opencode-acp 1.14.8-dev.5 → 1.14.9-dev.1

package/README.md

@@ -492,6 +492,15 @@ For the complete list with root cause analysis, see the [bug tracker](https://gi
 
 ## Changelog
 
+### v1.14.9-dev.1 — Dev Prerelease (1 PR since v1.14.8-dev.5)
+
+Dev prerelease covering PR #259. Published to `dev` npm tag for early testing.
+
+**PRs included**:
+- **#259** — Document multi-entry compress format in system prompt and T2/T3 nudge. The compress tool already supported `content` arrays (PR #156), but only single-entry was shown for block-based compression. Now both formats are documented neutrally.
+
+**Install**: `opencode plugin opencode-acp@dev --global`
+
 ### v1.14.8-dev.5 — Dev Prerelease (1 PR since v1.14.8-dev.4)
 
 Dev prerelease covering PR #257. Published to `dev` npm tag for early testing.

package/README.zh-CN.md

@@ -446,6 +446,15 @@ ACP 是 DCP 的直接替代品。迁移步骤：
 
 ## 更新日志
 
+### v1.14.9-dev.1 — Dev 预发布（v1.14.8-dev.5 以来 1 个 PR）
+
+Dev 预发布，涵盖 PR #259。发布到 `dev` npm tag 供早期测试。
+
+**包含的 PR**：
+- **#259** — 在系统提示词和 T2/T3 nudge 中文档化多条目 compress 格式。compress 工具已支持 `content` 数组（PR #156），但块压缩只展示了单条目格式。现在两种格式都被中立地文档化。
+
+**安装**：`opencode plugin opencode-acp@dev --global`
+
 ### v1.14.8-dev.5 — Dev 预发布（v1.14.8-dev.4 以来 1 个 PR）
 
 Dev 预发布，涵盖 PR #257。发布到 `dev` npm tag 供早期测试。

package/dist/index.js

@@ -7582,6 +7582,7 @@ Target blocks (oldest first):
 ${blockList}${extraCount}
 
 Compress range: \`content: [{ startId: "b${firstBlock.blockId}", endId: "b${lastBlock.blockId}", summary: "..." }]\`
+Multiple entries create separate blocks: \`content: [{ startId: "b${firstBlock.blockId}", endId: "b...", summary: "..." }, { startId: "b...", endId: "b${lastBlock.blockId}", summary: "..." }]\`
 
 ${rules}`;
       appendToLastTextPart(suffixMessage, tierText);
@@ -8830,7 +8831,7 @@ import { writeFile as writeFile2, mkdir as mkdir2 } from "fs/promises";
 import { join as join3 } from "path";
 import { existsSync as existsSync3 } from "fs";
 import { homedir as homedir3 } from "os";
-var LOG_VERSION = true ? "1.14.8-dev.5" : "dev";
+var LOG_VERSION = true ? "1.14.9-dev.1" : "dev";
 var Logger = class {
   logDir;
   enabled;
@@ -9099,7 +9100,7 @@ Summaries accumulate as the session grows. When tier-1 summaries pile up, the sy
 - Tier 2: Distillation of old tier-1 block summaries. Uses TIER 2 DISTILLATION rules (decisions/outcomes only, drop paths/code/process).
 - Tier 3: Ultra-condensation of tier-2 summaries. Uses TIER 3 CONDENSATION rules (bare facts, 1-3 lines per block).
 
-To compress blocks: use block IDs as boundaries: \`compress({ content: [{ startId: "b3", endId: "b15", summary: "..." }] })\`. This deactivates the consumed blocks and creates a new higher-tier block. The system prompt at the trigger tells you which rules to follow.
+To compress blocks: use block IDs as boundaries: \`compress({ content: [{ startId: "b3", endId: "b15", summary: "..." }] })\`. Multiple entries create separate blocks: \`compress({ content: [{ startId: "b3", endId: "b10", summary: "..." }, { startId: "b11", endId: "b20", summary: "..." }] })\`. This deactivates the consumed blocks and creates a new higher-tier block per entry. The system prompt at the trigger tells you which rules to follow.
 
 If you are unsure which \`mNNNNN\` refs are still compressible, or which blocks have already consumed which ranges, call \`acp_status\` first. It returns the visible context breakdown and the compressed block list.