs.length} recommendations applied. Run 'bun run sync:evolution' to update dashboard.`;
}
}
@@ -6970,11 +6998,11 @@ function showResearchModal() {
step.classList.add('done');
});
- const recs = INLINE_RECOMMENDATIONS && INLINE_RECOMMENDATIONS.length > 0 ? INLINE_RECOMMENDATIONS : [];
- const modelsCount = new Set(recs.map(r => r.current_model).concat(recs.map(r => r.source_of_truth_model || r.recommended_model))).size;
- const recsCount = recs.filter(r => r.score_delta > 0).length;
-
- document.getElementById('researchSummaryText').textContent =
+ const recs = Object.values(agentData.agents || {}).filter(a => (a.current?.recommendations || []).length > 0);
+ const modelsCount = new Set(recs.flatMap(a => [a.current?.model, a.current?.recommendations?.[0]?.target])).size;
+ const recsCount = recs.filter(a => (a.current?.recommendations?.[0]?.score_delta || 0) > 0).length;
+
+ document.getElementById('researchSummaryText').textContent =
`${modelsCount} models evaluated. ${recsCount} recommendations found. ${recs.length - recsCount} idle models detected.`;
researchSummary.classList.add('show');
}
diff --git a/agent-evolution/research-dashboard.html b/agent-evolution/research-dashboard.html
index 2f21577..a3fafb7 100644
--- a/agent-evolution/research-dashboard.html
+++ b/agent-evolution/research-dashboard.html
@@ -3,7 +3,7 @@
-
APAW Agent Model Research — generated 2026-04-30
+
APAW Agent Model Research — generated 2026-05-24