pi-cache-optimizer 2.8.21 → 2.8.22

package/README.md

@@ -37,7 +37,7 @@ Pi extension for improving provider-side KV / prompt cache hit rates. It keeps s
 - Requests long cache retention when Pi/provider compat supports it.
 - Adds a conservative per-session `prompt_cache_key` fallback for `openai-completions` proxy payloads when no effective key exists. The values this extension adds itself (that key fallback, the session-affinity header bridge, and cache hints) are a one-way hash of the Pi session id (`pi-<32 hex>`); keys and headers that Pi core sets on its own are left untouched, and an existing key is never overwritten. Pi 1.0+ owns this field for Responses/Codex transports.
 - Warns once for third-party OpenAI-compatible proxies missing cache/session-affinity compat flags.
-- Detects adaptive-thinking compat for Claude (opus-4.6+ including Opus 5, sonnet-4.6+ including Sonnet 5, fable-5+) and Kimi Coding K3 / `kimi-for-coding` custom channels.
+- Detects adaptive-thinking compat for Claude (opus-4.6+ including Opus 5, sonnet-4.6+ including Sonnet 5, fable-5+, haiku-5+ including Haiku 5.5) and Kimi Coding K3 / `kimi-for-coding` custom channels.
 - Stores cache statistics in per-extension-instance atomic shards, so parent sessions, child Pi agents, and parallel Pi processes cannot overwrite one another.
 - Shows current conversation-session provider/model footer stats by default; `total` aggregates all valid local shards for the exact provider/model.
 - Supports optional router-extension integration through versioned global protocols (`Symbol.for("pi.routing.registry.v1")` and `Symbol.for("pi.cache.hints.v1")`) without importing router packages.
@@ -62,7 +62,7 @@ Run `/reload` in Pi after install/update/remove so extension hooks refresh.
 
 On Pi 0.79.7 and newer, `pi update` updates Pi itself only. To update installed Pi packages such as this extension, run `pi update --extensions` (packages only) or `pi update --all` (Pi + packages).
 
-This extension requires Pi 0.82+ and is validated against Pi 1.0.3. It uses the official Pi package types directly for type-checking, along with extension hooks, `getAgentDir()`, and prompt options shared by those versions; it does not depend on Pi 0.83+ APIs such as `ctx.scopedModels` or the bundled TypeBox 1.3 aliases. Native virtual model support and codemode nested-call coalescing activate only on Pi 0.99+ hosts that produce them; older hosts keep the previous behavior. The local development baseline uses Node.js 22.19.0 or newer, matching Pi 1.0.3's engine requirement.
+This extension requires Pi 0.82+ and is validated against Pi 1.1.0. It uses the official Pi package types directly for type-checking, along with extension hooks, `getAgentDir()`, and prompt options shared by those versions; it does not depend on Pi 0.83+ APIs such as `ctx.scopedModels` or the bundled TypeBox 1.3 aliases. Native virtual model support and codemode nested-call coalescing activate only on Pi 0.99+ hosts that produce them; older hosts keep the previous behavior. The local development baseline uses Node.js 22.19.0 or newer, matching Pi 1.0.3's engine requirement.
 
 ## Commands
 
@@ -213,7 +213,7 @@ Some proxies rewrite or insert hidden 5-minute breakpoints after Pi's request ho
 
 ## Adaptive thinking models
 
-Claude models from opus-4.6 / sonnet-4.6 (including Opus 5 and Sonnet 5) / fable-5 onwards require `forceAdaptiveThinking: true` in compat. Kimi Coding K3 (`k3`) and `kimi-for-coding` also use adaptive thinking and need `allowEmptySignature: true` so replayed empty-signature thinking blocks remain valid. Without the required compat, Pi may send a legacy thinking payload or replay thinking incorrectly. Pi 0.83+ native Opus 5 catalogs are covered by the same adaptive-thinking detection; custom `anthropic-messages` channels still need the compat flag when Pi does not provide it.
+Claude models from opus-4.6 / sonnet-4.6 (including Opus 5 and Sonnet 5) / fable-5 / haiku-5 (Haiku 5.5, Pi 1.1.0+) onwards require `forceAdaptiveThinking: true` in compat. Kimi Coding K3 (`k3`) and `kimi-for-coding` also use adaptive thinking and need `allowEmptySignature: true` so replayed empty-signature thinking blocks remain valid. Without the required compat, Pi may send a legacy thinking payload or replay thinking incorrectly. Pi 0.83+ native Opus 5 catalogs are covered by the same adaptive-thinking detection; custom `anthropic-messages` channels still need the compat flag when Pi does not provide it.
 
 Pi's built-in catalog already sets this flag for official models. Custom channels in `models.json` that override these models must include the flag:
 

package/README.zh-CN.md

@@ -37,7 +37,7 @@
 - 在 Pi / provider compat 支持时请求长缓存保留。
 - 仅对 `openai-completions` 代理请求，在没有有效 key 时按会话保守补 `prompt_cache_key`；本扩展自己补的值（该 key、session-affinity 头补齐、cache hints）使用 Pi session id 的单向哈希（`pi-<32 位 hex>`）；Pi 核心自己设置的 key 和头保持不变，已有 key 也绝不覆盖；Pi 1.0+ 已负责 Responses/Codex transport 的 key。
 - 对缺少缓存 / session-affinity compat 的第三方 OpenAI-compatible 代理给出一次性提醒。
-- 检测 Claude（opus-4.6+ 含 Opus 5、sonnet-4.6+ 含 Sonnet 5、fable-5+）以及 Kimi Coding K3 / `kimi-for-coding` 自定义渠道的 adaptive-thinking compat。
+- 检测 Claude（opus-4.6+ 含 Opus 5、sonnet-4.6+ 含 Sonnet 5、fable-5+、haiku-5+ 含 Haiku 5.5）以及 Kimi Coding K3 / `kimi-for-coding` 自定义渠道的 adaptive-thinking compat。
 - 使用每个 extension instance 独占的原子 shard 保存缓存统计，避免父会话、子 Pi agent 和并行 Pi 进程互相覆盖。
 - Footer 默认显示当前 conversation session 的 provider/model 统计；`total` 可聚合同一精确 provider/model 的所有有效本地 shard。
 - 通过版本化全局协议（`Symbol.for("pi.routing.registry.v1")` 与 `Symbol.for("pi.cache.hints.v1")`）支持可选的 router extension 集成，而不导入任何 router 包。
@@ -62,7 +62,7 @@ pi remove npm:pi-deepseek-cache-optimizer && pi install npm:pi-cache-optimizer
 
 Pi 0.79.7 及之后，`pi update` 默认只更新 Pi 本体。若要更新已安装的 Pi package（包括本扩展），请运行 `pi update --extensions`（只更新 packages）或 `pi update --all`（Pi 与 packages 一起更新）。
 
-本扩展要求 Pi 0.82+，并已使用 Pi 1.0.3 验证。TypeScript 校验直接使用官方 Pi package 类型，同时只使用这些版本共有的 extension hooks、`getAgentDir()` 和 prompt options；不依赖 Pi 0.83+ 专有 API（例如 `ctx.scopedModels` 或 bundled TypeBox 1.3 aliases）。原生虚拟模型支持与 codemode 嵌套工具调用合并只在会产生它们的 Pi 0.99+ 上生效，较早版本保持原有行为。本地开发基线需要 Node.js 22.19.0 或更高版本，与 Pi 1.0.3 的 engine 要求一致。
+本扩展要求 Pi 0.82+，并已使用 Pi 1.1.0 验证。TypeScript 校验直接使用官方 Pi package 类型，同时只使用这些版本共有的 extension hooks、`getAgentDir()` 和 prompt options；不依赖 Pi 0.83+ 专有 API（例如 `ctx.scopedModels` 或 bundled TypeBox 1.3 aliases）。原生虚拟模型支持与 codemode 嵌套工具调用合并只在会产生它们的 Pi 0.99+ 上生效，较早版本保持原有行为。本地开发基线需要 Node.js 22.19.0 或更高版本，与 Pi 1.0.3 的 engine 要求一致。
 
 ## 命令
 
@@ -213,7 +213,7 @@ Anthropic 按 `tools → system → messages` 顺序处理 cache breakpoint，
 
 ## Adaptive thinking 模型
 
-Claude 从 opus-4.6 / sonnet-4.6（含 Opus 5、Sonnet 5）/ fable-5 开始需要在 compat 中设置 `forceAdaptiveThinking: true`。Kimi Coding K3（`k3`）和 `kimi-for-coding` 也使用 adaptive thinking，并需要 `allowEmptySignature: true`，以正确重放空 signature 的 thinking block。缺少这些 compat 时，Pi 可能发送旧版 thinking payload 或错误重放 thinking。Pi 0.83+ 的原生 Opus 5 catalog 已覆盖在同一 adaptive-thinking 检测中；如果自定义 `anthropic-messages` 渠道没有继承该 compat，仍需手动设置。
+Claude 从 opus-4.6 / sonnet-4.6（含 Opus 5、Sonnet 5）/ fable-5 / haiku-5（Haiku 5.5，Pi 1.1.0+）开始需要在 compat 中设置 `forceAdaptiveThinking: true`。Kimi Coding K3（`k3`）和 `kimi-for-coding` 也使用 adaptive thinking，并需要 `allowEmptySignature: true`，以正确重放空 signature 的 thinking block。缺少这些 compat 时，Pi 可能发送旧版 thinking payload 或错误重放 thinking。Pi 0.83+ 的原生 Opus 5 catalog 已覆盖在同一 adaptive-thinking 检测中；如果自定义 `anthropic-messages` 渠道没有继承该 compat，仍需手动设置。
 
 Pi 内置 catalog 已为官方模型设置此 flag。`models.json` 中覆盖这些模型的自定义渠道必须包含该 flag：
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-cache-optimizer",
-  "version": "2.8.21",
+  "version": "2.8.22",
   "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",
@@ -37,8 +37,8 @@
     "check:modules": "node scripts/check-module-graph.mjs"
   },
   "devDependencies": {
-    "@earendil-works/pi-coding-agent": "^1.0.3",
-    "@earendil-works/pi-server": "1.0.3",
+    "@earendil-works/pi-coding-agent": "^1.1.0",
+    "@earendil-works/pi-server": "^1.1.0",
     "@types/node": "^22.0.0",
     "jiti": "^2.7.0",
     "typescript": "^5.8.3"

package/src/model-detect.ts

@@ -32,8 +32,10 @@ export function modelOrAssistantMessageHas(message: unknown, model: PiModel | un
  *   claude-opus-4-6, claude-opus-4-7, claude-opus-4-8 (also dotted 4.6/4.7/4.8)
  *   claude-sonnet-4-6, claude-sonnet-5
  *   claude-fable-5
+ *   claude-haiku-5-5 (Pi 1.1.0+)
  *
- * We match broadly: opus >= 4-6, sonnet >= 4-6, fable >= 5.
+ * We match broadly: opus >= 4-6, sonnet >= 4-6, fable >= 5, haiku >= 5
+ * (Pi's own Bedrock/Anthropic detection treats every haiku-5* as adaptive).
  * Ids may carry date-stamp or size suffixes like "[1M]".
  */
 export const ADAPTIVE_OPUS_PATTERN = /(^|[\/\s:_-])(opus-4[.-][6-9]|opus-4-[1-9][0-9]|opus-([5-9]|[1-9][0-9]))($|[-_.:\/\s\[])/i;
@@ -42,10 +44,12 @@ export const ADAPTIVE_SONNET_PATTERN = /(^|[\/\s:_-])(sonnet-4[.-][6-9]|sonnet-4
 
 export const ADAPTIVE_FABLE_PATTERN = /(^|[\/\s:_-])fable-([5-9]|[1-9][0-9])($|[-_.:\/\s\[])/i;
 
+export const ADAPTIVE_HAIKU_PATTERN = /(^|[\/\s:_-])haiku-([5-9]|[1-9][0-9])($|[-_.:\/\s\[])/i;
+
 export function isAdaptiveGenerationModel(model: PiModel | undefined): boolean {
   if (!model) return false;
   const tokens = getModelIdNameTokenValues(model);
-  return tokens.some((t) => ADAPTIVE_OPUS_PATTERN.test(t) || ADAPTIVE_SONNET_PATTERN.test(t) || ADAPTIVE_FABLE_PATTERN.test(t));
+  return tokens.some((t) => ADAPTIVE_OPUS_PATTERN.test(t) || ADAPTIVE_SONNET_PATTERN.test(t) || ADAPTIVE_FABLE_PATTERN.test(t) || ADAPTIVE_HAIKU_PATTERN.test(t));
 }
 
 export function isKimiCodingAdaptiveModel(model: PiModel | undefined): boolean {