pi-optchat 0.8.7 → 0.8.8

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-optchat",
-  "version": "0.8.7",
+  "version": "0.8.8",
   "type": "module",
   "pi": {
     "extensions": [

package/src/compactor.ts

@@ -42,10 +42,21 @@ function primeFirst() {
     };
   };
 }
+/** Pi's agent loop retries a dropped connection itself; streamSimple doesn't, so a transient error is asked again before it surfaces. */
+export async function retryTransient(ask: () => Promise<AssistantMessage>, onReply: (reply: AssistantMessage) => void,
+  delays: readonly number[] = [1000, 2000], signal?: AbortSignal) {
+  for (let retry = 0; ; retry++) {
+    const reply = await ask();
+    onReply(reply);
+    if (retry >= delays.length || !isRetryableAssistantError(reply)) return reply;
+    await sleep(delays[retry], undefined, { signal });
+  }
+}
+
 /** The model is asked for 512 bytes; `accepted` is the longest line kept without a retry (the profile's summary size tolerance). */
 export function createCompressor(registry: ModelRegistry, choice: () => ModelChoice,
   onUsage: (message: AssistantMessage) => void = () => {}, accepted = () => DEFAULT_SETTINGS.summaryAcceptBytes,
-  retryDelays: readonly number[] = [1000, 2000]): Compressor {
+  retryDelays?: readonly number[]): Compressor {
   const gate = primeFirst();
   return async (input, signal) => {
     const selected = choice();
@@ -72,19 +83,12 @@ export function createCompressor(registry: ModelRegistry, choice: () => ModelCho
         return await stream.result();
       } finally { warmed(false); }
     };
-    // Pi's agent loop retries a dropped connection itself; streamSimple doesn't, so a transient error is asked again before it surfaces.
-    const answer = async () => {
-      for (let retry = 0; ; retry++) {
-        const reply = await ask();
-        onUsage(reply);
-        if (retry >= retryDelays.length || !isRetryableAssistantError(reply)) return reply;
-        await sleep(retryDelays[retry], undefined, { signal });
-      }
-    };
+    const answer = () => retryTransient(ask, onUsage, retryDelays, signal);
     for (let attempt = 0; attempt < 5; attempt++) {
       const reply = await answer();
       // A stop reason means the model answered: a refusal or a content filter, which asking again repeats.
-      if (reply.stopReason === 'error' && reply.rawStopReason !== undefined && !isRetryableAssistantError(reply))
+      // A provider's own 'error' stop (Mistral) is a failure on its side, not an answer: a plain error, tried again later.
+      if (reply.stopReason === 'error' && reply.rawStopReason !== undefined && reply.rawStopReason !== 'error' && !isRetryableAssistantError(reply))
         throw new Refused(reply.errorMessage ?? `Compactor stopped: ${reply.rawStopReason}`);
       if (reply.stopReason === 'error' || reply.stopReason === 'aborted') throw new Error(reply.errorMessage ?? `Compactor ${reply.stopReason}`);
       // A reply cut off at the token limit, or one that calls a tool, is no summary: ask again.

package/src/handoff.ts

@@ -1,7 +1,7 @@
 import type { ModelRegistry } from '@earendil-works/pi-coding-agent';
 import type { AgentMessage } from '@earendil-works/pi-agent-core';
 import type { AssistantMessage } from '@earendil-works/pi-ai';
-import { reasoningFor, type ModelChoice } from './compactor.ts';
+import { reasoningFor, retryTransient, type ModelChoice } from './compactor.ts';
 import { HANDOFF } from './prompts.ts';
 import type { RunInfo } from './runs.ts';
 import { textContent } from './transcript.ts';
@@ -30,7 +30,7 @@ function formatEvidence({ run, messages, transcriptError }: HandoffEvidence) {
 
 /** Summarize in one call when possible; otherwise fold chunks with the prior handoff included in the budget. */
 export function createHandoffSummarizer(registry: ModelRegistry, choice: () => ModelChoice,
-  usage: (message: AssistantMessage) => void) {
+  usage: (message: AssistantMessage) => void, retryDelays?: readonly number[]) {
   return async (run: RunInfo, messages: AgentMessage[], descendants: HandoffEvidence[] = []) => {
     const selected = choice(), model = registry.find(selected.provider, selected.model);
     if (!model) throw new Error('Profile compactor model unavailable');
@@ -50,11 +50,10 @@ export function createHandoffSummarizer(registry: ModelRegistry, choice: () => M
       let end = Math.min(transcript.length, offset + available);
       // Keep multibyte characters intact at chunk boundaries.
       while (end < transcript.length && (transcript[end] & 0xc0) === 0x80) end--;
-      const reply = await registry.streamSimple(model, {
+      const reply = await retryTransient(() => registry.streamSimple(model, {
         systemPrompt: HANDOFF,
         messages: [{ role: 'user', timestamp: Date.now(), content: prefix + transcript.subarray(offset, end).toString('utf8') }],
-      }, { reasoning: reasoningFor(model, selected.thinking), maxTokens, signal: AbortSignal.timeout(300_000) }).result();
-      usage(reply);
+      }, { reasoning: reasoningFor(model, selected.thinking), maxTokens, signal: AbortSignal.timeout(300_000) }).result(), usage, retryDelays);
       if (reply.stopReason === 'error' || reply.stopReason === 'aborted') throw new Error(reply.errorMessage ?? reply.stopReason);
       if (reply.stopReason === 'length') throw new Error('Handoff hit the model output limit before finishing');
       summary = textContent(reply.content).trim();