@lincoln504/pi-research 1.3.12 → 1.4.1

package/src/core/llm/agentic-repair.ts

@@ -34,6 +34,10 @@ export interface JsonRepairOptions {
   maxTokens?: number;
   /** Thinking level for the repair pass (default 'off' — repair emits JSON, not reasoning). */
   thinkingLevel?: ModelThinkingLevel;
+  /** Research session id, forwarded to the provider as its prompt-cache / session-affinity
+   *  key (see llm-utils.buildSafeOptions). Keeps the repair pass on the same upstream
+   *  replica as the call it is repairing. */
+  sessionId?: string;
   /** Usage sink invoked once per billed LLM attempt with the raw usage object from
    *  the response. Lets callers attribute the repair pass's tokens/cost to the run
    *  (metrics + observer) exactly as they do for the primary call. Every attempt that
@@ -70,7 +74,7 @@ export async function repairJsonWithLlm<T = any>(
   auth: { apiKey: string; headers?: Record<string, string | null> },
   options: JsonRepairOptions
 ): Promise<T | null> {
-  const { model, context, schema, serviceName = 'RepairService', signal, maxTokens = 16384, thinkingLevel = 'off' } = options;
+  const { model, context, schema, serviceName = 'RepairService', signal, maxTokens = 16384, thinkingLevel = 'off', sessionId } = options;
   
   logger.warn(`[${serviceName}] JSON parse failed; attempting agentic salvage`);
 
@@ -118,7 +122,8 @@ Return ONLY the valid JSON object. No prose before or after.`;
           ],
         }, buildSafeOptions(model, {
           ...auth,
-          signal
+          signal,
+          ...(sessionId ? { sessionId } : {}),
         }, maxTokens, thinkingLevel)),
         llmTimeout, `agentic-repair-${serviceName}`,
       );

package/src/core/llm/inject-date.ts

@@ -35,7 +35,10 @@ function getCurrentDateString(): string {
  * training-cutoff defaults). The full date follows for precision. Applies to
  * coordinator, researcher, and evaluator across all modes.
  */
-export function injectCurrentDate(prompt: string, _agentType: 'coordinator' | 'researcher' | 'evaluator'): string {
+export function injectCurrentDate(
+  prompt: string,
+  _agentType: 'coordinator' | 'researcher' | 'router' | 'synthesizer',
+): string {
   const monthYear = getCurrentMonthYearString();
   const fullDate = getCurrentDateString();
   // Derive the stale-year examples from the current year so the guidance stays correct in any

package/src/core/llm/llm-utils.ts

@@ -22,6 +22,13 @@ import { logger } from '../../logger.ts';
  *   thinking block only consumes the output-token budget (often truncating before the
  *   text block is emitted) for at most a marginal quality gain that does not justify the cost.
  *
+ * Callers should also pass the research `sessionId` in `options`. pi-ai forwards it as the
+ * provider's prompt-cache / session-affinity key — OpenAI's `prompt_cache_key`, OpenRouter's
+ * `x-session-id` — which keeps a run's calls on the replica that warmed their cache. Without
+ * it OpenRouter falls back to hashing the first system and user messages, which every round
+ * of a research run mutates, so it re-routes and re-warms. Providers that do not implement
+ * session affinity ignore the field, so passing it is unconditionally safe.
+ *
  * @param model - The model being called
  * @param options - Caller-provided options (an explicit `reasoning` here wins)
  * @param defaultCap - Default maxTokens cap (clamped to model.maxTokens)