Merge branch 'feat/tier-routing-feedback' into thedotmack/merge-alessandro-prs
This commit is contained in:
@@ -49,8 +49,8 @@ export class SDKAgent {
|
||||
// Find Claude executable
|
||||
const claudePath = this.findClaudeExecutable();
|
||||
|
||||
// Get model ID and disallowed tools
|
||||
const modelId = this.getModelId();
|
||||
// Get model ID (tier routing override takes precedence)
|
||||
const modelId = session.modelOverride || this.getModelId();
|
||||
// Memory agent is OBSERVER ONLY - no tools allowed
|
||||
const disallowedTools = [
|
||||
'Bash', // Prevent infinite loops
|
||||
|
||||
@@ -106,6 +106,8 @@ export class SessionRoutes extends BaseRouteHandler {
|
||||
|
||||
// Start generator if not running
|
||||
if (!session.generatorPromise) {
|
||||
// Apply tier routing before starting the generator
|
||||
this.applyTierRouting(session);
|
||||
this.spawnInProgress.set(sessionDbId, true);
|
||||
this.startGeneratorWithProvider(session, selectedProvider, source);
|
||||
return;
|
||||
@@ -126,6 +128,7 @@ export class SessionRoutes extends BaseRouteHandler {
|
||||
session.abortController = new AbortController();
|
||||
session.lastGeneratorActivity = Date.now();
|
||||
// Start a fresh generator
|
||||
this.applyTierRouting(session);
|
||||
this.spawnInProgress.set(sessionDbId, true);
|
||||
this.startGeneratorWithProvider(session, selectedProvider, 'stale-recovery');
|
||||
return;
|
||||
@@ -283,6 +286,7 @@ export class SessionRoutes extends BaseRouteHandler {
|
||||
this.crashRecoveryScheduled.delete(sessionDbId);
|
||||
const stillExists = this.sessionManager.getSession(sessionDbId);
|
||||
if (stillExists && !stillExists.generatorPromise) {
|
||||
this.applyTierRouting(stillExists);
|
||||
this.startGeneratorWithProvider(stillExists, this.getSelectedProvider(), 'crash-recovery');
|
||||
}
|
||||
}, backoffMs);
|
||||
@@ -813,4 +817,60 @@ export class SessionRoutes extends BaseRouteHandler {
|
||||
contextInjected
|
||||
});
|
||||
});
|
||||
|
||||
// Simple tool names that produce low-complexity observations
|
||||
private static readonly SIMPLE_TOOLS = new Set([
|
||||
'Read', 'Glob', 'Grep', 'LS', 'ListMcpResourcesTool'
|
||||
]);
|
||||
|
||||
/**
|
||||
* Apply tier routing: select model based on pending queue complexity.
|
||||
* - Summarize in queue → summary model (e.g., Opus)
|
||||
* - All simple tools → simple model (e.g., Haiku)
|
||||
* - Otherwise → default model (no override)
|
||||
*/
|
||||
private applyTierRouting(session: NonNullable<ReturnType<typeof this.sessionManager.getSession>>): void {
|
||||
const settings = SettingsDefaultsManager.loadFromFile(USER_SETTINGS_PATH);
|
||||
if (settings.CLAUDE_MEM_TIER_ROUTING_ENABLED === 'false') {
|
||||
session.modelOverride = undefined;
|
||||
return;
|
||||
}
|
||||
|
||||
// Clear stale override before re-evaluating — prevents previous tier
|
||||
// from persisting when queue composition changes between spawns.
|
||||
session.modelOverride = undefined;
|
||||
|
||||
const pendingStore = this.sessionManager.getPendingMessageStore();
|
||||
const pending = pendingStore.peekPendingTypes(session.sessionDbId);
|
||||
|
||||
if (pending.length === 0) {
|
||||
session.modelOverride = undefined;
|
||||
return;
|
||||
}
|
||||
|
||||
const hasSummarize = pending.some(m => m.message_type === 'summarize');
|
||||
const allSimple = pending.every(m =>
|
||||
m.message_type === 'observation' && m.tool_name && SessionRoutes.SIMPLE_TOOLS.has(m.tool_name)
|
||||
);
|
||||
|
||||
if (hasSummarize) {
|
||||
const summaryModel = settings.CLAUDE_MEM_TIER_SUMMARY_MODEL;
|
||||
if (summaryModel) {
|
||||
session.modelOverride = summaryModel;
|
||||
logger.debug('SESSION', `Tier routing: summary model`, {
|
||||
sessionId: session.sessionDbId, model: summaryModel
|
||||
});
|
||||
}
|
||||
} else if (allSimple) {
|
||||
const simpleModel = settings.CLAUDE_MEM_TIER_SIMPLE_MODEL;
|
||||
if (simpleModel) {
|
||||
session.modelOverride = simpleModel;
|
||||
logger.debug('SESSION', `Tier routing: simple model`, {
|
||||
sessionId: session.sessionDbId, model: simpleModel
|
||||
});
|
||||
}
|
||||
} else {
|
||||
session.modelOverride = undefined;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user