pi-cache-optimizer 2.8.0 → 2.8.1

package/README.md

@@ -71,6 +71,8 @@ This extension is validated against Pi 0.83.0 and remains designed for Pi 0.82+.
 | `/cache-optimizer config footer-mode total\|session\|process` | Persist the footer stats mode. Persistent command configuration overrides the environment variable. |
 | `/cache-optimizer fix` | Auto-repairs safe compat issues for the active model (adaptive thinking, DeepSeek reasoning, OpenAI proxy session affinity). Shows preview + risk warning, requires confirmation. **Only modifies `models.json` after explicit user approval.** |
 
+`/cache-optimizer` uses Pi's native Tab completion. Type `/cache-optimizer <Tab>` for the supported subcommands, `/cache-optimizer c<Tab>` for `config`, `/cache-optimizer config <Tab>` for `footer-mode`, and `/cache-optimizer config footer-mode <Tab>` for `total`, `session`, or `process`. Suggestions are prefix-filtered and invalid prefixes are left to Pi's normal fallback behavior.
+
 The interactive `/cache-optimizer` menu includes `Footer mode`, where you can choose `total`, `session`, or `process`. `enable` / `disable` are current-process switches. For a persistent opt-out, use environment variables below.
 
 ## Persistent opt-out
@@ -281,10 +283,10 @@ Pi 0.79+ also includes a built-in footer `CH` marker for the latest prompt cache
 Example footer:
 
 ```text
-OpenAI cache 3/10 · 0.002M/0.005M tok (40%) ⚠️ compat
+· OpenAI cache 3/10 · 0.002M/0.005M tok (40%) ⚠️ compat
 ```
 
-Format: `<label> <hit requests>/<total requests> · <cached input tokens>/<total input tokens> tok (<token hit rate>)`. Some adapters may also append `· write <tokens> tok`, and runtime diagnostics may append `⚠️ compat` or `⚠️ integrity`.
+The leading `· ` is owned by this extension and separates its status from statuses published by other extensions in the same footer. It is present for normal, disabled, router-restored, and warning-suffixed statuses. The stats format remains `<label> <hit requests>/<total requests> · <cached input tokens>/<total input tokens> tok (<token hit rate>)`; `/cache-optimizer stats` output is unchanged. Some adapters may also append `· write <tokens> tok`, and runtime diagnostics may append `⚠️ compat` or `⚠️ integrity`.
 
 Supported footer labels include: DS, Claude, OpenAI, Gemini, Kimi, Qwen, GLM, MiniMax, Mimo, Hunyuan, Mistral, Grok, Llama, Nemotron, Cohere, Yi, Doubao, ERNIE, Baichuan, StepFun, Spark, InternLM, Gemma, Phi, Jamba, Solar, Sonar, Nova, Reka, Falcon, DBRX, MPT, StableLM, Aquila, EXAONE, HyperCLOVA, Luminous, Hermes, Granite, Arctic, Pangu, SenseNova, Zhinao, MiniCPM, XVERSE, Orion, OpenChat, Vicuna, Wizard, Zephyr, Dolphin, OpenOrca, Starling, BLOOM, RWKV, and Aya.
 

package/README.zh-CN.md

@@ -71,6 +71,8 @@ Pi 0.79.7 及之后，`pi update` 默认只更新 Pi 本体。若要更新已安
 | `/cache-optimizer config footer-mode total\|session\|process` | 持久设置 footer 统计模式；持久命令配置优先于环境变量。 |
 | `/cache-optimizer fix` | 为当前模型自动修复安全的 compat 问题（adaptive thinking、DeepSeek reasoning、OpenAI proxy session affinity）。展示预览 + 风险提示，需要用户确认。**仅在用户明确批准后才修改 `models.json`。** |
 
+`/cache-optimizer` 使用 Pi 原生 Tab 补全：输入 `/cache-optimizer <Tab>` 查看支持的子命令，输入 `/cache-optimizer c<Tab>` 补全 `config`，输入 `/cache-optimizer config <Tab>` 补全 `footer-mode`，输入 `/cache-optimizer config footer-mode <Tab>` 补全 `total`、`session` 或 `process`。建议会按当前前缀过滤；无效前缀返回空结果，由 Pi 正常回退处理。
+
 交互式 `/cache-optimizer` 菜单包含 `Footer mode`，可以选择 `total`、`session` 或 `process`。`enable` / `disable` 是当前进程内开关。若要持久关闭某些能力，请使用下面的环境变量。
 
 ## 持久 Opt-out
@@ -280,10 +282,10 @@ Pi 0.79+ 已内置 footer `CH` 标记，用于显示最近一次 prompt cache hi
 示例 footer：
 
 ```text
-OpenAI cache 3/10 · 0.002M/0.005M tok (40%) ⚠️ compat
+· OpenAI cache 3/10 · 0.002M/0.005M tok (40%) ⚠️ compat
 ```
 
-格式：`<label> <命中请求数>/<总请求数> · <cached input tokens>/<total input tokens> tok (<token 命中率>)`。部分 adapter 还可能追加 `· write <tokens> tok`，运行时诊断可能追加 `⚠️ compat` 或 `⚠️ integrity`。
+开头的 `· ` 由本扩展负责，用于把本扩展状态与同一 footer 中其他扩展发布的状态隔开。普通、disabled、router 恢复以及带 warning 的状态都会保留此前缀。统计格式仍是 `<label> <命中请求数>/<总请求数> · <cached input tokens>/<total input tokens> tok (<token 命中率>)`；`/cache-optimizer stats` 的输出不变。部分 adapter 还可能追加 `· write <tokens> tok`，运行时诊断可能追加 `⚠️ compat` 或 `⚠️ integrity`。
 
 支持的 footer label 包括：DS、Claude、OpenAI、Gemini、Kimi、Qwen、GLM、MiniMax、Mimo、Hunyuan、Mistral、Grok、Llama、Nemotron、Cohere、Yi、Doubao、ERNIE、Baichuan、StepFun、Spark、InternLM、Gemma、Phi、Jamba、Solar、Sonar、Nova、Reka、Falcon、DBRX、MPT、StableLM、Aquila、EXAONE、HyperCLOVA、Luminous、Hermes、Granite、Arctic、Pangu、SenseNova、Zhinao、MiniCPM、XVERSE、Orion、OpenChat、Vicuna、Wizard、Zephyr、Dolphin、OpenOrca、Starling、BLOOM、RWKV、Aya。
 

package/index.ts

@@ -1146,6 +1146,82 @@ function parseFooterStatsMode(value: unknown): FooterStatsMode | undefined {
   return normalized === "session" || normalized === "total" || normalized === "process" ? normalized : undefined;
 }
 
+type CommandCompletionItem = {
+  value: string;
+  label: string;
+  description?: string;
+};
+
+const CACHE_OPTIMIZER_COMMANDS = [
+  "enable",
+  "disable",
+  "doctor",
+  "stats",
+  "config",
+  "compat",
+  "reset",
+  "fix",
+] as const;
+const CACHE_OPTIMIZER_CONFIG_ARGUMENTS = ["footer-mode"] as const;
+const CACHE_OPTIMIZER_FOOTER_MODES = ["total", "session", "process"] as const;
+
+function filterCommandCompletionItems(
+  values: readonly string[],
+  prefix: string,
+  argumentPath = "",
+): CommandCompletionItem[] | null {
+  const normalizedPrefix = prefix.trim().toLowerCase();
+  const matches = values
+    .filter((value) => value.startsWith(normalizedPrefix))
+    .map((value) => ({
+      // Pi replaces the complete argumentPrefix when applying a command
+      // completion, so nested suggestions must include their full path.
+      value: argumentPath ? `${argumentPath} ${value}` : value,
+      label: value,
+    }));
+  return matches.length > 0 ? matches : null;
+}
+
+function getCacheOptimizerArgumentCompletions(argumentPrefix: string): CommandCompletionItem[] | null {
+  if (typeof argumentPrefix !== "string") return null;
+  const trimmed = argumentPrefix.trim();
+  const parts = trimmed ? trimmed.split(/\s+/) : [];
+
+  if (parts.length === 0) {
+    return filterCommandCompletionItems(CACHE_OPTIMIZER_COMMANDS, "");
+  }
+
+  if (parts.length === 1) {
+    const subcommandPrefix = parts[0].toLowerCase();
+    // `config` is the primary `c` completion; `compat` remains available
+    // through its more specific `co` prefix. Surrounding whitespace is
+    // ignored so ` c ` behaves the same as `c`.
+    if (subcommandPrefix === "c") {
+      return [{ value: "config", label: "config" }];
+    }
+    if (subcommandPrefix === "config") {
+      return filterCommandCompletionItems(CACHE_OPTIMIZER_CONFIG_ARGUMENTS, "", "config");
+    }
+    return filterCommandCompletionItems(CACHE_OPTIMIZER_COMMANDS, parts[0]);
+  }
+
+  if (parts[0].toLowerCase() !== "config") return null;
+
+  if (parts.length === 2) {
+    const nestedPrefix = parts[1].toLowerCase();
+    if (nestedPrefix === "footer-mode") {
+      return filterCommandCompletionItems(CACHE_OPTIMIZER_FOOTER_MODES, "", "config footer-mode");
+    }
+    return filterCommandCompletionItems(CACHE_OPTIMIZER_CONFIG_ARGUMENTS, parts[1], "config");
+  }
+
+  if (parts.length === 3 && parts[1].toLowerCase() === "footer-mode") {
+    return filterCommandCompletionItems(CACHE_OPTIMIZER_FOOTER_MODES, parts[2], "config footer-mode");
+  }
+
+  return null;
+}
+
 function parsePersistedCacheOptimizerConfig(value: unknown): PersistedCacheOptimizerConfigV1 | undefined {
   const record = asRecord(value);
   if (!record || record.version !== 1) return undefined;
@@ -3666,6 +3742,11 @@ function formatCacheStats(adapter: CacheProviderAdapter, stats: CacheStats): str
   return `${adapter.label} ${stats.hitRequests}/${stats.totalRequests} · ${formatTokenCount(stats.cachedInputTokens)}/${formatTokenCount(stats.totalInputTokens)} tok${percent}${writeText}`;
 }
 
+function prefixFooterStatus(statusText: string | undefined): string | undefined {
+  if (!statusText || statusText.startsWith("· ")) return statusText;
+  return `· ${statusText}`;
+}
+
 /**
  * Compute a hit-ratio percentage string for a value between 0 and 1.
  * Returns e.g. "75%", "0%", "100%", or "N/A" for zero total.
@@ -6653,6 +6734,8 @@ export const __internals_for_tests = {
   // Cache stats helpers (module-level, usable from verify script)
   addUsageToCacheStats,
   formatCacheStats,
+  prefixFooterStatus,
+  getCacheOptimizerArgumentCompletions,
   emptyCacheStats,
   emptyAllCacheStats,
   parseCacheStats,
@@ -7240,6 +7323,7 @@ export default function (pi: ExtensionAPI) {
       }
     }
 
+    statusText = prefixFooterStatus(statusText);
     if (statusText === lastStatusText) return;
 
     lastStatusText = statusText;
@@ -7647,6 +7731,7 @@ export default function (pi: ExtensionAPI) {
   // ────────────────────────────────────────────────────────────────
   pi.registerCommand("cache-optimizer", {
     description: "Configure and diagnose Pi cache behavior",
+    getArgumentCompletions: getCacheOptimizerArgumentCompletions,
     handler: async (args: string, cmdCtx) => {
       syncSessionHash(cmdCtx);
       const selectedModel = cmdCtx.model;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-cache-optimizer",
-  "version": "2.8.0",
+  "version": "2.8.1",
   "description": "Improve Pi prompt/KV cache hit rates with stable prompts, OpenAI-compatible cache keys, proxy compat warnings, and footer cache stats.",
   "keywords": [
     "pi-package",