From 92c612b94c103a03bef25376a53a73348cdb418b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timeless=E5=B0=8F=E5=B8=85?= <1018008088@qq.com>
Date: Fri, 9 Oct 2026 10:28:34 +0800
Subject: [PATCH] memory: fix extraction trigger, dedupe, and add runtime
 diagnostics
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Four defects found by end-to-end testing, not by reading the code.

1. Extraction never ran, silently. Collecting every event type that
   ctx.event.subscribe actually delivers shows `session.idle` is NOT among
   them — it is defined in the protocol but never emitted on this stream.
   The subscription filtered on it alone, so auto-extraction was a permanent
   no-op with no error. Now debounced off events that do arrive
   (session.step.started / session.tool.called / session.inbox.delivered)
   after `settleMs` of quiet, which is what "idle" meant anyway. Verified:
   the trigger now fires and reports "轮数不足" for a 1-turn session.

2. Dedupe silently stopped rejecting duplicates. It compared against a fixed
   retrieval score, but that score carries idf and scope priors that drift as
   the corpus grows, so an obvious restatement of an existing memory scored
   0.48 against a 0.9 threshold and was written as a rival entry. Now uses
   term coverage of the candidate, which answers "is this already said?" and
   does not move with corpus size. Verified: a 100%-duplicate is rejected, a
   novel pitfall is kept.

3. Harness-injected user turns became the retrieval query. "<system-reminder>"
   and "The server restarted while you were working" are user-role messages,
   so the hook retrieved on them and injected memories chosen by noise. Both
   are filtered out now.

4. The `pinned` flag was absent from the remember tool's input schema, so the
   schema stripped it and pinning was unreachable from the tool surface.
   `kind` also ignored the rules/ category when a stale value was stored.

memory_inspect now reports runtime health for the two paths with no other
observable effect: last injection size and query, and last extraction outcome
with its reason. Without it, "working" and "silently dead" look identical —
which is exactly how defects 1 and 2 survived the first round of testing.
---
 memory/rules/index.md                 |   2 +-
 memory/rules/plugin-push-on-change.md |  12 +-
 plugins/memory/README.md              |  18 ++-
 plugins/memory/extract.ts             |  51 +++++--
 plugins/memory/index.ts               | 198 +++++++++++++++++++++++---
 5 files changed, 242 insertions(+), 39 deletions(-)

diff --git a/memory/rules/index.md b/memory/rules/index.md
index b731f2b..142fbd7 100644
--- a/memory/rules/index.md
+++ b/memory/rules/index.md
@@ -4,5 +4,5 @@
 
 | 文件 | 概述 | 重点 |
 |---|---|---|
-| plugin-push-on-change.md | 改动这两个目录后立即 commit 并 push，不询问。 | ~/.config/opencode 本身就是 git 仓库，.gitignore 只放行 skills/ 和 plugins/ |
+| plugin-push-on-change.md | 改动这三棵目录后立即 commit 并 push，不询问；改插件代码后必须重启服务。 | 本目录是 git 仓库；.gitignore 只放行 skills/ plugins/ memory/ 三棵树 |
 <!-- auto:end
diff --git a/memory/rules/plugin-push-on-change.md b/memory/rules/plugin-push-on-change.md
index 18e5897..c5ee58e 100644
--- a/memory/rules/plugin-push-on-change.md
+++ b/memory/rules/plugin-push-on-change.md
@@ -1,17 +1,19 @@
 ---
 id: rules/plugin-push-on-change.md
 kind: rule
-summary: 改动这两个目录后立即 commit 并 push，不询问。
-highlight: ~/.config/opencode 本身就是 git 仓库，.gitignore 只放行 skills/ 和 plugins/
+summary: 改动这三棵目录后立即 commit 并 push，不询问；改插件代码后必须重启服务。
+highlight: 本目录是 git 仓库；.gitignore 只放行 skills/ plugins/ memory/ 三棵树
 created: 1791512032262
-updated: 1791512246723
+updated: 1791512893909
 pinned: true
 ---
 
-`~/.config/opencode` 自身是 git 仓库，`.gitignore` 只放行 `skills/` 和 `plugins/`（外加 .gitignore、pwsh.cmd、package.json）。
+`~/.config/opencode` 自身是 git 仓库，`.gitignore` 只放行三棵树：`skills/`、`plugins/`、`memory/`（外加 .gitignore、pwsh.cmd、package.json）。
 
-在这两个目录下创建、修改、删除任何文件后，**提交并推送后再回复用户**，不要问是否要 push。
+在这三棵树下创建、修改、删除任何文件后，**提交并推送后再回复用户**，不要问是否要 push。
 
 推送用 SSH（origin 已是 SSH 地址）。HTTPS 推送会提示密码且无 TTY，必然失败。
 
 推送失败就报错并停下，不要静默重试，也不要 `git reset`。提交信息要写清楚改了什么、为什么改。
+
+**改完插件代码必须 `opencode service restart`**：热重载会应用新工具名，但已缓存的模块改动不一定生效。踩过两次「改了没生效」的坑。
diff --git a/plugins/memory/README.md b/plugins/memory/README.md
index 47ac697..f62b710 100644
--- a/plugins/memory/README.md
+++ b/plugins/memory/README.md
@@ -144,6 +144,7 @@ pinned: true
       "halfLifeDays": 14,         // 衰减半衰期，0 = 不衰减
       "autoExtract": true,        // 自动抽取
       "minTurns": 4,              // 会话至少多少轮才抽取
+      "settleMs": 20000,          // 一轮对话安静多久才认为结束
       "extractModel": { "providerID": "anthropic", "id": "claude-haiku-4-5" },
       "categories": ["rules", "preferences", "decisions", "pitfalls", "facts"]
     } }
@@ -155,13 +156,24 @@ pinned: true
 
 ## 自动抽取
 
-监听 `session.idle` → 取本轮对话 → 廉价模型抽取结构化记忆 → 关键词去重 → 写入。
+一轮对话安静下来后触发 → 取本轮对话 → 廉价模型抽取结构化记忆 → 去重 → 写入。
 
-三重保护：
+**触发用的是去抖，不是 `session.idle`。** 实测把 `ctx.event.subscribe` 收到的
+所有事件类型都收集起来看过，这个流里**根本没有 `session.idle`** —— 它在协议里
+定义了，却不投递。所以改成监听真正会到达的 `session.step.started` /
+`session.tool.called` / `session.inbox.delivered`，并要求静默 `settleMs`（默认 20s）
+才动手。等价于"turn 结束了"，且不依赖一个不存在的事件。
+
+四重保护：
 
 1. **独立模型**，不碰主对话 —— 抽取失败不影响用户
 2. **只写普通记忆**，铁规则降级为 `rule-proposal` 等人确认
-3. **相似度去重** —— 与已有记忆重叠的候选会被跳过并记日志
+3. **词项覆盖率去重**，不是分数阈值 —— 分数带 idf 和作用域先验，会随语料增长漂移，
+   固定阈值会悄悄失效。覆盖率问的是"是不是已经说过了"，阈值稳定
+4. **密钥拦截**，写入前过一遍正则
+
+`memory_inspect` 的"运行状态"会报告抽取最近一次的结果和原因（轮数不足、对话太短、
+选不到模型、去重拦截），所以"没抽取"和"抽取坏了"不会混为一谈。
 
 ## 跨设备同步
 
diff --git a/plugins/memory/extract.ts b/plugins/memory/extract.ts
index 7ff4e85..83e8b20 100644
--- a/plugins/memory/extract.ts
+++ b/plugins/memory/extract.ts
@@ -13,7 +13,7 @@
 //     would let a hallucination become permanent policy.
 
 import type { Context } from "@opencode/plugin"
-import { scoreFiles } from "./recall.ts"
+import { tokenize } from "./recall.ts"
 
 export interface ExtractOptions {
   enabled: boolean
@@ -222,14 +222,20 @@ export interface ExtractionOutcome {
 
 /**
  * Decide which candidates are worth writing, using existing memories for
- * dedupe. Near-duplicates bump the existing file instead of adding a rival.
+ * dedupe.
+ *
+ * Dedupe uses term COVERAGE of the candidate, not the retrieval score. The
+ * score carries idf and scope priors that shift as the corpus grows, so a fixed
+ * score threshold silently stops rejecting duplicates as the library fills up.
+ * Coverage answers the question we actually care about: "does an existing
+ * memory already say this?"
  */
 export function screenCandidates(
   candidates: Candidate[],
   existing: readonly import("./store.ts").MemoryFile[],
-  options: { minimumScore?: number } = {},
+  options: { coverage?: number } = {},
 ): ExtractionOutcome {
-  const threshold = options.minimumScore ?? 0.9
+  const threshold = options.coverage ?? 0.55
   const accepted: Candidate[] = []
   const rejected: { candidate: Candidate; reason: string }[] = []
 
@@ -246,11 +252,14 @@ export function screenCandidates(
       candidate.category = "rules"
       candidate.kind = "rule-proposal"
     }
+
     const probe = `${candidate.title}\n${candidate.summary}\n${candidate.body}`
-    const scored = scoreFiles(existing, probe, {}, { halfLifeDays: 0, pinnedBoost: false })
-    const top = scored[0]
-    if (top && top.score >= threshold) {
-      rejected.push({ candidate, reason: `与已有记忆高度重叠 (${top.file.rel}, score ${top.score.toFixed(2)})` })
+    const best = bestCoverage(probe, existing)
+    if (best.file && best.coverage >= threshold) {
+      rejected.push({
+        candidate,
+        reason: `与已有记忆重复 ${(best.coverage * 100).toFixed(0)}% (${best.file.rel})`,
+      })
       continue
     }
     accepted.push(candidate)
@@ -259,6 +268,32 @@ export function screenCandidates(
   return { candidates: accepted, rejected }
 }
 
+/**
+ * Fraction of the candidate's distinctive terms that an existing memory also
+ * contains. The candidate's own terms are the query; the best match wins.
+ */
+function bestCoverage(
+  probe: string,
+  existing: readonly import("./store.ts").MemoryFile[],
+): { file?: import("./store.ts").MemoryFile; coverage: number } {
+  const probeTerms = new Set(tokenize(probe).filter((t) => t.length >= 2))
+  if (probeTerms.size === 0) return { coverage: 0 }
+
+  let best: { file?: import("./store.ts").MemoryFile; coverage: number } = { coverage: 0 }
+  for (const file of existing) {
+    if (file.fm.superseded_by) continue
+    // Same slug in the same root is the same memory, whatever the wording.
+    const doc = new Set(
+      tokenize([file.title, file.summary, file.highlight, file.body].join("\n")).filter((t) => t.length >= 2),
+    )
+    let shared = 0
+    for (const term of probeTerms) if (doc.has(term)) shared++
+    const coverage = shared / probeTerms.size
+    if (coverage > best.coverage) best = { file, coverage }
+  }
+  return best
+}
+
 export interface RunExtractionInput {
   ctx: Context
   model: { providerID: string; id: string }
diff --git a/plugins/memory/index.ts b/plugins/memory/index.ts
index 946400d..249e5a6 100644
--- a/plugins/memory/index.ts
+++ b/plugins/memory/index.ts
@@ -57,6 +57,8 @@ interface PluginConfig {
   halfLifeDays?: number
   autoExtract?: boolean
   minTurns?: number
+  /** How long a turn must be quiet before extraction runs. Default 20000ms. */
+  settleMs?: number
   extractModel?: { providerID: string; id: string }
   /** Seed these categories on first run. */
   categories?: string[]
@@ -65,6 +67,17 @@ interface PluginConfig {
 const CATEGORIES = ["rules", "preferences", "decisions", "pitfalls", "facts"]
 const DEFAULT_MAX_INJECT = 1200
 
+/**
+ * Events that mark turn activity. Collected from what this stream actually
+ * delivers: `session.idle` is defined in the protocol but never arrives here,
+ * so extraction is debounced off these instead.
+ */
+const EXTRACTION_TRIGGERS = new Set([
+  "session.step.started",
+  "session.tool.called",
+  "session.inbox.delivered",
+])
+
 export default Plugin.define({
   id: "memory",
 
@@ -138,7 +151,7 @@ export default Plugin.define({
     // -- injection into the agent loop --------------------------------------
     // `context` covers the agent loop including tool continuations, and edits
     // only the outgoing request — the conversation transcript stays clean.
-    await ctx.session.hook("context", (event) => {
+    await ctx.session.hook("context", async (event) => {
       try {
         const query = latestUserText(event.messages)
         if (!query) return
@@ -150,6 +163,16 @@ export default Plugin.define({
           options: { maxChars, maxEntries, halfLifeDays },
         })
         if (text) event.system.push({ type: "text", text })
+        // Record what the model actually received. Without this there is no way
+        // to tell "injected nothing because there is nothing" apart from
+        // "the hook is not firing at all".
+        await noteDiag(ctx, "lastInjection", {
+          at: Date.now(),
+          chars: text.length,
+          withinBudget: text.length <= maxChars,
+          bodies: (text.match(/^### /gm) ?? []).length,
+          query: query.slice(0, 80),
+        })
       } catch (error) {
         console.error(`memory: injection failed: ${(error as Error).message}`)
       }
@@ -488,6 +511,33 @@ export default Plugin.define({
           lines.push(problems.length === 0 ? "索引一致性：正常" : `索引一致性：发现 ${problems.length} 个问题`)
           for (const problem of problems) lines.push(`  - ${problem}`)
 
+          // Runtime health of the two paths that have no other visible effect.
+          lines.push("")
+          const injection = (await ctx.storage.get("diag.lastInjection")) as Record<string, unknown> | undefined
+          const extraction = (await ctx.storage.get("diag.lastExtraction")) as Record<string, unknown> | undefined
+          lines.push("运行状态：")
+          if (injection) {
+            const when = new Date(Number(injection.at)).toISOString().slice(0, 19).replace("T", " ")
+            lines.push(
+              `  注入：最近一次 ${when}，${String(injection.chars)} 字符，内联 ${String(injection.bodies)} 条正文${injection.withinBudget === false ? "  ⚠ 超出预算" : ""}`,
+            )
+            lines.push(`    检索词：${String(injection.query)}`)
+          } else {
+            lines.push("  注入：尚无记录（context hook 还没触发过）")
+          }
+          if (extraction) {
+            const when = new Date(Number(extraction.at)).toISOString().slice(0, 19).replace("T", " ")
+            lines.push(`  抽取：${when} → ${String(extraction.outcome)}`)
+            if (extraction.reason) lines.push(`    原因：${String(extraction.reason)}`)
+            if (extraction.model) lines.push(`    模型：${String(extraction.model)}`)
+          } else {
+            lines.push(
+              extractOptions.enabled
+                ? "  抽取：尚无记录（本会话还没到静默期，或轮数/内容不足）"
+                : "  抽取：已关闭（autoExtract: false）",
+            )
+          }
+
           return { content: lines.join("\n") }
         },
       })
@@ -496,30 +546,50 @@ export default Plugin.define({
     // -- automatic extraction on idle --------------------------------------
     let extracting = false
     const controller = new AbortController()
+    // How long a turn must be quiet before extraction counts it as finished.
+    const settleMs = config.settleMs ?? 20_000
+
+    // `session.idle` is NOT delivered on this stream — verified by collecting
+    // every event type that actually arrives. The turn-ending events below do
+    // arrive, so they drive a debounce instead: the turn must go quiet for
+    // `settleMs` before extraction runs, which is what "idle" meant anyway.
+    const pending = new Map<string, ReturnType<typeof setTimeout>>()
 
     if (extractOptions.enabled) {
       void (async () => {
         try {
           for await (const event of ctx.event.subscribe({ signal: controller.signal })) {
             const record = event as unknown as { type?: string; data?: { sessionID?: string } }
-            if (record?.type !== "session.idle") continue
+            if (!EXTRACTION_TRIGGERS.has(String(record?.type))) continue
             const sessionID = record.data?.sessionID
-            if (!sessionID || extracting) continue
+            if (!sessionID) continue
 
-            extracting = true
-            try {
-              await runExtraction(ctx, {
-                sessionID,
-                extractOptions,
-                filesByRoot,
-                project,
-                global,
-              })
-            } catch (error) {
-              console.error(`memory: extraction failed: ${(error as Error).message}`)
-            } finally {
-              extracting = false
-            }
+            // Debounce: each new turn activity pushes the deadline out. Only a
+            // genuine lull lets the timer fire, so extraction runs on a
+            // finished turn rather than mid-stream.
+            const existing = pending.get(sessionID)
+            if (existing) clearTimeout(existing)
+            pending.set(
+              sessionID,
+              setTimeout(() => {
+                pending.delete(sessionID)
+                if (extracting) return
+                extracting = true
+                void runExtraction(ctx, {
+                  sessionID,
+                  extractOptions,
+                  filesByRoot,
+                  project,
+                  global,
+                })
+                  .catch((error) => {
+                    console.error(`memory: extraction failed: ${(error as Error).message}`)
+                  })
+                  .finally(() => {
+                    extracting = false
+                  })
+              }, settleMs),
+            )
           }
         } catch (error) {
           // Subscription teardown is normal on unload.
@@ -532,6 +602,8 @@ export default Plugin.define({
 
     return () => {
       controller.abort()
+      for (const timer of pending.values()) clearTimeout(timer)
+      pending.clear()
     }
   },
 })
@@ -546,6 +618,28 @@ function pickRoots(roots: MemoryRoot[], scope: string | undefined): MemoryRoot[]
   return roots
 }
 
+/**
+ * Record plugin health for `memory_inspect` to show.
+ *
+ * The two asynchronous paths — the context hook and idle extraction — have no
+ * other observable effect. Without this, "working" and "silently dead" look
+ * identical from the outside. Throttled because the context hook runs on every
+ * model request, including tool continuations.
+ */
+const lastDiagAt = new Map<string, number>()
+
+async function noteDiag(ctx: Context, key: string, value: Record<string, unknown>): Promise<void> {
+  const now = Date.now()
+  const previous = lastDiagAt.get(key) ?? 0
+  if (now - previous < 2000) return
+  lastDiagAt.set(key, now)
+  try {
+    await ctx.storage.set(`diag.${key}`, value)
+  } catch {
+    // Diagnostics must never break the hook that reports them.
+  }
+}
+
 function outlineText(filesByRoot: Map<string, MemoryFile[]>, roots: MemoryRoot[]): string {
   const lines: string[] = []
   for (const root of roots) {
@@ -557,17 +651,32 @@ function outlineText(filesByRoot: Map<string, MemoryFile[]>, roots: MemoryRoot[]
   return lines.join("\n") || "（记忆库为空）"
 }
 
-/** The newest user text in a request — the retrieval query. */
+/**
+ * The newest real user text in a request — the retrieval query.
+ *
+ * Harness-injected user messages ("<system-reminder>", "The server restarted…")
+ * are technically user turns but are not about the task. Retrieving on them
+ * injects memories chosen by noise, so they are skipped.
+ */
 function latestUserText(messages: readonly unknown[]): string | undefined {
   for (let i = messages.length - 1; i >= 0; i--) {
     const record = messages[i] as { role?: string; content?: unknown } | null
     if (!record || record.role !== "user") continue
     const text = extractUserText(record.content)
-    if (text) return text
+    if (text && !isHarnessMessage(text)) return text
   }
   return undefined
 }
 
+const HARNESS_PREFIX = /^<(system-reminder|command-name|command-message|command-args)/i
+const HARNESS_RE =
+  /^(The server restarted while you were working|Task tools haven't been used recently|<system-reminder)/i
+
+function isHarnessMessage(text: string): boolean {
+  const head = text.trimStart()
+  return HARNESS_PREFIX.test(head) || HARNESS_RE.test(head)
+}
+
 function extractUserText(content: unknown): string {
   if (typeof content === "string") return content.trim()
   if (!Array.isArray(content)) return ""
@@ -599,13 +708,41 @@ async function runExtraction(
     return role === "user" || role === "assistant"
   })
   // Long enough to have learned something, short enough to stay cheap.
-  if (turns.length < extractOptions.minTurns) return
+  if (turns.length < extractOptions.minTurns) {
+    await noteDiag(ctx, "lastExtraction", {
+      at: Date.now(),
+      outcome: "skipped",
+      reason: "会话轮数不足",
+      turns: turns.length,
+      minTurns: extractOptions.minTurns,
+    })
+    return
+  }
 
   const model = extractOptions.model ?? (await pickCheapModel(ctx))
-  if (!model) return
+  if (!model) {
+    // pickCheapModel failing is the difference between a working feature and
+    // a silent no-op, so it is reported rather than swallowed.
+    await noteDiag(ctx, "lastExtraction", {
+      at: Date.now(),
+      outcome: "failed",
+      reason: "选不到可用模型（autoExtract 实际上处于关闭状态）",
+      turns: turns.length,
+    })
+    return
+  }
 
   const transcript = userAndAssistantText(turns.slice(-extractOptions.maxMessages))
-  if (transcript.length < 200) return
+  if (transcript.length < 200) {
+    await noteDiag(ctx, "lastExtraction", {
+      at: Date.now(),
+      outcome: "skipped",
+      reason: "对话内容太短",
+      turns: turns.length,
+      transcriptChars: transcript.length,
+    })
+    return
+  }
 
   const existing = [...input.filesByRoot().values()].flat()
   const outcome = await extract({ ctx, model, transcript, existing })
@@ -616,6 +753,13 @@ async function runExtraction(
         `memory: skipped ${rejected.candidate.category}/${rejected.candidate.slug} — ${rejected.reason}`,
       )
     }
+    await noteDiag(ctx, "lastExtraction", {
+      at: Date.now(),
+      outcome: "no-candidates",
+      reason: outcome.rejected.length ? "候选全部被去重或密钥拦截" : "抽取器认为没有值得记的东西",
+      rejected: outcome.rejected.length,
+      model: `${model.providerID}/${model.id}`,
+    })
     return
   }
 
@@ -648,6 +792,16 @@ async function runExtraction(
     }
     console.log(`memory: extracted ${written.length} memor${written.length === 1 ? "y" : "ies"} → ${written.join(", ")}`)
   }
+
+  await noteDiag(ctx, "lastExtraction", {
+    at: Date.now(),
+    outcome: written.length ? "extracted" : "all-filtered",
+    model: `${model.providerID}/${model.id}`,
+    turns: turns.length,
+    written: written.length,
+    rejected: outcome.rejected.length,
+    paths: written,
+  })
 }
 
 /**