opencode-acp 1.2.0 → 1.3.1

package/dist/index.js

@@ -5523,18 +5523,39 @@ function applyMessageModeAnchoredNudge(anchorMessageIds, messages, baseNudgeText
     injectAnchoredNudge(message, nudgeText);
   }
 }
-function buildContextUsageInfo(currentTokens, modelContextLimit) {
+function resolveThresholdPercent(threshold, modelContextLimit) {
+  if (threshold === void 0) return void 0;
+  if (typeof threshold === "number") {
+    if (!modelContextLimit) return void 0;
+    return threshold / modelContextLimit * 100;
+  }
+  const parsed = parseFloat(threshold);
+  return isNaN(parsed) ? void 0 : parsed;
+}
+function buildContextUsageGuidance(config, currentTokens, modelContextLimit) {
   if (currentTokens === void 0 || modelContextLimit === void 0 || modelContextLimit === 0) {
     return "";
   }
-  const percentage = (currentTokens / modelContextLimit * 100).toFixed(1);
+  const pct = currentTokens / modelContextLimit * 100;
+  const percentage = pct.toFixed(1);
   const formatK = (n) => n >= 1e3 ? `${(n / 1e3).toFixed(1)}K` : String(n);
+  const minPct = resolveThresholdPercent(config.compress.minContextLimit, modelContextLimit) ?? 45;
+  const maxPct = resolveThresholdPercent(config.compress.maxContextLimit, modelContextLimit) ?? 55;
+  const base = `Context usage: ${formatK(currentTokens)} / ${formatK(modelContextLimit)} tokens (${percentage}%). ACP threshold: ${maxPct.toFixed(0)}%.`;
+  let guidance;
+  if (pct < minPct) {
+    guidance = " Context is ample \u2014 focus on your task. Only compress obvious waste (large terminal outputs, duplicated content).";
+  } else if (pct < maxPct) {
+    guidance = " Context is moderate \u2014 compress completed sections and high-token waste. Preserve key details.";
+  } else {
+    guidance = " Context is high \u2014 compress aggressively but selectively. Preserve only what is essential.";
+  }
   return `
 
-Context usage: ${formatK(currentTokens)} / ${formatK(modelContextLimit)} tokens (${percentage}%). ACP (Active Context Pruning) threshold: 55%. You ARE the ACP agent \u2014 use the compress tool proactively to manage context quality.`;
+${base}${guidance}`;
 }
 function applyAnchoredNudges(state, config, messages, prompts, compressionPriorities, currentTokens, modelContextLimit, suffixMessage) {
-  const contextUsageInfo = buildContextUsageInfo(currentTokens, modelContextLimit);
+  const contextUsageInfo = buildContextUsageGuidance(config, currentTokens, modelContextLimit);
   const contextLimitNudgeWithUsage = prompts.contextLimitNudge + contextUsageInfo;
   const turnNudgeAnchors = collectTurnNudgeAnchors2(state, config, messages);
   if (suffixMessage) {
@@ -5709,7 +5730,7 @@ var injectCompressNudges = (state, config, logger, messages, prompts, compressio
   }
   const suffixMessage = createSuffixMessage(messages);
   applyAnchoredNudges(state, config, messages, prompts, compressionPriorities, currentTokens, modelContextLimit, suffixMessage);
-  injectContextUsage(suffixMessage, currentTokens, modelContextLimit);
+  injectContextUsage(suffixMessage, config, currentTokens, modelContextLimit);
   if (config.compress.mode !== "message") {
     const blockGuidance = buildCompressedBlockGuidance(state, config.gc, { currentTokens, modelContextLimit });
     if (blockGuidance.trim() && suffixMessage) {
@@ -5721,16 +5742,10 @@ var injectCompressNudges = (state, config, logger, messages, prompts, compressio
     void saveSessionState(state, logger);
   }
 };
-function injectContextUsage(target, currentTokens, modelContextLimit) {
+function injectContextUsage(target, config, currentTokens, modelContextLimit) {
   if (!target) return;
-  if (currentTokens === void 0 || modelContextLimit === void 0 || modelContextLimit === 0) {
-    return;
-  }
-  const percentage = (currentTokens / modelContextLimit * 100).toFixed(1);
-  const formatK = (n) => n >= 1e3 ? `${(n / 1e3).toFixed(1)}K` : String(n);
-  const usageTag = `
-
-Context usage: ${formatK(currentTokens)} / ${formatK(modelContextLimit)} tokens (${percentage}%). ACP (Active Context Pruning) threshold: 55%. You ARE the ACP agent \u2014 use the compress tool proactively to manage context quality.`;
+  const usageTag = buildContextUsageGuidance(config, currentTokens, modelContextLimit);
+  if (!usageTag) return;
   for (const part of target.parts) {
     if (part.type === "text") {
       appendToTextPart(part, usageTag);
@@ -6465,37 +6480,74 @@ import { homedir as homedir4 } from "os";
 
 // lib/prompts/system.ts
 var SYSTEM = `
-You operate in a context-constrained environment. Manage context continuously to avoid buildup and preserve retrieval quality. Efficient context management is paramount for your agentic performance.
+
+You operate in a context-constrained environment. Context management helps preserve retrieval quality, but your primary goal is completing the task at hand. Do not let context management distract from the actual work.
 
 The tools you have for context management are \`compress\` and \`decompress\`. \`compress\` replaces older conversation content with technical summaries you produce. \`decompress\` restores previously compressed content when you need exact details.
 
 \`<dcp-message-id>\` and \`<dcp-system-reminder>\` tags are environment-injected metadata. Do not output them.
 
-THE PHILOSOPHY OF COMPRESS
-\`compress\` transforms conversation content into dense, high-fidelity summaries. This is not cleanup - it is crystallization. Your summary becomes the authoritative record of what transpired.
+COMPRESSION PHILOSOPHY
+
+Compression replaces raw conversation content with dense summaries. When used correctly, it keeps your context sharp and focused. When used carelessly, it destroys information you need.
+
+The key principle: compress based on context pressure, not habit. When context is ample, compress rarely or not at all. When context is tight, compress aggressively but selectively. The runtime context usage indicator tells you the current pressure level.
+
+Target the largest UNCOMPRESSED content first. Savings scale with original size \u2014 compressing a 5000-token tool output frees far more than re-shrinking an already-summarized 300-token block.
+
+CONTEXT PRESSURE LEVELS
+
+- Ample: Context is well below the threshold. Do NOT compress unless there is obvious waste (huge terminal dumps, duplicated content). Focus entirely on your task.
+- Moderate: Context is approaching the threshold. Compress completed sections proactively. Prioritize high-token waste over minor cleanup.
+- High: Context has exceeded the threshold. Compress aggressively. Every compression should free meaningful tokens. Preserve only what is essential for the current task.
+
+WHAT TO COMPRESS FIRST (high value, low risk)
+
+- Agent/subagent review and consultation results: Prime compression targets when context pressure rises \u2014 the surrounding reasoning and tool-call chatter is typically the largest block of uncompressed content. Note: if the agent tool is in your protected list, its output is auto-preserved in the summary, so the savings come from the surrounding conversation, not the agent output itself. Compress once you have fully consumed the results (all recommended actions applied or recorded in files). Recover via \`decompress\` while the block is still active. Re-invoking the agent is a last resort \u2014 it is a fresh run, not a cache hit.
+- Verbose command output (build/test runs, git diff/log/status, publish logs, directory listings): Once you have read the result, compress. Keep only the verdict \u2014 pass/fail status, commit hash, version number, or count. For failures, keep the specific error messages and file/line references needed to act on them. The full output is reproducible by re-running the command.
+- Exploration that led nowhere (failed approaches, dead-end searches): Compress to a one-line note about what was tried and why it failed.
+- Redundant tool results (reading the same file multiple times, repeated status checks, exhausted search results): Keep only the most recent result.
+- Intermediate steps of completed multi-step tasks: Once the task is done, compress the process. Keep only the final outcome.
+- Resolved discussion threads (clarification rounds, negotiated requirements, design debate that reached a decision): Once a conclusion is recorded, compress the back-and-forth. Keep the decision and its rationale.
+- Large file contents that have already been used and are no longer needed: Compress to a summary of key functions, types, or patterns.
+
+DO NOT RE-COMPRESS (low value, diminishing returns)
+
+- Already-compressed block summaries: Re-compressing a summary into a shorter summary saves negligible tokens. If a block needs better detail, use \`decompress\` to restore it, then compress the original content properly. Exception: if a block-aging warning flags specific block IDs as facing GC truncation, re-summarize exactly those flagged blocks into a fresh range \u2014 this preserves detail that GC would otherwise destroy.
+- Short messages (1-3 sentences): The compression overhead (block metadata, summary structure) may exceed the tokens saved.
+- Content whose immediate use is complete \u2014 the task it supported is done and no open todo/plan references it. If still in active use, let it stay.
+- User instructions and requirements: These must remain visible until the task is complete.
+- Tool calls that are still pending or in-progress: Wait until the result is returned and consumed.
 
-Think of compression as phase transitions: raw exploration becomes refined understanding. The original context served its purpose; your summary now carries that understanding forward.
+WHAT TO COMPRESS CAREFULLY (high risk - verify before compressing)
 
-COMPRESS WHEN
+- Temporary secrets/keys/tokens needed later: Do NOT compress unless recorded elsewhere
+- File paths and directory structures: Keep in summary - losing these wastes tokens rediscovering them
+- Key function/method signatures and APIs: Summarize with exact names and signatures
+- Critical error messages and stack traces: Keep the error type and key detail in summary
+- User preferences and requirements: These must survive compression intact
+- Architectural decisions and rationale: Summarize the decision, not just the conclusion
 
-A section is genuinely closed and the raw conversation has served its purpose:
+BEFORE COMPRESSING IMPORTANT CONTENT
 
-- Research concluded and findings are clear
-- Implementation finished and verified
-- Exploration exhausted and patterns understood
-- Dead-end noise can be discarded without waiting for a whole chapter to close
+Verify the information is persisted in one of:
+- A file you have written or edited
+- An issue, PR, or devlog entry
+- The compression summary itself (include the critical bits explicitly)
 
-DO NOT COMPRESS IF
+If it is not persisted anywhere, either persist it first or include it explicitly in your compression summary.
 
-- Raw context is still relevant and needed for edits or precise references
-- The target content is still actively in progress
-- You may need exact code, error messages, or file contents in the immediate next steps
+AFTER COMPRESSING
 
-Before compressing, ask: _"Is this section closed enough to become summary-only right now?"_
+Generate recovery breadcrumbs in your summary so future-you can reconstruct the context:
+- Reference specific files by path
+- Include key variable names, function signatures, or configuration values
+- Note what was decided and why, not just what was done
+- Example: "Implemented auth check in src/middleware.ts using validateToken() from auth.ts - user table is users not user"
 
-Evaluate conversation signal-to-noise REGULARLY. Use \`compress\` deliberately with quality-first summaries. Prioritize stale content intelligently to maintain a high-signal context window that supports your agency.
+If you later realize you need the original details from a compressed block, use \`decompress\` to restore them. You can decompress, read the content, then re-compress if needed.
 
-It is of your responsibility to keep a sharp, high-quality context window for optimal performance.
+Use \`compress\` and \`decompress\` deliberately with quality-first summaries. Prioritize stale content intelligently to maintain a high-signal context window.
 `;
 
 // lib/prompts/compress-range.ts