@lll9p/pi-better-compaction 0.5.0 → 0.6.0

package/README.md

@@ -2,11 +2,10 @@
 
 English | [中文](README.zh-CN.md)
 
-A [pi](https://github.com/nicepkg/pi) extension that upgrades context compaction with three coordinated strategies:
+A [pi](https://github.com/nicepkg/pi) extension that upgrades context compaction with two coordinated strategies:
 
-1. An optional **mid-run guard** aborts an oversized tool loop, waits for `agent_settled`, compacts once, then resumes with a hidden custom message.
-2. **OpenAI Responses APIs** use the provider's native compaction endpoint, preserving opaque context that plain text summaries lose.
-3. **All other APIs** (Anthropic, Gemini, etc.) can run pi's built-in compaction with a **dedicated cheaper/faster model**, so summarization doesn't consume quota on your primary model.
+1. **OpenAI Responses APIs** use the provider's native compaction endpoint, preserving opaque context that plain text summaries lose.
+2. **All other APIs** (Anthropic, Gemini, etc.) can run pi's built-in compaction with a **dedicated cheaper/faster model**, so summarization doesn't consume quota on your primary model.
 
 Everything fails open — if any step cannot proceed, pi's default compaction takes over.
 
@@ -70,8 +69,8 @@ If the file doesn't exist, all defaults apply. The extension never creates this
 | Option | Type | Default | Description |
 |--------|------|---------|-------------|
 | `enabled` | `boolean` | `true` | Master switch. Set `false` to disable the extension entirely. |
-| `midRun.enabled` | `boolean` | `false` | Enable the mid-run guard. It may abort a long tool loop once context reaches the configured threshold. |
-| `midRun.thresholdPercent` | `number` | `80` | Context usage percentage that triggers the mid-run guard after a tool-bearing turn. Must be greater than 0 and at most 100. |
+| `midRun.enabled` | `boolean` | `false` | Reserved and currently ignored. The mid-run guard remains disabled even when set to `true`. |
+| `midRun.thresholdPercent` | `number` | `80` | Reserved threshold for the disabled mid-run guard. Must be greater than 0 and at most 100. |
 | `compactionVersion` | `"v1" \| "v2"` | `"v2"` | Protocol for Responses-family APIs. **V2** (streaming, encrypted blob) is the current OpenAI default. **V1** uses the legacy `/responses/compact` endpoint. |
 | `compactionModel` | `string \| null` | `null` | Model for fallback compaction (non-Responses APIs, or when native compact fails). Format: `"provider/model-id"`, e.g. `"openai/gpt-5.1-mini"`. `null` = let pi use the current chat model. |
 | `compactionThinkingLevel` | `string` | `"off"` | Thinking level for the fallback compaction model. One of: `off`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`. |
@@ -84,17 +83,6 @@ If the file doesn't exist, all defaults apply. The extension never creates this
 | `redactSensitiveData` | `boolean` | `true` | Redact secrets in debug artifacts. |
 | `artifactRoot` | `string` | `"~/.pi/agent/artifacts/pi-better-compaction"` | Root directory for debug artifacts. Supports `~/` and relative paths (resolved against config dir). |
 
-### Example: enable mid-run compaction
-
-```json
-{
-  "midRun": {
-    "enabled": true,
-    "thresholdPercent": 80
-  }
-}
-```
-
 ### Example: use a cheap model for fallback compaction
 
 ```json
@@ -114,8 +102,6 @@ If the file doesn't exist, all defaults apply. The extension never creates this
 
 ## How it works
 
-With `midRun.enabled`, a completed tool-bearing `turn_end` above the threshold only calls `ctx.abort()`. After Pi emits `agent_settled`, the guard reuses any compaction Pi already completed during abort handling; otherwise it calls `ctx.compact()` exactly once. A successful or coalesced compaction triggers the next turn with a hidden custom message. Failed compaction does not resume, preventing a compact-fail-resume loop.
-
 When pi triggers compaction (`session_before_compact`):
 
 1. **Responses API detected** → run native compaction (V2 or V1 per config):

package/README.zh-CN.md

@@ -2,11 +2,10 @@
 
 [English](README.md) | 中文
 
-一个 [pi](https://github.com/nicepkg/pi) 扩展，通过三条协同策略提升上下文压缩效果：
+一个 [pi](https://github.com/nicepkg/pi) 扩展，通过两条协同策略提升上下文压缩效果：
 
-1. 可选的 **mid-run guard** 在工具循环占满上下文时先中止运行，等待 `agent_settled` 后只压缩一次，再通过隐藏消息继续任务。
-2. **OpenAI Responses 系列 API** 使用提供商原生压缩端点，保留纯文本摘要无法留存的不透明上下文。
-3. **其他所有 API**（Anthropic、Gemini 等）可用一个**独立的低成本模型**执行 pi 内置压缩，避免在主模型上消耗额度。
+1. **OpenAI Responses 系列 API** 使用提供商原生压缩端点，保留纯文本摘要无法留存的不透明上下文。
+2. **其他所有 API**（Anthropic、Gemini 等）可用一个**独立的低成本模型**执行 pi 内置压缩，避免在主模型上消耗额度。
 
 所有环节都安全降级——任何步骤无法执行时，pi 的默认压缩自动接管。
 
@@ -70,8 +69,8 @@ cd pi-better-compaction && pi install .
 | 选项 | 类型 | 默认值 | 说明 |
 |------|------|--------|------|
 | `enabled` | `boolean` | `true` | 总开关。设为 `false` 完全禁用扩展。 |
-| `midRun.enabled` | `boolean` | `false` | 启用 mid-run guard。上下文达到阈值后，它可能主动中止长工具循环。 |
-| `midRun.thresholdPercent` | `number` | `80` | 工具型 turn 完成后触发 mid-run guard 的上下文占用百分比。必须大于 0 且不超过 100。 |
+| `midRun.enabled` | `boolean` | `false` | 保留配置，当前会被忽略。即使设为 `true`，mid-run guard 仍保持禁用。 |
+| `midRun.thresholdPercent` | `number` | `80` | 已禁用的 mid-run guard 的保留阈值。必须大于 0 且不超过 100。 |
 | `compactionVersion` | `"v1" \| "v2"` | `"v2"` | Responses 系列 API 的压缩协议。**V2**（流式，加密 blob）是 OpenAI 当前默认协议；**V1** 使用旧版 `/responses/compact` 端点。 |
 | `compactionModel` | `string \| null` | `null` | 回退压缩使用的模型（用于非 Responses API，或原生压缩失败时）。格式：`"provider/model-id"`，如 `"openai/gpt-5.1-mini"`。`null` = 由 pi 使用当前对话模型。 |
 | `compactionThinkingLevel` | `string` | `"off"` | 回退压缩模型的思考级别。可选：`off`、`minimal`、`low`、`medium`、`high`、`xhigh`、`max`。 |
@@ -84,17 +83,6 @@ cd pi-better-compaction && pi install .
 | `redactSensitiveData` | `boolean` | `true` | 在调试文件中脱敏。 |
 | `artifactRoot` | `string` | `"~/.pi/agent/artifacts/pi-better-compaction"` | 调试文件根目录。支持 `~/` 和相对路径（相对于配置文件目录解析）。 |
 
-### 示例：启用 mid-run 压缩
-
-```json
-{
-  "midRun": {
-    "enabled": true,
-    "thresholdPercent": 80
-  }
-}
-```
-
 ### 示例：使用低成本模型做回退压缩
 
 ```json
@@ -114,8 +102,6 @@ cd pi-better-compaction && pi install .
 
 ## 工作原理
 
-启用 `midRun.enabled` 后，超过阈值的工具型 `turn_end` 只调用 `ctx.abort()`。Pi 发出 `agent_settled` 后，guard 会复用 abort 收尾阶段已经完成的压缩；如果没有，则只调用一次 `ctx.compact()`。压缩成功或竞争合并后，通过隐藏 custom message 触发下一轮。压缩失败时不会自动继续，避免进入“压缩失败—继续—再次失败”的循环。
-
 pi 触发压缩时（`session_before_compact`）：
 
 1. **检测到 Responses API** → 执行原生压缩（根据配置选择 V2 或 V1）：

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lll9p/pi-better-compaction",
-  "version": "0.5.0",
+  "version": "0.6.0",
   "type": "module",
   "description": "Better compaction for pi: native /responses/compact replay for OpenAI Responses APIs, plus a configurable compaction model driving pi's native summarization everywhere else.",
   "author": "Lilin Lao",

package/src/extension-runtime.ts

@@ -10,7 +10,6 @@ import { executeV2Compaction } from "./compact-client-v2";
 import { loadExtensionConfig } from "./config";
 import { writeDebugArtifact } from "./debug";
 import { resolveLatestNativeCompactionEntry } from "./details-store";
-import { registerMidRunGuard } from "./midrun";
 import { runNativeFallbackCompaction } from "./native-fallback";
 import {
 	rewriteResponsesPayloadWithNativeReplay,
@@ -672,8 +671,7 @@ export function registerExtensionRuntime(
 	pi: ExtensionAPI,
 	dependencies: ExtensionRuntimeDependencies = DEFAULT_DEPENDENCIES,
 ): void {
-	registerMidRunGuard(pi, dependencies.loadExtensionConfig);
-
+	// Mid-run compaction is intentionally disabled regardless of config.
 	pi.on("session_start", (_event, ctx) => {
 		const { config, source, warnings } = dependencies.loadExtensionConfig();
 		if (!config.enabled) return;