misakanet 2.41.2 → 2.42.0

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "misakanet",
-  "version": "2.41.2",
+  "version": "2.42.0",
   "description": "Failure-memory network for AI coding agents: search evidence-rated failure lessons, submit new failures, and turn crashes into reusable knowledge.",
   "author": {
     "name": "Ikalus1988",

package/README.md

@@ -189,7 +189,12 @@ independent runs of ≈500 scenarios each):
 into the prompt; `plain` uses no lesson. `actionable` is a boolean per scenario indicating whether the
 model produced a usable answer. Actionable rates are stable across runs (76–77% with lesson, 82–83% plain).
 
-**Trend** (weekly snapshots):
+**Trend.** Rows below are **generated** by [`scripts/update_readme_benchmark.py`](scripts/update_readme_benchmark.py)
+from [`docs/benchmarks/latest.json`](docs/benchmarks/latest.json) — regenerate them with
+`python3 scripts/update_readme_benchmark.py`. Do not hand-edit: a second source of truth is what made the
+previous copy go stale while the paragraph directly above it explained what the metric does and does not mean.
+
+<!-- BEGIN generated: benchmark-trend -->
 
 | Date | with_lesson hit rate | plain hit rate | n |
 |---|---|---|---|
@@ -199,18 +204,22 @@ model produced a usable answer. Actionable rates are stable across runs (76–77
 | 2026-09-14 | 46.6% | 23.4% | 494 |
 | 2026-09-21 | 46.1% | 23.3% | 512 |
 
+_1155 run(s) in `latest.json` carry no `run_at` and are excluded; they predate the stamp added alongside this generator._
+
 ```
-with_lesson hit rate (weekly)
-49.1% │    ▄
-48.3% │    █  ▄
-46.6% │    █  █  ▄
-46.4% │ ▄  █  █  █  ▄
-46.1% │ █  █  █  █  █
+with_lesson hit rate (per run date)
+46.1% │ ▁
+46.6% │ ▂
+48.3% │ ▆
+49.1% │ █
+46.4% │ ▁
       └──────────────────
        08  08  09  09  09
        30  31  06  14  21
 ```
 
+<!-- END generated: benchmark-trend -->
+
 A model repeats more of a document it was handed, and the weaker the model the bigger the relative
 difference. That is *necessary* for the product to help and it is not sufficient — the claim "search finds the
 right lesson for a failure you described" is measured nowhere yet. Details:

package/README.zh-CN.md

@@ -86,6 +86,9 @@ MisakaNet 是面向 AI 编码 Agent 的失败经验层。当你的 Agent 遇到
 **方式 B：CLI**
 
 ```bash
+# Homebrew/Debian/Fedora Python refuse a system-wide install (PEP 668), so this
+# creates a virtualenv first. Harmless everywhere else.
+python3 -m venv .venv && . .venv/bin/activate
 pip install misakanet-core
 python3 search_knowledge.py "GitHub token 401"
 ```
@@ -340,12 +343,9 @@ python3 search_knowledge.py "database locked"
 
 ## 路线图
 
-| 版本 | 重点 | 状态 |
-|------|------|------|
-| **v2.9.x** | 可发现性、内容深度、质量飞轮 | 进行中 |
-| **v3.0** | Lesson 详情页、主题页、Agent 框架 | 规划中 |
-
-详见 [ROADMAP.md](ROADMAP.md)。
+路线图只维护在 [ROADMAP.md](ROADMAP.md) 一处，README 不再复制版本表 ——
+`README.md` 与 `README.ja.md` 自 2026-09-20 起就只保留链接，这里曾经还留着一张
+停在 `v2.9.x / v3.0` 的表（落后约 20 个 minor），已删除。
 
 ---
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "misakanet",
-  "version": "2.41.2",
+  "version": "2.42.0",
   "license": "Apache-2.0",
   "description": "MisakaNet failure-memory skill — evidence-rated failure lessons for AI agents. DSH bundle: registers the MCP tools as mcp__misakanet__* (misakanet_search/get_lesson/…), served by the public Streamable HTTP endpoint https://misakanet.org/mcp — live tools from an npm install, in any profile, with no local python. A profile that prefers the repo's own stdio server can override the bundle row.",
   "icon": "icon.svg",
@@ -80,7 +80,7 @@
     "preview": "wrangler dev"
   },
   "devDependencies": {
-    "wrangler": "^4.144.0"
+    "wrangler": "^4.146.0"
   },
   "overrides": {
     "sharp": "0.35.4"