billion-context-dsh 0.2.10 → 0.2.11

package/README.en.md

@@ -3,7 +3,7 @@
 [English](./README.en.md) | [中文](./README.md)
 
 > **⚠️ Beta notice — not for production use**
-> This project (**v0.2.10**) is a work-in-progress beta. The [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) itself is also in **public beta**. **Do not use either in engineering / production environments** — expect breaking changes and rough edges.
+> This project (**v0.2.11**) is a work-in-progress beta. The [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) itself is also in **public beta**. **Do not use either in engineering / production environments** — expect breaking changes and rough edges.
 
 <p align="center">
 <strong>Built with gratitude on top of these projects</strong> — please give them a ⭐:
@@ -171,7 +171,7 @@ This project reuses `acp-kernel`'s compression core and `billion-context-pi`'s d
 | Key | Default | Meaning |
 |---|---|---|
 | `modelContextLimit` | auto-detected (fallback `128000`) | Context window used for the kernel's pressure decisions; an explicit value wins and skips the probe |
-| `autoModelContextLimit` | `true` | Probe the model's real window from the model API (`agent.ctx.llm.resolveModelInfo`); fall back to the default on failure, the `/acp` command shows the window source (the `acp_status` model tool carries no window info) |
+| `autoModelContextLimit` | `true` | Probe the model's real window from the model API (`agent.ctx.llm.resolveModelInfo`); fall back to the default on failure, the `/acp` command shows the window source (the `acp_status` model tool carries no window info). A failed probe is surfaced in the host log and the `/acp` panel (`restart to re-probe`) — the failure is cached like a success, so fixing the gateway requires a restart or an explicit `modelContextLimit` before the probe retries |
 | `nudgeMinContextLimitPct` | kernel default `0.45` | Nudge window lower bound (usage fraction) — validation only; the growth-driven trigger has no percentage floor — same default as billion-context-pi |
 | `nudgeMaxContextLimitPct` | engine default `0.70` (kernel/pi default `0.75`) | Over-limit line: above this the nudge fires regardless of growth — deliberately below the host compaction-basic 80% auto-compaction line so the forced nudge fires first; an explicit value wins |
 | `nudgeEmergencyThresholdPct` | engine default `0.85` (kernel/pi default `0.95`) | Emergency nudge (bypasses the per-turn dedup) — lowered from `0.95`: at 95% the model has no room to act and the 80% auto-compaction line shadows it; an explicit value wins |

package/README.md

@@ -3,7 +3,7 @@
 [中文](./README.md) | [English](./README.en.md)
 
 > **⚠️ 测试版声明——请勿用于生产环境**
-> 本项目（**v0.2.10**）仍处于开发中的测试版。[DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) 本身也处于**公开测试版**阶段。**请勿将两者用于工程化 / 生产环境**——预期会有破坏性变更与粗糙之处。
+> 本项目（**v0.2.11**）仍处于开发中的测试版。[DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) 本身也处于**公开测试版**阶段。**请勿将两者用于工程化 / 生产环境**——预期会有破坏性变更与粗糙之处。
 
 <p align="center">
 <strong>衷心感谢以下项目——请给它们一个 ⭐：</strong>
@@ -172,7 +172,7 @@ DSH 的每个模型请求都派生自其 append-only 会话日志（*surface*）
 | 键 | 默认值 | 含义 |
 |---|---|---|
 | `modelContextLimit` | 自动探测（回退 `128000`） | 用于内核压力决策的上下文窗口；显式配置时优先且跳过探测 |
-| `autoModelContextLimit` | `true` | 从模型 API 自动探测真实窗口（`agent.ctx.llm.resolveModelInfo`）；探测失败回退默认值，`/acp` 命令展示窗口来源（模型工具 `acp_status` 不含窗口信息） |
+| `autoModelContextLimit` | `true` | 从模型 API 自动探测真实窗口（`agent.ctx.llm.resolveModelInfo`）；探测失败回退默认值，`/acp` 命令展示窗口来源（模型工具 `acp_status` 不含窗口信息）。探测失败会在宿主日志与 `/acp` 面板提示（`restart to re-probe`）——失败结果同样被缓存，修复网关后需重启或显式设置 `modelContextLimit` 才会重新探测 |
 | `nudgeMinContextLimitPct` | 内核默认 `0.45` | Nudge 窗口下界（用量占比）——仅作配置校验，增长路径的触发没有百分比下限——与 billion-context-pi 相同的默认值 |
 | `nudgeMaxContextLimitPct` | engine 默认 `0.70`（内核/pi 默认 `0.75`） | 过限线：超过此值则无论增长与否都触发 nudge——刻意低于宿主 compaction-basic 的 80% 自动压缩线，保证强制 nudge 先触发；显式配置优先 |
 | `nudgeEmergencyThresholdPct` | engine 默认 `0.85`（内核/pi 默认 `0.95`） | 紧急 nudge（绕过每轮去重）——从 `0.95` 下调：95% 时模型已无操作空间且会被 80% 自动压缩线遮蔽；显式配置优先 |

package/dist/commands.d.ts

@@ -4,6 +4,6 @@
  * @module billion-context-dsh/commands
  */
 import type { CommandDefinition } from '@deepseek-ai/dsh-commands';
-import type { ToolEnvironment } from './tools.ts';
+import { type ToolEnvironment } from './tools.ts';
 /** Register the /acp command (idempotent per engine). */
 export declare function acpCommand(env: ToolEnvironment): CommandDefinition;

package/dist/index.js

@@ -3836,6 +3836,9 @@ function requireAgent(exec) {
   }
   return exec.agent;
 }
+async function resolveEffectiveWindow(env, agent) {
+  return env.windowFor === void 0 ? { limit: env.modelContextLimit, source: "explicit" } : await env.windowFor(agent);
+}
 var compressParameters = {
   // Tolerated wrapped-arguments form: some models emit
   // `{ "arguments": "{\"content\": [...]}" }` (double-nested) or
@@ -3947,7 +3950,8 @@ async function handleCompress(env, args, exec) {
   const coreMessages = allLogMessages(session);
   const surfaceMessages = eventsToCoreMessages(surfaceEventsOf(session));
   const tokenCount = resolveTokenCount(agent, surfaceMessages);
-  const config = kernelConfigFor(env);
+  const window = await resolveEffectiveWindow(env, agent);
+  const config = kernelConfigFor({ ...env, modelContextLimit: window.limit });
   const turn = env.kernel.processTurn({ messages: coreMessages, state, config, tokenCount });
   env.store.set(session, turn.state);
   const byRaw = turn.state.messageRefs.byRaw;
@@ -4231,7 +4235,8 @@ async function handleStatus(env, rawArgs, exec) {
   const coreMessages = allLogMessages(session);
   const surfaceMessages = eventsToCoreMessages(surface, toolNames);
   const tokenCount = resolveTokenCount(agent, surfaceMessages);
-  const config = kernelConfigFor(env);
+  const window = await resolveEffectiveWindow(env, agent);
+  const config = kernelConfigFor({ ...env, modelContextLimit: window.limit });
   const turn = env.kernel.processTurn({ messages: coreMessages, state, config, tokenCount });
   const statusMessages = eventsToCoreMessages(
     surface.filter((event) => !isCheckpointEvent(event)),
@@ -4304,6 +4309,7 @@ function windowSourceLabel(window) {
   if (window.source === "auto") {
     return `auto-detected from ${window.provider ?? "?"}/${window.model ?? "?"}`;
   }
+  if (window.probeFailed === true) return "default (auto-detection failed \u2014 restart to re-probe)";
   return "default (auto-detection unavailable)";
 }
 async function detectContextWindow(agent, provider, model) {
@@ -4327,7 +4333,7 @@ async function statusText(env, agent) {
   const coreMessages = allLogMessages(session);
   const surfaceMessages = eventsToCoreMessages(surfaceEventsOf(session));
   const estimated = resolveTokenCount(agent, surfaceMessages);
-  const window = env.windowFor === void 0 ? { limit: env.modelContextLimit, source: "explicit" } : await env.windowFor(agent);
+  const window = await resolveEffectiveWindow(env, agent);
   const limit = window.limit;
   const lines = [
     `ACP status \u2014 session ${session.id}`,
@@ -4336,6 +4342,9 @@ async function statusText(env, agent) {
     `  estimated context: ${estimated} / ${limit} (${Math.round(estimated / limit * 100)}%)`,
     `  context window: ${limit} (${windowSourceLabel(window)})`
   ];
+  if (window.probeFailed === true) {
+    lines.push(`  \u26A0 window auto-detection failed \u2014 using the ${limit} fallback (restart to re-probe, or set modelContextLimit explicitly)`);
+  }
   const state = structuredClone(env.store.stateFor(session));
   const config = kernelConfigFor({ ...env, modelContextLimit: limit });
   const turn = env.kernel.processTurn({ messages: coreMessages, state, config, tokenCount: estimated });
@@ -4569,7 +4578,14 @@ var AcpCompactionEngine = class extends CompactionEngine {
       window = { limit: DEFAULT_CONTEXT_WINDOW, source: "default", provider, model };
     } else {
       const detected = await detectContextWindow(agent, provider, model);
-      window = detected === null ? { limit: DEFAULT_CONTEXT_WINDOW, source: "default", provider, model } : { limit: detected, source: "auto", provider, model };
+      if (detected === null) {
+        this.ctx.logger.warn(
+          `billion-context-dsh: context-window auto-detection failed for ${provider}/${model} \u2014 using the ${DEFAULT_CONTEXT_WINDOW} fallback (restart to re-probe, or set modelContextLimit explicitly)`
+        );
+        window = { limit: DEFAULT_CONTEXT_WINDOW, source: "default", provider, model, probeFailed: true };
+      } else {
+        window = { limit: detected, source: "auto", provider, model };
+      }
     }
     this.windowCache.set(key, window);
     return window;