opencode-acp 1.18.0-pr.392.149 → 1.18.0-pr.394.151

package/README.md

@@ -10,6 +10,16 @@ The model decides <em>when</em> and <em>what</em> to compress — not a hard lim
 
 ---
 
+
+## 📄 Paper / Preprint
+
+- **[Model-Driven Incremental Hierarchical Compression: Training-Free Multi-Generational Context Management for Long-Lived Coding Agents](./paper/model-driven-incremental-hierarchical-compression-training-free-multi-generational-context-management-for-long-lived-coding-agents.md)** (English, v0.2)
+- [模型驱动的分层增量压缩:面向长寿命编码 Agent 的免训练多代上下文管理](./paper/模型驱动的分层增量压缩-免训练多代上下文管理.md)(中文版)
+
+A production-scale longitudinal study: 4.5 months, three hosts, 174,327 model calls, 18.76B cumulative input tokens (~24.7B across all hosts), zero window violations on 204,800-token models, marathon sessions of 8,584–12,049 calls.
+
+---
+
 <p align="center">
 <a href="https://www.npmjs.com/package/opencode-acp"><img src="https://img.shields.io/npm/v/opencode-acp.svg?style=flat-square" alt="npm"></a>
 <a href="https://github.com/ranxianglei/opencode-acp/blob/master/LICENSE"><img src="https://img.shields.io/npm/l/opencode-acp.svg?style=flat-square" alt="license"></a>

package/README.zh-CN.md

@@ -10,6 +10,16 @@
 
 ---
 
+
+## 📄 论文 / 预印本
+
+- **[模型驱动的分层增量压缩:面向长寿命编码 Agent 的免训练多代上下文管理](./paper/模型驱动的分层增量压缩-免训练多代上下文管理.md)**(中文版,v0.2)
+- [Model-Driven Incremental Hierarchical Compression: Training-Free Multi-Generational Context Management for Long-Lived Coding Agents](./paper/model-driven-incremental-hierarchical-compression-training-free-multi-generational-context-management-for-long-lived-coding-agents.md)(English)
+
+生产规模纵向研究:四个半月、三宿主、174,327 次模型调用、187.6 亿累计输入 token(三宿主合计约 247 亿),204,800-token 窗口零违规,马拉松会话 8,584–12,049 次调用。
+
+---
+
 <p align="center">
 <a href="https://www.npmjs.com/package/opencode-acp"><img src="https://img.shields.io/npm/v/opencode-acp.svg?style=flat-square" alt="npm"></a>
 <a href="https://github.com/ranxianglei/opencode-acp/blob/master/LICENSE"><img src="https://img.shields.io/npm/l/opencode-acp.svg?style=flat-square" alt="license"></a>

package/dist/index.js

@@ -9150,7 +9150,7 @@ ${rules}`;
     const lines = [
       `[ACP Debug] Recommendation filter:`,
       `  Input: ${compressible.length} range(s), ${fmt(compressible.reduce((s, r) => s + r.tokens, 0))} tokens`,
-      `  Output: ${candidatePlan.candidates.length} candidate(s) (${candidatePlan.truncatedCount} truncated)`
+      candidatesEnabled ? `  Output: ${candidatePlan.candidates.length} candidate(s) (${candidatePlan.truncatedCount} truncated)` : `  Output: ${recommendedRanges.length} range(s) (last segment marked dangerous)`
     ];
     logger.debug(lines.join("\n"));
   }
@@ -9162,7 +9162,7 @@ ${rules}`;
       const growth = currentTokens !== void 0 && (state.nudges.lastNudgeShownTokens ?? state.nudges.lastPerMessageNudgeTokens) !== void 0 ? currentTokens - (state.nudges.lastNudgeShownTokens ?? state.nudges.lastPerMessageNudgeTokens) : 0;
       const growthStr = growth > 0 ? ` (+${fmt(growth)} since last nudge)` : "";
       const plainTextTokens = composition.textTokens;
-      const efficiencyNote = effectiveTipsVariant !== "maxLimit" ? "\nThis is an efficiency nudge to compress early when content is no longer needed and keep context lean \u2014 not an overflow warning. A separate, stronger alert will appear if the context is actually full.\n\n" + COMPRESS_PHILOSOPHY : "";
+      const efficiencyNote = effectiveTipsVariant !== "maxLimit" ? candidatesEnabled ? "\nThis is an efficiency nudge to compress early when content is no longer needed and keep context lean \u2014 not an overflow warning. A separate, stronger alert will appear if the context is actually full.\n\n" + COMPRESS_PHILOSOPHY : "\nThis is an efficiency nudge to compress early and keep context lean \u2014 not an overflow warning. A separate, stronger alert will appear if the context is actually full.\n\n" + COMPRESS_PHILOSOPHY : "";
       const sysPart = composition.systemTokens > 0 ? `${fmt(composition.systemTokens)} system (${pct2(composition.systemTokens)}%) | ` : "";
       let breakdown = `${efficiencyNote}
 Breakdown: ${sysPart}${fmt(composition.toolTokens)} tool (${pct2(composition.toolTokens)}%) | ${fmt(composition.summaryTokens)} summaries (${pct2(composition.summaryTokens)}%) | ${fmt(composition.codeTokens)} code (${pct2(composition.codeTokens)}%) | ${fmt(plainTextTokens)} text (${pct2(plainTextTokens)}%) | ${fmt(composition.reasoningTokens)} reasoning (${pct2(composition.reasoningTokens)}%)${growthStr}`;
@@ -10154,22 +10154,39 @@ function renderOverview(visibleMessages, summaryTokens, systemTokens, blocks, fe
     }
   }
   if (!fetchFailed) {
-    const pruneMap = ctx.state.prune.messages.byMessageId;
-    const visibleRaw = rawMessages.filter((msg) => {
-      const msgId = msg.info?.id || "";
-      const entry = pruneMap.get(msgId);
-      return !entry || entry.activeBlockIds.length === 0;
-    });
-    const candidates = renderCompressionCandidates(rawMessages, ctx);
-    if (candidates.length > 0) {
-      lines.push("");
-      lines.push(...candidates);
+    if (ctx.config?.compress?.candidates === true) {
+      const candidates = renderCompressionCandidates(rawMessages, ctx);
+      if (candidates.length > 0) {
+        lines.push("");
+        lines.push(...candidates);
+      }
+    } else {
+      const pruneMap = ctx.state.prune.messages.byMessageId;
+      const visibleRaw = rawMessages.filter((msg) => {
+        const msgId = msg.info?.id || "";
+        const entry = pruneMap.get(msgId);
+        return !entry || entry.activeBlockIds.length === 0;
+      });
+      const protectedRefs = ctx.config?.compress ? computeProtectedRefs(visibleRaw, ctx.state, ctx.config.compress) : /* @__PURE__ */ new Set();
+      const contextRanges = buildCompressibleRanges(
+        visibleRaw,
+        ctx.state,
+        ctx.config?.compress?.protectedTools ?? [],
+        ctx.config?.protectedFilePatterns ?? [],
+        protectedRefs
+      );
+      if (contextRanges.compressible.length > 0 || contextRanges.protected.length > 0) {
+        lines.push("");
+        lines.push(
+          formatCompressibleRanges(contextRanges.compressible, contextRanges.protected)
+        );
+      }
     }
   }
   lines.push("");
   const hintTool = topToolName || "bash";
   lines.push(
-    `Tip: acp_status({scope:"uncompressed", view:"ranges"}) for raw ranges, or acp_status({scope:"uncompressed", view:"messages", tool:"${hintTool}"}) for per-message listing`
+    ctx.config?.compress?.candidates === true ? `Tip: acp_status({scope:"uncompressed", view:"ranges"}) for raw ranges, or acp_status({scope:"uncompressed", view:"messages", tool:"${hintTool}"}) for per-message listing` : `Tip: acp_status({scope:"uncompressed", view:"messages", tool:"${hintTool}"}) for per-message listing`
   );
   return lines;
 }
@@ -10536,7 +10553,7 @@ import { writeFile as writeFile2, mkdir as mkdir2 } from "fs/promises";
 import { join as join4 } from "path";
 import { existsSync as existsSync4 } from "fs";
 import { homedir as homedir3 } from "os";
-var LOG_VERSION = true ? "1.18.0-pr.392.149" : "dev";
+var LOG_VERSION = true ? "1.18.0-pr.394.151" : "dev";
 var LEVEL_RANK = {
   debug: 10,
   info: 20,
@@ -12749,7 +12766,7 @@ function createChatMessageTransformHandler(client, registry4, logger, config, pr
       });
     }
     const prePruneTokens = getCurrentTokenUsage(state, output.messages);
-    const candidateMessages = output.messages.slice();
+    const candidateMessages = config.compress.candidates === true ? output.messages.slice() : void 0;
     prune(state, logger, config, output.messages);
     hideConsumedCompressCalls(state, output.messages);
     assignMessageRefs(state, output.messages);
@@ -13219,7 +13236,7 @@ var server = (async (ctx) => {
   }
   const logger = new Logger(config.debug, config.debug ? "debug" : config.logLevel);
   logger.info("ACP plugin initialized", {
-    version: true ? "1.18.0-pr.392.149" : "dev",
+    version: true ? "1.18.0-pr.394.151" : "dev",
     workspace: ctx.directory,
     logLevel: logger.level,
     debug: config.debug,