@tduyng/pi-context 0.0.1 → 0.0.2

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tduyng/pi-context",
-  "version": "0.0.1",
+  "version": "0.0.2",
   "description": "Context-window suite: see what fills it, prune spent tool results, retire reads an edit made wrong, and recover what compaction dropped.",
   "keywords": [
     "pi",

package/src/cache-state.ts

@@ -54,6 +54,7 @@ function refreshAt(entry: SessionEntry): number | null {
     }
     if (entry.type !== 'message') return null
     if (entry.message.role !== 'assistant') return null
+    if (entry.message.stopReason === 'error' || entry.message.stopReason === 'aborted') return null
     const usage = entry.message.usage
     const read = usage.cacheRead ?? 0
     const write = usage.cacheWrite ?? 0

package/src/cached-compaction.ts

@@ -14,14 +14,23 @@ import {
 import type { Usage } from '@earendil-works/pi-ai'
 
 import { cacheState, formatExpiry, resolveRetention } from './cache-state.js'
-import { assistantText, forget, keptStartQuote, summaryInstruction, walkTrailing, type CapturedRequest, type CaptureStore, type TranscriptMessage } from './cached-request.js'
+import {
+    assistantText,
+    forget,
+    keptStartQuote,
+    summaryInstruction,
+    walkTrailing,
+    type CapturedRequest,
+    type CaptureStore,
+    type TranscriptMessage
+} from './cached-request.js'
 import { checkpointSummary } from './summary.js'
 
 const MAX_TOKENS_SHARE = 0.8
 
 type Preparation = SessionBeforeCompactEvent['preparation']
 
-type Decision = { kind: 'cached'; summary: string; tokens: number } | { kind: 'fallback'; reason: string }
+type Decision = { kind: 'cached'; summary: string; tokens: number; usage: Usage } | { kind: 'fallback'; reason: string }
 
 function traceFile(): string {
     return join(getAgentDir(), 'cached-compaction.jsonl')
@@ -51,11 +60,15 @@ async function cachedSummary(
     const keptStart = keptStartQuote(event.branchEntries, event.preparation.firstKeptEntryId)
     const instruction = summaryInstruction(keptStart, event.customInstructions)
     const transcript = convertToLlm([...captured.transcript, ...trailing, instruction])
-    const stream = ctx.modelRegistry.streamSimple(captured.model, { messages: transcript }, {
-        maxTokens: Math.min(Math.floor(event.preparation.settings.reserveTokens * MAX_TOKENS_SHARE), 32_000),
-        sessionId: ctx.sessionManager.getSessionId(),
-        cacheRetention: resolveRetention(process.env)
-    })
+    const stream = ctx.modelRegistry.streamSimple(
+        captured.model,
+        { messages: transcript },
+        {
+            maxTokens: Math.min(Math.floor(event.preparation.settings.reserveTokens * MAX_TOKENS_SHARE), 32_000),
+            sessionId: ctx.sessionManager.getSessionId(),
+            cacheRetention: resolveRetention(process.env)
+        }
+    )
     for await (const _ of stream) {
         // drain: the final assistant message carries text, usage and the stop reason
     }
@@ -65,7 +78,7 @@ async function cachedSummary(
     }
     const summary = assistantText(assistant)
     if (summary.trim() === '') return { kind: 'fallback', reason: 'the summary came back empty' }
-    return { kind: 'cached', summary, tokens: assistant.usage.input }
+    return { kind: 'cached', summary, tokens: assistant.usage.input, usage: assistant.usage }
 }
 
 function decideFallback(reason: string): SessionBeforeCompactResult {
@@ -94,7 +107,6 @@ let pendingTranscript: TranscriptMessage[] = []
 
 export default function cachedCompactionExtension(pi: ExtensionAPI): void {
     const store: CaptureStore = { captured: null }
-    let retentionApplied = false
 
     pi.on('context_with_system', (event) => {
         pendingTranscript = event.messages
@@ -109,10 +121,6 @@ export default function cachedCompactionExtension(pi: ExtensionAPI): void {
                 at: Date.now()
             }
         }
-        if (!retentionApplied && ctx.hasUI && process.env['PI_CACHE_RETENTION'] === undefined) {
-            retentionApplied = true
-            process.env['PI_CACHE_RETENTION'] = 'long'
-        }
     })
 
     pi.on('model_select', () => {
@@ -140,13 +148,9 @@ export default function cachedCompactionExtension(pi: ExtensionAPI): void {
             const decision = await cachedSummary(captured, event, ctx)
             if (decision.kind === 'fallback') return decideFallback(decision.reason)
             const previous = getLatestCompactionEntry(event.branchEntries)
-            const prepared = checkpointSummary(
-                decision.summary,
-                event.preparation.fileOps,
-                previous?.details
-            )
+            const prepared = checkpointSummary(decision.summary, event.preparation.fileOps, previous?.details)
             trace({ decision: 'cached', tokens: decision.tokens })
-            return runSummary(event.preparation, prepared.summary, prepared.details, undefined)
+            return runSummary(event.preparation, prepared.summary, prepared.details, decision.usage)
         } catch (error) {
             const reason = error instanceof Error ? error.message : String(error)
             return decideFallback(reason)

package/src/cached-request.ts

@@ -81,15 +81,13 @@ export function walkTrailing(captured: CapturedRequest, branchEntries: SessionEn
 
 export interface KeptStart {
     text: string
-    repeats: number
 }
 
 const QUOTE_CHARS = 120
 
 /**
  * The opening of the first message pi keeps verbatim, quoted back to the summarizer. The
- * quote marks where the kept window begins. A repeated opening is counted from the end,
- * so the quote names the last of them.
+ * quote marks where the kept window begins.
  */
 export function keptStartQuote(branchEntries: SessionEntry[], firstKeptEntryId: string): KeptStart | null {
     const start = branchEntries.findIndex((entry) => entry.id === firstKeptEntryId)
@@ -100,12 +98,7 @@ export function keptStartQuote(branchEntries: SessionEntry[], firstKeptEntryId:
         .filter((text) => text !== '')
     const first = quotes[0]
     if (first === undefined) return null
-    const text = first.slice(0, QUOTE_CHARS)
-    let repeats = 0
-    for (const quote of quotes) {
-        if (quote.startsWith(text)) repeats++
-    }
-    return { text, repeats }
+    return { text: first.slice(0, QUOTE_CHARS) }
 }
 
 /**
@@ -118,7 +111,6 @@ export function summaryInstruction(keptStart: KeptStart | null, customFocus: str
         keptStart === null
             ? 'Summarize the conversation so far.'
             : `Summarize the conversation only up to the message beginning "${keptStart.text}".\n` +
-              'A message with that opening may appear more than once: the boundary is the last of them.\n' +
               'Do not include anything after the boundary.'
     const message: BranchMessage = {
         role: 'user',