From 98b6a2aeedd591058c1d81e401d24f3ded162926 Mon Sep 17 00:00:00 2001 From: tanaka takashi Date: Wed, 12 Aug 2026 00:21:23 +0900 Subject: fix: implement native Ollama thinking semantics Model Ollama chat thinking separately from final content, preserve it only across assistant tool-call continuation, and keep private reasoning out of user results, session context, and logs. Accept native boolean and low/medium/high/max think values, normalize YAML booleans, and serialize explicit overrides using the native top-level chat field. Stop forcing think=false for structured planning, skill selection, and context summaries; corrected retries now retain the configured thinking mode. Update the specification, design, audit report, and requirement traceability for OLL-14. Add request/response, configuration, observability, retry, and tool-continuation coverage. Verified with 92 passing Agent.Core tests and a deepseek-v4-flash:cloud think:true MCP operational run. --- src/Agent.Core/Runtime/AgentRuntime.cs | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'src/Agent.Core/Runtime/AgentRuntime.cs') diff --git a/src/Agent.Core/Runtime/AgentRuntime.cs b/src/Agent.Core/Runtime/AgentRuntime.cs index 31a4414..5ca9d1c 100644 --- a/src/Agent.Core/Runtime/AgentRuntime.cs +++ b/src/Agent.Core/Runtime/AgentRuntime.cs @@ -262,7 +262,7 @@ public sealed class AgentRuntime(TaskRegistry registry, IOllamaClient ollama, Ag IReadOnlyList calls = result.ToolCalls ?? []; if (calls.Count > 0) { - messages.Add(new OllamaMessage("assistant", result.Content, ToolCalls: calls)); + messages.Add(new OllamaMessage("assistant", result.Content, Thinking: result.Thinking, ToolCalls: calls)); string? failureFingerprint = null; foreach (OllamaToolCall call in calls) { @@ -400,7 +400,7 @@ public sealed class AgentRuntime(TaskRegistry registry, IOllamaClient ollama, Ag callContext = new AgentLlmCallContext(Guid.NewGuid(), task.SessionId, taskId, null, "context_summary", iteration, counters.Replans, settings.Model); _observer.LlmRequest(callContext, messages); - OllamaResult result = await ollama.ChatStructuredAsync(messages, task.Temperature, schema.RootElement.Clone(), false, cancellationToken).ConfigureAwait(false); + OllamaResult result = await ollama.ChatStructuredAsync(messages, task.Temperature, schema.RootElement.Clone(), null, cancellationToken).ConfigureAwait(false); _observer.LlmResponse(callContext, result); registry.AddUsage(taskId, result.InputTokens, result.OutputTokens); registry.UpdateDiagnostics(taskId, counters.Iterations, counters.Replans); @@ -444,8 +444,7 @@ public sealed class AgentRuntime(TaskRegistry registry, IOllamaClient ollama, Ag OllamaResult? result = null; try { - bool? thinkOverride = attempt == 0 ? null : false; - result = await ollama.ChatStructuredAsync(attemptMessages, task.Temperature, formatDoc.RootElement.Clone(), thinkOverride, cancellationToken).ConfigureAwait(false); + result = await ollama.ChatStructuredAsync(attemptMessages, task.Temperature, formatDoc.RootElement.Clone(), null, cancellationToken).ConfigureAwait(false); _observer.LlmResponse(callContext, result); registry.AddUsage(task.TaskId, result.InputTokens, result.OutputTokens); registry.UpdateDiagnostics(task.TaskId, counters.Iterations, counters.Replans); -- cgit v1.2.3