claude-mem-lite 6.9.0 → 6.10.0

package/.claude-plugin/marketplace.json

@@ -9,7 +9,7 @@
   "plugins": [
     {
       "name": "claude-mem-lite",
-      "version": "6.9.0",
+      "version": "6.10.0",
       "source": "./",
       "homepage": "https://github.com/sdsrss/claude-mem-lite",
       "description": "Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. A lighter, lower-cost alternative to claude-mem (episode batching + a smaller model; cost savings are an internal estimate, not a measured benchmark)."

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-mem-lite",
-  "version": "6.9.0",
+  "version": "6.10.0",
   "description": "Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. A lighter, lower-cost alternative to claude-mem (episode batching + a smaller model; cost savings are an internal estimate, not a measured benchmark).",
   "author": {
     "name": "sdsrss"

package/README.md

@@ -119,7 +119,9 @@ How claude-mem-lite differs from the major neighbors in the LLM-memory space (ve
 - **Schema auto-migration** -- Idempotent `ALTER TABLE` migrations run on every startup, safely adding new columns and indexes without data loss
 - **LLM concurrency control** -- File-based semaphore limits background workers to 2 concurrent LLM calls, preventing resource contention
 - **stdin overflow protection** -- Hook input truncated at 256KB with regex-based action salvage for oversized tool outputs
-- **Cross-session handoff** -- Captures session state (request, completed work, next steps, key files) on `/exit`, then injects context when the next session detects continuation intent via explicit keywords or FTS5 term overlap. **The `/clear` and `/compact` arm fires since v5.4.0** (R10-P1-1); before that it had never once written a row — `session_handoffs` on the maintainer's install held 4 `exit` rows and **0** `clear` rows. Two host facts settled it, both measured rather than assumed. (1) `Stop` runs at the end of every assistant *turn*, not once per session, and it deleted the session file that SessionStart reads to learn which session just ended — so the branch was unreachable, and mem sessions were minted per turn (58 prompts over 16 host sessions produced 56 mem sessions and 56 summary rows, 2026-09-07). (2) Claude Code **rotates its session id across `/clear`**: of 21 real transcripts, 12 carry a `/clear` command record, and in 12/12 that record's timestamp precedes its own file's first record by ~0.1s — the command is issued in the old session and replayed into a new file under a new id. So `Stop` no longer deletes the file, SessionStart asks the host's `source` (`startup`/`clear`/`compact`/`resume`) instead of guessing from the file, and the handoff's prompt lookup falls back to the unscoped set when the new session's id matches none. Revert path: `CLAUDE_MEM_LEGACY_STOP_UNLINK=1`
+- **Cross-session handoff** -- Captures session state on `/exit` and `/clear`, then injects context when the next session detects continuation intent
+  <br>**Changed in v6.10.0**: the injected block went from two sections to six. Its observation queries were keyed on the hook-minted session id while every `mem_save` writes a `manual-<project>` id, so `completed` and `key_decisions` could not reach a saved lesson at all — 17 of 17 stored rows held 0 bytes in both. The block now also carries `## Tree state` (branch, short sha, uncommitted count) and `## Next steps`, read from the project's newest `tasks/<slug>-paused.md` when it is under a week old. Four additive nullable columns land on `session_handoffs`; the schema version deliberately does not move, so an older build still opens the database (measured: the v6.9.1 tree read and wrote a database this release had migrated). Revert by pinning `claude-mem-lite@6.9.1` — no data-directory work.
+  <br>Original behaviour and the measurements behind it via explicit keywords or FTS5 term overlap. **The `/clear` and `/compact` arm fires since v5.4.0** (R10-P1-1); before that it had never once written a row — `session_handoffs` on the maintainer's install held 4 `exit` rows and **0** `clear` rows. Two host facts settled it, both measured rather than assumed. (1) `Stop` runs at the end of every assistant *turn*, not once per session, and it deleted the session file that SessionStart reads to learn which session just ended — so the branch was unreachable, and mem sessions were minted per turn (58 prompts over 16 host sessions produced 56 mem sessions and 56 summary rows, 2026-09-07). (2) Claude Code **rotates its session id across `/clear`**: of 21 real transcripts, 12 carry a `/clear` command record, and in 12/12 that record's timestamp precedes its own file's first record by ~0.1s — the command is issued in the old session and replayed into a new file under a new id. So `Stop` no longer deletes the file, SessionStart asks the host's `source` (`startup`/`clear`/`compact`/`resume`) instead of guessing from the file, and the handoff's prompt lookup falls back to the unscoped set when the new session's id matches none. Revert path: `CLAUDE_MEM_LEGACY_STOP_UNLINK=1`
 - **Git-SHA continuation anchor** (v2.31.0) -- Handoff rows include `git_sha_at_handoff`; any handoff matching the current `HEAD` counts as continuation regardless of TTL. Code state is a stronger continuation signal than wall-clock time
 - **Startup dashboard** (v2.31.0) -- SessionStart hook aggregates `git status` + `~/.claude/tasks/*.json` + `~/.claude/plans/*.md` + most-recent exit handoff + recent event count into a single structured block injected via `hookSpecificOutput.additionalContext`
 - **Activity namespace** (v2.31.0) -- Dedicated `events` table + FTS5 for non-memdir types (`bugfix`, `lesson`, `bug`, `discovery`, `refactor`, `feature`, `observation`, `decision`) that don't compete with `WHAT_NOT_TO_SAVE` semantics on the observations table. CLI: `claude-mem-lite activity save|search|recent|show`. `hook-llm` routes non-memdir summary types through `persistHaikuSummary` so upgrades from observations→events are atomic. (v3.39: the `/lesson` and `/bug` slash commands were redirected from this events table to searchable **observations** — `mem_search` never read the events table, so explicit saves were unfindable; the events table remains the auto-capture activity log.)

package/README.zh-CN.md

@@ -91,6 +91,7 @@
 - **LLM 并发控制** -- 基于文件的信号量将后台 worker 限制为 2 个并发 LLM 调用，防止资源争用
 - **stdin 溢出保护** -- Hook 输入在 256KB 处截断，对超大工具输出使用正则挽救关键信息
 - **跨会话交接** -- 在 `/clear` 或 `/exit` 时捕获会话状态（请求、已完成工作、后续步骤、关键文件），下次会话检测到继续意图时自动注入上下文（支持显式关键词和 FTS5 术语重叠匹配）
+  <br>**v6.10.0 变更**：注入块从 2 段变为 6 段。此前它的观测查询按钩子铸造的会话 id 过滤，而每一次 `mem_save` 写的是 `manual-<project>` id，两个命名空间不相交，所以 `completed` 与 `key_decisions` 根本够不到已保存的经验——库里 17 行交接记录这两个字段全是 0 字节。现在还会带 `## Tree state`（分支、短 sha、未提交文件数）和 `## Next steps`（读取项目里最新且未超过 7 天的 `tasks/<slug>-paused.md`）。`session_handoffs` 新增 4 个可空列；schema 版本号**刻意不动**，所以旧版本仍能打开数据库（已实测：v6.9.1 的代码能读写本版本迁移过的库）。回退方式：固定到 `claude-mem-lite@6.9.1`，无需处理数据目录。
 - **插件缓存 hook 自愈** -- Claude Code runtime 从 `~/.claude/plugins/cache/<mp>/<plugin>/<ver>/hooks/hooks.json` 读取插件 hook，而非 marketplace 源。当 `install.mjs` 写入 `settings.json` 的 hooks 与残留 cache `hooks.json` 同时存在（例如曾装过 marketplace 版本，或插件被 Claude Code 自动升级重建 cache），runtime 会注册两套 hook → 每次 SessionStart / UserPromptSubmit 都触发两份。`install.mjs` 和 `hook-update.mjs` 现在会清理每个 cache 版本目录下的 `hooks.json`；`hook.mjs session-start` 每次启动自愈（通过 `hasInstallManagedHooks` 门控，不影响纯插件模式用户）；`install.mjs status` 会报告 cache 污染状况（自 v2.31.1 / v2.31.2 起）。
 - **Git-SHA 延续锚点**（v2.31.0）-- handoff 记录包含 `git_sha_at_handoff` 字段，任何匹配当前 `HEAD` 的 handoff 都视为延续会话，不受 TTL 限制。代码状态比时钟时间更能反映上下文延续。
 - **启动面板**（v2.31.0）-- SessionStart hook 将 `git status` + `~/.claude/tasks/*.json` + `~/.claude/plans/*.md` + 最近 /exit 交接 + 最近事件数聚合为一个结构化块，通过 `hookSpecificOutput.additionalContext` 注入。

package/cli.mjs

@@ -136,6 +136,46 @@ const INSTALL_COMMANDS = new Set([
   'release',
 ]);
 
+// A reader that leaves is not an error. `claude-mem-lite search x | head -1`,
+// `| grep -q`, or quitting `less` closes the read end while we are still writing;
+// Node then emits 'error' on the stdout Socket, and with no listener that is an
+// UNHANDLED error event — a ~20-line stack ending in `outVerbatim` where the user
+// expected the shell prompt.
+//
+// WHICH COMMANDS, measured rather than generalised (20 trials each, `| head -1`,
+// pre-fix): `search`, `export`, `recent`, `stats`, `doctor`, `timeline`,
+// `citation-stats` 20/20; `browse` 19/20; `help`, `status`, `context`, `get`,
+// `memdir-audit` 0/20. So NOT "every stdout-bearing command" — what decides it is
+// whether a write is still pending when the reader goes, which depends on how many
+// lines the consumer takes and how the output is batched — NOT on the 64 KB pipe
+// buffer, which an earlier draft of this comment blamed: pre-ship review found
+// `stats` crashing at `head -20` on an output far under it. That output's size is
+// corpus dependent, so no byte count is quoted here. This is also why the crash
+// survived so long — it is invisible to exactly the pipe depths a smoke test picks.
+//
+// Lives HERE, at the published `bin`, and not at `cli/common.mjs`'s `out()`: the
+// crash reproduces on `doctor` too, whose writes are `console.log` inside
+// install.mjs, so a chokepoint fix would cover the CLI half and leave the installer
+// half loud. One process-level listener covers both routes below.
+//
+// SWALLOW, DO NOT EXIT. The first cut called `process.exit(0)` here, on the
+// reasoning that a CLI whose consumer has gone should stop rather than serialise a
+// whole-DB `export` into a dead pipe. Pre-ship review measured what that costs:
+// `doctor | head -1` under `pipefail` exited 0 on 10/10 runs while the same doctor
+// exits 1 unpiped, because `runDoctor` assigns `process.exitCode = 1` AFTER its last
+// print (install.mjs, "Diagnostic-tool exit-code contract") and the forced exit lands
+// first. That silently turns a failing `claude-mem-lite doctor || alert` — the
+// wrapper that contract names — into a passing one. `process.exitCode ?? 0` does not
+// rescue it: the verdict does not exist yet at kill time. Returning instead reads
+// exit 1 on 10/10 and keeps the crash fixed (doctor 0/10, search 0/10 EPIPE stacks).
+// Correctness over the saved work: the process finishes into a pipe nobody reads,
+// which is wasted effort but never a wrong answer. Non-EPIPE is rethrown — this is a
+// classifier, not a blanket swallow, the same charter `explainBrokenInstall` follows.
+process.stdout.on('error', (err) => {
+  if (err && err.code === 'EPIPE') return;
+  throw err;
+});
+
 const cmd = process.argv[2];
 
 // `version` and `-V` are aliases, not extra syntax: the bare subcommand is what a user

package/hook-context.mjs

@@ -27,6 +27,7 @@ import {
   effectiveQuiet,
   isQuietHooks,
   KEY_CONTEXT_LIMIT,
+  UNCONSUMED_HANDOFF_SQL,
 } from './hook-shared.mjs';
 import { extractUnfinishedSummary } from './hook-handoff.mjs';
 import { recentInjectableEvents, renderInjectableEvent } from './lib/events-injection.mjs';
@@ -752,6 +753,7 @@ export function buildSessionContextLines(
         SELECT working_on, unfinished, key_files
         FROM session_handoffs
         WHERE project = ? AND type = 'clear' AND session_id = ? AND created_at_epoch > ?
+          AND ${UNCONSUMED_HANDOFF_SQL}
         ORDER BY created_at_epoch DESC LIMIT 1
       `,
         )
@@ -761,7 +763,7 @@ export function buildSessionContextLines(
           `
         SELECT working_on, unfinished, key_files
         FROM session_handoffs
-        WHERE project = ? AND type = 'clear' AND created_at_epoch > ?
+        WHERE project = ? AND type = 'clear' AND created_at_epoch > ? AND ${UNCONSUMED_HANDOFF_SQL}
         ORDER BY created_at_epoch DESC LIMIT 1
       `,
         )