pi-observational-memory 2.4.1 → 2.4.3

package/README.md

@@ -76,7 +76,7 @@ flowchart TD
     Conv([Conversation accumulates])
     Obs[Observer<br/>async, fire-and-forget<br/>compresses each chunk into timestamped,<br/>relevance-tagged observations<br/>stored as silent tree entries]
     Comp[Compaction<br/>extension-owned; merges accumulated<br/>observations with prior compaction state]
-    RP[Reflector + Pruner<br/>Reflector runs focused passes<br/>to crystallize durable patterns<br/>Pruner drops observations by id<br/>across up to 5 passes]
+    RP[Reflector + Pruner<br/>Reflector runs two focused passes<br/>to crystallize durable patterns<br/>Pruner drops observations by id<br/>across up to 2 passes]
     Sum[Summary mechanically assembled<br/>## Reflections<br/>&nbsp;&nbsp;[id] durable insight<br/>## Observations<br/>&nbsp;&nbsp;[id] YYYY-MM-DD HH:MM relevance ...<br/>Becomes the compactionSummary<br/>the agent sees on the next turn]
 
     Conv -->|every ~1k raw tokens since last bound| Obs
@@ -126,7 +126,31 @@ To run the background memory work (observer, reflector, pruner) on a cheaper / f
 }
 ```
 
-The six settings most worth knowing:
+Nested agent-loop turns default to `16` for each memory role. To tune them (useful for controlling cost on large observation pools):
+
+```json
+{
+  "observational-memory": {
+    "observerMaxTurnsPerRun": 8,
+    "reflectorMaxTurnsPerPass": 12,
+    "prunerMaxTurnsPerPass": 12
+  }
+}
+```
+
+A turn is one assistant/model response cycle inside Pi's nested agent loop. These caps are checked after a turn finishes; they are not hard mid-stream interrupts and are not literal tool-call counters.
+
+For memory model calls, you can also tune thinking effort with one unified setting. Valid values are `off`, `minimal`, `low`, `medium`, `high`, and `xhigh`; the default is `low`.
+
+```json
+{
+  "observational-memory": {
+    "thinkingLevel": "low"
+  }
+}
+```
+
+The settings most worth knowing:
 
 | Setting | Default | What it controls |
 |---|---|---|
@@ -135,6 +159,10 @@ The six settings most worth knowing:
 | `reflectionThresholdTokens` | `30,000` | The observation pool size at which reflector + pruner engage |
 | `passive` | `false` | Disables proactive observation and extension-triggered compaction while keeping manual/Pi compaction and commands active |
 | `compactionModel` | session model | Which model runs the observer / reflector / pruner — point at a cheaper one to save cost |
+| `observerMaxTurnsPerRun` | `16` | Assistant-turn cap for each observer run |
+| `reflectorMaxTurnsPerPass` | `16` | Assistant-turn cap for each reflector pass |
+| `prunerMaxTurnsPerPass` | `16` | Assistant-turn cap for each pruner pass |
+| `thinkingLevel` | `low` | Thinking effort for observer, reflector, and pruner calls; `off` omits Pi's reasoning option |
 | `compaction.keepRecentTokens` | `20,000` | How much recent conversation Pi keeps verbatim post-compaction (Pi setting; structural to the extension) |
 
 For shell/session-level control, `PI_OBSERVATIONAL_MEMORY_PASSIVE` overrides global and project settings. Use `1`, `true`, `yes`, or `on` to enable passive mode; use `0`, `false`, `no`, or `off` to force it off.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-observational-memory",
-  "version": "2.4.1",
+  "version": "2.4.3",
   "description": "Observational memory extension for pi — cache-friendly tiered compaction with observations and reflections.",
   "type": "module",
   "license": "MIT",
@@ -40,11 +40,12 @@
     "@mariozechner/pi-tui": "*"
   },
   "devDependencies": {
-    "@mariozechner/pi-agent-core": "^0.66.1",
-    "@mariozechner/pi-ai": "^0.66.1",
-    "@mariozechner/pi-coding-agent": "^0.66.1",
-    "@mariozechner/pi-tui": "^0.66.1",
+    "@mariozechner/pi-agent-core": "^0.73.0",
+    "@mariozechner/pi-ai": "^0.73.0",
+    "@mariozechner/pi-coding-agent": "^0.73.0",
+    "@mariozechner/pi-tui": "^0.73.0",
     "@types/node": "^22.0.0",
+    "typebox": "^1.1.38",
     "typescript": "^5.6.0",
     "vitest": "^4.1.5"
   }

package/src/commands/status.ts

@@ -5,6 +5,7 @@ import {
 	rawTokensSinceLastBound,
 	rawTokensSinceLastCompaction,
 } from "../branch.js";
+import { observationPoolTokens as estimateObservationPoolTokens } from "../compaction.js";
 import { countByRelevance, formatRelevanceHistogram } from "../relevance.js";
 import type { Runtime } from "../runtime.js";
 import { estimateStringTokens } from "../tokens.js";
@@ -21,12 +22,12 @@ export function registerStatusCommand(pi: ExtensionAPI, runtime: Runtime): void
 
 			const { reflections: committedRefs, committedObs, pendingObs } = getMemoryState(entries);
 			const committedRefItems = committedRefs as MemoryReflection[];
-			const committedObsTokens = committedObs.reduce((s, r) => s + estimateStringTokens(r.content), 0);
+			const committedObsTokens = estimateObservationPoolTokens(committedObs);
 			const committedObsCount = committedObs.length;
 			const committedRefsTokens = committedRefItems.reduce((s, r) => s + estimateStringTokens(reflectionContent(r)), 0);
 			const committedRefsCount = committedRefItems.length;
 
-			const pendingObsTokens = pendingObs.reduce((s, r) => s + estimateStringTokens(r.content), 0);
+			const pendingObsTokens = estimateObservationPoolTokens(pendingObs);
 			const pendingObsCount = pendingObs.length;
 
 			const relevanceHistogram = countByRelevance([...committedObs, ...pendingObs]);
@@ -41,7 +42,7 @@ export function registerStatusCommand(pi: ExtensionAPI, runtime: Runtime): void
 			// at compaction entry. We over-count by the tail slice and can't predict the gap obs here.
 			// Precise version would simulate the new firstKeptEntryId by walking back keepRecentTokens from
 			// the branch tail and split pending into pre-tail vs tail-covering.
-			const observationPoolTokens = committedObsTokens + pendingObsTokens;
+			const observationPoolTokens = estimateObservationPoolTokens([...committedObs, ...pendingObs]);
 			const obsPct = Math.min(100, Math.round((sinceBound / obsThreshold) * 100));
 			const compPct = Math.min(100, Math.round((sinceCompaction / compThreshold) * 100));
 			const refPct = Math.min(100, Math.round((observationPoolTokens / refThreshold) * 100));

package/src/commands/view.ts

@@ -1,5 +1,6 @@
 import type { ExtensionAPI } from "@mariozechner/pi-coding-agent";
 import { getMemoryState } from "../branch.js";
+import { observationPoolTokens as estimateObservationPoolTokens } from "../compaction.js";
 import { countByRelevance, formatRelevanceHistogram } from "../relevance.js";
 import type { Runtime } from "../runtime.js";
 import { estimateStringTokens } from "../tokens.js";
@@ -17,14 +18,15 @@ export function registerViewCommand(pi: ExtensionAPI, runtime: Runtime): void {
 			const committedRefTokens = committedRefItems.reduce((s, r) => s + estimateStringTokens(reflectionContent(r)), 0);
 			const committedRefCount = committedRefItems.length;
 
-			const committedObsTokens = committedObs.reduce((s, r) => s + estimateStringTokens(r.content), 0);
+			const committedObsTokens = estimateObservationPoolTokens(committedObs);
 			const committedObsCount = committedObs.length;
 
-			const pendingObsTokens = pendingObs.reduce((s, r) => s + estimateStringTokens(r.content), 0);
+			const pendingObsTokens = estimateObservationPoolTokens(pendingObs);
 			const pendingObsCount = pendingObs.length;
 
 			const totalObsCount = committedObsCount + pendingObsCount;
-			const totalTokens = committedRefTokens + committedObsTokens + pendingObsTokens;
+			const totalObsTokens = estimateObservationPoolTokens([...committedObs, ...pendingObs]);
+			const totalTokens = committedRefTokens + totalObsTokens;
 			const relevanceHistogram = countByRelevance([...committedObs, ...pendingObs]);
 
 			const plural = (n: number, singular: string, plural: string) => (n === 1 ? singular : plural);