fix: name each tool once, and stream the reasoning live (#18)

src/lib/hooks/useChat.ts

@@ -7,6 +7,7 @@ import { isSelfHosted } from "../ollama";
 import { OllamaError } from "../ollama";
 import type { ResolvedPreferences } from "../preferences";
 import { createSession, createTurn, saveSession, withTitleFromFirstTurn } from "../sessions";
+import { EMPTY_TRACE, afterToolCall, withFinalTrace, withThinking, type ThinkingTrace } from "../thinking";
 import { toolsFor } from "../tools";
 import type { PendingAttachment, Session, VisionSupport } from "../types";
 import { errorMessage, isAbortError } from "../utils";
@@ -61,6 +62,13 @@ export interface UseChat {
   session: Session;
   isStreaming: boolean;
   streamingResponse: string;
+  /**
+   * The reasoning to show right now: only the part since the last tool call.
+   *
+   * Deliberately not the whole trace. The full one is carried on the turn for
+   * storage; this is the live view, and it is cleared each time a tool starts so
+   * a long research turn does not stack every round's thinking on screen.
+   */
   streamingThinking: string;
   /** Short activity line such as "Searching the web", shown while a turn is in flight. */
   status?: string;
@@ -102,7 +110,7 @@ export function useChat(options: UseChatOptions): UseChat {
   const abortRef = useRef<AbortController | null>(null);
   const liveRef = useRef(false);
   const responseRef = useRef("");
-  const thinkingRef = useRef("");
+  const thinkingRef = useRef<ThinkingTrace>(EMPTY_TRACE);
   const statusRef = useRef<string | undefined>(undefined);
   const flushTimerRef = useRef<ReturnType<typeof setTimeout> | null>(null);
 
@@ -131,14 +139,14 @@ export function useChat(options: UseChatOptions): UseChat {
       flushTimerRef.current = null;
       if (!liveRef.current) return;
       setStreamingResponse(responseRef.current);
-      setStreamingThinking(thinkingRef.current);
+      setStreamingThinking(thinkingRef.current.current);
     }, FLUSH_INTERVAL_MS);
   }, []);
 
   const flushNow = useCallback(() => {
     clearFlushTimer();
     setStreamingResponse(responseRef.current);
-    setStreamingThinking(thinkingRef.current);
+    setStreamingThinking(thinkingRef.current.current);
   }, [clearFlushTimer]);
 
   const setStatusValue = useCallback((value: string | undefined) => {
@@ -185,7 +193,7 @@ export function useChat(options: UseChatOptions): UseChat {
       commit(started);
 
       responseRef.current = "";
-      thinkingRef.current = "";
+      thinkingRef.current = EMPTY_TRACE;
       setStreamingResponse("");
       setStreamingThinking("");
       setError(undefined);
@@ -242,11 +250,18 @@ export function useChat(options: UseChatOptions): UseChat {
                 scheduleFlush();
               },
               onThinkingDelta: (delta) => {
-                thinkingRef.current += delta;
+                thinkingRef.current = withThinking(thinkingRef.current, delta);
                 scheduleFlush();
               },
               onStatus: (value) => setStatusValue(value),
-              onToolStart: (_name, label, count) => setActivity({ label, count }),
+              onToolStart: (_name, label, count) => {
+                // The reasoning that produced this call is spent, so the live
+                // segment is cleared and the tool line takes its place. The full
+                // trace is untouched, because the stored turn keeps all of it.
+                thinkingRef.current = afterToolCall(thinkingRef.current);
+                setActivity({ label, count });
+                flushNow();
+              },
               onToolCall: (record) => {
                 toolCalls = [...toolCalls, record];
               },
@@ -254,7 +269,7 @@ export function useChat(options: UseChatOptions): UseChat {
           });
 
           responseRef.current = result.content;
-          thinkingRef.current = result.thinking;
+          thinkingRef.current = withFinalTrace(result.thinking);
           toolCalls = result.toolCalls;
         } catch (thrown) {
           if (isAbortError(thrown)) {
@@ -268,7 +283,7 @@ export function useChat(options: UseChatOptions): UseChat {
         const finished = {
           ...turn,
           response: responseRef.current,
-          thinking: thinkingRef.current,
+          thinking: thinkingRef.current.full,
           toolCalls,
           error: failure,
         };
@@ -306,6 +321,7 @@ export function useChat(options: UseChatOptions): UseChat {
       setError(undefined);
       setStreamingResponse("");
       setStreamingThinking("");
+      thinkingRef.current = EMPTY_TRACE;
       commit(next);
     },
     [commit, setStatusValue],