feat(core,server,docs): default max_turns to -1 (unlimited) to avoid unexpected run cutoffs (#232)

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

packages/docs/content/agent-loop.en.md

@@ -13,7 +13,7 @@ This page shows the context_engine's overall flow first, then breaks down each s
 session.run(newMessages, { approve, signal })
   │  carry-over from a previous interrupt? → prepend to this run's input
   ▼
-┌── turn loop (≤ max_turns, default 100) ───────────────────────┐
+┌── turn loop (≤ max_turns; default -1 = no cap) ───────────────┐
 │                                                               │
 │  request_begin                                                │
 │  LLM.streamGenerate(newMessages)                              │

packages/docs/content/agent-loop.zh.md

@@ -13,7 +13,7 @@ SDK 的唯一执行入口是 `session.run(newMessages, opts?)`：输入本次新
 session.run(newMessages, { approve, signal })
   │  存在上次中断的补发内容?→ 前置到本轮输入
   ▼
-┌── 轮循环(≤ max_turns,默认 100)──────────────────────────────┐
+┌── 轮循环(≤ max_turns,默认 -1 不限制)────────────────────────┐
 │                                                               │
 │  request_begin                                                │
 │  LLM.streamGenerate(newMessages)                              │

packages/docs/content/configuration.en.md

@@ -98,7 +98,7 @@ Edit this file via the CLI (`penguin config model …`) or the Web Models page
 | `description` | — | Agent description |
 | `version` | `1` | Agent State version (a natural number), incremented on each successful optimization |
 | `system_prompt` | built-in template | Required; the only template with placeholder substitution |
-| `max_turns` | `100` | Maximum LLM turns per Task (-1 removes the cap) |
+| `max_turns` | `-1` | Maximum LLM turns per Task (`-1` = unlimited; a positive integer caps the Task) |
 | `model.max_tokens` | `32000` | Output Token limit per Request (-1 = no cap, provider default) |
 | `model.thinking_level` | `medium` | `none` / `low` / `medium` / `high` / `xhigh`; the session default, overridable per-Task |
 | `model.timeoutMs` | `120000` | Per-Request timeout (milliseconds) |
@@ -122,7 +122,8 @@ version: 3
 system_prompt: |
   …
 
-max_turns: 100
+# -1 (the default) = unlimited; set a positive integer to cap the turns of a single Task.
+max_turns: -1
 
 model:
   max_tokens: 32000

packages/docs/content/configuration.zh.md

@@ -98,7 +98,7 @@ output = 0.857143
 | `description` | — | Agent 描述 |
 | `version` | `1` | Agent State 版本号（自然数），每次成功优化自增 |
 | `system_prompt` | 内置模板 | 必填；唯一进行占位符替换的模板 |
-| `max_turns` | `100` | 单个 Task 的最大 LLM 轮数（-1 不限制） |
+| `max_turns` | `-1` | 单个 Task 的最大 LLM 轮数（`-1` 不限制，正整数为上限） |
 | `model.max_tokens` | `32000` | 单次输出 Token 上限（-1 不设上限，用服务商默认） |
 | `model.thinking_level` | `medium` | `none` / `low` / `medium` / `high` / `xhigh`；作为会话默认档位，可被逐轮 Task 参数覆盖 |
 | `model.timeoutMs` | `120000` | 单次 Request 超时（毫秒） |
@@ -122,7 +122,8 @@ version: 3
 system_prompt: |
   …
 
-max_turns: 100
+# -1(缺省)不限制轮数;设为正整数则限制单个 Task 的轮数。
+max_turns: -1
 
 model:
   max_tokens: 32000