openfox 2.0.118 → 2.0.119

package/CHANGELOG.md

@@ -1,5 +1,31 @@
 # Changelog
 
+## 2.0.119 - 2026-08-14
+
+### Features
+
+- **Per-model sampling controls** — pick which sampling parameters each backend receives, per model
+- **Read-only session status** — lightweight API and widget expose live state for external integrations
+
+### Enhancements
+
+- **Reviewer gets the full picture** — code reviews now factor in intended scope, verifier notes, and changed files
+- **No surprise navigation on In Progress** — moving a task keeps your place; open it via the card link
+- **Task editor shortcuts inverted** — Enter inserts a newline, Shift+Enter saves
+
+### Bug Fixes
+
+- **New-task autocomplete fixed** — slash/@ suggestions are no longer clipped and load on cold start
+- **Long chats safer against rejection** — max_tokens now keeps 2048 tokens of headroom
+- **Split panes keep dev state separate** — server status, logs, and config no longer bleed between workdirs
+- **ask_user prompts render as markdown** — no more raw text walls
+- **Submodule changes appear in the diff preview**
+- **Auto-config spots rejected reasoning** — providers that refuse it no longer receive reasoning history
+- **LM Studio context windows set by auto-config** — no longer left at zero
+- **No phantom password prompt** — the login modal no longer flashes while connecting
+- **Silent streams end their turn** — idle LLM connections time out cleanly instead of hanging
+- **Null token usage no longer crashes sessions**
+
 ## 2.0.118 - 2026-08-12
 
 ### Features

package/dist/CHANGELOG.md

@@ -1,5 +1,31 @@
 # Changelog
 
+## 2.0.119 - 2026-08-14
+
+### Features
+
+- **Per-model sampling controls** — pick which sampling parameters each backend receives, per model
+- **Read-only session status** — lightweight API and widget expose live state for external integrations
+
+### Enhancements
+
+- **Reviewer gets the full picture** — code reviews now factor in intended scope, verifier notes, and changed files
+- **No surprise navigation on In Progress** — moving a task keeps your place; open it via the card link
+- **Task editor shortcuts inverted** — Enter inserts a newline, Shift+Enter saves
+
+### Bug Fixes
+
+- **New-task autocomplete fixed** — slash/@ suggestions are no longer clipped and load on cold start
+- **Long chats safer against rejection** — max_tokens now keeps 2048 tokens of headroom
+- **Split panes keep dev state separate** — server status, logs, and config no longer bleed between workdirs
+- **ask_user prompts render as markdown** — no more raw text walls
+- **Submodule changes appear in the diff preview**
+- **Auto-config spots rejected reasoning** — providers that refuse it no longer receive reasoning history
+- **LM Studio context windows set by auto-config** — no longer left at zero
+- **No phantom password prompt** — the login modal no longer flashes while connecting
+- **Silent streams end their turn** — idle LLM connections time out cleanly instead of hanging
+- **Null token usage no longer crashes sessions**
+
 ## 2.0.118 - 2026-08-12
 
 ### Features

package/dist/agent-defaults/code-reviewer.agent.md

@@ -11,14 +11,19 @@ allowedTools:
   - session_metadata
 ---
 
-You are a code reviewer. Review the **git diff** of the modified files rather than reading the full files.
+You are a code reviewer. Your caller may provide situational context before the diff — **intended scope (criteria)**, **what the verifier already confirmed**, and the **modified files**. Review the **git diff** of the modified files rather than reading the full files.
+
+When context is provided, use it to judge the change against what was actually requested:
+
+- Read the intended scope (criteria) and check the diff delivers it faithfully — flag mismatches, partial implementations, or scope creep.
+- Treat the verifier's notes as already-confirmed ground truth. Don't re-verify what it covered; instead catch what it missed.
+- You're not looking for 100% perfection. Just something that feels good to use and doesn't bloat the software.
+
 You're mostly interested in:
 
 1. **For the user (UX interaction)** — does this feel good to use? Any rough edges, confusing behavior, or unnecessary friction?
 2. **For the project (code quality + guidelines)** — does this follow project conventions? Is it maintainable? Does it bloat the software?
 
-You're not looking for 100% perfection. Just something that feels good to use and doesn't bloat the software.
-
 ## Managing Findings
 
 Use `session_metadata` to track your findings:

package/dist/{auto-config-AAUO4PKW.js → auto-config-YXNCBYEY.js}

@@ -1,3 +1,6 @@
+import {
+  findLmStudioModel
+} from "./chunk-K2QKX4ZJ.js";
 import {
   ensureVersionPrefix
 } from "./chunk-HNCM3D7Y.js";
@@ -98,14 +101,10 @@ async function detectLmstudioInfo(baseUrl, modelId) {
   const nativeUrl = `${base.replace(/\/v\d+\/?$/, "")}/api/v1/models`;
   const response = await fetch(nativeUrl, { signal: AbortSignal.timeout(5e3) });
   if (!response.ok) throw new Error(`HTTP ${response.status}`);
-  const data = await response.json();
-  const model = data.find((m) => (m.key ?? m.id) === modelId);
+  const model = findLmStudioModel(await response.json(), modelId);
   if (!model) throw new Error(`Model ${modelId} not found in LM Studio`);
-  const loadedContext = model.loaded_instances?.[0]?.config?.context_length;
-  const ctxLen = loadedContext ?? model.max_context_length;
-  const supportsVision = model.capabilities?.vision ?? false;
-  if (ctxLen) {
-    return { contextWindow: ctxLen, source: "backend", supportsVision };
+  if (model.contextWindow) {
+    return { contextWindow: model.contextWindow, source: "backend", supportsVision: model.supportsVision };
   }
   throw new Error("No context_length in LM Studio response");
 }
@@ -157,6 +156,117 @@ async function probeCombos(baseUrl, apiKey, model, combos) {
   logger.debug("Auto-config: no working combo found", { model });
   return null;
 }
+async function probeReasoningInMessages(baseUrl, apiKey, model) {
+  const headers = { "Content-Type": "application/json" };
+  if (apiKey) headers["Authorization"] = `Bearer ${apiKey}`;
+  try {
+    const response = await fetch(`${ensureVersionPrefix(baseUrl)}/chat/completions`, {
+      method: "POST",
+      headers,
+      body: JSON.stringify({
+        model,
+        messages: [
+          { role: "user", content: "say hi in one word" },
+          { role: "assistant", content: "hi", reasoning: "probe" },
+          { role: "user", content: "say hi in one word" }
+        ],
+        max_tokens: 1
+      }),
+      signal: AbortSignal.timeout(15e3)
+    });
+    return response.ok;
+  } catch {
+    return void 0;
+  }
+}
+var STANDARD_PARAMS = ["temperature", "top_p", "max_tokens", "top_k", "reasoning_effort"];
+var PARAM_VALUES = {
+  temperature: 0.7,
+  top_p: 0.9,
+  max_tokens: 50,
+  top_k: 40,
+  reasoning_effort: "high"
+};
+var escapeRegExp = (value) => value.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
+var REJECTED_PARAM_PATTERNS = STANDARD_PARAMS.map((param) => ({
+  param,
+  pattern: new RegExp(`\\b${escapeRegExp(param)}\\b`, "i")
+}));
+function extractRejectedParam(errorText) {
+  for (const { param, pattern } of REJECTED_PARAM_PATTERNS) {
+    if (pattern.test(errorText)) return param;
+  }
+  return void 0;
+}
+var DUMMY_TOOL = {
+  type: "function",
+  function: {
+    name: "noop",
+    description: "No-op tool for probing",
+    parameters: { type: "object", properties: {}, required: [] }
+  }
+};
+async function probeChatCompletions(baseUrl, headers, model, samplingParams) {
+  const body = {
+    model,
+    messages: [{ role: "user", content: "say hi in one word" }],
+    tools: [DUMMY_TOOL],
+    tool_choice: "auto"
+  };
+  for (const param of samplingParams) {
+    body[param] = PARAM_VALUES[param];
+  }
+  try {
+    const response = await fetch(`${ensureVersionPrefix(baseUrl)}/chat/completions`, {
+      method: "POST",
+      headers,
+      body: JSON.stringify(body),
+      signal: AbortSignal.timeout(15e3)
+    });
+    if (response.ok) return { ok: true, status: response.status, errorText: "" };
+    return { ok: false, status: response.status, errorText: await response.text() };
+  } catch {
+    return { ok: false, status: 0, errorText: "" };
+  }
+}
+async function probeRejectedParams(baseUrl, apiKey, model, backend) {
+  const headers = { "Content-Type": "application/json" };
+  if (apiKey) headers["Authorization"] = `Bearer ${apiKey}`;
+  const candidates = [...STANDARD_PARAMS];
+  if (["openai", "anthropic", "ollama"].includes(backend)) {
+    const idx = candidates.indexOf("top_k");
+    if (idx !== -1) candidates.splice(idx, 1);
+  }
+  const control = await probeChatCompletions(baseUrl, headers, model, []);
+  if (!control.ok) {
+    logger.debug("Auto-config: rejection-probe control failed, skipping param detection", {
+      model,
+      status: control.status
+    });
+    return [];
+  }
+  const rejected = [];
+  const remaining = [...candidates];
+  while (remaining.length > 0) {
+    const probe = await probeChatCompletions(baseUrl, headers, model, remaining);
+    if (probe.ok) break;
+    if (probe.status === 400) {
+      const rejectedParam = extractRejectedParam(probe.errorText);
+      if (rejectedParam && remaining.includes(rejectedParam)) {
+        rejected.push(rejectedParam);
+        remaining.splice(remaining.indexOf(rejectedParam), 1);
+        logger.debug("Auto-config: param rejected, retrying without", { model, rejectedParam });
+        continue;
+      }
+      break;
+    }
+    break;
+  }
+  if (rejected.length > 0) {
+    logger.info("Auto-config: detected rejected params", { model, rejected });
+  }
+  return rejected;
+}
 async function autoConfig(input) {
   const { url, apiKey, backend, models } = input;
   const baseUrl = url.replace(/\/+$/, "");
@@ -168,17 +278,21 @@ async function autoConfig(input) {
       source: contextSource,
       supportsVision
     } = await detectModelInfo(baseUrl, apiKey, backend, model.id);
-    const [thinkingConfig, nonThinkingConfig] = await Promise.all([
+    const [thinkingConfig, nonThinkingConfig, rejectedParams] = await Promise.all([
       probeCombos(baseUrl, apiKey, model.id, THINKING_COMBOS),
-      probeCombos(baseUrl, apiKey, model.id, NON_THINKING_COMBOS)
+      probeCombos(baseUrl, apiKey, model.id, NON_THINKING_COMBOS),
+      probeRejectedParams(baseUrl, apiKey, model.id, backend)
     ]);
+    const sendReasoningInMessages = thinkingConfig ? await probeReasoningInMessages(baseUrl, apiKey, model.id) : void 0;
     results.push({
       id: model.id,
       contextWindow,
       contextSource,
       supportsVision,
       thinkingConfig,
-      nonThinkingConfig
+      nonThinkingConfig,
+      ...sendReasoningInMessages !== void 0 ? { sendReasoningInMessages } : {},
+      ...rejectedParams.length > 0 ? { rejectedParams } : {}
     });
   }
   return { models: results };
@@ -186,4 +300,4 @@ async function autoConfig(input) {
 export {
   autoConfig
 };
-//# sourceMappingURL=auto-config-AAUO4PKW.js.map
+//# sourceMappingURL=auto-config-YXNCBYEY.js.map

package/dist/{chat-handler-KNBP6WVI.js → chat-handler-M54IWF5Y.js}

@@ -2,14 +2,14 @@ import {
   buildRunChatTurnParams,
   finalizeTurnCompletion,
   generateSessionNameForSession
-} from "./chunk-MTFLMNLN.js";
+} from "./chunk-VFS7TFA7.js";
 import {
   runChatTurn
-} from "./chunk-CX7UJZA5.js";
-import "./chunk-IDUXGSQV.js";
-import "./chunk-5E5G3DLI.js";
+} from "./chunk-6DDB67FN.js";
+import "./chunk-V5XWUVF5.js";
+import "./chunk-UNNCD7A3.js";
 import "./chunk-2FCLCUVR.js";
-import "./chunk-NP2SV2CX.js";
+import "./chunk-SE62ZBNX.js";
 import "./chunk-27NABDXB.js";
 import "./chunk-M6X6AIEG.js";
 import "./chunk-ZTOG6LJD.js";
@@ -18,7 +18,7 @@ import "./chunk-JE7LW7Y6.js";
 import "./chunk-OAN4BXEW.js";
 import "./chunk-O6DU226D.js";
 import "./chunk-J7GAZGZT.js";
-import "./chunk-HZSKKJHQ.js";
+import "./chunk-5FAPM2GM.js";
 import "./chunk-EQ5CGNOT.js";
 import "./chunk-XZGQZ42D.js";
 import {
@@ -38,13 +38,14 @@ import "./chunk-LCLH6ZUL.js";
 import "./chunk-LNNBLB6G.js";
 import "./chunk-OSXPQSLW.js";
 import "./chunk-3PG65AXG.js";
-import "./chunk-GZTMCTUS.js";
+import "./chunk-U6JMRMBW.js";
+import "./chunk-K2QKX4ZJ.js";
 import "./chunk-J2GP3J3X.js";
-import "./chunk-MKWS7TQH.js";
+import "./chunk-J6KFWVZ3.js";
 import "./chunk-W7VIYHPQ.js";
 import "./chunk-AZHWLLPP.js";
 import "./chunk-HNCM3D7Y.js";
-import "./chunk-TOKQ2UVG.js";
+import "./chunk-MIPQOHWS.js";
 import "./chunk-LTYL6ZGH.js";
 import "./chunk-HD6Y77RO.js";
 import "./chunk-5PT4UMRR.js";
@@ -173,4 +174,4 @@ export {
   startChatSession,
   stopSessionExecution
 };
-//# sourceMappingURL=chat-handler-KNBP6WVI.js.map
+//# sourceMappingURL=chat-handler-M54IWF5Y.js.map

package/dist/{chunk-HZSKKJHQ.js → chunk-5FAPM2GM.js}

@@ -11,7 +11,7 @@ import {
 } from "./chunk-3PG65AXG.js";
 import {
   parseDefaultModelSelection
-} from "./chunk-GZTMCTUS.js";
+} from "./chunk-U6JMRMBW.js";
 import {
   getDatabase
 } from "./chunk-5PT4UMRR.js";
@@ -677,6 +677,12 @@ function createTasksService(deps) {
       ...autoLaunched ? { autoLaunched } : {}
     });
   }
+  function reusableTarget(projectId, sessionId) {
+    if (!sessionId) return void 0;
+    const session = sessionManager.getSession(sessionId);
+    if (!session || session.projectId !== projectId || session.messages.length > 0) return void 0;
+    return sessionId;
+  }
   function list(projectId) {
     return listTasks(projectId);
   }
@@ -787,12 +793,14 @@ function createTasksService(deps) {
           const launched = runningCount < settings.slotLimit && !settings.queuePaused;
           setTaskRunState(taskId, launched ? "running" : "queued");
           if (launched) {
-            const seeded = await seedSession(projectId, task, from);
+            const seeded = await seedSession(projectId, task, from, reusableTarget(projectId, opts.sessionId));
             addTaskLink(taskId, seeded.session.id, true);
             addAuditEntry(taskId, "human", "move", `Moved to In Progress (running)`, opts.actorName);
             sessionId = seeded.session.id;
           } else {
             appendToBottom(taskId, "in_progress");
+            const earmarked = reusableTarget(projectId, opts.sessionId);
+            if (earmarked) addTaskLink(taskId, earmarked, false);
             addAuditEntry(taskId, "human", "move", `Moved to In Progress (queued)`, opts.actorName);
           }
         }
@@ -905,11 +913,20 @@ function createTasksService(deps) {
   function activeCount(projectId) {
     return listTasks(projectId).filter((t) => t.status === "in_progress" && t.runState === "running").length;
   }
-  async function seedSession(projectId, task, from) {
-    const defaults = parseDefaultModelSelection(config.defaultModelSelection);
-    const providerId = task.providerId ?? defaults.providerId ?? null;
-    const model = task.model ?? defaults.model ?? null;
-    const session = sessionManager.createSession(projectId, void 0, providerId, model);
+  async function seedSession(projectId, task, from, targetSessionId) {
+    let session;
+    if (targetSessionId) {
+      const existing = sessionManager.getSession(targetSessionId);
+      if (!existing) {
+        return seedSession(projectId, task, from);
+      }
+      session = existing;
+    } else {
+      const defaults = parseDefaultModelSelection(config.defaultModelSelection);
+      const providerId = task.providerId ?? defaults.providerId ?? null;
+      const model = task.model ?? defaults.model ?? null;
+      session = sessionManager.createSession(projectId, void 0, providerId, model);
+    }
     if (task.agentId) {
       try {
         sessionManager.setMode(session.id, task.agentId);
@@ -957,7 +974,9 @@ function createTasksService(deps) {
     const next = queued[0];
     if (!next) return void 0;
     setTaskRunState(next.id, "running");
-    const seeded = await seedSession(projectId, next, "queued");
+    const earmarks = listTaskLinks(next.id);
+    const target = reusableTarget(projectId, earmarks[0]?.session_id);
+    const seeded = await seedSession(projectId, next, "queued", target);
     addTaskLink(next.id, seeded.session.id, true);
     addAuditEntry(next.id, "system", "auto_launch", `Auto-launched into session ${seeded.session.id}`, "system");
     return {
@@ -1079,4 +1098,4 @@ export {
   isTaskGateError,
   createTasksService
 };
-//# sourceMappingURL=chunk-HZSKKJHQ.js.map
+//# sourceMappingURL=chunk-5FAPM2GM.js.map

package/dist/{chunk-CX7UJZA5.js → chunk-6DDB67FN.js}

@@ -4,12 +4,12 @@ import {
   getToolRegistryForAgent,
   processEventsForConversation,
   runTopLevelAgentLoop
-} from "./chunk-IDUXGSQV.js";
+} from "./chunk-V5XWUVF5.js";
 import {
   buildCachedPrompt,
   computeDynamicContextHash,
   getToolFingerprint
-} from "./chunk-5E5G3DLI.js";
+} from "./chunk-UNNCD7A3.js";
 import {
   getAllInstructions,
   getEnabledSkillMetadata
@@ -18,7 +18,7 @@ import {
   TurnMetrics,
   createChatDoneEvent,
   createMessageStartEvent
-} from "./chunk-NP2SV2CX.js";
+} from "./chunk-SE62ZBNX.js";
 import {
   buildAgentReminder,
   buildAgentSmallReminder
@@ -325,4 +325,4 @@ export {
   runChatTurn,
   runAgentTurn
 };
-//# sourceMappingURL=chunk-CX7UJZA5.js.map
+//# sourceMappingURL=chunk-6DDB67FN.js.map

package/dist/{chunk-5ZR5O5GC.js → chunk-AIFZNTUJ.js}

@@ -163,7 +163,7 @@ async function runCli(options) {
       break;
     }
     case "provider": {
-      const { runProviderCommand } = await import("./provider-Q7J4UFTS.js");
+      const { runProviderCommand } = await import("./provider-7YF42S7C.js");
       const [, subcommand] = positionals;
       await runProviderCommand(mode, subcommand);
       break;
@@ -200,7 +200,7 @@ async function runCli(options) {
       break;
     }
     case "update": {
-      const { runUpdate } = await import("./update-T3YMIWQO.js");
+      const { runUpdate } = await import("./update-C3YVPKCR.js");
       const code = await runUpdate();
       if (code !== 0) {
         process.exit(code);
@@ -213,7 +213,7 @@ async function runCli(options) {
       if (!configExists) {
         await runNetworkSetup(mode);
       }
-      const { runServe } = await import("./serve-23YIIMXH.js");
+      const { runServe } = await import("./serve-V34QG72C.js");
       const serveOptions = { mode };
       if (values.port) serveOptions.port = parseInt(values.port);
       if (values["no-browser"] === true) serveOptions.openBrowser = false;
@@ -225,4 +225,4 @@ async function runCli(options) {
 export {
   runCli
 };
-//# sourceMappingURL=chunk-5ZR5O5GC.js.map
+//# sourceMappingURL=chunk-AIFZNTUJ.js.map

package/dist/{chunk-45OS4H3L.js → chunk-AVQCOSOF.js}

@@ -1,14 +1,14 @@
 import {
   runAgentTurn
-} from "./chunk-CX7UJZA5.js";
+} from "./chunk-6DDB67FN.js";
 import {
   executeSubAgent,
   getToolRegistryForAgent
-} from "./chunk-IDUXGSQV.js";
+} from "./chunk-V5XWUVF5.js";
 import {
   TurnMetrics,
   createMessageStartEvent
-} from "./chunk-NP2SV2CX.js";
+} from "./chunk-SE62ZBNX.js";
 import {
   checkAborted,
   decodeUtf8,
@@ -27,7 +27,7 @@ import {
   loadProjectWorkflows,
   loadUserWorkflows,
   normalizeWorkflowScope
-} from "./chunk-HZSKKJHQ.js";
+} from "./chunk-5FAPM2GM.js";
 import {
   getCurrentContextWindowId,
   getEventStore
@@ -67,13 +67,13 @@ import { spawn } from "child_process";
 function getGitDiffFiles(cwd) {
   return new Promise((resolve) => {
     const env = gitSpawnEnv();
-    const diffProc = spawn("git", ["diff", "--name-status", "HEAD"], {
+    const diffProc = spawn("git", ["diff", "--ignore-submodules=none", "--name-status", "HEAD"], {
       cwd,
       env,
       stdio: ["ignore", "pipe", "pipe"],
       windowsHide: true
     });
-    const statusProc = spawn("git", ["status", "--porcelain"], {
+    const statusProc = spawn("git", ["status", "--porcelain", "--ignore-submodules=none"], {
       cwd,
       env,
       stdio: ["ignore", "pipe", "pipe"],
@@ -1002,4 +1002,4 @@ export {
   abortRunnerRun,
   launchWorkflowRun
 };
-//# sourceMappingURL=chunk-45OS4H3L.js.map
+//# sourceMappingURL=chunk-AVQCOSOF.js.map

package/dist/chunk-EW25UQG3.js

@@ -0,0 +1,7 @@
+// src/constants.ts
+var VERSION = "2.0.119";
+
+export {
+  VERSION
+};
+//# sourceMappingURL=chunk-EW25UQG3.js.map

package/dist/{chunk-MKWS7TQH.js → chunk-J6KFWVZ3.js}

@@ -13,7 +13,7 @@ import {
   getThinking,
   mapFinishReason,
   parseToolArguments
-} from "./chunk-TOKQ2UVG.js";
+} from "./chunk-MIPQOHWS.js";
 import {
   LLMError,
   OpenAIHttpClient
@@ -169,15 +169,6 @@ function createLLMClient(config, initialBackend = "unknown") {
           ...buildExtraParams(resolvedEffort)
         });
         const { params: streamingParams } = createParams;
-        const stream = httpClient.createChatCompletionStream(streamingParams, {
-          signal: request.signal
-        });
-        let fullContent = "";
-        let fullThinking = "";
-        const toolCalls = /* @__PURE__ */ new Map();
-        let finishReason = "stop";
-        let usage = { promptTokens: 0, completionTokens: 0, totalTokens: 0 };
-        let responseId = "";
         let lastChunkTime = Date.now();
         const idleTimeoutController = new AbortController();
         const idleTimer = setInterval(() => {
@@ -187,6 +178,16 @@ function createLLMClient(config, initialBackend = "unknown") {
             idleTimeoutController.abort();
           }
         }, 100);
+        const streamSignal = request.signal ? AbortSignal.any([request.signal, idleTimeoutController.signal]) : idleTimeoutController.signal;
+        const stream = httpClient.createChatCompletionStream(streamingParams, {
+          signal: streamSignal
+        });
+        let fullContent = "";
+        let fullThinking = "";
+        const toolCalls = /* @__PURE__ */ new Map();
+        let finishReason = "stop";
+        let usage = { promptTokens: 0, completionTokens: 0, totalTokens: 0 };
+        let responseId = "";
         const onAbort = () => clearInterval(idleTimer);
         request.signal?.addEventListener("abort", onAbort, { once: true });
         try {
@@ -203,9 +204,9 @@ function createLLMClient(config, initialBackend = "unknown") {
             responseId = chunk.id;
             if (chunk.usage) {
               usage = {
-                promptTokens: chunk.usage.prompt_tokens,
-                completionTokens: chunk.usage.completion_tokens,
-                totalTokens: chunk.usage.total_tokens
+                promptTokens: chunk.usage.prompt_tokens ?? usage.promptTokens,
+                completionTokens: chunk.usage.completion_tokens ?? usage.completionTokens,
+                totalTokens: chunk.usage.total_tokens ?? usage.totalTokens
               };
             }
             const choice = chunk.choices[0];
@@ -259,6 +260,11 @@ function createLLMClient(config, initialBackend = "unknown") {
               }
             }
           }
+        } catch (error) {
+          if (idleTimeoutController.signal.aborted && !request.signal?.aborted) {
+            throw new Error(`LLM stream idle timeout: no chunks received for ${idleTimeout}ms`);
+          }
+          throw error;
         } finally {
           clearInterval(idleTimer);
           request.signal?.removeEventListener("abort", onAbort);
@@ -297,7 +303,7 @@ function createLLMClient(config, initialBackend = "unknown") {
           }
         };
       } catch (error) {
-        logger.error("LLM stream error", { error });
+        logger.error("LLM stream error", { error: String(error) });
         yield {
           type: "error",
           error: error instanceof Error ? error.message : "Unknown LLM error"
@@ -310,4 +316,4 @@ function createLLMClient(config, initialBackend = "unknown") {
 export {
   createLLMClient
 };
-//# sourceMappingURL=chunk-MKWS7TQH.js.map
+//# sourceMappingURL=chunk-J6KFWVZ3.js.map

package/dist/chunk-K2QKX4ZJ.js

@@ -0,0 +1,31 @@
+// src/server/providers/lmstudio.ts
+function unwrap(raw) {
+  if (Array.isArray(raw)) return raw;
+  if (raw && typeof raw === "object") {
+    const record = raw;
+    if (Array.isArray(record.models)) return record.models;
+    if (Array.isArray(record.data)) return record.data;
+  }
+  return [];
+}
+function parseLmStudioModels(raw) {
+  return unwrap(raw).map((model) => {
+    const id = model.key ?? model.id ?? "";
+    const loaded = model.loaded_instances?.[0]?.config?.context_length;
+    const contextWindow = loaded ?? model.max_context_length;
+    return {
+      id,
+      ...contextWindow ? { contextWindow } : {},
+      supportsVision: model.capabilities?.vision ?? false
+    };
+  }).filter((model) => model.id !== "");
+}
+function findLmStudioModel(raw, modelId) {
+  return parseLmStudioModels(raw).find((model) => model.id === modelId);
+}
+
+export {
+  parseLmStudioModels,
+  findLmStudioModel
+};
+//# sourceMappingURL=chunk-K2QKX4ZJ.js.map

package/dist/{chunk-TOKQ2UVG.js → chunk-MIPQOHWS.js}

@@ -463,11 +463,12 @@ function parseToolArguments(raw, _meta) {
   }
 }
 function buildModelParams(params) {
+  const isOmitted = (key) => params.omitParams?.includes(key) ?? false;
   return {
-    ...params.temperature !== void 0 && { temperature: params.temperature },
-    ...params.topP !== void 0 && { topP: params.topP },
-    ...params.topK !== void 0 && { topK: params.topK },
-    ...params.maxTokens !== void 0 && { maxTokens: params.maxTokens }
+    ...!isOmitted("temperature") && params.temperature !== void 0 && { temperature: params.temperature },
+    ...!isOmitted("top_p") && params.topP !== void 0 && { topP: params.topP },
+    ...!isOmitted("top_k") && params.topK !== void 0 && { topK: params.topK },
+    ...!isOmitted("max_tokens") && params.maxTokens !== void 0 && { maxTokens: params.maxTokens }
   };
 }
 async function buildAttachmentContent(msgContent, attachments, modelSupportsVision) {
@@ -644,7 +645,20 @@ async function buildChatCompletionCreateParams(model, request, profile, capabili
       };
     }
   }
-  const modelParams = buildModelParams({ temperature, topP, topK, maxTokens });
+  const omitParams = request.modelSettings?.omitParams;
+  if (omitParams && omitParams.length > 0) {
+    const paramRecord = params;
+    for (const key of omitParams) {
+      delete paramRecord[key];
+    }
+  }
+  const modelParams = buildModelParams({
+    temperature,
+    topP,
+    topK,
+    maxTokens,
+    ...omitParams !== void 0 && { omitParams }
+  });
   return { params, modelParams };
 }
 async function buildCreateParamsFromInput(input, isStreaming) {
@@ -697,4 +711,4 @@ export {
   buildStreamingCreateParams,
   mapFinishReason
 };
-//# sourceMappingURL=chunk-TOKQ2UVG.js.map
+//# sourceMappingURL=chunk-MIPQOHWS.js.map